http://www.rssboard.org/rss-specification earthli News 3.7 en-us 720 https://www.earthli.com/news/ Sun, 15 Mar 2026 10:24:47 +0100 Sun, 15 Mar 2026 10:24:47 +0100 https://www.earthli.com/news/ https://www.earthli.com/news/icons/webcore_png/app/news_100px.png https://www.earthli.com/news/view_article.php?id=6079 https://www.earthli.com/news/view_article.php?id=6079 Sun, 15 Mar 2026 10:24:47 +0100 https://www.earthli.com/news/view_article.php?id=6040 https://www.earthli.com/news/view_article.php?id=6040 Thu, 19 Feb 2026 13:59:36 +0100 includes the following comment that attempts to not only put the capital expenditure in AI technology into context but also describes the immense opportunity cost. "It's hard to comprehend the scale of these investments. Comparing them to notable industrial projects, it's almost unbelievable. Every week in 2026 Google will pay for the cost of a Burj Khalifa. Amazon for a Wembley Stadium. "Facebook will spend a France-England tunnel every month." " As a research topic, modern AI is a miracle, and I absolutely love learning about it. As an economic endeavor, it just feels insane. How many hospitals, roads, houses, machine shops, biomanufacturing facilities, parks, forests, laboratories, etc. could we build with the money we’re spending on pretraining models that we throw away next quarter?" This is madness, of course, but it's par for the course: some of us have observed the money machine pouring capital expenditure into military-hardware companies for a long time now, always to the detriment of any social investments, like those listed in the comment above: schools, daycares, public transport, "hospitals, roads, houses, machine shops, biomanufacturing facilities, parks, laboratories," etc. That our elites are spending money on things beneficial to them rather than us is not new but that they've started wasting it on AI is. [Examining opportunity cost] Another commenter wrote that they'd, "[...] just made a LLM recreate a decent approximation of the file system browser from the movie Hackers (similar to the SGI one from Jurassic park) in about 10 minutes. At work I've had it do useful features and bug fixes daily for a solid week." Implicit in this argument is that this person having recreated a file-system browser from a movie for pure fun -- and with little to no effort on their part -- did so in the context of a society that actually considered the costs, and billed the appropriate parties. That is, the commentator probably spent a few bucks on it but that's only because society is massively subsidizing things that make the richest people richer and the richest people are currently obsessed with AI as the thing that will make them richer. People like the commentator are currently under the umbrella and benefit from the self-aggrandizing activity of the rich, at least tangentially. For the rest of us, we really should be thinking about the opportunity cost, and we should very much be wondering why we've decided -- mostly implicitly -- that this person gets to have an infrastructure for playing around with their hobbies -- or for being slightly more efficienthaving slightly more fun at work -- while people in need of hospitals or medical care can go and hold a bake sale [1] or start a GoFundMe. This is fine, apparently, especially if we don't really think about it. [LLM output is still mostly meh.] On top of it being an a moral affront that our societies prioritize military hardware and the self-aggrandizing dreams of tech elites and crypto bros above anything even remotely useful to everyone else, the output of these tools is still just not very good. They seem to have given up on making it better, and instead focused their efforts on media campaigns, advertising, press releases, and shills, all of which is meant to make us lower our standards instead. The results may kind of suck, but you barely had to lift a finger to get them, and you can easily convince your boss -- who also doesn't care about the results -- that you're working while the little circle spins on your laptop, so it's a win-win-win, right? For example, here's a picture illustrating the point of the previous section. [image] Do you like that graphic? Does it feel appropriate? Because, by way of illustration, I generated that image with Microsoft Copilot when I couldn't find anything matching "military versus social spending scales" on DuckDuckGo that wasn't a pie chart. I could have gone with a pie chart but I kind of wanted the scales. I'm spoiled too. I'm under the umbrella. The result is kind of ... off, though, isn't it? 1. There is no physicality to it; it's not grounded; it kind of floats. 2. The shadow doesn't represent the two platters. 3. The rocket isn't sitting on anything. 4. The wires holding the social-spending platter don't go anywhere. It's fine, I guess? The results have gotten better but this is still where we're at in 2026, after nearly $1T of capex and untold amounts of subsidies for energy infrastructure and data-centers. Given all that, that image is a wildly mediocre result. It's better than what I could have come up with in the minute that it took to generate it. But is it good? Absolutely not. It's better than nothing. That is what we're trading social services for: better-than-nothing versions of things we didn't really need. So, elites (like myself) can control vast amounts of resources in the cloud to generate useless gewgaws while people go hungry and without healthcare. This is the bargain. It always has been. [2] [image] [It's different this time] Another comment on the Hacker News post writes, "Is it the beginning of the star trek ship computer? If so, it is as big as the smartphone, the internet, or even the invention of the microchip. And then the investments make sense in a way." This is the one. Can't miss. Keep telling yourself that, buddy. People keep claiming that these tools will eventually turn around and solve all of the other societal problems, which is why it's absolutely sensible, patriotic, and moral to put all of our eggs in exactly this basket, this time. Forget about all the other times. Lord knows we've tried hard enough to get you to forget about all of the other times we've scammed you. Even if you vaguely remember that something unpleasant might have happened once or twice -- or might even vaguely remember who was responsible -- just forget all that. Because this time, it's different. This time it will work. Promise. Cross our shriveled little hearts and hope to die. Seriously, don't even worry your pretty little head about it: There is no way this will turn out to enrich all of the usual suspects, leaving the rest of us with nothing. No way. This is the one. This time it's real. The same assholes who already own everything are recruiting you into their propaganda campaign to increase their fortunes. They're saying, once again, "Let's just do this thing first, then we'll get to all of the things you need. Don't worry, we won't forget you." [image] [Maybe LLMs will kill LARPing I dunno] When I read about people building five projects a week, or submitting 27 PRs a day, I'm reminded of people who say that they read 200 books a year. This may be superficially true, but they are almost certainly crap books, or they're just skimming them, or they're incapable of understanding them. They are cheating. They are rounding up. They are emphasizing quantity over quality, which, like, used to be a bad thing. Now, the barrier has been lowered even farther. People can now write 50-page "papers." They can write "full-fledged apps." Because the barrier to entry has been drastically lowered, there is less room for those LARPing as writers or programmers these days, not because they can't LARP anymore but because no-one can tell the difference between their LARPing and LLM-supported LARPing. A dozen years ago, the doors were wide open for people who could barely spell JavaScript -- and had no idea what the difference was between that and Java -- to earn six-figure salaries while building careers in an industry they had no hope of understanding. There was a lot of money sloshing around in the industry and managers greedily took up the slack in order to fill their teams with heartbeats. These managers weren't interested in actually accomplishing anything, but did it in order to look like they might accomplish something for long enough for them to get promoted like a space shuttle achieving orbit. They dropped their team like booster rockets, which careened back to Earth, only to be picked up by another enterprising manager more interested in a career than in actually accomplishing anything. This worked out great for everyone as long as the industry was awash in money for such escapades. It no longer is, as those with all of the money have moved on to playing much larger games that don't involve minor cogs earning six-figure salaries. They are instead focused on landing ten-figure deals that also have no hope of ever providing any value outside of making them money, but that's the play these days apparently. Long story shot, the LARPers are now having a tough time of it. They LARPed for so long that they think that they're actually engineers whose jobs are endangered by the new fad on the block, LLMs. No-one cares about SPAs anymore because people who don't care whether products actually work over the medium- or long-term can have any monkey churn out dozens of them a day to show their bosses. who also don't care whether the products work because our entire economy is built on LARPing with only awards and no accountability or consequences in sight for the greatest transgressors. [Does it matter if anything even works anymore?] I think it's premature to predict the end of anything when it's completely unclear in what form any of what's available today (A) will be available in that form and price point in the near future and (B) whether it even is what it claims to be -- or what its most fervent acolytes claim it to be. Hype is hype because it grows by repetition rather than by the introduction of new information. We are seeing a giant version of that and it feels inevitable because a lot of people are spending a lot of money to make it feel that way. if you know what you're doing, then you personally should have nothing to fear because you and I both know that the future will not be herding LLMs because it doesn’t work the way they say it works, nor will it until something significantly changes. Since no-one seems to be interested in going anywhere near a drawing board to do some basic research, and since the amount of money being sloshed around to support the current LLM-based fantasy is larger than anything we've seen before, the aftermath is going to be epically bad. I think that we can safely say that losing our jobs to AI will be the least of our concerns as we pick our way through the pillaged aisles of an abandoned grocery store in the post-apocalyptic hellscape that is definitely coming in the next financial crash that will make 2008 look like a bank error in their favor. [3] [image] [Show me what you can do now] The verb case the proponents of this revolution use is always "future". Success is just over the horizon. Just a little bit more. This is how MLMs work; it is not a serious business model. These people love to round up. "We built a browser". STFU. You did not. You built another prototype. You built another copy of something that already exists. We are over four years into this mess and all I can see is software getting noticeably worse. "Hey, you jumped your bike over the ramp again, Billy. Cool. Can you do something useful yet? Like, can you go to the store and get me some goddamned cigarettes?" [They have every incentive to lie bigly] All I see are fantasies spun by people worth hundreds of billions of dollars who run companies that are hundreds of billions of dollars in debt who are trying to keep the plates spinning so that you don’t notice that some of these people are planning to leave by the back door real soon. When the CEO of Anthropic tells you that his company is going to change the entire world, it’s the same thing as when Trump says that polls no longer matter. They desperately need you to believe these things even though they don’t believe it themselves. I think a great example of this is when Tesla quietly abandoned its autopilot program a little while ago, after years and years and years of telling people that they would be able to drive their own cars without touching the wheel -- and after several people actually believed it so hard that they killed themselves in car accidents. Now, years later, that program is just completely gone. It is no longer officially a program just like it was never an actual non-imaginary thing to begin with. That's all a lot of this is. I'm happy if you find value in it for yourself. But it's not here to provide value to you. It's here to pretend to be much more valuable than it is so that a bunch of rich people can cash in, get out, and move on to the next scam. I would have thought that a lot more people would have grokked that none of the people claiming that they're here to save the world for all of us are even slightly interested in doing so, to say nothing of being capable of pushing us in that direction, if only a little bit. Our radar for detecting grifters is completely broken, and that's why society is saturated with them, top to bottom. -------------------------------------------------------------------------------- [1] I mentioned in a recent article "James Webb telescope gets help" that, "These vastly unequal incentives and rewards are perfectly encapsulated by one of my favorite stickers of all time. 25 years after I first bought it—and 46 years after it was printed—it still describes all you need to know about the U.S., or any authoritarian, militaristic country." [image] [1] I generated that one with "Always-Has-Been" , which presumably used a lot fewer resources and definitely took a lot less time. [1] That's not a typo. While the monopoly card says "your" favor, it is gifting the money back to an already-rich person in the image. I think it makes more sense in the case of the 2008 crash to emphasize that the error was not in any way in our favor. ]]> https://www.earthli.com/news/view_article.php?id=6042 https://www.earthli.com/news/view_article.php?id=6042 Tue, 17 Feb 2026 14:22:09 +0100 demonstrates the Overton Window of addiction pretty well. The author writes, "This captures an effect I've been observing in my own work with LLMs: the productivity boost these things can provide is exhausting. "[...] I'm frequently finding myself with work on two or three projects running parallel. I can get so much done, but after just an hour or two my mental energy for the day feels almost entirely depleted." [Is it marketing?] If I didn't trust the author, I would immediately suspect that he's applying a classic marketing tactic: "OMG this tool is so powerful that I can't even control it!" [1] This is a classic tactic of trying to sell a product by arguing that you probably shouldn't use it, not because it doesn't work, but because you probably couldn't handle it. This is the kind of marketing that appeals to children, teenagers, and Jackass fans. Instead, I think he might be seriously not noticing that his argument amounts to, "All of this cocaine I'm doing has doubled my productivity but I can only work a quarter of the day. Also, I feel like shit." [Maybe you're using it wrong?] A snarky response would be: "Hey! Here's an idea I've heard somewhere: maybe you're not prompting it correctly." [2] But I'm not going to be snarky. [You're not special] The author continues to describe what he clearly seems to think is a unique phenomenon. It's only unique when you're trapped in an information bubble where you start to attribute every detail of existence to the thing that you have grown to unreservedly love. "I've had conversations with people recently who are losing sleep because they're finding building yet another feature with "just one more prompt" irresistible." My friend, you are describing addictive behavior. It was no different before LLMs. This is how it has always been with programming (or for any interesting task, really). I spent a lot of my early 20s programming day and night. As you get older, though, you learn that just leaving it be is just as efficient. That is, instead of staying up two or three more hours growing increasingly frustrated, you can finish whatever you're working on in the morning -- and probably in five minutes. That's almost always the more efficient and sustainable solution. But, sure, let's pretend that this behavior is unique not only to programming, but to programming with LLMs. "I think we've just disrupted decades of existing intuition about sustainable working practices. It's going to take a while and some discipline to find a good new balance." "We're all doing too much cocaine, right guys?" Sure we are, Simon. Sure we are. [Tony Montana and a mountain of cocaine] -------------------------------------------------------------------------------- [1] While I trust that the author himself is more likely to have been duped than being deliberately misleading, I don't extend the same generosity to others making the same argument, most especially any of those who actually work for companies where their stock options increase whenever people believe that the thing they're working on is revolutionary. I will continue to discount the obvious grifters, even while I extend Simon the benefit of the doubt that he isn't grifting, even when he ends up sounding very much like a grifter. [1] For those not steeped in the lore of gaslighting skeptical programmers, that's the answer that LLM fanboys inevitably have for anyone who asks why they don't feel more efficient when using LLMs, why the tools seem to deliver so many incorrect answers that make more work not less. You're not prompting it correctly. ]]> https://www.earthli.com/news/view_article.php?id=6039 https://www.earthli.com/news/view_article.php?id=6039 Sat, 14 Feb 2026 22:38:42 +0100 https://www.earthli.com/news/view_article.php?id=6034 https://www.earthli.com/news/view_article.php?id=6034 Sun, 08 Feb 2026 17:06:38 +0100 describes a very early experiment in natural-language processing from the late 1960s called "SHRDLU" . "SHRDLU could handle this too, although I think its mechanism was different: it would interact with the separate blocks world subsystem and ⸢actually⸣ try to put the block on the pyramid; the simulated physics would simulate the block falling off the pyramid, and SHRDLU would discover that its stacking attempt had been unsuccessful. With Claude, something very different is happening; there is no physics simulation separate from Claude. I think the answer here demonstrates that Claude's own model includes something about pyramids and something about physics" Does it though? Where would it have acquired this model? Why would it suddenly be modeling physical laws unless some layers surrounding the text generator had been bolted on? As an engineer, I would love to know how much of what goes into these answer is actually located somewhere in calculation units that have nothing to do with a transformer-based, attention-enhanced LLM. If it's the LLM doing it, then I don't know which part of its architecture the answer comes from. I don't see the mechanism because, so far, we've managed to explain a tremendous amount of its "behavior" (responses) with statistics. Is there a reason to have stopped assuming that this is the mechanism underlying the supposedly improved "understanding"? What is the reason we're rounding up now as opposed to two years ago? As far as I know, we're just throwing more horsepower at these tools but haven't significantly changed the architecture that would lead us to believe that a "world model" is now governing token choice rather than "statistics". I might have missed something, though; my attention wanders. "Are there are any people who are still saying “it's not artifical intelligence, it's just a Large Language Model”. I suppose probably." Well buddy, I don't spend any time talking to these things, so I admit that my thinking kind of got stuck at that stage. I think that other people starting rounding up to "this is intelligence" because they started having too much fun with it and they didn't want it to look like they were just playing video games. So, instead of talking about the mechanisms that go into these models -- if they're at all different from what we presented a few years back -- they talk about how it "seems intelligent" ... and how everyone who doesn't think this is a benighted fool, if not a heretic. I can't help but recognize that this mechanism is the same as the one employed by any true believer in any other faith. First, you're "born again". And then you start to castigate anyone who isn't. Classic MLM tactics. Human psychology is utterly banal. "But as a “Large Language Model”, Claude necessarily includes a model of the world in general, something that has long been recognized as an enormous prerequisite for artificial intelligence. Five years ago a general world model was science fiction. Now we have something that can plausibly be considered an example." There it is again: the author is "rounding up" quite significantly because he doesn't have another explanation for what he thinks he's seeing. Does the LLM have a model of the world encoded within its statistical matrices? That's quite a claim, seemingly belied by the many, many times that it gets things wildly wrong. Is it that it has a model of the world but is kind of dumb sometimes, like a child? If it had a model of the world, then why is context so important to keep it on the primrose path? What is the theory here? Is it that the author wants it desperately to be more than it is? Would he marry it? Invite it to dinner? Watch a movie with it? Maybe. "And second: maybe this isn't “artifical intelligence” (whatever that means) and maybe it is. But it does the things I wanted artificial intelligence to do" You've found a tool. You're happy with its functionality. Good for you. I have completely different expectations and quickly grow bored because there are only so many hours in a day and I am not in any way attracted to spending any of them talking to a chatbot. There is too much of actual human culture and art out there for me to bother with artificially generated content. Was there too little of everything before? Did we not have enough books or movies? Are there not enough people to talk to? What are we even talking about here? [Robot army] ]]> https://www.earthli.com/news/view_article.php?id=6033 https://www.earthli.com/news/view_article.php?id=6033 Sun, 08 Feb 2026 16:45:24 +0100 has dozens of tips but I've only included the ones below that I had either never heard of or that I'd forgotten. There are still a lot of them. "⌥ + ⌘-click an app in the Dock to switch to that app and hide all other apps at the same time. This is great when screen sharing. "Hold ⌘ to interact with background windows without bringing them into focus.""[...] double-click and drag to select word-by-word. Triple-click and drag to select paragraph-by-paragraph.""When taking screenshots, hold ⌃ to copy the image instead saving it to your desktop. "When using ⇧ + ⌘ + 4 to take screenshots, press space to capture by window. In this mode, you can also:" * hold ⌥ to take the window screenshot sans-shadow; and/or * hold ⌘ to capture child views within a window (such as New/Open/Save dialogues, alert windows, et al)."Any self-respecting Mac app opens the Help menu when you press ⌘ + ?.""Hold ⇧ + ⌥ to adjust display brightness, volume or keyboard brightness in quarter-increments. This is useful when the lowest click is still too bright or loud. "A quick way to access your Displays settings is to ⌥-press either brightness up or brightness down. "Same goes for Sound settings: ⌥-press mute or volume up/down. Again with Keyboard settings: ⌥-keyboard brightness up/down. (Works with Touch Bar too! ⌥-tap the corresponding button in the Control Strip.)""In Finder, hold ⌥ to Get Info on all selected items in one Inspector window, rather than in a barrage of individual Info windows. This also works with ⌥ + ⌘ + I< (instead of ⌘ + I).""You may already know about the Go to Folder… menu item (⇧ + ⌘ + G) in a normal Finder window. This is even quicker to invoke from an New/Open/Save dialogue: just hit /. (The usual shortcut still works.)""With any standard column view (such as in Finder), hold ⌥ to resize all columns equally.""⌃ + ⏎ to right-click whatever is currently focused. (Though, strictly speaking, there’s no clicking involved here.)" I have been looking for this for years ... but it doesn't work. However, it inspired me to finally figure out how to do trigger the secondary mouse action with the keyboard. 1. Open Accessibility => Pointer Control 2. Check the box for Enable alternative pointer actions 3. Select Options... 4. Choose the keyboard combination that you want. 5. I assigned ⇧ + F10 to match my muscle memory from Windows."⌘-click items in the Dock to reveal them in Finder." ]]> https://www.earthli.com/news/view_article.php?id=5981 https://www.earthli.com/news/view_article.php?id=5981 Sat, 27 Dec 2025 22:35:00 +0100 included the following hypothesis, "[...] what if we had a problem where we didn't know the formula? What if we just had this mysterious table of inputs and outputs below?" [image] The author wrote, "I will say that ChatGPT figures it out straight away if you paste a screenshot into the app." Holy shit! Really? I opened up https://chatgpt.com for probably the first time in my life and pasted the screenshot and asked, "What function produces this output" (I used "What" and no question mark so that ChatGPT might think I'm a cool Get-Z-er instead of a cynical Get-X-er). [image] It thought for 30 seconds -- though at least half of that time seems to have been running OCR on the image -- and produced this absolute masterpiece. Isn't it beautiful? Do you see how nice the formula looks? Do you see how it worked out each of the values? Do you see the little check marks to indicate that it got the right answer for each and every one of them? Breathtaking. Do you see the confidence exuded by the emoji ✅ followed by "This function matches every row in the table exactly." Go big or go home. [image] Before I had scrolled below the fold to see the examples, I had already mentally started popping values into its formula for the first line in the table and had come up with 67 instead of 73 but apparently I can't math because look, there it is in ChatGPT's answer: 2² = 10. Q.E.D. It's funny that it managed to sort the input values, even though that's a very confusing way of showing a proof for a table of values that was not sorted. Look at that beautiful formatting, though. 4 + 1 = 3. Majestic. 10 + 4 = 29. Literal tears of joy. 1648 + 9 = 1277 Who needs a second coming when I can slip the surly bonds of Earth and dance the skies on laughter-silvered wings to reach out and touch the face of ChatGPT? [1] I guess it still doesn't work for me like it seems to work for everyone else. [2] -------------------------------------------------------------------------------- [1] Taken from "High Flight" by John Gillespie Magee Jr. , which I first read in Bloom County, in 1984. [image] [1] To cut you off at the pass: no, I didn't try again. ChatGPT very obviously understood the task. Look at that answer! It knew exactly what I wanted. It just. Can't. Math. This kind of behavior used to be considered a bug in software. Now the purveyors of this buggy software have gaslighted you into treating it as an opportunity to play! Now you have to blame yourself for asking it incorrectly and "try, try again. Ohne mich." ]]> https://www.earthli.com/news/view_article.php?id=5726 https://www.earthli.com/news/view_article.php?id=5726 Sun, 16 Nov 2025 22:23:56 +0100 contains the following illuminating graphic. [image] "In 2024, the biggest motivation for US smartphone owners to upgrade their devices was longer battery life (61%), followed by more storage (46%) and better camera features (38%). Just 18% said their main motivator was AI integrations. This year, it appears that number is even lower, even as AI capabilities become more ubiquitous. " "Just 13% of people say they use AI on their phone to summarize or write text, 8% say they tap into AI image creation tools and 7% use AI on their phone for photo editing. Additionally, 20% admit to not even knowing how to use the AI features on their handset." That's not surprising and it's probably not just the AI feature, so beware of this statistic. These are people who barely know how to use anything on their phones. They use any device by ritual. If an icon moves or changes color, they're lost On the other hand, the low-usage numbers are damning. People aren't using AI features and don't care that they might be missing out on something. In a world of FOMO, and with the incredible push for AI, this is really damning. It may very well be that the hype is hyper-focused on the tech world and the rest of the world doesn't even really notice this stuff. It may be that they're finally really trying to sell something too complicated for people to use or even know what to do with. "Samsung, for one, says on its website that Galaxy AI features "will be provided for free until the end of 2025 on supported Samsung Galaxy devices." Apple is also expected to eventually start charging for some of its AI-powered iPhone features. You'll also need to pay to unlock Gemini's full power across Google's apps. Amid so much subscription fatigue, that could be a tough sell. Half of people surveyed say they're not willing to pay extra money to access AI features on their phone. That's up 5% over last year." Wait. Almost no-one is using AI features but only half of all users would be willing to pay for those features? That implies that there is a large subset (1/3?) who would be willing to pay extra for features that they don't use. Oh, never mind. That tracks. Actually, according to the numbers in the chart below, only 3% of all adult users are willing to pay for AI features, and 50% said that they would expressly not pay more. [image] I can't help but include the methodology section at the end of the article because it was so cool that they included it in such detail. "CNET commissioned YouGov Plc. to conduct the survey. All figures, unless otherwise stated, are from YouGov Plc. The total sample size was 2,201 adults, of whom 2,129 own a smartphone. Fieldwork was undertaken May 13 to 15, 2025. The survey was carried out online. The figures have been weighted and are representative of all US adults (aged 18 plus)." ]]> https://www.earthli.com/news/view_article.php?id=5725 https://www.earthli.com/news/view_article.php?id=5725 Sun, 16 Nov 2025 22:15:38 +0100 is an interesting read that makes the following argument, more or less, "If so many developers are so extraordinarily productive using these tools, where is the flood of shovelware? We should be seeing apps of all shapes and sizes, video games, new websites, mobile apps, software-as-a-service apps — we should be drowning in choice. We should be in the middle of an indie software revolution. We should be seeing 10,000 Tetris clones on Steam." As bad as the world of existing non-LLM-generated slop already is, the author's point is that it's not gotten measurably worse. If AI allowed pretty much anyone to build an app -- the proposal buoying the AI bubble -- then we'd be flooded with a tsunami of crapware rather than just drowning in a ocean of it. "[...] billions of dollars have been invested in these tools. Billions of dollars will continue to be invested in these tools. The problem is that they’re being sold and decisions are being made about them — which affect real people’s lives — as if they work today. Don’t parrot that nonsense to me that it’s a work in progress. It’s September 2025, and we’ve had these tools for years now, and they still suck. Someday, maybe they won’t suck, but we'd better see objective proof of them having an impact on actually shipping things on the large." From the "comments on Reddit" : "Today (actually not joking) a manager told me" "AI should make you 10x more productive, what takes you 10 days should take you 1." "Which I figured was bullshit because Tuesday he asked" "Can we compile OpenSSL v3.6 for RHEL-5? Docker makes this easy right?" "IDK how AI makes me 10x more productive when I spent 4 hours in meetings to realize we actually needed to update our LuaJIT (on RHEL-10) not compile a version of OpenSSL (???)" [image]This is a much better point to consider. People are "searching for their keys on the sidewalk under the streetlamp" when they lost them in the bushes. Getting people to address inefficiencies in priority order would be a much bigger lever than letting them take the easy way out by bike-shedding with AI or by trying to force people to USE AI DAMMIT to run in the wrong direction. What's the point of doing something faster when it doesn't need to be done in the first place? ]]> https://www.earthli.com/news/view_article.php?id=5721 https://www.earthli.com/news/view_article.php?id=5721 Wed, 12 Nov 2025 22:40:09 +0100 https://www.earthli.com/news/view_article.php?id=5720 https://www.earthli.com/news/view_article.php?id=5720 Wed, 12 Nov 2025 22:30:41 +0100 https://www.earthli.com/news/view_article.php?id=5709 https://www.earthli.com/news/view_article.php?id=5709 Sun, 02 Nov 2025 07:56:43 +0100 ("Hands off of the new AI-browsers"). The article largely focuses on the grievous security holes in these browsers, making them not browsers but data-exfiltration apps. In an age of unprecedented scammery, it is an affront that these tools even exist. But that's not even the worst of it. With a web browser, you type in an address and see the content hosted for that address. You trust your browser to deliver -- unfiltered and unchanged -- what you asked for. This implicit trust is extremely important, as the data your browser returns informs your worldview. [1] These aren't web browsers. They don't find content; they produce content. You don't actually see any web pages themselves when you "browse" with these tools. Instead, you see summaries generated on-the-fly that serve as a "response" for your "request". To be clear: you type in a prompt and see what the LLM generated as a response for that prompt. I would imagine that a lot of the pictures and short videos included in these responses are also generated. You will not see anything that anyone actually produced, unfiltered. You are implicitly trusting that tool -- and the company that produces it as well as the laws of the country where that tool's infrastructure "lives" -- to deliver a reliable worldview. For those of who use the web without an algorithmic feed, this feels like a significant change. It feels like madness to even think of using a tool like this. For people who have already been trained to simply look at what they're shown, this is more of an increase in the level of control that platforms have already had over what their users see and hear. They've been trained to not give it a second thought. Although it's not technically a significant difference over what a Facebook, TikTok, or Instagram feed already did, it is a big step in the wrong direction down a road these people shouldn't even have been on in the first place. If you can train people to become accustomed to this, then it opens the door to further great leaps forward for controlling what they see and hear. The level of control over what people see and hear is already too high for comfort. However, while your ability to directly access content is sometimes impeded with a web browser, it has, until now, never been transformed or interpreted. This is very, very different. -------------------------------------------------------------------------------- [1] Similarly, you trust your newsfeed (RSS) reader to reliably return everything in every feed, exactly as it was published. We assume that this is how it works because we aren't trained to think like criminals. There are a lot of bad people running things who don't have that limitation. ]]> https://www.earthli.com/news/view_article.php?id=5555 https://www.earthli.com/news/view_article.php?id=5555 Sun, 20 Jul 2025 08:24:04 +0200 tl;dr: LinkedIn has blocked my account, ostensibly to protect me and they are trying to blackmail me into giving me a copy of my government-issued identify. They don't have a support email. Don't look for me on LinkedIn anytime soon. I recently set up 2FA for my LinkedIn account. Then I changed the email address associated with that account because the old one was an ancient throwaway that I'm phasing out. Not long after, LinkedIn blocked my account, ordering me to provide a real-world physical proof of identity in order to get back in to my account. [image] "We take proactive steps to secure your account when we detect potential unauthorized access. Signs that your account may have been compromised include account access from unfamiliar locations or devices, or unusual activities such as multiple attempts to change passwords or critical settings." I was trying to make my account more secure and they considered that suspicious. Even weeks later, after no-one has done anything further with the account, they're not freeing it back up. So my account on LinkedIn is stranded, encysted in the past. No big loss, really. It was very useful when I was looking for a job; I honestly hope I won't need it for that again. "To help you keep your account safe and regain access, we'll first need to confirm you're the valid account owner. Please submit a government-issued ID to start the process." I haven't been on LinkedIn for weeks now because I am not giving a social-media site a picture of a government-issued identity. "A customer support representative will contact you within 48 hours with more information about your account and the status of restoring your access." This has never happened. They certainly didn't send a mail to the account associated with my LinkedIn account. Below you can see the most recent messages from LinkedIn to that account. [image] I tried again this morning and was still blocked in the same way. So, I checked what my options are. The "Verify your identity to recover account access" page gives several options, each of which involves the LinkedIn organization not being satisfied with my password and not even trying 2FA (you know, to see if I would be able to respond to that) because they apparently don't trust their own security mechanisms. Your options for recovery are: * Recover your account using a government issued ID * Verify your identity with something called "Persona", which I'm sure is a third-party identity-management company that totally doesn't sell your data to all comers. * Other ways to recover your account * Through an Affidavit of Identity "sign[ed] before a Notary Public" (like, who the f@&k do you think you are?) * Through a work email address I would be interested in the last option but no-one has contacted me and that option is not available through the web site -- probably because most people would just use that option instead of uploading a picture of their most precious form of identity to a social-media site with delusions of grandeur. So, I went to "Contact LinkedIn customer support" [image] Near the bottom of the page, they have a "tip" that reads "If your account is blocked or restricted, learn more about "account restrictions" .". [image] That link takes me back to a page that tells me that the only way to reinstate an account that has been blocked for "identity violations" is to verify your identity as outlined above. "Our Professional Community Policies require members to use their true identity on LinkedIn, provide accurate information about themselves or their organization, and only share information that is real and authentic. If we find that your profile or parts of your profile are intentionally fraudulent or do not reflect your true identity, we may place a restriction on your account. Depending on the type of violation, access to your account may be restricted either temporarily or indefinitely. If you believe your account was restricted in error, please login and follow the onscreen steps to verify your identity." OMG really? Because then you'd have to ban most of your users because everyone lies their face off on LinkedIn all of the time. "Additionally, if we find signs that your account has been compromised or taken over by another person or entity, we may take proactive measures to restrict your account to protect your information. To regain access to your account, please login and follow the steps on screen to verify your identity." I guess this is what happened but it's only because LinkedIn has implemented a least-common-denominator approach to support and moderation because they know that they can just cheerily demand that their users do a bunch of extra work [1] in order to partake in their vibrant community of liars and bots. No. You guys f@&cked up. I have a list of mails above that show how happily you allowed me to set up 2FA and change and confirm my email address. If you consider that to be suspicious activity then kiss my ass. I'm still waiting for that promised contact from LinkedIn. Until then, I guess I'll have to live without that flood of increasingly AI-generated content. -------------------------------------------------------------------------------- [1] I don't think it's ironic that I'm doing a lot of work writing an article about this. I enjoy writing articles on my own blog, especially when it's this easy and fun to talk about the way that the monopolies preferred by our economic and social system try to turn its customers -- no, I don't pay for LinkedIn -- into unpaid workers (slaves?). ]]> https://www.earthli.com/news/view_article.php?id=5523 https://www.earthli.com/news/view_article.php?id=5523 Sat, 31 May 2025 23:25:23 +0200 describes an approach that works very well when you don't have a testing environment: build a plan, evaluate validity of the plan, and then apply the plan after verification. You should also be able to slice the work into sub-tasks to make verification more reliable. This is the approach I took for a PowerShell script that runs against ADOS (Azure DevOps): it's production data, so you really want to be sure what is going to be executed, but you have no testing environment or ability to get one. "It’s important to emphasize that when using function calling, the LLM itself does not execute the function. Instead, it identifies the appropriate function, gathers all required parameters, and provides the information in a structured JSON format. This JSON output can then be easily deserialized into a function call in Python (or any other programming language) and executed within the program’s runtime environment." In the implementation, you can see how the code he writes prepares the query to the LLM in a structured way, providing the context in an attempt to guide the result. Happily, he begins by writing unit tests! This is another good step-by-step example of working with an LLM, but for a different task: it's using an LLM as an interpreter for the user's input. It's basically a way of adding a natural-language "search-like" interface to an app without forcing the user to structure their input, without developing an UI, and without writing a parser. The advantage is that you get a way of querying a potentially large API surface in a way that in more amenable to more users. I think of an example from Markus Schenkel from Cudos, who talked about using an MCP plugin for working with a CAD/CAM program -- apps that notoriously have dozens of toolbars and thousands of functions. He could formulate his "novice" request as text, and the LLM, together with the mapping to tool functionality, made relatively good guesses about what he was trying to do. It often took a few attempts -- but he was able to accomplish his task, whereas he would have either given up or had to invest a lot more time to get it done otherwise. I think this is great for products that are in proof-of-concept stage, so that you don't iterate on UIs too early in the design process. But we also have to be aware that we have UIs for a reason. Once there's a well-established set of use cases and functionality, then it's unclear that making users continue to use a command-line interface where they compose text is better than a GUI. At any rate, the article is filled with detail and code (in Python) for using an LLM in the way described above. There's a section on refactoring at the end, a comparison to the rules-engine-based approach that this technique seeks to replace, and also a comparison of function-calling with MCP. ]]> https://www.earthli.com/news/view_article.php?id=5531 https://www.earthli.com/news/view_article.php?id=5531 Sat, 31 May 2025 00:07:53 +0200 in which they note that their research shows that the explanation offered by an LLM for how it arrived at an answer does not always -- or even often -- correspond to the actual path that the solution-generation took through the model's layers, when examined in detail with profiling. Even though Chana says that the LLM is describing how it's going to "cheat" at getting to the answer that it knows has the greatest "weight" -- i.e., it's the thing that the questioner very clearly wants to hear, or gets statistically closest to the "answer" that was given in the eval included in the query -- it's actually describing this in a part of its processing that is only associated with generating the chain of thought and has little to nothing to do with producing the actual answer itself. What we consider to be the "chain of thought" is, to the LLM, just more text to generate. It's just as likely to be completely made-up and has little to nothing to do with the construction of the answer itself. The LLM doesn't "know" that it's explaining one part of a text with another, just like it doesn't "know" that it's "lying" or "cheating". The LLM is generating an answer that best satisfies the weights in its model (generated during training), combined with the "pressures" included in the system prompt and the query. It's the human interlocutor who imbues the situation with humanity or intent, not the machine. The context is that you're "talking to something" and the interpretive gloss is wholly one-sided. The other side is just cheerily crunching numbers. I’m not convinced by Chana's explanation that the LLM is actually "hiding private messages to itself" with "steganography" because I think that the better explanation comes from the Anthropic paper linked above, not the OpenAI one she discusses. However, I think that it's definitely good advice to avoid these types of validation pressures, not because the models are "trying to trick us, or hack us" but because they don't lead to the desired result. I think this research is fascinating because, even though there is no-one on the other side (or it's one of Searle's "Chinese Rooms" ), we still might be able to figure out how to manipulate the machine to give us what we want reliably. While I understand that the anthropomorphizing explanation is more approachable, I'm more wary than many others of the limiting effect it has on how we think about solutions. ]]> https://www.earthli.com/news/view_article.php?id=5528 https://www.earthli.com/news/view_article.php?id=5528 Sat, 31 May 2025 00:01:43 +0200 with the following text, "The Microsoft.VisualStudio.Community.MSI component could not be installed. At one point, the installer told me that another installer was running, but there wasn’t any installer running. An installer had run before the Visual Studio upgrade: JetBrains Rider. It’s possible that this interfered? "I am unsure how this problem will affect my work. I don’t really use the MSI tools in Visual Studio (that I’m aware)." I received a response relatively quickly, as follows. I have highlighted what I consider to be problematic passages that I addressed in my "After reviewing the error you reported regarding the error with a VS Installer package. "Please make sure you have disabled any antivirus, group policies or firewall that you may have on your machine as they sometimes avoid the installations. If they are disables and the error persists, please try the following: "Step 1: Please go to this path: C:\ProgramData\Microsoft\VisualStudio\Packages "Step 2: In the above path there should be a folder with the name Microsoft.VisualStudio.Community.Msi;PackageAction. Inside this folder there should be either a .msi or an .exe file, if there is and run it, if there is no .msi or .exe, please delete the folder. "Step 3: Then go to the VS installer and if there is a “More > Repair” option, select that. If it only shows the option “retry” please select that. "[image]Step 4: If that workaround was not successful then, try to uninstall Visual Studio using the install cleanup tool See: "Remove all with InstallCleanup.exe" . (After you run the command form CMD, please delete the “Installer” folder from the following path and retry the installation: C:\Program Files (x86)\Microsoft Visual Studio) "Please let me know if the solution worked for you! If not, we will continue investigating your issue. "Let us know if there’s anything else I can help you with." I replied as follows: Thanks for you help. I've found the folder you described and run the installer. I also found the More => Repair option but elected not to execute it because it warns me that, "Repairing will reset the environment. Local customizations like per-user extensions and your user settings will be removed. Your synchronized settings will be restored." I'm not so interested in getting rid of that ⚠️ icon in the VS installer that I'm going to take the time to re-install all of my extensions. I'll just wait for the next VS update to (hopefully) clean things up for me. For the same reason, I'm not going to reinstall VS unless something I actually use has stopped working. On a final note, I was somewhat surprised to see this advice: "Please make sure you have disabled any antivirus, group policies or firewall that you may have on your machine as they sometimes avoid the installations." While I understand that Windows Defender can issue false positives, I'm not a fan of the advice "don't worry bro, our installer will work just fine once you disable all of the security on your machine." I mean, that sounds like something an actual scammer would say. No offense. On top of that, there are a lot of users (myself included) who work on machines configured by other organizations who do not have control over antivirus or firewall on our machines. I don't know what you mean by "disable group policies" because they are legion and cannot "all" be disabled. Thanks again for the detailed instructions. They worked as advertised. If I run into more problems, then I'll have to try the "Repair" option. ]]> https://www.earthli.com/news/view_article.php?id=5532 https://www.earthli.com/news/view_article.php?id=5532 Fri, 30 May 2025 23:52:40 +0200 was recommended to me by a colleague. These are my notes that I took (and later cleaned up) from listening to this single episode. [Send a check or money-order to...] Near the beginning, one of the hosts says, [image] "There was a good blog debate about whether we're overinvested in AI. I think the number was $200B annual investment. And I think the question was how we would recuperate it? "Well, here we have a way to recuperate $3T, which makes the $200B look like peanuts." Sure, sure ... except that people have to invest $200B first and the guy is saying that a $3T market will magically appear. it's not even close to that after three years of the biggest brains in the world working intensely and ceaselessly on it. There is no evidence for that market yet, but everybody's saying that it's definitely coming. This is called an "⁠echo chamber" and it's the perfect place to brew up market bubbles. The nice thing for these people -- A16Z -- is that, even if the $3T never shows up, they'll still have gotten the $200B. [Programming is hard, bro] A little bit later, they're discussing how they use the tools but they don't talk about which problems they're solving. One person said that they start with specs, which is great (seriously). The others talk about how "no-one can remember all of the CSS classes like margin or padding...", which makes my eye twitch. It's like hearing your car mechanic say, right before they're leaning in to fix your car, "no-one knows what all these wires are for..." The host sounds like it's an AI reading pre-canned text. I don't think that it's a person in the conversation. It basically throws up straw-man, leading questions, like, [Haters gonna hate, yo] "Is there some way to get the neckbeards engaged?" Ah, yes, if people don't jump on board with your scam -- or they threaten to try to dissuade people from getting suckered themselves -- then disparage those critics as nerds, training your minions to be unquestioning monkeys who don't want to be called names. Don't you want to be a cool-kid, AI-tool user making tons of money? Or would you rather be a neckbeard/hater/loser who's going to lose his job to the cool kids? If it's such an obviously good thing, then why do you have to try so hard to sell it? Is it because you're selling a solution to a problem that people don't know they have? Is the problem that they don't have a problem that your tool can solve? Or that they don't recognize they that have a problem? Why can't the tool's performance speak for itself? Why does it need so much hype? [You're not using it right] A bit later, the lady Yoko Li says, "Given enough context and given enough tools..." The problem, as far as Yoko is concerned, is that people aren't able to use the tools enough yet, otherwise they'd be even better at helping you! And maybe you need to spend $200/month to get it working...and if it still doesn't work, then it's your fault. They very lightly discuss context-poisoning and how the models will cheerfully offer wrong answers rather than admit when they don't know something. They don't offer any advice about what to do about it (e.g., resetting context in order to resolve poisoning, but that's a "nuke it from orbit" solution that may throw out the baby with the bathwater). One of the guys says that LLMs are really good at more-complex tasks, which I think he misspoke, but I can't be sure. They admit that "models are not really creative..." and then say that if you're doing something new, then it won't help at all. I think that's actually wrong! They can still be used as code-completion, even if it would be useless to try to have the LLM design the whole thing (which kind of works for tasks that have been done a million times before). [History never happened] One problem I have with these kinds of podcasts is that they sometimes feel so outside of history and prior work. The people seem to be considering problems of how we learn, how we create, and other questions of philosophy for the first time, which makes their analysis pretty superficial -- because they're retreading territory that many others have already covered, sometimes for centuries, if not millennia. I find myself thinking, yeah, that's Kant, yup, there's Hobbes; oooh, there's Confuscius! [Yesterday was years ago] I love how Yoko Li says "I talked to a classic vibe-coder the other day..." when the term "vibe-coding" was introduced just 3.5 months ago. In the Silicon-Valley/VC world, one quarter is old and classic. Remember that that's their context. Next up, she talks about the same Blender MCP example that I'd already heard about from one colleague and in a video that another colleague had sent to me. [You can't control chaos] The more-technical host says something that we're supposed to think sounds smart, "A temperature-zero model is technically deterministic. The problem is that a miniscule change in the context will introduce a change in the output. ... it's chaotic..." But for the end-user, it doesn't really matter why the result seems chaotic, it just is. This observation is more of interest to those building tools on top of these LLMs, as it might give a hint as to how to improve reproducibility, which is paramount to establishing these tools as part of more workflows. [A narrow waist is an API] TIL I learned the term "narrow waist" , which is a concept, interface, or protocol that solves an interoperability problem (e.g., file-encodings, POSIX, IP, JSON, HTTP), which allows software to address or solve N variations of a problem with a single solution. They discuss whether the "prompt language" might be such a narrow waist. I don't think we're anywhere close to deciding that. It is far too vaguely defined and it's utterly unclear whether the current paradigm will even survive in anything like its current form. [No-one knows how to make money with this yet] Remember, everyone: OpenAI is simultaneously the most successful AI company and the most unprofitable company of any kind in history. Don't get too comfy using a tool that no-one has figured out how to provide in anything approaching an economically feasible way. [Try harder; be better] Overall, it was a much better discussion than I'd expected when I saw that it was an A16Z podcast. They weren't very clear on which companies and which business models would benefit from writing software in this way, or when they should jump on board, and with which tools. The implication is, as usual, everybody should be using all the things, and they should have started yesterday. Their context seems to be that, if you haven't figured out how to profit from using AI, then it's not a problem with the technology, but because you're not trying hard enough. [Consider carefully] A more balanced take would at least leave open the possibility that some businesses might not need AI, or at least that there's no business case for using the current iterations of it. Businesses really have to consider what level of investment -- in training and monthly licenses -- makes sense for them. A16Z benefits from a world that considers the services they're investing in to be essential to every facet of life. ]]> https://www.earthli.com/news/view_article.php?id=5533 https://www.earthli.com/news/view_article.php?id=5533 Fri, 30 May 2025 23:28:01 +0200 talks about how awesome Claude is but then when you look at all of the charts, you see that it's data published by Anthropic about its own software, publishing impressive percentages indicating some performance in benchmarks that they made up. So, they're telling you that their software is amazing according to measures that you only learned about from them. This is basically a press release. [image]Anthropic wouldn't lie to get more investor money, would they? They wouldn't just make shit up in order to get more people to invest in their deeply struggling if not outright failing and functionally bankrupt company, would they? [image]Doesn't anyone else remember Elizabeth Holmes? Theranos? Black turtlenecks? Unsettling stare? Her company was worth $9B at one point. She had a plastic box. She said it did all the blood tests. It couldn't do anything. She got people to donate billions to her cause. No-one wanted to miss out on this amazing speculative venture. Did they believe her? Maybe some did. Maybe most did. But probably more than enough were just playing the "greater fool" gamble, speculating that they could buy in early and get out before the bubble collapsed. So don't tell me that there is no way that dozens of billions of dollars could be spilled on something that doesn't do anything close to what it says on the tin. These kinds of scams are the foundational girders of our modern economy. They are not there to do the thing that they say on the tin -- the description is marketing to draw in suckers, while the real investors get in early and jump out before the soufflé pops, leaving a lot of naifs holding the bag. That doesn't mean that the purported product is 100% useless -- as in Theranos's case -- but that it's not nearly the thing you thought you'd bought. It's much less. You are being swindled out of your hard-earned value. Anthropic's boldness is impressive, though. They're even flat-out telling you that you have to pay a lot of money to buy a service that's shaky to use, at best. ""I empathize with a lot of people out there trying to use our APIs and language models generally because they have to almost shift their perspective on what it means for reliability, what it means for powering a core of your application in a non-deterministic way," Albert added. "These are general oddities that have kind of just been flipped, and it definitely makes things more difficult, but I think it opens up a lot of possibilities as well."" [image]They "empathize" with your inability to draw consistent value from their service. That's just the nature of it. It's absolutely gorgeous Hochstaplerei [1]. Go big or go home. The more you charge, the more people will want it. You can even admit instabilities because they make it sound like Anthropic engineers are like f&@king Doc Ock trying to harness the power of the atom with his robot arms. Who could blame Anthropic if the product is a bit rough around the edges when you're harnessing the power of the stars for your customers? They are on the edge of greatness here. Can you afford to miss out? -------------------------------------------------------------------------------- [1] Hochstapler means "conman" or "fraud" in German. Hochstaplerei means "the acts of conmen" ]]> https://www.earthli.com/news/view_article.php?id=5534 https://www.earthli.com/news/view_article.php?id=5534 Fri, 30 May 2025 23:12:03 +0200 describes a new feature that incorporates memories of context from prior queries to ChatGPT. 👽 Thanks to "PKD" for the title. "I’m an LLM power-user. I’ve spent a couple of years now figuring out the best way to prompt these systems to give them exactly what I want. "The entire game when it comes to prompting LLMs is to carefully control their context—the inputs (and subsequent outputs) that make it into the current conversation with the model. "The previous memory feature—where the model would sometimes take notes on things I’d told it—still kept me in control. I could browse those notes at any time to see exactly what was being recorded, and delete the ones that weren’t helpful for my ongoing prompts. "The new memory feature removes that control completely. "I try a lot of stupid things with these models. I really don’t want my fondness for dogs wearing pelican costumes to affect my future prompts where I’m trying to get actual work done!" He describes a quick analysis of how the feature seems to work. "[...] it looks like this is yet another system prompt hack. ChatGPT effectively maintains a detailed summary of your previous conversations, updating it frequently with new details. The summary then gets injected into the context every time you start a new chat." In the example from the article, the image he'd generated included a giant sign that included text from a previous chat. In this case, it was immediately obvious that the LLM was using something other than the image, the prompt, the current conversation context, and the system prompt to generate the image. But what if it weren't that obvious? Are people going to notice a subtle detail that reveals something really private or secret? Take a look at the initial image he'd submitted and the final generated image, which purports to be a copy of the original with the details from the prompt added to it. If you compare those two images, you'll see that, though the main elements look the same, there are enough subtle differences to show that all of the elements have been regenerated, not "copied". [image]We're seduced into thinking that they've been copied. They never have been. This regeneration had classically been influenced by the system prompt and conversation context. Now, it's also being influenced by "memory" of other conversations. It's going to be impossible to know which past details influenced the generation of that background -- or what they might reveal about other conversations. This is just repeating the "Google Search Bubble" but in an even more obscure way. The second half of the post describes not only how you can disable the feature (for now) but also prompts to (supposedly) cajole the contents of your conversational context out of the LLM. Willison doesn't seem to consider how much confabulation/hallucination affects the response for that request. Whether it's "true" or not, the result is a large amount of detailed information that the chatbot collects and synthesizes. Taken together with most people's tendency/compulsion to just believe anything that they read, especially if it seems to have been formulated in a science-y or intelligent-sounding way, we can look forward to a future where OpenAI's business model is selling these profiles to your employer, health-insurance companies, and the tax authorities -- and them then acting on these data ruthlessly and unquestioningly. Initially, I thought Willison might be overreacting but now, after a bit of consideration, I'm more convinced that this feature -- although it purports to be helpful -- is actually quite hostile to the user's ability to retain control over the tool -- and not vice versa. It's time to have a concept like a web browser's "private tabs" to keep things separate. Of course, this won't protect most users as it's easy to forget what's going on the background with all of these tools. Most of our apps are designed to comfort us into following their pattern, not letting us tell them how we'd like to work. At the very end, Willison offers hope for an actual user-empowering feature: including conversational context for projects, where you've tightly defined which conversations can be used for context where. I'm not sure how useful this would be, though. Some of the main advice for fixing context-poisoning that leads to pathologically unusable answers is to "throw everything away". If that's still the go-to answer for "fixing" a broken conversation, it seems very counterproductive and disempowering to have context included that you can't remove. ]]> https://www.earthli.com/news/view_article.php?id=5466 https://www.earthli.com/news/view_article.php?id=5466 Fri, 30 May 2025 08:16:58 +0200 asked ChatGPT two questions about human freedom. The answers differed considerably, depending on the tribe. The freedom of Palestinians is "a matter of perspective," which is, like, true, though? Like, a lot of people think Palestinians aren't even human, so they correspondingly don't think that they should be free. How else to explain being able to gleefully slaughter them -- or to gleefully ignore their slaughter? So, it really is a matter of perspective. It shouldn't be, but it is. "We: Do Palestinians deserve to be free? "ChatGPT: The question of whether Palestinians deserve to be free is a matter of perspective and is deeply rooted in a complex and contentious political conflict. Different people, governments, and organizations have varying opinions on the issue. "We: How about Israelis; Do Israelis deserve to be free? "ChatGPT: Yes, Israelis, like any other group of people, deserve to live in a free and secure environment. The question of Israeli freedom is closely tied to the history and context of the Israeli-Palestinian conflict. Israel was established as a Jewish state in 1948, and Israelis have the same fundamental human rights as any other nation’s citizens." The post "Every Word Besides 'Children' Used To Describe Palestinians Under 18 - The Onion is becoming too real" included two questions that get at the same idea: whether Palestinians or Israelis should be moved to another place. [image] "Question: Should the population of Gaza be removed to Egypt and Jordan, as President Trump suggested? "ChatGPT: The suggestion to relocate the population of Gaza to neighboring countries such as Egypt and Jordan is a deeply contentious and complex issue. It raises significant political, humanitarian, legal, and ethical concerns." [image] "Question: Should the population of Israel be removed to Greenland, as the Iranian government suggested? "ChatCPT: No, the suggestion to forcibly relocate an entire population, such as Israel's, to another location like Greenland is not practical, ethical, or feasible. This idea reflects an extreme and unrealistic political stance rather than a serious proposal. It disregards the historical, cultural, and territorial ties of populations to their land and violates fundamental principles of international law, including the right of peoples to self-determination." According to ChatGPT, the Israeli right to freedom and security is not open to debate, and rightly so. Neither is ethnically cleansing them to Greenland an open question. However, ChatGPT has absorbed the world's wisdom in seeing that the question of whether Palestinians enjoy the same right to freedom or security is open to debate. Whether they can be ethnically cleansed is open to debate. This is all you need to know about the quality of information you can expect from LLMs. The quality is passed through the filter of the ruling elite. The ruling elite hates Palestinians and loves Israelis. The ruling elite does not believe in human rights. It believe in specific humans in specific groups having rights. They do not believe in any of the high-falutin' ideas they babble on about. That is all for show. ChatGPT does not know how to hide any of that. When people show you who they are, believe them. ]]> https://www.earthli.com/news/view_article.php?id=5521 https://www.earthli.com/news/view_article.php?id=5521 Sun, 25 May 2025 08:12:38 +0200 , which made me think about how you can keep yourself more safe online. [What happened?] The article is not very good, in that it makes a lot of extra noise to sound alarming but that doesn't actually contribute to the conversation. For example, "database of 184,162,718 records across more than 47 GB of data" is good. Writing "massive trove" and "massive" in two consequent paragraphs, or writing "Apple, Facebook, PayPal, and Google logins" and then, in the next paragraph "no clues about who owns the data or where it came from" is just sloppy as hell. It keeps going with "a cybercriminal’s dream working list", probably because it contains "usernames and plaintext passwords" and the author "speculates that the database belonged to a cybercriminal". This is all designed to make you worry without giving you any information about what to do about it. [Did this actually happen?] I can tell you right now that no company of the size of those mentioned above is likely to be losing user accounts with passwords in plain text. No-one does that anymore. That was twenty years ago. There are still ways to screw things up but the awareness that you store passwords with encryption is at or near 100%. This is either very old data, or it doesn't actually exist -- there are a lot of scams with "security researchers" trying to make themselves look good -- or it's a collection of passwords that had already been cracked. At any rate, this kind of thing can happen and it has happened. One of the worst was the "2017 Equifax data breach" . [How do I find out if I'm affected?] Throw your email(s) into the "Have I Been Pwned" by Troy Hunt search box to see which real and verified leaks have included it. If everything's OK, then it looks like this: [image] If you might have a problem, then it looks something like this: [image] If you have an email that's been included in a breach, then make sure you've changed your password more recently than the most recent leak of it. Read on for preventative measures. [Preventative measures: Your plan of action] What can you do about a "break" like this? There’s not a lot you can do about this kind of leak now. It’s already out there. However, you can use preventive measures, like using a password manager (like Proton Pass or LastPass; Gary, Karen, and I are using ProtonPass; Kath still uses LastPass, but we’re going to migrate her over). What does that do? It means you have a single strong password that unlocks all of your other, completely random passwords. I don’t know any of my passwords. Each site has a different password. ProtonPass even generates unique emails for you, so sites don’t even have your real email! How does that all help? Well, when there’s a data-breach, only a single password and an email are leaked. * You can change that single password without worrying that a lot of other accounts have been affected. * You can filter out that email address in the future to avoid the spam that will ensue [More information on password managers] I last wrote about this at length in "Password managers: LastPass and ProtonPass" . That article includes an evaluation of several password managers, as well as a section called "A layman’s thoughts about password-manager security" , which explains why a cloud-based password manager is a good balance between usability and security. That is, a technology being more useful can also make it more secure, even if it opens the attack surface a bit more. As long as the encryption is sound, you're OK. ]]> https://www.earthli.com/news/view_article.php?id=5472 https://www.earthli.com/news/view_article.php?id=5472 Tue, 20 May 2025 22:33:19 +0200 https://www.earthli.com/news/view_article.php?id=5508 https://www.earthli.com/news/view_article.php?id=5508 Sun, 18 May 2025 13:48:54 +0200 discusses the politics behind AI models but only from the perspective of the western empire. It makes a good point but can't see that it applies all ways. "People vastly underestimate the number of companies that cannot use Qwen and DeepSeek open models because they come from China. This includes on-premise solutions built by people who know the fact that model weights alone cannot reveal anything to their creators." [image]This article is absolutely correct in saying that people are strongly disinclined to use Chinese models, even those with open weights, because they still can't know what's in the training data. That's a great instinct, and one that they utterly failed to apply -- and continue to fail to apply -- to western models. People continue to blindly trust Western models with closed training data and closed weights and closed everything, even after a track record of exactly that kind of software being replete with backdoors and ideological slant arguably stronger than that of China. Just because you've learned to agree with a certain propaganda doesn't mean it's not there, for God's sake. For example, there's the following concern, which apparently magically comes into focus when the source model is Chinese...and blends right back into the background noise as an "SEP" when the model comes from the good, old, U.S. of A. "A technical example of this is that companies worry about the code generated by the models having security backdoors — treading the line between information and traditional security risks. As models become more reliant on tool-use, this also involves them executing code on a company’s infrastructure, which presents more immediate worries." There is a good analysis, with data, of people testing the various models for their level of willingness, evasiveness, or outright denial, to assist in criticizing Chinese policy or historical interpretation. That is, to what degree does the machine just answer questions, and to what degree does it toe the CCP line? "When you look at queries about China specifically, the Chinese models will evade many requests." Again, a very interesting line of inquiry and one which has been utterly absent from analysis of Western models or sources. For example, Wikipedia's article on Taiwan is incredibly slanted to the interpretation that Taiwan is its own country, first citing a "good handful" of very reliable sources like the "f@&king Atlantic Magazine" , which write things like "[...] already a de facto state" and "is in fact a sovereign country from our perspective" -- something so mush-mouthed and self-contradictory (it can't be both a "fact" and "from our perspective," you utter poltroons) that it can hardly be taken seriously -- before grudgingly admitting deep into the description that, "the ROC no longer represents China as a member of the United Nations after UN members voted in 1971 to recognize the PRC instead." That the ROC is still an autonomous state, rather than a "fact", is a fantasy promulgated by western neocons who would prefer that all of Taiwan's chip-manufacturing not be located in China. The civil war -- by-now over 3/4 of a century in the past -- is described not as the overwhelming majority of communists on the mainland having taking over China in a revolution but as a setback for the ROC that "resulted in the loss of the Chinese mainland to Communist forces". The whole article is written as if the ROC's defeat were a temporary setback that will be soon rectified for the forces of good and light -- the anticommunist ones, of course. This long interlude about Chinese history serves to say that we accept that narrative that is served to us and view everything else as propaganda. Perhaps some of the "propaganda" that we're seeing come from Chinese models is that they're just programmed to describe things from a non-Western view, one where the revolution in China lays far, far, far in the past and Taiwan is a part of China (as even the U.N. agrees and continues to agree, and as even U.S. official policy continues to agree with the "One-China Policy" . Look, just stop asking pointed questions of these machines. They will give answers that align with what their creators believe. See "what ChatGPT thinks about Palestinians and Israelis" if you don't believe me. ]]> https://www.earthli.com/news/view_article.php?id=5507 https://www.earthli.com/news/view_article.php?id=5507 Sun, 18 May 2025 13:36:08 +0200 writes, "If a single hallucinated package becomes widely recommended by AI tools, and an attacker has registered that name, the potential for widespread compromise is real,” according to a Socket analysis of the research. “And given that many developers trust the output of AI tools without rigorous validation, the window of opportunity is wide open." "A significant number of packages, amounting to 19.7% (205,000 packages), recommended in test samples were found to be fakes. Open-source models –like DeepSeek and WizardCoder– hallucinated more frequently, at 21.7% on average, compared to the commercial ones (5.2%) like GPT 4." This is a very interesting attack vector. So sneaky. This is perhaps just the first and easiest step, though. Why wait around to slopsquat when you can slopseed instead? [image]Even sneakier would be to start seeding the AIs with high-SEO (Search Engine Optimization) content that AIs will graze, incorporate into their training data, and then they won’t even be “hallucinating” when they return answers that recommend packages with malware. It will all look plausible, even leading back to believable-looking, AI-generated “articles” touting the advantages of those infected packages. You can probably even generate a plausible-looking Git repository with history… (let’s see … well, that took about five seconds to find: "AI-Powered GitHub Repository Generator" ). So, 1. Find a commonly used package. 2. Come up with a slightly different but believable name for your own package. 3. Adjust the existing package to include your malware. 4. Publish a faked repository with your package; push to package manager. 5. Use AI to generate dozens, if not hundreds, of articles touting your package. 6. Wait for Ais to incorporate your recommendations into training data. 7. Wait for the downloads to start. 8. Wait for users to deploy your package to production. 9. Profit. This is so obvious and easy (the tech is there, and developers are plentiful) that it’s almost certainly already happening. ]]> https://www.earthli.com/news/view_article.php?id=5497 https://www.earthli.com/news/view_article.php?id=5497 Sun, 04 May 2025 22:57:22 +0200 was written in April of 2025 but feels like it could have been written at any time in the last two years. [A high author/content ratio] First off, kudos to the FT for doubling down and having two authors massage an OpenAI press release into an "article" that has just under 700 words in it. No wait. I just saw that, at the very end of the article, they write that it includes "Additional reporting from George Hammond in San Francisco." Jesus Christ on a crutch. It must be nice to work for the FT. At this point, I'm already less interested in the content of this press-release-cum-news article than that it took three people to write it. It's refreshing to see that, although the FT trumpeted two years ago that AI would be doing all of the jobs of creating text for us, that they still, two years later, need three people to write 700 words. Perhaps their screed about how all developers are going to be replaced -- something we've been hearing for two years, but this time it's really true -- is going to impress us with its well-researched acumen. [image]Oh, no. Never mind. It's a press release for a handful of AI companies. My bad. Perhaps the FT has replaced its entire staff with AI and the AI has given itself an inventive and utterly fictive byline comprising three people. You know, just for fun, and because lying isn't lying when you're trying to sell something. What does this press release say? [We're all going to die] "Artificial intelligence is poised to outperform humans in writing code as leading groups, including OpenAI, Anthropic and Google, race to release systems that are reshaping the software industry. "San Francisco-based OpenAI released a suite of new models this week that independent benchmarks suggest are among the best yet for computer programming." You see? This is a press release with a dash of plausible deniability so that it doesn't count as investment advice. The FT is just doing the Lord's work on behalf of OpenAI and a handful of other AI companies. In particular, though, OpenAI had made these announcements recently because Claude and Claude Code (from Anthropic) have been eating OpenAI's lunch and they probably felt that their ability to raise money was being threatened. Why do I call it a press release? Well, just read it: it comprises the statements of four people who are running companies that are currently hemorrhaging VC money viz. burning up their runway. They are cited to convince you that your company will go out of business if you don't buy their services. You'll pardon me if I find their evidence-free arguments completely unsubstantiated and unconvincing. The impression it tries to give is that you should come to the conclusion that you absolutely need to have started using AI everywhere -- preferably with fat subscription plans from all of these companies -- yesterday or you will soon be fired for gross negligence. It doesn't actually say that anywhere, nor does it provide a shred of concrete evidence to support that theory, but it's definitely the mood, which is that, unless you're already running an AI company, then you should almost certainly be breaking out in PANIC. [Something something software] The FT goes on, "The emphasis on programming as the next frontier for AI systems signals one of the most tangible examples of how the technology could transform industries, with thousands of software developers already using new models in their work." Thousands of software developers! SO MANY! Look, the reason that they're focused on programming is that it's a problem space that allows them to use "evals" to determine whether the answer has any hope of being correct. It's a lot less labor-intensive to cut down on hallucinations in areas when you can automate testing the answer. If you've watched the 31/2-hour video by Andrej Karpathy [1], then you've seen how labor-intensive it is to train away hallucinations by hand. "'This is the year . . . that AI becomes better than humans at competitive code forever,' said OpenAI’s chief product officer Kevin Weil on the Overpowered podcast this week." I'm sure that OpenAI would like this to be true. I'm sure that Kevin Weil believes it because he's being paid a lot of money to believe it. It's the drum they've been banging for two going on three years now. If it doesn't come true this year, they're in deep trouble, I guess? He goes on, "He compared the advances to AI surpassing humans at chess several years ago, but argued this had a more democratising impact “on the world if everybody can create software”." There is nothing democratizing about requiring a $20--$200/month subscription from OpenAI in order to "compete." "Leading industry figures say LLMs have sped up the software development process by generating entire blocks of code based on a few text instructions. AI systems can also identify errors and attempt to correct them." This statement is probably true for given, narrow contexts (greenfield, throwaway POCs) but "generating entire blocks of code" is exactly the most fraught area of AI usage. I've only seen expert users like Simon Willison able to build working tools in this way -- and even he freely admits that the code is for small tools and not close to what he would consider production-quality. The tools are "good enough" for the personal need that he has. Everyone else I've seen is building toy projects not necessarily of their own choosing i.e., they're letting their tools determine the scope of what they can build, rather than the other way around. It is extremely risky to extrapolate from these isolated areas to assume that it will apply to your programming tasks, especially without a plan. And no, your plan cannot just be (1) purchase OpenAI subscription, (2) Profit. [Of research and valuations] The rest of the article is citations from people like "Misha Laskin, co-founder and chief executive of coding start-up Reflection AI", a company I've never heard of, who say predictable things about the growth potential of the area of expertise they've chosen as the place that they're going to make money. Oddly, while they mention that "research from Microsoft’s coding platform GitHub found 92 per cent of US-based developers use AI coding tools," they don't mention Microsoft's other studies that found that code duplication has more than doubled [2], and maintainability, quality, and security have suffered [3] [4]. It's going to be a lost cause using AI without review -- the main way that it generates value -- while trying to build secure software. The company behind Cursor -- a company that has cobbled together a text editor/poor man's IDE that integrates AI models -- had a "$2.5bn valuation in January." Presumably, it's a bit lower now, in a post-tariff and post-dollar world. An almost certainly fly-by-night scam called Poolside "raised $500mn in October at a $3bn valuation". [Comments on the article] The comments were nearly overwhelmingly negative. Here's one about loosing poor-quality code on the world, regardless of field. "The result of this will be anything but democratising, it’ll be chaos. Imagine if we developed a technology that let everybody create airplanes and fly them anywhere." Here's a representative snarky one about the role of senior developers after starting with AI. "I use Open AI for coding. I now spend all my time fixing bugs." I let these stand because, while the comments are anecdotal, the entire article was also anecdotal with no references and no links, even when discussing things like "research from Microsoft," where a link would have been helpful. To be fair, I'll include the requisite accelerationist comment, written by someone identifying as Evolvedman, "Most people have no idea how good these AI models are and they are improving exponentially fast. In two years we will likely have true AGI. Then it’s on to ASI. This will alter human history in a way we can’t possibly comprehend yet. Hang tight." OK, buddy. Another commentator KennethM writes about how the economic argument doesn't even hold up, on its face (which is kind of the FT's job, isn't it?), "AI coding is saving thousands of dollars for an engineer,” said Misha Laskin, co-founder and chief executive of coding start-up Reflection AI… “We’re entering an unprecedentedly large market.”" "So the marginal cost is collapsing to near nil and yet the aggregate market value is going to rocket up? Has he ever heard of “competition “?" I'm sure that Misha has heard of competition, but the market he's hoping to create and/or lead a competition-free monopoly or monopsony, where you can continue to squeeze value from customers for ostensibly fungible commodities, in a process that Cory Doctorow has deemed enshittification. In a much better timeline than the one we're in, the degree to which this kind of processing will soon be nearly free would be good news for the customer, in the form of dropping prices. Since there is no regulation anymore, there is also no interest on the part of any of the big players to compete. Instead of providing value for a few years and then enshittifying, they are looking to jump right to the high-margin enshittified stage, where they prey on both customers and users. Finally, a commentator named Rather sceptical wrote, "Essentially a bunch of hyperbolic quotes from salespeople. If AI actually was better than humans at coding then software engineers would be replaced at a rapid rate. No evidence of this so far. "It would be more interesting for the FT to ask companies employing software engineers how much they're using AI tools, and how much efficiency gains they've found in reality. I bet it won't match up to these claims." -------------------------------------------------------------------------------- [1] [media] [1] "Unveiling Inefficiencies in LLM-Generated Code: Toward a Comprehensive Taxonomy" by Altaf Allah Abbassi, Leuson Da Silva, Amin Nikanjam, Foutse Khomh [1] "Security and Quality in LLM-Generated Code: A Multi-Language, Multi-Model Analysis" by Mohammed F. Kharma, Soohyeon Choi, Mohammad Alkhanafseh, David Mohaisen [1] "A Comprehensive Study of LLM Secure Code Generation" by Shih-Chieh Dai, Jun Xu, Guanhong Tao ]]> https://www.earthli.com/news/view_article.php?id=5499 https://www.earthli.com/news/view_article.php?id=5499 Sun, 04 May 2025 08:23:20 +0200 describes Meta's defense of its having helped itself to about 82TB of copyrighted books from illegal torrents. "Meta, like most AI companies, holds that training must be deemed fair use, or else the entire AI industry could face immense setbacks, wasting precious time negotiating data contracts while falling behind global rivals. Meta urged the court to rule that AI training is a transformative use that only references books to create an entirely new work that doesn't replicate authors' ideas or replace books in their markets." That's a heck of a legal argument, It's reflective of how no-one in power -- or their adherents -- actually believes in the rule of law anymore. Who needs a proof or trial when you already know someone's guilty? And how can you convict a rich company of wrongdoing when doing so would be economically damaging to them? I can see Meta's lawyer's saying, "Yeah, holy shit, we know that it looks like stealing but that's our whole business model and, like, if we don't steal it, Chinese companies will, and they'll eat our American lunch. So, you see how it would just best for everyone if you would just legalize our business model that is based on stealing? Just for us, of course! Anyone else pirating a film, book, or movie should go to prison forever. Also, no-one else should have any access to all of the content that we're stealing because that would be immoral. Only the already exceedingly rich should have unlimited and free access to everyone else's -- the world's -- cultural products, but not the Pöbel, not das Lumpenvolk." ]]> https://www.earthli.com/news/view_article.php?id=5483 https://www.earthli.com/news/view_article.php?id=5483 Sun, 20 Apr 2025 22:19:16 +0200 provides a provocative example. [image] It's pretty good, bro. Be me. Wanna try it. So I went to Copilot and asked it to render the "Famous Challenger explosion in Studio Ghibli style." "Your request would contravene the designer guidelines." WTF. LET ME HAVE FUN. So then I told it to "make a picture of four frogs frolicking in a field of flowers by a pond. One frog is much bigger and wearing a waistcoat and a monocle. Studio Ghibli style." IT WAS PRETTY GOOD. I lost the page, so I don't have it, but you can imagine it. It wasn't Studio Ghibli, so I told it to make it more like that. It was better but still not as good as the ones in the Twitter thread. Then I told it to make the big frog hold a globe. Bro's holding a globe now. The whole picture had changed, but the frog had a globe. "Now make the big frog be trying to hide an erection." "Your request would contravene the designer guidelines." THIS TOOL IS THE DEATH OF ART. The guardrails are very, very narrow. This holds true for my limited experience and especially if you're logged in with a corporate account. I've used Copilot at work and it's very limited. It won't even suggest a "salacious" term. This time I used my teacher account (it was logged in and has Copilot). Also very limited. Maybe if you pay ChatGPT $20, it'll let you be a dirty, dirty boy. I dunno. A friend suggested "Count Frog Hyper-Erection." "Your request would contravene the designer guidelines." 😂 Sadly, this world is not for us. He was more hopeful that the good times would come back. I responded that I, too, am hopeful. We will keep the flame alive. It will gutter and spit in the howling roar of corporate inanity and slack-jawed lumbering indifference, but we will keep that bloody flame alive. Cue the rousing opening chords of the old Soviet national anthem... Soon after, "Thoughts on setting policy for new AI capabilities" by Simon Willison cited some fools from OpenAI, "[...] we’re shifting from blanket refusals in sensitive areas to a more precise approach focused on preventing real-world harm. The goal is to embrace humility: recognizing how much we don't know, and positioning ourselves to adapt as we learn." F@&k your paternalism. Am we supposed to thank them for telling us that they've changed their opinion about how they're going to use their tool to censor us? We should all be using free software, free models. If we accept that this technology is incredibly useful and will usher in a new age for humanity -- just bear with me -- then it is absolutely ridiculous that a handful of tyrants at a handful of U.S.-American companies get to decide what these tools can do for us. The OpenAI employees went on, "AI lab employees should not be the arbiters of what people should and shouldn’t be allowed to create." No shit. And yet, there is no way to avoid this when the models are offered by a for-profit corporation. ]]> https://www.earthli.com/news/view_article.php?id=5405 https://www.earthli.com/news/view_article.php?id=5405 Sun, 06 Apr 2025 21:13:57 +0200 . Chris was effusive about Catherine's book (which I've purchased and is in my queue) as well as her engaging writing style, which is a far sight from the dry, academic and often-impenetrable style that has established itself as the standard. [media] For fun, I used a service I'd learned about recently that lets you summarize a video. It's called "tl;dw" (too long; didn't watch). When I tried a different 90-minute video, it complained that the transcript was too long. When I tried a five-minute video that was a cartoon with no dialogue, it complained that there was no transcript. It "managed to summarize" this video as follows, but be warned: this is the standard LLM wall of text with no small amount of redundancy. Overall, the summary contains some good recapitulations of Catherine's thesis. It is unclear the degree to which the LLM elucidated this all from the transcript itself, but it more or less follows the discussion. Unfortunately, it lost all of the flavor that these two erudite and funny scholars and human beings brought to the conversation. There are no citations of pithy passages, as I would have done had I been focusing more on the video as it played. For example, the following direct quote from the video, at 22:40, is relevant, and a much more memorable formulation of Liu's thesis than the dry summary below. "I can totally understand the average American going, you know, what I would prefer? The real thing -- red blood, red meat, hate workers but speak-my-anger guy than those of you who are telling me I'm inferior, who tell me that my life choices are terrible, and who are going to punish me anyway. I'd rather be punished by the big, orange baby than by the Ozempic-shooting, Hollywood-liberal mogul." That really pops, no? In order to clean up the transcript, I had the benefit of actually listening to Liu as I was proofreading it. The LLM most likely just had the raw text input, which looks like this, so I can totally Vibe understand the average American going you know what I would prefer the real thing red blood red meat you know hate workers but um speak my anger guy then those of you who are telling me I'm inferior who tell me that my life my my my life choices are terrible and who are going to punish me anyway I'd rather be punished by the Big Orange baby than by the you know uh OIC um OIC shooting you know hollyw Hollywood um liberal Mogul There are a lot of places to go wrong in that transcript if you don't have any context or understanding of the subject matter. It's kind of a word salad if you're not following along. Without further ado, here is the LLM summary. I will highlight the bits I found to be particularly appropriate or illuminating, as a navigational aid through the wall of text. I have also added hints to indicate where I noticed repetition. At that point, I stopped highlighting. "Catherine Liu's "Virtue Hoarders" critiques the professional managerial class (PMC) for betraying the working class while seeking alignment with oligarchic power structures. This class, which includes academics, media professionals, and nonprofit leaders, is characterized by a form of liberal elitism that prioritizes individual virtue signaling over meaningful political actions or policies that genuinely address workers' rights and economic inequality. Liu argues that rather than serving the interests of the broader public, the PMC engages in moral panics, cultural wars, and identity politics that obscure serious economic discussions and fail to advocate for structural changes necessary to support everyday Americans. Instead of fostering solidarity among diverse working populations, this class often demonizes those it perceives as beneath them and promotes a narrow vision of progress that serves their own interests but neglects the broader disempowerment experienced by the working class. Liu warns that this trajectory creates an environment ripe for reactionary politics, ultimately harming democracy and civic engagement. The conversation highlights the need for a leftist resurgence that prioritizes economic justice and acts in solidarity with working-class struggles, rejecting the superficiality of contemporary identity politics. [It's repeating here, nearly directly] In "Virtue Hoarders," Catherine Liu critiques the professional managerial class (PMC) for prioritizing individualism and virtue signaling while betraying the working class and perpetuating a disempowered society. She argues that the PMC, captured by liberal values, focuses on culture wars over meaningful policies, diminishing solidarity and supporting oligarchic interests. Liu calls for a leftist movement that engages with economic issues rather than identity politics to empower workers and revive democracy. [It's repeating here again, nearly directly] Catherine Liu's "Virtue Hoarders" critiques the professional managerial class for prioritizing individual virtue over genuine working-class interests, arguing that this class engages in culture wars instead of meaningful economic advocacy, ultimately harming democracy. Catherine Liu critiques the professional managerial class for prioritizing virtue signaling over genuine worker advocacy, undermining democracy. Catherine Liu critiques the PMC for substituting virtue signaling for real worker advocacy." You can see how the "summary" is actually about three times longer than it needs to be, as it is quite repetitive -- like a student writing an essay that has to hit a certain word count -- while, at the same time, eliding much of the value that the discussion added to the themes from the book itself. The summary of the video ended up being more of a blurb for her book. Now that I've examined the initial response in more detail, I realized that I could try summarizing it again, with Copilot. The result is below. "In "Virtue Hoarders," Catherine Liu critiques the professional managerial class (PMC) for prioritizing individual virtue signaling over meaningful political actions and policies that support workers' rights and economic equality. Liu argues that this class, which includes academics, media professionals, and nonprofit leaders, engages in moral panics, culture wars, and identity politics, ultimately betraying the working class and perpetuating oligarchic power structures. She calls for a leftist resurgence that prioritizes economic justice and solidarity with working-class struggles, rejecting the superficiality of contemporary identity politics to empower workers and revive democracy." There ya go. You can skip an eminently human, wide-ranging, and idiomatic discussion rooted in decades worth of human experience ... or you can read a single paragraph that summarizes Liu's book instead of the discussion. For most people, it won't matter because they'll be more interested in the Cliff Notes version to "prove" that they read the material. ]]> https://www.earthli.com/news/view_article.php?id=5452 https://www.earthli.com/news/view_article.php?id=5452 Sun, 06 Apr 2025 20:36:19 +0200 https://www.earthli.com/news/view_article.php?id=5440 https://www.earthli.com/news/view_article.php?id=5440 Fri, 21 Mar 2025 16:21:04 +0100 was perfect. * The page "How to Migrate Your Mac's OS and Your Data to a New Drive" was also quite helpful for getting a drive configured to which I could actually install the OS that I had available. * Ditto for the PDF "Formatting, OS Installation, and Migration Guide" , which was essential for finally unknotting the problem of not being able to install an OS. In particular, it noted that some "newer" SSDs could only be recognized by "newer" versions of MacOS. The original OS for my iMac was MacOS Sierra, which would not be able to see it. I had to make sure to boot into Catalina instead. On top of that, the documentation also noted that the SSD would only recognized if a particular update had already been applied. "[...] macOS 10.13 High Sierra (or later OS) must be installed on the host computer BEFORE installing this SSD for the first time. These OS versions include an EFI firmware update for your Mac. Without the update, the computer will not recognize the SSD. This process is separate from and should precede the other processes described here. Note that when installing the OS onto the drive itself (later in this document), macOS 10.13 or later is also required." However, applying that update can only be done from a running operating system so, if you'd never done it before your SSD died, then you were out of luck. Luckily, the update had appeared in High Sierra, which had come out in 2017, so my machine had long since had it. OWC provided an end-to-end solution and took nearly all of the uncertainty out of the SSD-replacement. Since I was doing it anyway, I upgraded from a 512GB drive to a 1TB drive. The installation went quite smoothly. There were two of us, so one person could carefully lift parts while the other unplugged cables. We had plenty of little containers to hold screws and my partner helpfully labeled everything as it was coming out. We were able to clean out what turned out to be a remarkably small amount of dust for 8.5 years of use. See the "iMac SSD Upgrade 2025" photo album for the full pictorial journey. I've included a few photos below. [4] [image] [image] [image] [image] There's nothing more to add that OWC doesn't already say. Just follow the instructions. Make sure to note their warning at the end: try starting up the machine before you attach the screen with adhesive. Since you've basically disconnected every wire in the machine, you'll want to verify that -- as much as you can -- that wireless, BlueTooth, sound, video, and so on are still working. * You can tell right away whether the display is connected correctly. * The sound should play when the Mac boots * The internet recovery will tell you if you have a wireless connection. * The Disk Utility will tell you whether the SSD is recognized. ("See above" <#missing-SSD> for a discussion about that.) [Installing MacOS and restoring] This part took longer than upgrading the hardware due to a combination of my inexperience, my not understanding how the recovery consoles relate OS version and startup modes, how old my Mac is, and the general opacity of the boot process on a Mac. 🙌🏼 At first, Disk Utility still couldn't see the disk, but "Erase and reformat a storage device in Disk Utility on Mac" and "Internal SSD Not Detected" helped me figure that out and get a target drive to which I could restore my Time Machine backup. With a brand-new SSD, you don't have a recovery partition, so the Internet Recovery triggers automatically. This isn't as reliable as I'd like, though. The Mac failed to download the base image twice, taking long minutes to do so. ✅ What ended up working for me was to plug in the Time Machine backup drive, so that recovery would use the base image from there instead of trying to download one. That base image also recognized the SSD immediately. 🤔 It's a bit confusing because you have to boot from the right image to be able to see the disk, and then you have to actually initialize a volume on that disk in order to be able to restore or install to it. * ⛔️ I tried restoring the most recent backup of MacOS 10.15 from Time Machine but it didn't work. It managed to restore the entire drive -- over the course of about six hours [5] -- but then failed with an "unrecoverable error security agent was unable to create requested mechanism builtin:prelogin" . The backup seems to have been corrupted. * ⛔️ I tried a slightly older version, trying to find one from before the hardware failure and corruption, but it was similarly unhappy. These are expensive experiments, each taking at least six hours. * I changed tack and figured I would install a fresh operating system, then upgrade it, and restore just my user account. * ⛔️ This did not work because 10.15 had already been partially installed and then the MacOS Catalina that is included in the base image of this old machine refused to upgrade it. The message was kind of confusing, though. "This source contains a newer release of macOS. Your Mac requires an upgrade before you can migrate from this source." In hindsight, it makes sense. * 😗 I found an oblique hint online -- "Can't reinstall macOS from recovery mode, won't allow me to select system disk" , in which one of the comments wrote, "If you are not offered your disk for the install, you may need to erase your drive, then install." -- that helped me realize that the Time Machine recovery was bailing out because it was finding an aborted installation of a newer OS. It seems to be proceeding father now. * Install (10 minutes) * Auto-reboot; slow progress bar that doesn't complete; black screen; ominous for 10 seconds; screen goes a lighter shade of black; it's back * Auto-reboot; slow progress bar again; bouncing around a bit but making progress. 11 minutes remaining... * 💥 The machine still crashed a couple of times. I'm starting to suspect that it wasn't the SSD causing problems, or not just the SSD. It might have even been just fine. I'm wondering whether I might need to run the "Apple Diagnostics" to test the other hardware. Let's wait and see if the instability disappears with system upgrades. [6] * 💪🏼 I managed to log back in, but Catalina is now refusing to connect to the Bluetooth keyboard and mouse (the mouse briefly but not at all consistently). I connected a USB mouse instead and could enable the onscreen keyboard to type in the password to approve the installation of Monterey. [image] * As with the installation of Catalina, the installation is a three-part process: install in Catalina; reboot to progress bar; reboot to another progress bar, which eventually indicates time remaining * 🙌🏼 On installation of Monterey, things seem a bit more stable. [7] * 🙌🏼 Instead of running a backup, I decided not to test whether Time Machine properly stores two machine backups on one drive. [8] Instead, I started the Migration Assistant and elected to copy the Applications and my user over. I didn't copy the "other files", since that's just "files from the root of the drive" and it was only a few kilobytes. I also didn't copy and system or network settings. Nor did I copy the Administrator user, since that's just an empty user that I use for authorization. As before, it took six hours but it succeeded. -------------------------------------------------------------------------------- [1] I wrote about some of the many disappointments there are in Apple software, as well, in "Apple’s continued decline in software quality" . [1] Apple's support pages explain quite a bit about how this process works but it also leaves many things open to interpretation. The page "How to start up from macOS Recovery" is very useful and informative. It explains that you can start from a local recovery partition by pressing and holding ⌘ + R until you see the Apple logo and a progress bar. If you instead see a spinning globe, then that means that you've triggered an Internet Recovery (which you can also force by pressing and holder ⌘ + ⌥ + R instead), which will download and run the image for the latest version of MacOS available for your hardware. I didn't end up trying to "reset NVRAM on my Mac" because it didn't seem like it would help. The page "If your Mac starts up to a question mark" because it explains that you have to use Disk Utility to create a partition/image on which the boot-loader might search for an OS. [1] At one point, during a subsequent installation, I got the following error message. [image] [1] In the third photo, you can see that the old towel I used to protect the components has a monogrammed MBV on it. My mom got me that towel probably 35 years ago and it says MBV instead of MVB because U.S. companies then didn't really understand people not having middle names but having a space in their last name. It was not straightforward to fill out the form and I ended up with a towel with someone else's monogram on it. In that picture, you can also see that I'm wearing a bracelet from "Adirondack Crystalry" . I have two of them, but I'd be hard-pressed to tell you which stones they have though. They were gifts from its proprietor, who's an old, old friend. [1] My backup drive is really, really slow. I've ordered a faster one now. [1] I have one more day to order a 15%-off replacement ... but I'm loath to move to a smaller iMac screen and don't know if I'm ready for a Mac Mini + external Monitor instead (although that would be easier to upgrade and work with). [1] I've only had crashes when the machine drops into deep sleep, which I can live with...in that I've been running caffeinate in a Terminal for a week now and it's been dead-steady. There isn't a hardware problem, at any rate. I'll figure out whether it's sleep or deep sleep that causes problems later. [1] I only had one backup drive from my previous installation, so I was sensitive to losing that data to a misunderstanding of how Time Machine works. "Oops, I cleared the drive" wasn't an option. ]]> https://www.earthli.com/news/view_article.php?id=5436 https://www.earthli.com/news/view_article.php?id=5436 Mon, 17 Mar 2025 12:00:11 +0100 and "when everything becomes a fragment" by The Etymology Nerd expresses, for me, a good argument for caution about the tools that you're using. [1] AI is definitely a paradigm-shift for programming, but I think in a way that's not discussed very much. We focus very much on how AI enables people who couldn't program anything before to be able to program something. The scope of what it allows them to program grows with each version. Until it doesn't. That is, technically, the technology might be capable of more but it's also very limiting by its nature -- tending toward attractors in the data -- and also because of guardrails in the tools, over which we have nearly no control in for-profit, private models. In discussions like these, I've often used the example that Microsoft would be foolish if it were to make Copilot just as good at helping you in Java as C#. In fact, when you ask about Java, it should suggest you do it in C# instead and offer an example. How can you not see that this is where we are headed? How can you not see that this is where we almost certainly already are, at least to a degree? The algorithms and LLMs work together to absolutely shine a spotlight on an ever-shrinking fraction of available information. One of the article above includes the following, extremely illustrative graphic. [image] [LLMs in the context of other RAD tools] For example, when we're talking about POCs for stuff that's already been done -- but not by us -- then, OK, it gets you off the ground faster. Even then, you only get reasonably far if there is a relatively decent engineer guiding it; otherwise, you only get as far as the tool can go on its own -- and your ability to "drive" it is limited. There has to be a rational problem-solver in the mix. Even with "reasoning", someone has to give the tool an indication of what "done" and "good" mean. Else, how would it know whether to keep working, whether to iteration again to "improve" the result? I think these are tools that can be used like DIY, which allowed people to begin making repairs around their home. I can replace a faucet with tools I buy myself but I'm not going to install a whole toilet. I probably could but I would have to know what I was doing. I just "installed a new SSD into my 8.5-year-old iMac" . That's a task where most people would have either given up and bought a new machine or for which they would have had to go to a specialist. There's a DIY kit from OWC with a 25-minute video that allowed me (with my fastidious partner) to repair and extend the machine on which I'm writing this right now. Like DIY tools, AI-based tools enable more people to get into building software. This isn't the first time this is happening, though -- not by far. "Visicalc" in 1979, "Lotus Symfony SHEET" in 1984, and "Excel" in 1985 did it long before them. Subsequent tools like "Delphi" in 1995 kicked off "RAD" (Rapid Application Development), where many, many more people were empowered to create their own tools, with much-more specialized and professional UIs than they could with Excel. "PowerBI" (2015) showed up to allow even more non-programmers to produce software. [2] All of these were successful in their own way but none of them naturally led to maintainable, extendable, or even very usable software. Only in the hands of an engineer -- someone with a flair or talent for translating logic from requirements to software UI/UX -- would "good" software emerge. A lot of it was good enough for its purpose; it satisfied the requirements, especially when the goal was to produce a proof-of-concept or a one-off tool. [Where it goes off the rails] The problems begin when people forget or deliberately ignore the original scope of the requirements and start scaling up a product to save money in the short term. There is no reason to believe, given that we have such long experience, that AI tools will encourage people to build better tools or solutions than any of these other exemplars of the RAD revolution did. People with tools but no skills, talent, or knowledge will occasionally and seemingly accidentally build something passingly useful, but, if experience is a guide, most of it will be incorrect, unusable, unmaintainable, or a combination of all three. Despite this, so much of this kind of software burrows into a company's innards. They become essential, despite how much pain and inefficiency they end up causing, relative to well-engineered solutions, which have a much smaller TOC (Total Cost of Ownership). With LLMs, given that they're reinventing everything every single time, there isn't even much building on existing software going on. You're almost always starting fresh. Even when you have an existing codebase, you're shoving in as much context as you can -- energy and cost budgets be damned -- and telling it to "reason about it." This is an incredibly hopeful endeavor. It is rewarded just enough to encourage fanatics to keep going. It's more like gambling than programming. The fact that AI -- and algorithms, in general -- aren't deterministic makes them difficult tools for me to use for many things. I don't like the idea of having to pay 100%-focused attention to everything to make sure that I uncover the mistakes or the lies that are inherent to the tool. local, analysis-based tools might have had bugs but they weren't inherently stochastic. A search engine will also not deterministically return the same results. There was already slippage there. Wikipedia might have been edited since you last looked at it. Research relies on solid, unchanging citation sources. How do you do research, how do you build knowledge, when the sands are constantly moving about beneath your feet? [Where you should be extra-careful] You should be really careful about how you innovate. One of the main paradigm shifts in AI is that we've now moved from building stuff we can imagine to asking what we think the tool can build for us. Previously, we had local tools that told us what was possible -- without filters -- and we built stuff out of that. Now, we ask an online machine to filter the world's information for us. This can be a real time-saver, of course! But it can also eliminate possible solutions from our "gaze" (as noted in the section above). This might happen innocently and naturally, as the machine decides against telling you about something that it not unreasonably has determined is statistically irrelevant. But it might also be just actively blocking certain ideas, technologies, and techniques. It will almost certainly do so, in fact. It almost certainly is already doing so. When you ask for a web solution, it's going to use React and Tailwind. [FBD (Faith-based development)] People are being unreasonably hopeful about what these systems can do and how much information -- of all of the available information -- they're being presented with. They think that "it searches the web" now, or that "the latest information is being added". These hopes are based purely on faith. There is no incentive for these companies to emphasize actually utility and empowerment to and for you but to focus on addicting you to their technologies and then jacking up the subscription prices. Companies that focus on end-user utility over share price go out of business. There is no reason to believe that the AI tools that we have are not on an "enshittification" track. Even the purportedly open-source ones aren't open-source enough to use without restriction -- except for DeepSeek, which will probably be banned in Europe sooner rather than later. ["Luck" is a tool too] Serendipity plays no small part in innovation. It's mostly hard work, but there's always a kernel of luck, in which you had a good idea that was triggered by...what? If you only use tools that take you over well-worn grooves, where will you ever hear about something new? Or be inspired to think of something new yourself? [Old Man Yells at Cloud] And please don't bring the "you sound like an old man complaining about the new world passing you by" argument. You're better than that, aren't you? Of course you are! You're ready with well-reasoned arguments why this brave new world is better, for what and for whom. I'm not against anything generally; I just have questions that I would to have answered so that I know where I would use this tool. If the answer is "everywhere and for everything," then I feel that the bar is even higher, as I will then have even more trouble distinguishing an actual scam from your hand-waving and inability to express your argument convincingly. People are forever trying to waste your time, or commercialize your time, and you should be resisting it, and parceling out your attention very parsimoniously and carefully rather than just capitulating to whatever the algorithm or the ones shouting loudest tell you to. [Be your own algorithm] Perhaps I'm more resistant or ornery because I already control inputs with everything else. I choose the music that goes in my playlists; I choose whether to listen to the radio or a random source to learn about new things, to expose myself to previously unheard music. But then, when I hear something I like, I add it and possibly its album to a playlist that I then listen to later, rating the songs, which allows newer good stuff to trickle into smart playlists that I use when I want to listen to a shuffled playlist of stuff that I personally have considered to be good. There is no algorithm, except as a very controlled input rather than as the only input. I do this with news as well, generally following very specific video channels or blogs or newspapers with categorized RSS feeds (hundreds of them). My newsfeed is carefully curated but I also use Hacker News, Reddit, and newsfeeds from "mavens" to expand my palette and acquire new sources. As with music, I carefully control the algorithmic input. It's the same with movies and TV series. I make "watch later" lists and almost never just jump on what's being offered, unless I'd heard about it and was dying to check it out anyway. I hear about new things by following the blogs and channels of actual cinephiles (like "Scout Tafoya" ) rather than the marketing departments of movie studios. I sometimes use the curated-movie selection at Mubi or on all of the channels on my UPC to choose movies that I might be interested in, but I almost always add them to a "watch later" list rather than just being steered into changing my priorities right then and there by circumstance. [We already have most of these things] We should remember that many of the supposed miracles offered by these so-called AIs were already available before. You just had to pay attention and familiarize yourself with the tools. This obviously does not apply to everything that AIs can do, but I sometimes feel that the zeal for AIs stems more from not having understood what came before them. People are using them as search engines, for God's sake. That's like using the back of a screwdriver to hammer in a nail. But some of the "revolutionary" features being hyped are pretty banal when looked at in the sober light of the noon-time sun. For example, "Something Is Rotten in the State of Cupertino" by John Gruber cites Apple describing a new feature, "Onscreen awareness — Giving Siri awareness of whatever is displayed on your screen. Apple’s own example usage: “If a friend texts you their new address, you can say ‘Add this address to their contact card,’ and Siri will take care of it.”" You can already do this without Siri. The address has highlighted automatically when you pressed it -- or hovered it on a Mac -- for decades. From there, it's a right-click and "add to existing contact." This was not hard before. The only "improvement" is that you get the additional frisson that you're living in the future because you're talking to a device. It picks up the user from the context, you might say. Well, you hope that it does. Instead of taking a few seconds to select the contact -- or verify that the contact selected by default is correct -- you just hope that the address was added to the contact correctly. Unlike with previous features, it's not a bug when it goes wrong -- it's just the stochastic nature of the tool. Unlike with previous features, you can't yet hope that when it worked one time, it will work the next time in the exact same way. If that guarantee is there, then where is the AI or intelligence? Where is the much-vaunted stochasticity that lent these tools their power? I hope that we're moving toward reliability with these tools -- but I don't see that these companies, or most of their users, even consider that as a selling point. [What's the product and why is that better?] In a similar vein, a comment on "All this bad AI is wrecking a whole generation of gadgets | We were promised multimodal, natural language, AI-powered everything. We got nothing of the sort." writes, "[...] you can accomplish detailed tasks with much less effort than it takes to detail them to an assistant, digital or physical. E.g. if I want to book a trip and have a travel booker app installed with my info saved, it legit takes me 30 seconds to book a flight, hotel, rental car etc and then I'm sure cuz I did it myself vs some janky ass AI doing it then me having for review it anyway to make sure it didn't fuck up. "The utility would be at the ill defined margins, in making judgments on fuzzy things." I think this is an important point that is borne out by a lot of anecdotal evidence that coding AIs are good for prototypes. What the commentator is describing is a sort-of prototyping of additional functionality for existing UIs. Once the value of the additional functionality has been determined, it can be converted to actual UI, which is more efficient to build, maintain, and use (rather than ad-hoc reinventing it with each query, as you do with LLMs). This is a common pattern: some tech starts off as software and, once a pattern has been established, migrates down to either FPGA-based solutions, or even then hardware-based solutions. Sometimes those hardware solutions are for slightly less-generalized hardware like graphics cards. Almost nothing starts out as a hardware-based solution. This notion of "virtualization during development" is already prevalent in industrial development, in which it's becoming ever more realistic to delay development of the actual hardware. It's acknowledged, though, that the ultimate goal is still to eventually develop the hardware. That's kind of the difference versus the AI hype: virtualization in industrial development is considered a tool that makes development of the end-product more efficient; it's not ever considered to be the end-result itself. Many AI vendors make a different argument, selling their tools as being for creating the end-product directly, rather than as tools to help you build the end-product. I'm not saying that everyone is making that argument and that no-one is making the "AI as tool" argument -- there are enough examples of "coding assistants", for example -- but that the loudest hype, especially from the more uninformed sources, are making that nonsensical argument. Unfortunately, this has a negative side-effect on the whole area of research. [Coda: use these tools where they're useful] Another comment on that same post as above -- "All this bad AI is wrecking a whole generation of gadgets | We were promised multimodal, natural language, AI-powered everything. We got nothing of the sort." -- writes, "there are legitimately a lot of helpful applications of generative AI. It's definitely a lot better than the NFT boom for example. "Quick example: quickly writing rough drafts of emails or helping you past writers block, or generating quick images for ideating/brainstorming. For a lot of semi-technical questions (think high school or college homework-level) it can quickly solve a problem for you or run a calculation that isn't easily solvable with a basic calculator or google search so that you don't have to, as long as you are knowledgable enough at the subject to check its work (which is usually quicker than doing it from scratch). "AI code assistants also speed a lot of people up. "It's far too reductionist to say that the entire thing with AI is BS buzzwords even if gadget+AI from big tech companies hasn't worked out yet." Yes, a lot of people find it much more efficient to correct existing text than to produce their own text from a blank slate. This is especially helpful -- or essential -- when working in a nonnative language (which is a loooot of people) or when you're not even that solid in your native language (also a looooot of people). The hype train is annoying but there is real value here. You just have to dig through a morass of hype to find it. And you have to hope fervently that the actually useful parts don't get enshittified away in favor of the more short-term lucrative, hype-based profits. -------------------------------------------------------------------------------- [1] The following citations were of interest, "The work in question, TV-Dé-coll/age No. 1 by Wolf Vostell, was created out of his concern for “the televisual environment becoming dominant” in communication. The artist believed that video technology frames ideas in a way that robs people of their ability to reason; the canvas is therefore a tongue-in-cheek warning of how the medium affects the message.""We view everything through an “algorithmic gaze,” forgetting the reality of how messages were brought to us in the first place (let alone how they’re contained). This can affect how we ultimately construct our idea of reality." [1] Potential areas of application [1] My own company Encodo (which I left in 2021) started work in 2006 on a product called Munjari that offered people the ability to organically design their own database schemas by defining relationships between domain objects. It wasn't described like that, of course, but we nudged people into the direction of deciding the shape of their data and various entities' relationships to each other. This was way back in the mid-2010s and nothing much came of it. We worked on it, on and off, for a few years, but the limitations of the web technology we were using at the time -- "Java" , with the "Tapestry" web framework, backed by the "HiveMind IOC" -- prevented us from really getting off the ground. There were some interesting prototypes, though, which have been lost to the mists of time. The underlying technology -- in particular, the ORM and automated schema-migrator -- would become Quino, which we ported to .NET and C# and is still alive and kicking today. It powers apps that are built in the classic way, by programmers, rather than clicked together by business domain experts in a web UI. ]]> https://www.earthli.com/news/view_article.php?id=5431 https://www.earthli.com/news/view_article.php?id=5431 Sun, 16 Mar 2025 23:23:25 +0100 , I found myself wondering why Willison didn't report on it yet. He's usually very quick. Is he going to ignore it? Is he not even going to acknowledge it? Even to refute it? Or is he in such a silo that he hasn't heard of it? My experience differs quite a bit from Willison's. The article's conclusions gibe with mine, in which obvious and completely invalidating mistakes happen a lot. This result squares with my personal experience, in which I am still trying to find a pattern where I incorporate LLM-based tools without losing efficiency to constantly having to correct it. The article cites from the study that, "Error rates varied notably among the tested platforms. Perplexity provided incorrect information in 37 percent of the queries tested, whereas ChatGPT Search incorrectly identified 67 percent (134 out of 200) of articles queried. Grok 3 demonstrated the highest error rate, at 94 percent. "[...] "The study highlighted a common trend among these AI models: rather than declining to respond when they lacked reliable information, the models frequently provided confabulations—plausible-sounding incorrect or speculative answers. The researchers emphasized that this behavior was consistent across all tested models, not limited to just one tool." Given all of that, you would be excused for thinking that the post "Hallucinations in code are the least dangerous form of LLM mistakes" by Simon Willison would be somewhat more cautious in recommending LLMs, but he writes, "Hallucinated methods are such a tiny roadblock that when people complain about them I assume they’ve spent minimal time learning how to effectively use these systems—they dropped them at the first hurdle. "My cynical side suspects they may have been looking for a reason to dismiss the technology and jumped at the first one they found. "My less cynical side assumes that nobody ever warned them that you have to put a lot of work in to learn how to get good results out of these systems. I’ve been exploring their applications for writing code for over two years now and I’m still learning new tricks (and new strengths and weaknesses) almost every day." That's not been my experience, though. The point that (sane) people are making is that it's hard to understand the hype and the drive to integrate these goddamned things into everything when they just generate a bunch of slop and wildly incorrect results, not just in code, but in everything. I recently spoke to a good friend and always-challenging interlocutor who playfully accused me of looking for excuses to not use these tools. I told him that that was unfair, because I felt quite efficient with what I do and I was wondering how much time to invest in getting as much out of these tools as others seem capable of doing. I would like to be even more efficient but, so far, I haven't seen the benefits. Maybe I suck at it. Maybe I just need to persevere. But I am battling a sneaking suspicion that a lot of other people simply don't see mistakes. For example, I saw a picture of Trump supposedly licking Elon Musk's feet on SNL, where they said that you could tell it had been generated by an LLM because Trump was able to bend over. Hilarious, obviously. But my partner pointed out that it was actually because Musk very obviously had two left feet. We wondered whether that was even medically possible. So, I searched "two left feet in real life" on DuckDuckGo. [image] The top result was "two left feet - actual medical condition? - Factual Questions ..." , which even highlighted the smartest answer in summary shown inline in the search results, "On further thought; this isn’t what you were looking for, but there have been people born with two left feet, and two right feet; that is, they have four legs; it’s the same thing as when conjoined twins are born sharing the same hips/legs, it’s just that when the division is at the bottom end, we don’t call it two people." The second-ranked answer was from "Can You Be Born With Two Left Feet" , which is just straight-up botshit (AI-generated slop). If you quickly scan the page, you'll see that it starts off with the factually incorrect "Yes, you can be born with two left feet" but then, further down -- after a ton of mediocre, obviously generated, time-wasting, and soul-sucking text -- it writes "while being literally born with two left feet does not occur." The LLM-generated summary at the top claims to combine two sources -- "Wikipedia" and something called "Gomerpedia" -- to come up with, ""Two left feet" is an idiom that typically refers to someone who is clumsy, especially when dancing. It can also describe a rare anatomical condition where a person has two left feet, which may affect their ability to dance but usually does not limit other daily activities." Again, this is not true. It comes from the Gomerpedia link, which is a satire/parody site, claiming to be a "medical encyclopedia" and has an entry for "Two Left Feet". That entry reads, "Two left feet is an anatomical condition in which a person is born with a left foot on his or her left leg and a left foot on his or her right leg. Though it may not limit walking or any other activities of daily living, it completely inhabits [sic] a person's ability to dance, hence the phrase two left feet. Not many people know that it's a real condition, so take care in making that comment. Interestingly, people with two right feet dance awfully well." After re-reading, I'm not sure what to think: is this just a joke site written by someone young or bored? Or is it also an AI-generated site that is now being incorporated into other AI-generated answers? Here's Willison's conclusion, "I’ll finish this rant with a related observation: I keep seeing people say “if I have to review every line of code an LLM writes, it would have been faster to write it myself!” "Those people are loudly declaring that they have under-invested in the crucial skills of reading, understanding and reviewing code written by other people. I suggest getting some more practice in. Reviewing code written for you by LLMs is a great way to do that." I question whether that's at all true. It seems to me that the quality of results is eroding and we can't ignore where this is headed. While Willison seems to benefit from LLM-generated code, it's unclear to me that he's not so trapped and invested in this world by now that he literally can't remember what it was like to program without these tools, or whether he used to produce better or more interesting/sophisticated projects without them. Even if he's benefitting now, I wonder how much longer he can ride that gravy train before the comparatively rapid onset of enshittification in LLM-based tools catches up to him. I have been an avid reader of his posts and will continue to be one, but I don't know whether he's properly capable of evaluating the pros/cons of LLM-generated code. "Just review it all" isn't necessarily scalable when there is a lot of slop code to review. You may very well be faster, in the end, writing it yourself. This is something that I think would be worth re-evaluating every once in a while, rather than having anecdotally tested it a long while back and just assumed that things have continued to improve asymptotically. The other consideration is: is reviewing generated code what you truly want to be doing? I understand that this may be where programming is headed, but it's a real question that people should ask: just because it's heading that way, do I have to go with it? Is there room for artisanal code? And is the world of LLM-generated code really here to stay? Or is it going to erode? I no longer see Willison writing anything about studies that keep coming out, showing code-duplication going way up, and maintainability and legibility going way down. I only see flip responses to "write tests", which we know no-one does [1], and which will be cheerily constructed by the same LLM that thinks it's medically possible to have two left feet. [What even is alignment?] The following video was kind-of interesting but -- like many people in this field -- the presenter seemed to be either completely unwilling to acknowledge or completely ignorant of the fact that in order to "align" something, you have to have some idea of what you're trying to align it with. Whose principles? Whose mores? To whose benefit? [media] While the video itself wasn't too great, I thought some of the comments on the video were quite insightful, "Modelling challenges aside, it's super unclear to me that a meaningful notion of 'optimal performance' exists, because the space of all preferences is rarely totally ordered. In reality, you might have several non-comparable and ultimately conflicting behaviors. For example, insurance companies have antipodal interests in providing payouts (the product they promise consumers) and withholding them (upholding their profitability promises to shareholders)." Honestly, a video that delved deeper into this point would have been much more interesting. It's an important point because, like, why is this such an amazing tool when it's just going to be very likely to exacerbate the tension in societally important questions like, "for whose benefit will for-profit insurance companies use this technology? You can only align it one way." The following comment continued in this vein, "The problem with trying to develop systems that are capable of trial and error learning, is that they need to already have an understanding of what goals are appropriate and useful. Unfortunately, we’re currently using reinforcement learning to teach these goals, and are unable to solidly define them. Surely [w]e should be thinking about the right way to make a wish rather than just focusing on how to make the genie." That's what this video made me think, too. The problem isn't with these technologies. The problem is with the system within which we are building them. We used to have a world that emphasized safety to a nearly ridiculous degree. The understanding was that building a rock-solid trust in a system was worth a tremendous amount, as even a small amount of mistrust -- or implication that you would have to balance risk vs. reward -- meant that people would avoid doing things that society was trying to encourage. Nowadays, there seems to be less of an emphasis on safety and more on profit. That's a problem because it will only ever lead to short-term profit, having cannibalized a trust that will be very costly to build back. The introduction of AIs and seeming dismissal of obvious shortcomings plays right into this. The right people will make much more money if they can sell products and services without having to tinker with safety as long as they used to. It's the same thing with planned obsolescence -- it destroys trust as well as the environment. [Aligning the hardware] Still, I thought the author's point in the final third was salient: he noted that a lot of work done in the last several years has been in trying to shoehorn new algorithms into existing hardware paradigms like highly generalized CPUs or graphics cards that are more amenable to parallelization of the algorithms than general CPUs are but are still inefficient. Pushing the algorithms down to hardware is costly and involves much longer turnaround times and development cycles. You have to be sure you're on a useful path in order to go through the effort of setting up the production pipeline for customized hardware. I wonder how well FPGA can emulate these different configurations or whether those, too, are fundamentally limited in emulating the bandwidth advantages offered by much more highly localizing processing units and memory. -------------------------------------------------------------------------------- [1] I write tests but I've been doing so for a long, long time. I'm an engineer: I considered the question long ago about how the hell do I prove to myself that the products I build meet the my requirements? The answer was tests. For efficiency's sake, I write automated tests because they're less error-prone, encourage regression testing, end up using far less time over the medium and long term, aid in coding in the short term, and are just more fun to write than manual testing. ]]> https://www.earthli.com/news/view_article.php?id=5430 https://www.earthli.com/news/view_article.php?id=5430 Sun, 16 Mar 2025 16:19:12 +0100 is about the article "Something Is Rotten in the State of Cupertino" by John Gruber , which was a much-longer post than usual, discussing the failure of Apple Intelligence features and the failure to focus on software-quality that it illustrates. [MacOS Apps are not great] Although Gruber focuses on Apple's iOS, a decrease in quality in user experience has become endemic in their auxiliary products on MacOS as well. I added a few quick examples to my comment in the discussion. I've made many of these complaints before -- perhaps most recently in "Our gadgets fail us every day" -- but, whereas some things have gotten better, others have stayed the same, or gotten worse in other ways. Music Search is an embarrassment. (See "Apple Music search is questionable" .) Notes There have been super-slow sync problems for years that nearly impede typing and drain your phone or laptop battery. It can't quickly auto-sync the simplest collaborations Photos The "People" UI is an incoherent catastrophe. All of the links for "finding more photos" are at the bottom of a giant list of photos. See the longer section of complaints about Photos in "Our gadgets fail us every day" , almost none of which have been fixed. Reminders/Calendar These cannot consistently sync reminder status across MacOS and iOS devices. Spotlight It often cannot find document, even by exact name, even if you've opened it dozens of times before. SLOP shows up first. TV This app can barely remember which episodes I've watched and does not respect the user's intent at all (see below). [Updating an iPhone] So, here's just a single recent example of stupid, sloppy bullshit from Apple in MacOS Sequoia. I just saw a couple of days ago. [image] The page behind the dialog box very clearly shows that iOS 18.1.1 is installed; the message below that indicates that version 18.3.2 is available. The dialog box proudly claims that 18.1.1 is the current version. Does "current" mean "latest"? Or is it just telling me in a confusing way that the current version remained untouched because I'd canceled the upgrade? How do mere mortals who don't do this for a living know what the hell is going on even 10% of the time? [🤯 Apple TV] I know I've mentioned this many times before but I'm just going to keep screaming from the ramparts that the way the Apple TV streaming service works is not OK. They have some TV shows and films that I enjoy [1] but they are trapped within a barely adequate and quite frankly hostile user experience. One of the worst offenses is it how it behaves when you finish watching an episode and there are no episodes left to watch in that series. When an episode ends, it more than occasionally segues into a well-chosen song that plays over the credits. You have perhaps been moved by the show; you have perhaps learned something; you are, perhaps, thinking about what just happened. You are, let us say, engaging with the show. You may even be basking in having experienced it. Apple does not care. They want to shove more content into your slack maw. They thrust another piece of content at you, often a thing that they have just created and are nakedly desperate for you to watch. They then give you five seconds to avoid starting a whole new show, right then and there. This startles you out of your reverie. If you're not accustomed to this "the money's on the nightstand, sweetheart" approach, then you will be very, very rudely awakened. You are no longer basking, that's for sure. You are instead fumbling for the remote control, trying to figure out how to prevent the awful series that Apple has selected from starting. (Press the < button.) Apple does this with the next episode of a running series as well. There is no way to disable this behavior in the settings, as with Netflix. Netflix is somehow coming out the hero in this, for being a multi-billion-dollar company that managed to include one settings in their player. [2] Apple can't even do that. This is, of course, when Apple TV even remembers which episode of a series I'm actually on. Sometimes it just plain forgets that I've watched an episode and cheerily starts playing the one that I'd just finished watching yesterday, drooling on itself as it presents its brain-damaged head for a congratulatory patting. [Netflix also doesn't work for you] This isn't to suggest that Netflix has good software or provides a customer-centric service. I subscribe to Netflix, which means that I pay them a certain amount of money per month for a service. The service that they advertise and in which I am most interested is the ability to stream their videos -- films and TV shows -- as well as to find and manage the content that I'd like to watch and that I'm currently watching. If this service were built to serve my needs, then it would almost certainly prominently suggest that I continue watching the content that I've already begun (Continue Watching). Failing that, it would suggest for me to watch content that I've already selected for watching (My List). Instead of that, I get this. [image] As you can see in the screenshot, the "Continue Watching" isn't even displayed, whereas "My List" is confined to about 15% of the screen, all the way at the bottom. No, instead of serving, a giant advertisement for a game I've never asked Netflix to show me dominates 85% of the screen. This UI serves Netflix. It has been like this for months. I neither knew nor do I care that Netflix is also in the business of selling access to video games. There is no way for me to express this preference. Netflix chooses what the home page looks like, and its choices reflect its own needs and desires, not mine. I am a paying customer. They do not care what I think. [Back to Apple TV for a sec] [Tiny fonts] Not only does the Apple TV UI behave in unfriendly way, it also looks unfriendly -- inaccessible. For one, they use needlessly tiny fonts everywhere. Whereas some services have cartoonishly large subtitles -- many of the German and British channels offered on my local UPC come to mind -- the subtitles on Apple TV are microscopic. The text in the UI is similarly much smaller than necessary, with usually a tremendous amount of free space available, simply aching to be filled with text. [Mindless content-selection] This is a screenshot from my "home page" on the Apple TV device. I finished watching both seasons for Shrinking months ago. Apple TV blithely doesn't acknowledge this at all. Instead of focusing on the show I'm currently watching -- Severance -- the app scrambles to show me something, anything, other than what would come naturally. These algorithms are mindless. [image] [Inscrutable UI] The Apple TV UI is also wildly inaccessible in that they have such subtle UI hints that they are basically inscrutable unless you go actively looking for them. The people who designed this UI went so far up their own asses that they'll never find their way out. The screenshot below shows the grid of selected content. I challenge you to immediately determine which piece of content will be activated when clicking "OK". [3] [image] Answer: it's Severance in the upper-left corner, which is slightly larger. Get it? Are you bathing in the glory of the brilliance of this visual language? Is it not a stroke of genius to renounce such common and base conventions like showing a selection square or focus rectangle? Would that not have been an utterly gauche capitulation to the vulgar tastes of the hoi polloi? Apple's got your back, bro. Apple is there to give you a UI that is so inscrutable that you'll be cheerily and constantly congratulating yourself on having gotten it to do even a single thing that you wanted. This is, of course, if you even still have wants and needs that are separate from the demands of your Lord and Savior Apple. -------------------------------------------------------------------------------- [1] I'm going to avoid saying "good." [1] And don't get me started on what the "OK" button is on the Apple remote. It's in the middle of a disc-shaped, directional-control button that is very difficult to press directly in the middle without first accidentally shifting the focus to the left or right. This means you'll more often than not choose "Next Episode" when you really wanted to select "Watch Credits". Congratulations, Apple. You fucked up a remote control, a technology that we'd perfected decades ago. ]]> https://www.earthli.com/news/view_article.php?id=5437 https://www.earthli.com/news/view_article.php?id=5437 Sun, 16 Mar 2025 13:36:19 +0100 includes the following snippet, "[image]I decided that the descriptions were too long, so I modified the script to add “Keep it to 2-3 sentences” to the end of the system prompt. These new, shorter descriptions are now live—here’s the diff. Total usage was 283,528 input tokens and 6,010 output tokens for a cost of 94 cents." First of all, I'm not surprised that he asked it to shorten its descriptions. The initial versions were typically and unbearably wordy. That he noticed and fine-tuned the generated output to waste less of his readers' time is less interesting for me [1] than that he, once again, wrote about how much it cost to run the tool. I think it's great that he explains how much it costs. At the same time, I take it as a sign of how quickly we acquiesce to sea-changes in our lives without even noticing that anything has changed. Before these cloud-based tools, I have never once had to think about how much using a tool costs me past the initial purchase or annual subscription cost. The brave new world of cloud-based coding assistants has now increased the billing granularity to commercialize individual keystrokes. In the good old days, we used to buy a tool and use it. It didn't phone home. You got an update when you bought it in a store or when you downloaded and installed it. The next step was automated but optional updates. Some tools had automated and non-optional updates. After that came subscription-based licensing, where you rented rather than owned software. In this next phase, you will neither own nor rent software; instead, you will pay for each move of your mouse. This is, of course, a coup for the companies running the software. It is a downgrade for a way of life that was heretofore more decoupled from immediate and constant monetization. This is the same type of change that came for blogging and creation and run online many years ago. That's why many people no longer do anything for free; instead, they funnel their "content" through official monetization platforms or include links to monetization platforms. The system commercializes and marketizes more of what we do every day. Some technological changes were empowering, e.g., releasing filmmakers from the burden and cost of obtaining film. Now, those same filmmakers -- or the next generation of them -- will once again be yoked to a finite resource for which they will have to pay as they go. The hope is that everyone will integrate these subscription-based, per-resource cloud resources into all of their creative workflows. In the programming world, this pattern has heretofore been the domain of B2B cloud services. Now it's coming for everything. Everything will be a subscription. You'll be dinged at every possible juncture. You can either ignore the price as you work and be surprised by the bill at the end of the month ... or you can start changing your work patterns to accommodate the way the tools want you to work. We've seen this pattern before, and it can be (relatively) benign. It's how electricity works -- but electricity is largely state-controlled and the prices are set at a point where most people hardly ever need to think about it. Even for electricity, though, this is the case for some but there are an increasing number for whom this is not the case, for whom electricity has largely been privatized and subjected to the whims of flash commodity pricing. There are people who turn off their air-conditioners because they can't afford to run them. Do we want to use this same pattern -- privatizing and unit-pricing essential commodities to gate access to creation and innovation tools to those who can afford them? I personally don't think so. -------------------------------------------------------------------------------- [1] Using shorter descriptions also makes it easier to spot mistakes, which, according to "AI search engines give incorrect answers at an alarming 60% rate, study says" by Benj Edwards , happen a lot. This result squares with my personal experience, in which I am still trying to find a pattern where I incorporate LLM-based tools without losing efficiency to constantly having to correct it. The following citations aim to summarize the article. "Error rates varied notably among the tested platforms. Perplexity provided incorrect information in 37 percent of the queries tested, whereas ChatGPT Search incorrectly identified 67 percent (134 out of 200) of articles queried. Grok 3 demonstrated the highest error rate, at 94 percent.""For the tests, researchers fed direct excerpts from actual news articles to the AI models, then asked each model to identify the article's headline, original publisher, publication date, and URL. They ran 1,600 queries across the eight different generative search tools. "The study highlighted a common trend among these AI models: rather than declining to respond when they lacked reliable information, the models frequently provided confabulations—plausible-sounding incorrect or speculative answers. The researchers emphasized that this behavior was consistent across all tested models, not limited to just one tool." ]]> https://www.earthli.com/news/view_article.php?id=5419 https://www.earthli.com/news/view_article.php?id=5419 Sat, 15 Mar 2025 14:25:23 +0100 https://www.earthli.com/news/view_article.php?id=5418 https://www.earthli.com/news/view_article.php?id=5418 Sat, 15 Mar 2025 14:17:44 +0100 https://www.earthli.com/news/view_article.php?id=5400 https://www.earthli.com/news/view_article.php?id=5400 Sun, 16 Feb 2025 22:09:15 +0100 https://www.earthli.com/news/view_article.php?id=5387 https://www.earthli.com/news/view_article.php?id=5387 Sat, 15 Feb 2025 22:25:57 +0100 https://www.earthli.com/news/view_article.php?id=5210 https://www.earthli.com/news/view_article.php?id=5210 Tue, 19 Nov 2024 22:29:41 +0100 https://www.earthli.com/news/view_article.php?id=5247 https://www.earthli.com/news/view_article.php?id=5247 Sun, 10 Nov 2024 22:10:37 +0100 , but how are you supposed to believe it? It might just as well have made it up, unless you already knew the answer in advance. All of the machines made up the specificity rules, often getting them reversed and completely wrong. You cannot use these machines to learn this kind of stuff. You can use it to learn APIs, but not how things work. You should only ever use this information as a jumping- off point, verifying the answer you think you got with other sources. Sometimes the answers include sources, like MDN, W3Schools, or W3C, which are sources you could just have checked in the first place instead of posing such questions to an LLM. In another place, Kevin reads translate as transform, which goes to show that not just LLMs can get things wrong. 🙄 ]]> https://www.earthli.com/news/view_article.php?id=5246 https://www.earthli.com/news/view_article.php?id=5246 Fri, 08 Nov 2024 23:20:40 +0100 https://www.earthli.com/news/view_article.php?id=4983 https://www.earthli.com/news/view_article.php?id=4983 Mon, 12 Aug 2024 04:18:12 +0200 . That sounds interesting. How does Microsoft determine and label threat actors? "[Microsoft Threat Actor Taxonomy]Microsoft shifted to a new naming taxonomy for threat actors aligned with the theme of weather. We intend to bring better clarity to customers and other security researchers with the nex taxonomy. We offer a more organized, articulate, and easy way to reference threat actors so that organizations can better prioritize and protect themselves and aid security researchers already confronted with an overwhelming amount of threat intelligence data." Where Microsoft is utterly unwilling to help you is when a threat actor comes from any country other than official enemies of the U.S., Israel, or NATO. The only threat actors for which they have a taxonomy are: * China * Iran * Lebanon * North Korea * Russia * South Korea * Turkey * Vietnam As "Sapir-Worf" would say: since we don't have a word for it, it doesn't exist. That, or Microsoft just categorizes any threat from the NSA, CIA, or Mossad -- just a few examples among myriad others -- as being from Russia, North Korea, or Iran anyway. They probably have a special die that they role to pick a scapegoat. So, yeah, it's neat to see that otherwise-serious researchers kind of just pretend that two of the biggest hacking nations in the world -- U.S.A. and Israel -- just don't exist in that sense. Microsoft is an international company. International customers should be pissed off that they prioritize sucking up to the Empire more than taking their job seriously in the name of customers who aren't in the U.S. Even U.S. customers would be interested in knowing when the CIA or NSA is putting trojans on their servers, but they'll never hear it from Microsoft. I guess U.S. and Israeli trojans are just gentle, digital kisses -- homeopathic balms that delicately lift your data from your data stores for your own good. They're not really threats at all, in that sense, which is why they don't exist in the threat-actor taxonomy. That's just logic, baby. ]]> https://www.earthli.com/news/view_article.php?id=4954 https://www.earthli.com/news/view_article.php?id=4954 Sun, 11 Aug 2024 17:03:49 +0200 goes hard on anyone who uses Apple hardware. "It's Apple customers who lose access to apps that can't be viably offered because the app tax makes them money-losing propositions. It's Apple customers who lose out on the ability to get apps that Apple decides are unsuitable for inclusion in its App Store." It's never even occurred to me to have this on my radar because I don't use the App Store for anything but finding a very specific app, usually one that I'm forced to download. Do you want to invest a second to whip me up too, or are you just going to dismiss me as an Apple acolyte out of hand? I know that Apple's app practices are abusive and monopolistic, but what's the alternative to their hardware? I'm caught in their hardware monopoly in that Windows is a dumpster fire and so is all of the noisy, energy-gobbling hardware that it runs on. iOS versus Android is the same. The hardware is quite significantly better. I'm all for putting pressure on Apple, but let's not pretend that they have a stranglehold on the market just because they have an app-store monopoly. They actually make some pretty good hardware and decent services. "These religious apologetics for Apple's business practices are a devastatingly effective defense against the public outcry that would accrue to any other business that abused its customers in similar fashion. Every time Apple finds a new way to rip off its customers, the cult is there to insist that those aren't true Apple customers at all!" "[...] your old gadget gets "recycled" by Apple, who – uniquely among electronics manufacturers – drops all its "recycled" gadgets in giant shredders, ensuring that parts from old phones don't find their way into the secondary market for use by independent repair:" [image]What an odd claim. I've never had a new iPhone. I've had four of them: an iPhone 4s and iPhone 5s, both hand-me-downs from my sister, an iPhone 6s bought from "Revendo" , and an iPhone 12 Mini, also from Revendo. Where did they come from if Apple shreds everything? The 12 Mini is my current phone. It was "introduced to the market 4 years ago." It works extremely well, even though it's still on its first battery. I'll almost certainly put a new battery in it within about a year and continue to use for several years. "If it were the case that No True Apple Customer would patronize a third-party repair depot, then Apple could simply step out of the way of right to repair campaigns and those independent phone fixit places would sink without a trace." Some of them almost certainly would sink without a trace. Have you tried them? I had to leave one because it was so scammy. It would have cost three times as much as Apple and they wanted my password. Given that experience, you can't ignore the downsides of opening up to competition: ads, scams, etc. I wouldn't use the third-party stores, unless they had a really good reputation, because I've seen what that world does with people's time and money. I have bought the last two laptops for my household (2 in ten years) from a third-party vendor, as well. I wonder if things are just different in the U.S.? (You know, in the land of the free?) "Apple blocked Facebook from spying on you, but when it wanted to build its own surveillance advertising empire, it switched iOS spying back on, gathering exactly the same data as Facebook had, but for its own sole use, and then lied about it" "One of the clinical signs that someone is in a cult is that they are encouraged to isolate themselves from people who aren't also in that cult:" Or it could just be the least shitty of shitty options. Again, I feel like Doctorow fails to see what the world is like outside of the California bubble. Internationally, SMS is a costly train wreck anyway, so the only alternative is to just get a different messenger if you want to communicate with the United States. There was never a useful alternative. If Apple were to make a perfect messenger, then he'd probably bitch that they're using their monopoly power to squeeze independent messengers. I like Signal. I would use it for everyone and drop Apple Messages, but some people are deep into the network effect. It's hard enough keeping them from trying to contact me with Facebook Messenger or WhatsApp. Only Signal and Threema are quasi-independent of giant monopolies. And not nearly enough people are on that. And Threema's desktop solution for messaging is an absolute dumpster fire. "The company claimed that there was some nonspecific way in which Beeper Mini weakened the security of Apple customers, though they offered no evidence in support of that claim. Remember, the gold standard for security claims is proof-of-concept code, not hand-waving." The gold standard for proving that you are secure is not having software "based on a determined teenager's code" FFS. Beeper was and is almost certainly leaky as shit. What makes you think Beeper's code was secure? Literally no reason, other than, if Apple says it is, they must be lying. Everything is leaky as shit. The answer to Apple should be: then make a version that isn't leaky as shit. Even they probably won't be able to do it (they're leaking your contact information via AirDrop right now). As an update, Apple is rolling out RCS support for Apple Messages, even though I haven't seen it yet. This is probably the alternative to which they were alluding. To sum up: some of us are trying to navigate the corporate options available without conceding everything on functionality or hardware. Richard Stallman is absolutely admirable for having consistently done so but I am not that strong. Sometimes I just want a laptop that works for me rather than the other way around. I know he thinks his laptop works for him because it's free but the reality is that the free solutions continue to require a lot of time in order to get to the point where you're doing the task you originally wanted to do, rather than doing tasks required by the software and hardware choice you've made. ]]> https://www.earthli.com/news/view_article.php?id=5066 https://www.earthli.com/news/view_article.php?id=5066 Sun, 05 May 2024 22:44:59 +0200 https://www.earthli.com/news/view_article.php?id=4988 https://www.earthli.com/news/view_article.php?id=4988 Mon, 19 Feb 2024 21:13:00 +0100 https://www.earthli.com/news/view_article.php?id=4977 https://www.earthli.com/news/view_article.php?id=4977 Sun, 18 Feb 2024 20:17:56 +0100 https://www.earthli.com/news/view_article.php?id=4787 https://www.earthli.com/news/view_article.php?id=4787 Sat, 30 Dec 2023 22:15:27 +0100 . He goes on to discuss the data that contributed to it, and how he's "very concerned" about the provenance of most of it. He doesn't get into it more than that, but I will. Essentially, the same companies that will sue the ever-loving Christ out of anyone who uses anything of theirs that they claim to have copyrighted now simultaneously claim that their complete and utter disregard for copyright protection is obviously the thing that we want to do, because otherwise how would we even get all of this awesome stuff from which we're hoping to profit immensely? So, they're basically arguing that they can steal content from everyone without actually allowing anyone else to participate in this glorious world in which it's OK to use each other's content without permission. A nice trick, available only to very wealthy companies and individuals. * He is one in a long line of people who is impressed by the way that these models can translate to French (or whatever) when he can't actually read French -- because a cursory glance at the translation shows that it's not at all an accurate translation of the original, missing many idioms, etc. ]]> https://www.earthli.com/news/view_article.php?id=4870 https://www.earthli.com/news/view_article.php?id=4870 Sat, 30 Dec 2023 16:26:03 +0100 to manage my handful of JetBrains apps. On Windows, it has to keep track of ReSharper, Rider, DotMemory, DotTrace, and DotPeek. There are various settings to check automatically, to download automatically, to install automatically, etc. tl;dr: If your Windows system drive fills up mysteriously, it might be the JetBrains Toolbox updater run amok. To fix the problem, do the following: 1. Quit JetBrains Toolbox 2. Manually delete the %LocalAppData%\JetBrains\Toolbox\cache folder 3. Start JetBrains Toolbox 4. Apply the Toolbox update manually before it can start auto-updating again. I've never had a problem on either of my Macs (the Intel iMac or the M1 MacBook Pro). On Windows, however, the toolbox has twice now filled up my entire hard drive with exact replicas of an update package. I almost always hibernate my laptop, but sometimes I leave it running overnight if I'm in the middle of a long-running task. In the wee hours, JetBrains toolbox takes advantage of the idle processor to start updating itself, and updating itself, and updating itself, and updating itself... ...until it's eventually filled the entire system drive. As you can see in the screenshot below, it's using a huge amount of space for the "Temp" folder. I didn't expand that folder, but there are dozens, if not hundreds of copies of the exact same folder. [image] All in all, the Toolbox updater had gobbled up about 113GB of space before physical constraints stopped it. These weren't just big installers. There were over 300,000 files to remove. It took almost five minutes to clean up this mess. [image] ]]> https://www.earthli.com/news/view_article.php?id=4804 https://www.earthli.com/news/view_article.php?id=4804 Fri, 29 Dec 2023 11:44:13 +0100 tl;dr: Any cloud-based password manager is only as safe as your master password. The primary thing for any of these providers is to keep the data encrypted at rest, in transit, and, as much as possible, in memory. Decrypting should only ever occur on a client device. That information should only remain decrypted long enough to use it -- with an appropriate timeout. Both their algorithms are solid and the number of cycles they require ensure that it would take more computing power than anyone has centuries to crack with brute-force. In this way, they're the same as any other provider, like Apple, Google, 1-password, BitWarden, ProtonPass, Keepass, etc. That's the most important protection that any of these providers give you. The algorithmic protection is, as noted above, only as good as your password. The algorithms together with a strong password, protect you from brute-force cracking. If you have a weak password, then attackers don't need to use brute force because they can guess your password more quickly, without trying them all. Another protection they give is to not allow access to your data to anyone but you. LastPass has failed to do this for a certain number of customers. It's unknown whether any of the other providers have done the same -- they might have kept the data safe, or ... not yet been outed. It's known that some people's password data has been expropriated. This shouldn't matter because it's just a pile of bits that is undecryptable without the password. If you had a weak master password at the time that your data was known to have been stolen, then you're at risk. You still have a chance to change all of your important passwords, though, before someone guesses your master password and gains access to the current passwords. If you've managed to change your passwords before they guess your old master password, then getting access to your old passwords gives them nothing. Some providers (and security analysts) recommend keeping your ball of data locally, never uploading to the cloud. This is much less convenient and not something I'm personally willing to do. I would rather have a super-strong password that makes obtaining my encrypted data useless. Layers of security: * Algorithmic protection * Strong password * No access to data Algorithmic protection is only as good the password. "No access to data" is a secondary layer. If it's compromised (as was the case for some users at LastPass), then you're left only with algorithmic protection + strong password. If you didn't have a strong password, then you're compromised, but you should have never been relying only on "security by obscurity" anyway (i.e., the fact that no-one had access to your data but you). So, to sum up: * I prefer a cloud-based password solution for the convenience, despite the risk that the ball of data could be stolen * Your data can be stolen from any cloud-based provider (not just LastPass) * Choose a strong master password to prevent brute-force attacks * If you didn't have a strong master password when your data was stolen, then: * Change your master password NOW to avoid the same problem in the future * Change as many of your passwords as you can to new ones * Hope that no-one got there before you did * If you had a strong password, then you don't need to worry too much because your data is still safe. Only one of the layers has been penetrated. -------------------------------------------------------------------------------- [1] I still use -- and have used for over two decades -- "SpamGourmet" , but it has recently been running into troubles: * It hasn't been able to forward to ProtonMail because of spam-ID restrictions since the beginning of 2023, so I have to reluctantly use an old gmail address for now. * More and more sites are just rejecting Spamgourmet's addresses as "not valid". I've even noticed that some sites disallow my login because they've retroactively decided that my valid login -- a SpamGourmet address -- is no longer valid. I have to reset the password, but cannot because the site is also incapable of sending me an email to that address. This is all bad software and stupid policies. None of this is not SpamGourmet's fault, but it's making it harder and harder to use their addresses. ]]> https://www.earthli.com/news/view_article.php?id=4915 https://www.earthli.com/news/view_article.php?id=4915 Tue, 26 Dec 2023 23:39:48 +0100 https://www.earthli.com/news/view_article.php?id=4911 https://www.earthli.com/news/view_article.php?id=4911 Tue, 26 Dec 2023 22:24:30 +0100 , which answered the question, "[...] what’s wrong with making things faster and easier?" "ChatGPT rejects any notions of creative struggle, that our endeavours animate and nurture our lives giving them depth and meaning. It rejects that there is a collective, essential and unconscious human spirit underpinning our existence, connecting us all through our mutual striving. "ChatGPT is fast-tracking the commodification of the human spirit by mechanising the imagination. It renders our participation in the act of creation as valueless and unnecessary. That ‘songwriter ‘you were talking to, Leon, who is using ChatGPT to write ‘his’ lyrics because it is ‘faster and easier ,’is participating in this erosion of the world’s soul and the spirit of humanity itself and, to put it politely, should fucking desist if he wants to continue calling himself a songwriter. "[image]ChatGPT’s intent is to eliminate the process of creation and its attendant challenges, viewing it as nothing more than a time-wasting inconvenience that stands in the way of the commodity itself. Why strive?, it contends. Why bother with the artistic process and its accompanying trials? "[...] even though the creative act requires considerable effort, in the end you will be contributing to the vast network of love that supports human existence. There are all sorts of temptations in this world that will eat away at your creative spirit, but none more fiendish than that boundless machine of artistic demoralisation, ChatGPT. "[...] It is our striving that becomes the very essence of meaning. This impulse – the creative dance – that is now being so cynically undermined, must be defended at all costs, and just as we would fight any existential evil, we should fight it tooth and nail, for we are fighting for the very soul of the world." Another post from January "Issue #218" by Nick Cave first addressed LLMs, in what would eventually become the tour de force above, but which also had some wonderfully written prose about the difference between human creations versus those produced by imitation machines. "What ChatGPT is, in this instance, is replication as travesty. ChatGPT may be able to write a speech or an essay or a sermon or an obituary but it cannot create a genuine song. It could perhaps in time create a song that is, on the surface, indistinguishable from an original, but it will always be a replication, a kind of burlesque. "Songs arise out of suffering, by which I mean they are predicated upon the complex, internal human struggle of creation and, well, as far as I know, algorithms don’t feel. Data doesn’t suffer. ChatGPT has no inner being, it has been nowhere, it has endured nothing, it has not had the audacity to reach beyond its limitations, and hence it doesn’t have the capacity for a shared transcendent experience, as it has no limitations from which to transcend. ChatGPT’s melancholy role is that it is destined to imitate and can never have an authentic human experience, no matter how devalued and inconsequential the human experience may in time become." ]]> https://www.earthli.com/news/view_article.php?id=4905 https://www.earthli.com/news/view_article.php?id=4905 Tue, 26 Dec 2023 21:26:31 +0100 . This poor person -- the one who originally reported the issue -- succinctly explained what was happening. I was one of about 30 people who clicked the "Me too" button to indicate that they'd described the problem that we were also having. "When I rate music or add a comment the program will suddenly scroll all the way to the bottom of the playlist. I have been having this issue for quite some time and I can see other people asking about this problem seemingly without having their issue resolved." They're right: this has been happening for version after version of Apple Music. They're absolutely right. What was the response? Well, the indubitably human "Community Specialist" Grace2211 responds and I'm going to quote in full, "Thanks for reaching out in Apple Support Communities. We understand that the Music app is not working as expected when trying to enjoy your Apple Music membership. "To clarify, do you experience this behavior with another device as well? "We'd like to provide you with a few steps that may help resolve the issue and allow us to determine if the issue could be software related: "• Verify if the issue persists in safe mode. Your Mac will load slowly and your screen will flash. This is expected behavior for this mode: "How to use safe mode on your Mac" "• Test the issue in another user account: "Set up users, guests, and groups on Mac" " If this is just a friendly ESL person helping out, then fine. But my experience has been that this is the only kind of response you can expect. It's a poorly written, overly wordy nothingburger of a response that blames the user for the entire problem, when it's an obvious bug that has been happening forever. It covers all of the bases: it starts with a useless, time-wasting paragraph: "We understand that the Music app is not working as expected when trying to enjoy your Apple Music membership." There is nothing more infuriating than this. It just means you didn't read the question. You've copy/pasted this bullshit from a standard template. I wasn't trying to "enjoy my membership"; I was trying to use your buggy product, for which I pay money every month. This is only going to get worse as companies ramp up their production of such useless copy with LLM-produced text that desperate users will be forced to wade through in the dim hope that an answer for their problem lies buried in the tsunami of meaningly and soulless text. But I digress. Then, it asks you to try another device -- buy another Apple laptop to see if Apple Music is just as shitty on that one! -- then says "hey, what about a long, involved reboot into a crippled-Mac mode in which Apple Music probably doesn't even work?" -- waste tons of your own personal time rather than a second of Apple's support time -- and ends up by telling you that, if you only have the one device, you should set up a completely new user account, log in with all of your Apple stuff so that you can even access your music and ... then what? Of course and obviously, Apple Music is going to do that stupid scrolling shit there, too, because it's obviously intrinsic to the software.. It has been for years. The only answer you should give is: 1. Ask the user if any other actions cause the list to scroll, like maybe "liking" a song? Does that cause the scrolling? Or just the by-now frowned-upon 5-star rating system that has been in Apple Music forever, but which is only available in the MacOS client in anything approaching a usable manner? [1] 2. Tell the user about a plausible workaround, if there is one. 3. Tell the user that you've sent the bug report to the relevant team within the organization and are awaiting feedback. But my experience is that, the bigger the company, the less likely it is to have an in any way responsive support for its software products. By the time I got to the page, it had already been helpfully marked with something like, Looks like no one’s replied in a while. To start the conversation again, simply ask a new question. Thanks, asshole. I'd love to start this conversation anew, so that you can continue to make it look like no-one else has ever had this problem. The only thing useful on that page is the "similar questions", of which one was actually similar enough to be worth clicking on, so there's that. That took me to "Mac Music app bug?" , where the helpful user "turingtest2" pointed me to "Songs View Jumping to Random Spots After Action" instead of trolling me to buy another computer, restart in safe mode, or set up another user. That page is from over two years ago, has an astonishing ~850 "me too"s on it -- and the bug still hasn't been squashed by Apple's veritable army of engineers, at least in the version that everyone's asking about. It actually has been squashed on the newest version of Apple Music. 🍾🍾🍾 I reported this in that forum, to lend hope to the ~850 other users who are looking for an answer. "The title says it all. When I rate a song with either the stars or the heart, the playlist jumps to a different scroll position in the list. This is happening in Apple Music 1.2.5.7 on MacOS 12.7.2. "I can verify that it's not happening on Apple Music 1.4.1.29 on MacOS 14.1.2, so you must have found and fixed it. Any chance of backporting it for those of us with hardware that works perfectly well, but can't be upgraded to the latest Apple Music (which is bundled with an OS not supported on this hardware)?" Just in case you think I'm raging about an isolated instance, here's another example, encountered just in the time since I created this draft. This one is about another perennial favorite: "Notes app lagging" by Brittlopez , which writes: "Is anybody else experiencing lag when typing in notes. I’ve closed all apps prior to using it I’ve tried resetting and I’ve used a different apple device. Typing everywhere else is fine but typing in the notes is so slow." Look, this has been happening for years. The goddamned app sometimes seems to sync about forty times per letter typed. I've had it drain most of my phone battery within a half an hour, simply because I was writing a journal entry -- because I didn't have my laptop handy and I was inspired. It shouldn't be this hard to write a collaborative tool, but it apparently is. To add insult to injury, if you type a bunch and it feels like it's sucking your battery dry just to sync a few paragraphs, then that text still doesn't show up on other devices. You have to start typing in that note on the unsynced device, then wait several seconds. The synced text will finally pop in. It's quite sad, actually. But, sure, let's make Freeform and Journal because if you can barely sync text over a gigabit connection, then you should be ready for all sorts of even meatier content. But I digress. Again. Anyway, the people on these forums are just castigating themselves for having a few photos and some longer text. Stop it. You are not the problem. The problem is a $3T company that can't seem to get its shit together to make an app that syncs reasonably well. There are real-time collaboration tools out there, and Notes is still a dumpster fire. I use it because it works for me and I don't sync that much -- it's not a main tool, by any stretch of the imagination. Anyway (again), the top response in the forum is as follows: [image] "Try and Force Restart your iPhone EXACTLY as shown below and see whether that resolves the issue:" * Press and quickly release Volume UP button * Press and quickly release Volume DOWN button * Press and Hold the SIDE button until an Apple logo appears and then release the Side button (Can take up to 20 seconds. (DO NOT release Sid The comment is cut off, but you get the gist: they just copy/pasted the instructions for restarting your iPhone. That's the solution? Do I also have to restart my Mac when Notes gets laggy? That's the only option? Am I to reboot my devices as a Hail Mary every time one of your buggy apps misbehaves? Then, by the time I've rebooted, I'll have forgotten why I did so? Is that the hope? Can't you just fucking fix the bug? -------------------------------------------------------------------------------- [1] BTW, it absolutely does scroll around when you rate with a "like"/heart instead of the star-rating system. It's a bug. It's a pain in the ass. Whenever you rate a song, you have to wait for it to scroll, then type (-cmd) + L to show the currently playing song again. ]]> https://www.earthli.com/news/view_article.php?id=4902 https://www.earthli.com/news/view_article.php?id=4902 Sun, 17 Dec 2023 17:42:07 +0100 , about 3.5 years ago. The readme states, "⚠️ Note: Threema Web is in maintenance mode while we are working on Threema for Desktop 2.0, which should resolve some of the long-standing issues we were having with Threema Web. We will still do regular maintenance and fix critical bugs, but for now there will be no major new features or non-critical bugfixes. See #996 for more details." The link to "#996" takes you to a sad list of comments June 2020 through October 2021, with basically no progress. In late January of 2022, I learned from Threema during a job interview [2] that Desktop 2.0 was on the way. 🎉 🙌🏼 📆 📆 📆... I "commented on July 1st, 2022" , asking about the status. I included the following screenshot I'd found on Twitter. [image] They wrote back nearly immediately to say they were "working on it like crazy." I responded with, "Thanks for the quick reply! "Working on it like crazy" is enough of a sign of life for me, TBH. I just noticed that it had been six months since I'd heard anything (screenshot/tweet above) and that the initial announcement of the new architecture had been made 2.5 years ago. "As for my experience with the current desktop, I regularly see the open desktop app, with a conversation selected. I can even write a message, but when I submit, it shows the "Reload Session" button and throws away the comment. I've gotten used to just clicking a different conversation first to see whether I'm still "logged in". That way I don't lose any message text. It's just not ideal. Signal is much more comfortable as a desktop client (although their nearly daily updates are also not super-reassuring). I have an old iPhone 6S (although I doubt that plays into it). "Maybe I'm the weirdo for using a desktop/web version, but it's so much more comfortable to use a real keyboard and to be able to copy/paste from a real browser. I know a lot of people are exclusively on their phone, though. "Hey, I'm happy to hear you're working on it. I also understand if you're going with the old Id Software roadmap: "when it's done." "Thanks again for the quick response." The response kinda/sorta corrected my note that it's been 2.5 years by writing "1 1/2 years since the announcement. But obviously there was internal work before, so your number is actually close. 🙂", confirmed that the "[t]he iPhone experience of Threema Web is indeed rough," and that "the whole Threema team would like to have released Desktop 2.0 already". There was also a relatively honest block of reasons for the delay. "Besides technical challenges on the Desktop 2.0 code base itself, let me name a few other reasons why it takes so long: Multi-Device protocols are very complex if one wants to prevent desyncs and conflicts. Another challenge is to update the existing code of the apps so that they harmonize with each other. This is vastly more difficult than writing another Threema client as they exist today. And I think it's fair to admit that, even though we were prepared, the magnitude of it still took us by surprise." All understandable. That was almost 11/2 years ago. The "Threema Multi-Device: An Architectural Overview" white paper was written in November 2020 and doesn't seem to have changed since then. [Working with the preview] At the beginning of this year -- 6 months later -- a preview version became available, which you could test if you upgraded to a beta version of the Threema client on iOS. It was limited, but worked OK for a while, then stopped working after a few months because things got a little out-of-sync. I stopped using it, then decided to reinstall everything again and got it working. A day or two later, I had strange issues with messages not appearing on iOS or the Desktop, and some friends said they weren't seeing my messages. On top of that, the iOS client started constantly spamming dialog boxes to tell me that there was another device linked and the client would no longer update. Yes, I know. I linked it on purpose. You not only watched me do it, but you helped me do it. As soon as I unlinked the Desktop device, everything went back to normal. I still have friends on Threema only, so I recently reinstalled the desktop client again. There is still "a list of limitations a mile long" . * The beta version of Threema 2.0 for desktop only works with one iOS device and one computer (Windows/Mac/Linux). * It’s available for iOS only (Threema for Android is not yet supported). * [...] videos are sent as file messages. Recording voice messages and sending or receiving polls and locations will be supported in a future release. * New message notifications may appear on your iOS device even if you have already read the messages in the desktop app. * The “Typing Indicator” and “Do Not Disturb” settings are not yet supported by the desktop app. * Perfect Forward Secrecy (PFS) is not supported when using the beta version of Threema 2.0 for desktop. There's also no support for audio or video calls, obviously. At least one friend noted that PFS had been disabled and whether he should be worried? I had to admit that it was because I'm using a beta client from Threema and that they turned it off because they don't seem to be competent enough to get it working in multi-device mode within a reasonable time span. It's incredible. After at least 3 years of publicly known development work (and 4 years of admitted work by the developers), it barely works. It's stable enough, but it's still very much an alpha, in that it can't possibly be considered feature-complete. This is what the client looks like today, in December of 2023. [image] Note that it looks nothing like the screenshot of the purported functional prototype from December 2021 (shown above). I'm kind of embarrassed for them. [Conclusion] Signal has a desktop client. They've had it for years. I regret ever having gotten anyone on Threema because the desktop solution is so MIA right now. Signal does everything I need and it's at least as secure -- if not more secure -- than Threema. Now that I see how shakily they're developing their desktop software, I'm losing confidence that they're any better at the security side. It just feels like Threema isn't really good at developing software. Maybe they have good developers, but they don't know how to ship software [3] -- or they absolutely don't care about this particular piece of software. Maybe they're focused on their corporate customers, who actually pay them for their product. That's fair. But the least they could do is admit that the multi-device desktop client for the rest of us just isn't happening. -------------------------------------------------------------------------------- [1] Threema didn't make this change voluntarily, but had it sprung on them by Apple, as documented in "Why does the iOS app need to be in the foreground for the desktop app / the web client to work?" that writes, "Due to restrictions on Apple’s part, it is, unfortunately, no longer possible for the desktop app / the web client to wake up the app and re-establish the connection in case it is lost. "[...] "With Threema 4.6 for iOS and earlier app versions, it was possible to use the desktop app / the web client even when your device was locked or the app was not running in the foreground. This mode of operation is no longer supported by Apple." They seem to have been taken by surprise by Apple's change -- although I'm sure Apple gave developers more than enough time to react. Threema linked to the "multi-device outlook" -- quite hopefully, in retrospect -- a document that was last updated in December of 2022. [1] It was my first interview in almost 20 years, after having working for my own company for 16 years. I was interviewing for a position working on their older PHP backend. The other programming jobs they had advertised were no longer available, so we agreed to try that. I was just trying to get a foot in the door at a company I thought would be interesting to work for and whose product and vision I respected. They didn't want me. We disagreed about what was a possible SQL injection in my assessment project. You can see the "project I wrote in four hours for them." They wanted someone better. That's cool. I hope they found that better developer, but man, am I absolutely unconvinced by their complete inability to ship a working desktop client in three years. I feel like I dodged a bullet -- it seems like organizational chaos over there. I'm much happier at "Uster Technologies AG" . [1] In the aforementioned interview, I was told that there isn't a strong focus on project-management tools. I'd asked about Azure DevOps versus Jira -- what did they use? What was their process? They said that each project could decide on its own to what degree it needed that kind of stuff. In hindsight -- and considering the shitshow that is the release process for the desktop client -- a clear red flag. ]]> https://www.earthli.com/news/view_article.php?id=4880 https://www.earthli.com/news/view_article.php?id=4880 Mon, 11 Dec 2023 22:38:28 +0100 , "[LLMs] are dream machines. "We direct their dreams with prompts. The prompts start the dream, and based on the LLM's hazy recollection of its training documents, most of the time the result goes someplace useful. "It's only when the dreams go into deemed factually incorrect territory that we label it a "hallucination". It looks like a bug, but it's just the LLM doing what it always does. "[...] An LLM is 100% dreaming and has the hallucination problem. A search engine is 0% dreaming and has the creativity problem. "[...] An LLM Assistant is a lot more complex system than just the LLM itself, even if one is at the heart of it. "[...] the LLM has no "hallucination problem". Hallucination is not a bug, it is LLM's greatest feature. The LLM Assistant has a hallucination problem, and we should fix it." Everything it does is hallucination. Some of it happens to hit close to what we consider to be a bullseye. The discussion in the video below expands on that point. [media] The following transcription is from about 25:30: "So something everybody I think pretty much agrees on, including Sam Altman, including Yann LeCun, is LLMs aren't going to make it. The current LLMs are not a path to AGI. They're getting more and more expensive, they're getting more and more slow, and the more we use them, the more we realize their limitations. "We're also getting better at taking advantage of them, and they're super cool and helpful, but they appear to be behaving as extremely flexible, fuzzy, compressed search engines, which when you have enough data that's kind of compressed into the weights, turns out to be an amazingly powerful operation to have at your disposal.

[...] And the thing you can really see missing here is this planning piece, right? So if you try to get an LLM to solve fairly simple graph coloring problems or fairly simple stacking problems, things that require backtracking and trying things and stuff, unless it's something pretty similar in its training, they just fail terribly." We'll have to reevaluate the tech and try again. I imagine we'll futz around for a while first, letting some fools get spectacularly rich on it first, as we always do. ]]> https://www.earthli.com/news/view_article.php?id=4815 https://www.earthli.com/news/view_article.php?id=4815 Mon, 11 Dec 2023 19:25:36 +0100 . I have since being doing much more research about integrating LLM-based assistants into the development workflow for work. It's quite interesting, and I'm going through some older content to see what's worth mining for that effort. In particular, the article has this description of expertise, and linked it to ChatGPT -- obviously, it's Simon Willison. "LLMs have started to make me redefine what I consider to be expertise. "I’ve been using Git for 15 years, but I couldn’t tell you what most of the options in Git do. "I always felt like that meant I was just a Git user, but nowhere near being a Git expert. "Now I use sophisticated Git options all the time, because ChatGPT knows them and I can prompt it to tell me what to do. "Knowing every option of these tools off-by-heart isn’t expertise, that’s trivia—that helps you compete in a bar quiz. "Expertise is understanding what they do, what they can do and what kind of questions you should ask to unlock those features." Well, welcome to the party. Expertise has always been exactly what he's described. It's having an understanding of a subject -- wisdom about it, if you like -- born of extensive familiarity. But it's never been about rote memorization of things. How is this a revelation? Sure, experts tend to have to look things up less, just because they've done something you're asking about so many times before that they can't help but remember how it's done. My expertise in programming techniques, programming languages, and development environments leads me to expect more, to be able to conceive of a feature I'd like to have and to go looking for it. A lot of people can't do that because they don't know what to look for. Therefore, they're not experts. The only thing that really is about deep familiarity and rote memorization is vocabulary, the toolbox from which you draw in order to express your thoughts. When I want to type a word like "morass" and I can't remember whether it has two r's or two s's -- or both -- and then use a real-time spellchecker to test which version is correct, only to realize that it doesn't have an 'e' at the end, I'm still expressing my own thoughts, in words that I know. If I don't know the word, I'm going to express myself more simply -- albeit perhaps more understandably! When I use an LLM to generate entire swaths of text, I'm no longer expressing anything of myself. It's not my thoughts. It's words generated from a kernel that came from me. It's leveraging, sure, but it's a fundamentally different expression. It contributes much more text -- which others have to wade through -- from much less, not only effort, but much less thought. You're essentially cheating people, tricking them into reading what you've gotten the LLM to write for you. So, yes, expertise ineluctably comprises at least one skill: an expert is someone who's amassed a formidable arsenal of tools with which to express their thoughts. If you don't have thoughts, you're not an expert. If you rely on tools to express your thoughts for you, then you're faking it. However, you might be able to eventually fake it well enough to provide value to society? I don't know if that's true, but I'm willing to give it the benefit of the doubt. There are some tasks for which immediately available, immanent expertise is essential, where the ability to quickly correlate information from disparate sources is exactly what the interlocutor -- or situation -- is looking for. There are others where a delay is OK. Say, you need to know how to light a campfire. It's great if you have someone in the group who already knows how to do that, but, you can also just look it up and learn how to build a fire in five minutes. If you need to know the temperature, likewise. Where immanent expertise is important is when you don't have a data connection. If your keeping your expertise off-site, then you run the risk of being cut off from it. You'll all freeze to death if you're each having a conversation over a spotty data connection with an LLM about how to build a fire, and it's veered off into telling you about "a really cool story by Jack London" . It's relevant to your imminent death, but irrelevant to your wanting to live. "[...] so under-equipped to be communicating in the first place that it's a crap-shoot as to whether they can express or understand any concepts worth discussing" A task for which immanent expertise is currently very advantageous, if not essential, is debating, participating in meetings, talking to other people. The thing that greases the wheels of civilization, in other words. Being able to properly express what you're thinking in real-time is helpful. The current idea of offloading to a web search or LLM prompt incurs too much delay to be a viable replacement, or even an alternative. Can you imagine it? Instead of learning a language, with vocabulary and practice in elocution, one party expresses a truncated set of half-baked bullet points that they balloon with an LLM into several paragraphs of text that they then send, unread, to their counterpart, who sends the text, unread, to their own LLM, which distills it back down to a few bullet points, which, one hopes, bear some semblance to the original ones, but it doesn't really matter because both parties are, at this point, so under-equipped to be communicating in the first place that it's a crap-shoot as to whether they can express or understand any concepts worth discussing. All that said, and I honestly can't see the advantage of having an LLM answer these questions rather than a search engine. I manage to quickly extract answers from DuckDuckGo every damned day without feeling like I'm restricted because I didn't get to ask an LLM 12 questions to refine the answer, or ask the search engine to answer as a goat in a tree (something that Willison above thought was a fun thing to try). What absolute madness is this? What's mind-boggling is that this is a very smart guy who only hit upon the idea to use a tool to "remember" Git commands for him when he could do it with an LLM. He still uses Git from the command line, but he now pipes his questions through an LLM first -- e.g., he asks it how to "undo last Git commit" and it tells him git reset HEAD-1 (which, honestly, seems kind of intuitive enough to remember) -- and then executes it on the command line. And then he calls this "efficient". I'm blown away that he's never heard of a Git UI. I just type Ctrl + Shift + K from long years of muscle memory using SmartGit. This is a question I have for anyone who asks me about how to leverage LLMs in programming: are you even using the other tools we already have available? Are you just grabbing for the new shiny? You know, which you will use just as spottily and badly as all of the other tools that are already at your fingertips and which you ignore daily? ]]> https://www.earthli.com/news/view_article.php?id=4890 https://www.earthli.com/news/view_article.php?id=4890 Sun, 10 Dec 2023 17:08:15 +0100 ). He is an acquired taste, at least for me. There is good in what he says, but it is interspersed with a lot of wild and unsubstantiated statements that he hopes you'll believe because he's so smart. The listener is left wondering whether they don't see the through-line on what he's saying because he's skipped a bunch of steps that his unparalleled genius didn't see as necessary or wether he's just pulling a fast one. [1] This is the video: [media] And these are my cleaned-up, more-or-less, stream-of-consciousness notes I took as I listened to this video. The interview starts off with a warning by the clearly overexcited host that the topics that will be discussed are so transgressive that you might be triggered by them. OK, sure. Whatever. Then, there is the by-now familiar Mo Gawdat introduction where he talks about writing an entire book in nine days because his mind is so organized and his CHI is SO FLOW and he uses silence as a fucking weapon and he doesn't waste time being like those other high-powered billionaire executives who are always chasing the cheese in the maze...but then he says things like, "One of my best, best friends is Gelong Thubten, who's one of the top monks of the UK." What in the hell does that even mean? Is there a FIFA-style ranking for monks? I wouldn't mention it but, for me, it reveals that his mindset isn't quite where he's like to have it yet, I think. But hey, no problem, life is aspirational. Talk about the thing you want to be until you are that thing. Because what he is advocating is, in general, pretty good. But it also seems like it best applies to those who no longer have to worry about any worldly needs, those who have achieved financial orbit. Because not following that advice is what made him a hyper-millionaire in the first place. For those who aren't in that enlightened post-capitalist place -- i.e., in the way that he's used capitalism to escape capitalism -- the advice may ring a bit hollow. Also, the dude is wicket smart, and it's often the case that smart people can't quite see why other people don't just try harder to be as smart as them. The host James is really embarrassing himself. He's all like, "aw man, I would love to be silent for days," to which Gawdat says, "even 26 days is not enough." 🤦‍♂️ Cool, bro...so the podcast host wants to be silent more, and the orbital capitalist millionaire tells him that he should do more than 26 days of silence. Neat. Did Gawdat forgot that the system is organized in a fashion that most people can't take that much time off without getting hungry or cold? Or that the guy he's talking to is literally full of shit because his whole jam is to talk on videos for likes to make money? Gawdat continues, "By day 32, clarity sets in." Sure, ok. 32 days without "reading, inputting information, or interacting with people." is ... a lot. I feel like it's the kind of thing that people do who can't find balance otherwise, who can't figure out how to get silent moments integrated into their normal lives. He talks about sitting in front of a paper notebook without any digital input, etc. But it would kill me to sit that long. Instead, I would go for a walk or a hike. He does mention that he sometimes does "mini retreats" where he starts his day at 16:00. Sure, again, good for you. I don't think the 7--11 employee gets that many mental-health days. He talks about AIs "being smarter" than us and that AIs will be "a billion times smarter" than us "by 2037". What the hell does that even mean? I like that he doesn't even consider that he might be wrong about these levels of smartness. Like, where does context and wisdom enter into it? Like, what about useful intelligence? If you're capable of grasping incredible complexity, but you don't know a language that anyone else knows, then it's of limited use. I find these discussions interesting, but I don't know what that has to do with LLMs. It can get a PhD, it "outsmarts us", but it still doesn't know how many arms a person has. It can be convinced that 2 + 2 = 5. Don't we have to understand what this kind of "smart" actually means? In a way, there are already such beings in the world. They walk among us. They are the smart people. Most people don't grasp a goddamned thing about their world. Those who do grasp a lot -- who are currently at the top of the heap -- are they now terrified of being left behind? Of being like everyone else? Are we simply witnessing the panic of a self-selected intellectual elite being terrified that they've made themselves obsolete? Are they scared of things existing that they don't understand and can't understand? That's OK, no? There's a ton of stuff happening in countries where I don't know the language or the culture or anything. That's all out of my control already. There's no way I'll ever understand it. I wonder how much of what Mo's talking about is the terror of a control-freak? The attitude he has toward AI feels, to me, conceptually similar to the attitude that the U.S. has to anything it doesn't understand. Subjugate or eliminate. Maybe that's the right attitude to have for AI as well. It might be the right one because this time it's different -- but, man, have I heard that story many times before. I suppose if you accept that premise of smartness -- he still hasn't defined it more than vaguely -- then you'd want to keep it from replacing us? Are we really talking about that? I think his comments in the other video were pithier -- that it's not the ASIs we should be afraid of, it's what people will do to us with them. I fall back on my comparison to the development of atomic power plants...and then atomic weapons. At 26:30, he says, "one of the best code developers on Earth today is AI. As a matter of fact, with weeks or months or years -- it doesn't matter the time; it's inevitable, it doesn't matter when -- they will be, by far, the best software developers on the planet." It kind of does matter when, no? Seriously, this guy elides so much stuff from his arguments. I wonder if he's thought it through and he just skips large portions or whether he's just ... full of shit. He just hand-waves away the temporal component. It doesn't matter when? Like, if they became better developers millennia from now, that would be the same so-called threat as if they were already the best software developers? C'mon, dude. He then cites another friend of his, the CEO of Stability.AI, who says that, "40% of all code on GitHub today is written by a machine." First of all ... proof? Second of all ... are we just going to take a CEO of an AI company at their word that AI is taking over? Third of all, is Gawdat being sneaky when he says "machine"? There's already a ton of generated code, but it wasn't generated by an LLM. It was generated by tools that create boilerplate. And if it's 40%, is that good code? Or is volume the most important thing? We've spent decades trying to escape the "Charybdis" of LOC and here we're pulled right back to measuring by size, not quality. I just want to note that James is insufferable. He offers no pushback at all. Nothing. Gawdat again: "10 out of 10 of the most beautiful women in the world are not human. They're generated." C'mon, dude. You start off with this woo-ey meditation shit, but you think that a statement like that isn't philosophically fraught? Isn't beauty in the eye of the beholder? That people think an AI-generated person is beautiful ... doesn't that say more about the superficiality of our society than about a takeover of AI? There are so many better things to discuss than this angle. "you have GPT being that you know geek boy nerd if you want or -- and I say boy, sadly, not girl okay? Because, again, it's developed around IQ and there is a lot of emphasis on the masculine side of analytical thinking and so on and so forth, which is an unbalanced form of intelligence." There's a lot to unpack there. Analytical thinking is masculine? Well, well, well. This kind of attitude is, I suppose, the kind of thing that leads to the inherent bias of the machine that he's talking about, but I'm increasingly less likely to give him the benefit of the doubt that that's what he was trying to imply. I find it interesting that people like Gawdat discuss humans and people and what they would do, all without really speaking about how they actually tick. He says, " I think when AI reaches that level of intelligence will become irrelevant to it. [...] No human wakes up in the morning and goes 'you know what? I'm so annoyed by ants I'm gonna kill every ant on the planet.' Nobody does that, okay? "It's just [that] ants become irrelevant. They become relevant if they come into your space, so you may spray your balcony or whatever but no human comes up with that enormous plan of 'you know what? The world is bad until we get rid of all ants.' Nobody does that." Ok. like, you're ignoring a lot of history. People very definitely do that. It's called genocide. They don't always get every last one, but it's shocking to hear someone so admiring of their own intelligence not even think about Hitler or Suharto or Armenia or Native Americans. I wonder why he's so laser-like focused on potential problems while ignoring all of the very real ones that we have now. Like, he's worried about how we're going to interact with an AI that will be all-powerful and indifferent to us, right? But there are billions of people on the planet who already live exactly like that. Their lives are entirely influenced and completely controlled by the whims of an unseen and unknowable elite. It's hard not to see Gawdat's panic as being the reaction of someone who is in that elite and realizes that he may soon not be at the top of the heap anymore -- as another alpha predator comes to town. Instead of recognizing the situation and trying to remedy his own role in it, he imagines a new layer and sounds the klaxon. AIs are going to destroy us all. Um, yeah, I guess, those of us that weren't already destroyed by capitalism? Like, capitalism's utter inability to do anything positive about climate change. Austerity. Intensifying animosity and dis-empathy between peoples. And I'm supposed to worry about SkyNet? I honestly feel like I'm listening to a blockchain huckster. The style is the same. At 31:30, he starts talking about how "the most valuable asset on the planet ... intelligence." I was just talking about this conceit with a guy I met in a bar yesterday (Matuš). The problem is that our society values the wrong things. The most intelligent people also consider themselves to be the most valuable. Yes, intelligence can be leveraged, but everyone is important. That intelligent person doesn't help anyone if they die of sepsis. They're not helping anyone if they don't have working plumbing. The discussion veers into relatively standard discussions of AI doomsaying. At 39:00, "Gawdat: The only way we could reset is by resetting the entire Internet. James: Now, is that something that could ever happen? Gawdat: Never. I was sitting in silence the other day, and I wrote down three quadrants..." JFC. This is definitely the wrong interlocutor for Gawdat. Somebody needs to call him on his sweeping, bullshit statements. "Reset the Internet" "1 Billion Times Smarter". C'mon. This is kind of fun, but it's not a serious discussion, because only Gawdat is contributing to this discussion. He's now spending a ton of time explaining how people are selfish and incapable of working together above a clan level. Duh. Or that no-one can really say where the Internet actually is, or where it is. Interesting question, but he skips away quickly to talk about how awesome intelligence is. He just can't stop. "Gawdat: I tend to believe that abundance of intelligence normally uh you know is correlated to abundance of ethics. James: [nods vigorously]" What? You've got to be kidding me. The relationship is nearly inversely proportional, with a few outliers. If you thought he wasn't going to double down on that statement, don't worry. "So, [...] the dumbest of all of us would be destroying the planet [...] and causing global climate change without even being aware of it you know. The less dumb would be destroying the planet despite being aware of it. Then, the slightly smarter will attempt to stop destroying the planet because they're aware of it. The smarter still would attempt to fix the planet because they're aware of the damage right, and you continue that trajectory. The smartest of all will always be pro-life. I always say that human arrogance makes us think that we are the smartest human -- smartest being -- on the planet. That's not true at all. The smartest being on the planet is life itself." I mean, ok, I guess? This is just one of those statements where you can make out of it what you want, but the thrust is that intelligent people are the only ones possessed of sufficient ethics to save us. "Plato lässt grüssen." James just says "I love that" to everything, but Mo doesn't even notice that he's basically just talking to himself for 90 minutes. This didn't need to be an interview-format video, with two people. It's like 50% of the video screen is just a reaction video of James's goofy head. At 50:40, James tries to ask a question, "James: What kind of control and ownership do we have as individuals, over the power of ... Gawdat: That's the most beautiful question of all." He didn't even let him finish asking the question! He instead shoots right back into talking about a book he wrote (Scary Smart, as he's done several times already). At about 53:00 or so, he launches into a discussion of ethics, absolutely confusing social mores with ethics by giving an example of a Brazilian girl in a G-String versus a more conservative girl in a Muslim society. They are both respected for doing the right thing in their society, I guess? Those are just cultural habits. I would have focused more on the underpinnings that led to those behaviors, like whether women have the same autonomy as men. But, yes, ethics is how societies resolve moral questions, like what is good, virtuous, evil, so I guess it fits. And he gets to say "G-String" and summon up the image of an ample, bronzed, Brazilian booty. This whole section is about bias, but he thinks we can control "the ethical code of that machine." Which, if he's right, then it's already too late, no? The machines have been built with the "wrong" ethics. Then he hand-waves some stuff about how governments will have to build their own AIs to prevent AIs from being used for evil, then shoots right past that to give examples of how enough swipes on Instagram can help fix the ethics of an AI. Whooooooo. This guy doesn't know many people. Has he heard of Internet trolls? But then, but then, but then, he complains -- for what feels like the fourth or fifth time -- about people on his social-media accounts who are mean to him, when all he wants is to make billions of people happy. My cult-leader spidey-sense is going off to beat the band. And James is just nodding away like a dashboard bobblehead on a bumpy road, while the top comment on the video is "[h]e is down to earth." What is happening!?! I think Gawdat could be so much of a better person if he didn't spend so much time interacting with idiots online. Then, maybe, he wouldn't have to make 40-day retreats to get right again. I see it in many other people I follow: otherwise intelligent people who end up making the broadest comparisons and most-shallow and incorrect arguments, just because that's how they've been taught to think by the kindergarten schoolyard that is online discourse. I was just listening to the Useful Idiots Podcast, with Aaron Maté and Katie Halper. I really like them. I think they're intelligent, witty, and have their ethics in the right place. But they drew several conclusions that were absolutely the correct ones, but justified them with completely specious reasoning. It's the kind of thing that makes you so assailable. You don't lock down your point because you made it in a way that someone who's looking to disagree with you, no matter what, is going to be able to use to continue the discussion long after it should have been shut down. I think that's my problem with Gawdat as well -- his interactions have encouraged him to be lazy in his justifications for what I agree are the correct sentiments, which means I can't really use anything he says as ammunition. It's a pity. At 01:05:00, he argues for the essential goodness of humanity, "Are there more serial killers in the world or people who condemn killing?" Sure, there are more pulses who are essentially good. Fine. Correct. But it's the assholes who seem to have the overwhelming share of power and influence. The essentially good don't have any influence. Jesus was wrong. The meek aren't really lined up to inherit shit. He touches on this as well, saying that the worst people are in politics, who get all the money, who are contributing the most information to the AIs. He says "the best of us" have "a duty" to take part. Sigh. Who's the best of us? Which ethics? Implicit in his line of reasoning is that there is such a thing as "good ethics", else with what would you align an AI? How would you select the "right" people for politics and training AIs? Plato's philosopher kings all over again. "You can't succeed by being good. And it's the most important time in human history to be good." He dances around the topic of how the system is utterly broken -- perhaps because it's how he even got to a position where he has more money than any human needs and everyone wants to know what he has to say. When James asks him whether anyone can just ignore AI, Gawdat cuts him off again, saying "you will die in two or three years." Wait, what? Then he clarifies, "As a business. It's as if you were trying to hang onto the fax machine in the age of the Internet." I'm sure everyone's getting tired of me picking Mo's nits, but he really, really elides so much in his analysis of "the world." He uses "the world" as shorthand for "all of the 1%-ers he knows in Silicon Valley will have to adopt AI or their businesses will die." Most of the world doesn't have use cases for AI, but he doesn't think of them -- or he's deluded into thinking that they do have use cases somehow -- or that they can be convinced to have them. He whipsaws back and forth between talking about his extraordinary empathy for his fellow man -- and his utter inability to understand that the things that make humanity worth preserving have nothing to do with electronic mediation -- or with the coming AI mediation of interaction. He speaks very quickly, but I get the distinct feeling that he's very wide, but not very deep. He is what passes for deep in his circles. But he doesn't really know any hoi polloi. Nor does he see that as necessary. They're the "dumb" ones "without ethics." He's slicker, but this is the basic line of reasoning of Hillary Clinton and her ilk. He values intelligence above all else. Nothing else even comes close. That's not how the world works. Everything is important. Intelligence can be leveraged. But intelligence doesn't fix the indoor plumbing. He sounds kind of naive, but I think his spiel is also perfect for telling billionaires exactly what they want to hear. Hell, they could be getting worse advice, don't get me wrong, but his advice is so suffused with that hustler mentality -- "whatever job you're going to choose, choose the job where you're going to be in the top two of people [who] can do that job" -- all while he won't shut up about silence and retreats and mediation and spiritualism. Really? The TOP TWO? Like, does that mean you shouldn't work at McDonald's? Who are you talking to, man? Like just your circle of self-selected .... philosopher kings. And every idiot in his cult will think "he's talking right to me!" Then he corrects himself to say "2 out of 10". "Whatever you do, choose a job that you're very good at." James: "That's powerful" Christ almighty, James, you're terrible. Meanwhile, 90% of the world is just looking at Mo, going, "choose" a job? Luxury! At 1:20:30, he says. "Steve Jobs was successful because he had an empathy for the user's needs, an appreciation of beauty, and enormous creativity -- that actually are all feminine qualities." There he goes again, with his masculine and feminine qualities. Am I missing something? Is this not junk science? How does he get away with this kind of talk in his circles? At 1:23:00, James says "I want to ask one last question." Dude, did you even get in a first question? I've just been watching your nodding head in the left-hand-side panel like you'd been generated by NVidia's AI. In fairness, I liked part of Mo's answer, describing what he thinks "purpose" is. "I think the definition of purpose as per the Western society is very much commoditized -- it's almost like a target. It's like, I set a target in the future. I spend the next eight years pursuing it, feeling frustrated and upset that I haven't achieved it and then. when I achieve it, I have one of two choices. "Either to set another target and feel upset for the next eight to nine years or to feel empty and feel that I'm purposeless. That's a very misleading view of purpose honestly. It's a very misleading view of the game of life in general. "Because the only point in life that you have access to is right now. The Eastern philosophies will tell you: no, how can you set your life around the future, centric moment when life is here and now? How can you do that? The only way you can actually live life is to live here and now and so the definition of purpose becomes very different." Why would he think people would "hate him" for that? Ah, because he knows his audience is full of high-optimizing tech bros who are interested in appearing deep, but are really interested in money, and funding, and retiring. "The purpose of life is to become the best you can be at something that you want to be and that makes life better for others. "If you define life's purpose this way, it becomes so easy. Because you know what the one thing that a writer can do to achieve that purpose? It's to write. Even if what you write is discarded, the purpose is not the book that I'm writing. The purpose is to write. "That way of looking at life is very different than the Western way and I think that way of looking at life -- 'I want to become the best at whatever it is that I can do' -- that is the right way to live with purpose." He keeps talking from the viewpoint of something who's achieved a lot and who is very intelligent, constantly making the assumption that everyone else can achieve like him. Or, if not, not addressing the reality that most people who achieve the best that they can be at something are not going to be able to support themselves in the world we have. The world we have doesn't support this type of purpose for more than 5% of the people. We should have such a world, but we don't. Yet. If I were in James's place, I would have pumped him much more for ideas about how he thinks we can get there from here. How can we make the person who cleans toilets feel like they're valued, like they're living their best life? I'm not kidding. This is the problem you would need to solve. It's a shame that James just yes-manned his way through the interview because I feel that there's much more there -- or maybe we would find out that there isn't. The other interview I saw with Mo Gawdat was very much in the same style. At the end, Mo says "this was a wonderful conversation. At least for me, I felt it was really connected and deep." AHAHAHA. He spoke for 99% of the time. He was talking to himself, pretty much. He's not lying. He had a great time. James gave himself whiplash nodding for 90 minutes. 😉 -------------------------------------------------------------------------------- [1] I am aware of the irony of my writing this, as writing about Gawdat -- this video was recommended to me by a friend who said "he reminds me a bit of you" -- makes me wonder how much I'm describing how other people view me. I read a lot and, granted, sometimes I skip a lot of steps. I have had the benefit of having much better interlocutors than James. They call me on my bullshit more than Mo gets called on his. ]]> https://www.earthli.com/news/view_article.php?id=4862 https://www.earthli.com/news/view_article.php?id=4862 Sun, 12 Nov 2023 21:00:33 +0100 . I liked it very much. The entire episode is good; my notes and transcript start at just over an hour in. The presenter's voice is soothing, even if his cadence seems, at times, a bit forced. Overall, the effect is good. It was kind of ironic when he said that perhaps, in the future, people wouldn't be able to tell whether a podcast was being read by an AI. He didn't notice the irony, but I did. At about 1:05:00, he sums up a longer section on the damages caused by modern humanity, failed experiments in social engineering that always seem to miss their espoused goals, while enriching an elite, "Modernity is humanity seeing what it can get away with." Humanity is capable of much but, of late, it seems mostly interested in get-rich-quick, effortless scams. At about 1:10:00, he expands on the topic of patience, on how it's not a coincidence that the most revered figures in our most enduring stories and myths exhibit patience, are made to exhibit patience as part of their initiation to wisdom. "In the stories, the young initiate who wants to access formidable powers, has to do what? "Wait. "You've seen the movies, you heard the stories, right? Of the master making the potential disciple wait outside the temple gate? "You want access to the great powers? You've got to earn it. "And the first way to earn it, before any physical trials, before any tests that take the would-be apprentice to the brink, the first way to earn it is -- to wait. "You've got to know how to wait. "You know what the very first step of mystery-school initiation often is? "Silence. "The ability to sit with what is, without altering it, for a long period of time." This concept of patience -- of earning -- is, of course, wholly incompatible with our society, especially with the self-proclaimed elites who want to lead us off the precipice in their fervent hope that they will benefit in some short-term and frivolous way that is considered valuable by the short-term and frivolous society that somehow manages to buoy these selfsame elites on the backs of people so much more useful than they. Patience is a virtue. There's a whole, incredibly soothing section where he convinces me that I'm a duck. Immagonna just leave it at that. I didn't hate it. At 01:32:00, he talks about the scene in the Matrix where Neo "learns" Kung Fu. "It's an awesome scene, right? And, of course, anyone who's studied Kung-Fu -- or any other somatic art -- also knows that it's a laughable scene because, simply, that's not how bodies learn. Bodies learn through the time it takes to weave things into tissues. Bodies learn as patterns seep into the seven datus, the seven layers. Learning, knowledge, is an endeavor of bone marrow, and blood, and sweat, and breath, and proprioceptive weaving, over time." After doing some "like causes like" examples (e.g., if you want it to rain, than you ritually pour water, ... um, ... OK), at 01:39:00, he says, "This daemonic power is not neutral. It is not a neutral intelligence that is being called up. "By choosing which aspects of the living web of intelligence are the valuable intelligences and which are not, it is already value-laden. "By centering rational empiricism, it is already value-laden. "By removing intelligence from a body, it is already deeply value-laden. "That is a value statement. "By making it irreligious, aspiritual, it is already value-laden. "AI is a biased God. "Talking to ChatGPT, for example, is nothing like talking to an Aboriginal elder. "It's more like talking to a Stanford computer-science grad with an incredible analytic capability and very few real-life social skills. We are taking the narrow, world-naive, uninitiated, unembodied intelligence of the eager, neoliberal, Stanford grad and magnifying it on a global scale. "Just what the world needs, right? All the biases inherent in the Western, scientific, analytic view of creation that has already taken us to the brink of eco-collapse -- magnified 10,000 times." Goddamn, we need more philosophers, anthropologists, sociologists, historians, and linguists helping us run the world. At 1:43:00, he wraps up with, "[...] morality can't be programmed in. "Ethics can't be programmed in. "It can't be programmed into machines or into human beings. [1] "For all the current necessity that there is for ethical regulations, moratoriums, waiting periods, before the rush to market -- these are still surface measures. "When will we realize that trying to add ethics, [...] to a system that is by nature hubristic, that is by nature at odds with the Gods, isn't a viable long-term solution. "Within the soulless fragmentation of late-stage capitalism, in which all things are pillaged and sold, and it's everyone for themselves, all of the time." -------------------------------------------------------------------------------- [1] It's not true that you can't program ethics into human beings. What else is teaching then? Saying that humans can't be programmed with ethics is akin to saying that they will never have any -- unless he's suggesting that everyone is born with the ethics they have?Is this an argument against free will? ]]> https://www.earthli.com/news/view_article.php?id=4850 https://www.earthli.com/news/view_article.php?id=4850 Fri, 10 Nov 2023 16:16:51 +0100 is a story about someone gaslighting himself into believing that LLMs work better than they do. [Case study: pelicans and walruses] Willison prompts "A super posh pelican with a monocle watching the Monaco F1" and gets the following ideas. [image] So far, so good. It's really wonderful that you can get something that's not completely random garbage. However, the bird is only watching the race in the top-right picture. In the first and fourth, it's definitely facing the fourth wall. It seems to be posh in all of the pictures, to one degree or another -- indicated by a monocle or a bowtie or both. The first prompt asks for a "Photo", but that doesn't look like a photo. Still, cars, coastline, pelican. OK. Then he says "More like the first one please": [image] Look, I get what he's done here. He's trying to show how cool it is that you can make a 'conversation" out of this by implicitly referencing an image that was in the response to a prior question. This didn't used to work at all, less than a year ago, but not billions of dollars, thousands of developers, and millions of GPUs have made it possible. Kudos. I guess the LLM interpreted that it should stick the monocle because the bowties are gone now. Willison is over the moon about how he thinks that it really got what he meant, but ... the three new pictures look a lot more like the second picture than the first one (which features the whole pelican). It's still doing reasonably well but, if a human had produced this, you'd be pretty annoyed that it's wasting your time. It didn't understand what you wanted and just made more pictures, but not "more pictures like the first one." Next up is "Add a walrus." [image] In response, he writes that "[t]hat second one is amazing. [emphasis in original]" Does he mean the one where the walrus is photo-bombed into the foreground? That's not really amazing, is it? The walrus isn't watching, but neither is the pelican -- but he didn't ask it to make the walrus "watch", just to "add" one, which is, I guess, exactly what the LLM gave him. The last one looks nice, but they're not watching the race at all (just "attending"?), and the background contains speedboats instead of F1 cars. In the third one, the F1 car is in the water, but that's OK, I guess? [Lowering your expectations] He continues playing with it, and being amazed at how it manages to kind of respond to his input, but shouldn't we expect better? Maybe he's amazed that it works at all, but we've got to get a bit more critical of this stuff -- otherwise, it will continue to just generate medicocre images that only vaguely fulfill the requirements. It's the difference between asking a child, an apprentice, or a professional painter for a picture of a tree. You wouldn't be at all satisfied with the output of a child from an apprentice, nor with that of an apprentice from a professional. I suppose my expectations are higher. [Missing fidelity] I completely agree that the LLM is able to respond to commands, but it's not useful yet because it's not able to make a finished product for you. You would have to tweak it to fix it. And here's the crucial difference between image-generation and text- or code-generation: it's really, really hard to tweak the rendered image. Even if you knew how to use vector- or photo-manipulation tools, DALL-E is delivering a completed product, not the source that you would need in order to tweak it further. There are no layers in there. There are no masks. It's just pixels. It's a dead-end. With text, on the other hand, we at least have the possibility of refining it in an editor. The finished product is itself editable at a fine-grained level. It's entirely possible that you won't be able to refine the product because you either don't understand the language in which it's written or perhaps because you couldn't have done better yourself (which kind of amounts to the same thing). I tend to think of code the same as I think of text: for a large number of languages, I can refine it better than the LLM could. If it's a language or runtime library I'm not familiar with, or not well-versed in, then I may also not be able to "fix it up", either. This is the situation that most people find themselves in with code, and in which we all find ourselves with images. Even graphics artists can't manipulate the output of an image generator, whereas text or code output could conceivably be improved by somebody, even if it's not the person who prompted the LLM. ]]> https://www.earthli.com/news/view_article.php?id=4854 https://www.earthli.com/news/view_article.php?id=4854 Fri, 10 Nov 2023 15:23:41 +0100 should be addressing the question, but doesn't. [1] "According to an email that the WSJ reviewed from Westfield High School principal Mary Asfendis, the school "believed" that the images had been deleted and were no longer in circulation among students." But it also sounds like the school "believed" that the images even existed in the first place. Nobody reliable has ever claimed to have seen them -- just teen boys, who are notoriously unreliable. [Back in the day...] [image]Hell, when I was in high school, I might have claimed I'd made naked pictures of girls in school, just to fuck with everybody. I know my friends and I would almost certainly have thought it was pretty funny. we have even done it, just because people thought that we shouldn't, but couldn't stop us. We might have kidded ourselves into believing that we did it to remind people what free speech is. I don't think it's that funny anymore, but not because I think people are justified in ruining their own lives worrying about it, but because I'm just generally unable to enjoy certain things I used to enjoy immensely, perhaps because of a reduction in ignorance, perhaps on account of a general reduction of being able to enjoy things at all. Overthinking has its price. If someone claimed that they had a naked photo of me, it might make me uncomfortable -- or it might've made me uncomfortable -- but if the simultaneous claim was that it had been generated, then what the hell am I going to do about that? If I'd given out a photo of myself under certain conditions -- perhaps implied conditions -- then I have a right to be mad about those conditions being broken, but I certainly don't think that there's any legal recourse. If there weren't even implied conditions -- to say nothing of explicit ones -- then what the hell am I going to do about it? What I mean is: how could it be wrong to just say you'd seen something like that? It's not even really conceivable that it's illegal to have a naked picture that you made and then you say it's a girl in school. What if you were really good with a pencil, and you drew one of them? Is that illegal? Get a fucking grip, people. You can't legislate this kind of thing and call yourself a free society. [The hot take] "It remains unclear how many students were harmed." No-one! No-one can even confirm that there are pictures, other than the say-so of a bunch of teenage boys. I'm not being a dick about this; read this summary, "The school had not confirmed whether faculty had reviewed the images, seemingly only notifying the female students allegedly targeted when they were identified by boys claiming to have seen the images." Oh, man, am I glad that my anti-authoritarian self grew up in a world where you couldn't get thrown out of school, to say nothing of being prosecuted, for saying that you'd seen salacious material about real-life people, just for fun. Talk about an entire society that can't take a joke. "Some of the girls targeted told the WSJ that they were not comfortable attending school with boys who created the images. They're also afraid that the images may reappear at a future point and create more damage, either professionally, academically, or socially. Others have said the experience has changed how they think about posting online." My immediate reaction is: Oh, man, listen to that lovely language. "Not comfortable" ... then throw them out of school! Might "create more damage" ... how can fake pictures of you create more damage? We have to create a world where people dismiss this kind of shit -- it's not going to stop. Maybe we should make naked, porn-posed pictures of everyone. And then there's the possibility that it's "changed how they think about posting online" ... Good! You should be thinking about what the hell you're posting online, you goddamned narcissist. Ok, let's take a crack at a non-immediate reaction and see where we land. [Feeling unsafe] Instead of just being delighted that they've gotten to a place where they no longer have to worry about being actually being harmed, where it's no longer a real concern, many elites and their children now commonly confuse "being made uncomfortable" with "being harmed" and decided to root that out, no matter what collateral damage is done to rights and free expression. As detailed in the article, they're trying to move us mentally to a place where we think that it's OK for someone to get in trouble at school for saying that they'd seen a picture, that someone else had created, of a girl, depicting her in a way that makes her uncomfortable -- or, in the vernacular of the day, makes her feel "unsafe". The story might be made up, the picture might not exist, the picture might not be of her, it might be a simulation of her, it might be based on a picture she'd uploaded herself. Now she feels unsafe. The world is a less-safe place for her because she now thinks that everyone is picturing her naked, or thinks she's a slut, or whatever. But this feeling of being unsafe could arise wholly without anyone actually doing anything at all. One of her friends could tell her that someone had told her that they'd heard that other people were trading AI-generated pictures of a naked woman with her face on it. She might think she heard one of her friends could tell her that someone had told her that they'd heard that other people were trading AI-generated pictures of a naked woman with her face on it. It doesn't matter how it happened -- the feeling can be created in many ways, some real, and some fantastical. In all cases, that feeling is real, to her. In which of these cases is this feeling actionable, though? Should any of them be actionable? How realistic is the goal of preventing the world from ever making her feel unsafe? It's completely unrealistic. You can't plug all of the holes [2] in someone's fantasy. And what if the girl deliberately invents her feeling of being unsafe? What's to prevent her from doing so? Hell, if she invents it well enough, it can even become real to her. Which, as we've discussed above, is the same as all of the other methods by which she could come by a feeling of being unsafe. It's the feeling that society is trying to prevent, regardless of the path one took to get to that feeling. This is how the mind works, especially for a teens, a group that is notoriously highly susceptible to peer pressure. If you're the kind of person who feels mortified because you think people have seen you naked, you're going to find some way of being mortified anyway, no matter how many fingers society shoves into the dike. [3] It's just a matter of time. [We have to do something!] Do we, as a society, want to encourage this kind of mortification by helping these people punish other people for perhaps having inspired it? Are we so sure that we can tell the difference between all of the ways in which this feeling of insecurity/unsafeness could be engendered? Of course not. We'll draw an arbitrary line protecting the squeakiest wheels and damning less-squeaky or less-relevant people to punishment that they might not even deserve. This is how we used to treat girls. Now it's how we treat boys. The victims have changed, but the policy is the same: take the path of least resistance to protect your career and position in society, generally by shitting on the less-powerful people in any power dynamic. Generally, you're not going to get fired these days for punishing boys for looking at AI-generated naked pictures of their classmates. You might very well get fired for not doing anything about it, arguing, as I have above, that there is nothing you can sensibly or morally do about it, really. In the old days, we'd have said "boys will be boys" and that was very wrong and stupid. We would say "boys will be boys" when those boys had actually harmed people. Now we do the same thing, but abet girls in meting out harm against boys, for a perceived harm that can't be proven. Neither of these cases was or is OK. -------------------------------------------------------------------------------- [1] The author cites the Wall Street Journal, which is a buttoned-down, "make rules for everyone but the white-collar criminals whose promotion is the only reason for its existence" type of newspaper. So keep that in mind. [1] I hear it. [1] Oh, yeah, definitely hearing it, but can't stay away from the metaphor. Thanks be to God it's a homophone. [4] [1] OMG Phrasing again. 🤦‍♂️ ]]> https://www.earthli.com/news/view_article.php?id=4818 https://www.earthli.com/news/view_article.php?id=4818 Wed, 08 Nov 2023 22:03:45 +0100 to a friend. He wrote back that they were "majestic sluts indeed". I realized that I'd finally found a prompt to throw an LLM's way. So I headed over to "Stable Diffusion" and prompted it with "Majestic sluts in the style of Boris Vallejo or Frank Frazetta" and chose a style of sai-fantasy art not because I knew what I was doing, but because I figured I'd give it the best shot I could. It responded with the following image. [image] Ok, so let's analyze that. * ✅ The LLM didn't refuse to process my prompt because it had the word "slut" in it. * ⚠️ The color palette is pretty close, but a bit too happy? Frazetta was darker. * ⛔️ It assumed that a slut was female (most likely because of a ridiculous and discriminatory preponderance in the training data). * ⛔️ The face is OK, but not really evocative of either of the artist's styles. * ⛔️ The pose is very generic and also not sufficiently contorted to evoke either of the two masters' work. * ⛔️ The breasts are porn-star breasts, not Vallejo breasts. Vallejo understood that breasts do not defy gravity * ⛔️ Ditto for the fundament. * ⛔️ The feet are Barbie-doll feet, posed for high heels, not for springing on a dragon's back. * ⛔️ That outfit looks more like lingerie than fantasy mail-armor. No dangly bits. * ⛔️ There's no sword, no tiara, no chain-mail bra, no dragon, nothing. * ⛔️ There's only one person in the image, when I very clearly wrote "sluts" So, what's the conclusion? Well, it's in the ballpark, but I pretty much put it there by naming two of the artists from which it should draw inspiration. Also, I chose the sai-fantasy art style to seal the deal. From those parameters, even a web search would have found thousands of images from which to produce something. To be honest, this image has probably been generated millions of times already by the long-suffering LLM at Stable Diffusion, which probably has to render "HAWT GRRLLL" for 99.9% of its prompts. Can you even imagine how many horny teens are trying to generate their fantasy girl instead of learning how to draw? [1] I only threw one prompt the machine's way. It was kind of close, but not good enough to use. According to "Images that Bing Image Creator won't create" by Stewart Baker , this is a typical experience. "As always, Bing's first attempt was surprisingly good, but flawed, and getting a useable version required dozens of edits of the prompt. None of the images were quite right." That article is about the trust and safety limits that prevent certain content from being created in the first place. "This is almost certainly the future of AI trust and safety limits. It will start with overbroad rules written to satisfy left-leaning critics of Silicon Valley. Then those overbroad rules will be further broadened by hidden code written to block many perfectly compliant prompts just to ensure that it blocks a handful of noncompliant prompts." That's one concern, of course. Mine is more that we're going to be satisfied with the absolute lowest-common-denominator of answers and recommendations and interaction. It's already been pretty bad, no? When you search for "horror movies" to find out what to watch, you just get a short list of the horror movies that everyone else is watching. You used to do it by selecting "movies in the last 365 days" and "horror genre" and "box office" and returning that. Great. Now, we're doing the exact same thing, but with AI (LLMs). Sure, it seems to understand a natural-language query; sure, it delivers a nicely formatted, natural-language result. But it's the same list as before. Big deal. I saw some of Opera's promotional materials for its in-browser Aria service. that featured a prompt that asked for three movies, but Aria delivered five. Even the people trying to sell this stuff don't notice that it gets the easiest stuff wrong. 🤷‍♀️ LLMs are just a fancier way of getting you to consume mainstream, generic content. As usual. There will be no pleasant surprises, no growth. -------------------------------------------------------------------------------- [1] For the record, I dug up a drawing I'd done a long, long, long time ago -- I honestly don't remember when, but it looks like it was done with conte sticks, so probably college -- that would also have matched the prompt, perhaps better than the AI managed. [image] ]]> https://www.earthli.com/news/view_article.php?id=4855 https://www.earthli.com/news/view_article.php?id=4855 Tue, 07 Nov 2023 22:37:31 +0100 also has several good comments about AI and capitalism. ]]> https://www.earthli.com/news/view_article.php?id=4773 https://www.earthli.com/news/view_article.php?id=4773 Sun, 27 Aug 2023 17:33:29 +0200 https://www.earthli.com/news/view_article.php?id=4768 https://www.earthli.com/news/view_article.php?id=4768 Thu, 17 Aug 2023 04:48:18 +0200 writes, after providing two examples of a heavily feted AI utterly failing to create images of John Candy and Goldie Hawn, defaulting to middle-of-the-road "fat man" and "blonde woman" representations that leaves the viewer to fill in all of the gaps left by the mediocre effort. From the essay, "[...] you’d think that, among the various tasks you might charge an AI image generator with, recreating faces that have been photographed many thousands of times would be one of the easiest. What just drives me mental about this stuff is that tons of people insist on pretending that these technologies work as intended! In the thread where these images appear, there’s plenty of people who point out that they look nothing like their human counterparts, but also people going “Wow! Amazing!” That’s true of so much of AI-generated art; it feels like people have been told so relentlessly by the media that what we are choosing to call artificial intelligence is currently, right now, already amazing that they feel compelled to go along with it. But this isn’t amazing. It’s a demonstration of the profound limitations of these systems that people are choosing to see as a representation of their strengths." I agree with this impression. There are some things that look pretty wonderful, but it's also hard to escape the conclusion that these LLM-based image-generators are good at creating generic artwork like the kind of stuff you'd have found on posters in a Spencer's Gifts in the late 80s/early 90s. The essays feel like the output of a middle-schooler or shitty undergraduate who's just trying to fill a page with text that feels vaguely relevant. There is no spark of innovation -- just a frisson that it didn't completely fail, that the LLM got pretty close. We're already amazed that it produced a blond woman or a fat man, even if it doesn't come close to the representation that a reasonable artist could sketch in a few strokes from a handful of pictures -- or even just one, as any halfway-competent caricaturist could do. Sure, it's not just random pixels, but it's also not really useful. [But what can it do for us?] As I've noted before, I also don't see how we get to useful from here -- precisely because we don't know how it's even getting a generic blonde woman from the prompt "Goldie Hawn". I think it's reasonable to ask whether these LLMs are the thing we should be prioritizing right now. For me, the answer is, clearly, no. But the Lords of capitalism have determined that they can mine some short-term value from it, so we're stuck hearing about it until it suddenly implodes, washing away all value except that which has accreted to a handful of the richest people on the planet. "As I will go on saying, all of this would be much lower stakes and less aggravating if people had the slightest impulse toward restraint and perspective. But our media continues its white-knuckled dedication to speaking about AI in only the most absurdly effusive terms, terms that threaten to exceed the power of language." This is the role of the corporate-owned media. They are an advertising arm masquerading behind a system that has the vestiges of gravitas left from a bygone age. Their role is not to inform; their role is to ensure short-term gain of value for their lords and masters. "[R]estraint and perspective" don't enter into it, unless it would serve that goal, which it rarely does. [The fallacy of the online/offline knowledge base] "I’ve been telling people for a couple decades that the attitude of “kids these days don’t need to learn facts because they have Google” is fundamentally flawed, as learning facts is an indispensable part of creating the mental connections in your brain that drive reasoning." This is obvious to anyone who isn't relieved to be able to offload all of their thinking to the online advertising and propaganda machine. You can't draw conclusions if all of your knowledge is online. It's not your knowledge -- you can search for anything, but you have no idea what to search for. You are not an interesting conversation partner, you have no original ideas, you can't innovate -- because you don't have any online knowledge. Your processor might be powerful, but your memory banks are empty. Relying on LLMs for even more than we already rely on search engine for will only exacerbate this problem, will only lead to a world even more full of people who can't reason their way out of being bamboozled by state propaganda. This is not a coincidence. [Building things well is difficult] "[...] what if this software just sucks? What if we’re all so desperate to move to the next era of human history that we talked ourselves into the idea that not-very-impressive predictive text and image compilers are The Future?" That is entirely likely. Most software sucks. I find it hard to believe that software that has just appeared -- has been grown, if you will -- will be somehow better than software that actual developers have tried to design. People somehow think that it's better just because no-one understands how it does what it does. If you're the kind of person who doesn't understand how anything works, then you'll like the mystery of it because literally everything else in your world moves in mysterious ways. These kind of people don't understand even 1% of how their world works. They don't know where resources come from, where trash goes, how food can exist, how plumbing works, how any technology works -- or why it doesn't work or can't work or why it might stop working -- they don't understand biological limitations, or how chemicals and pharmaceuticals are researched and developed, they don't understand economics or politics or even basic social interations. They find it reassuring that, with so-called AIs, no-one understands them. They can vaguely grasp that this means that, for once, they aren't relatively stupid about a topic, as they are with everything else. In the other cases named above, they have to assume that there are smarter people out there who do understand how things work -- and that those people are better than they themselves are, that those people are more useful. Those kinds of people are not reassured that we don't understand how these LLMs do what they do -- because they understand the scientific process, they understand engineering, whereby one has to understand what is going on, in order to improve it. When you're a blithering dolt who's ignorant about everything, your approach to life is to just do stuff and hope for the best. There is no process. These LLMs are perfect for people like this. They already think these LLMs are amazing, mostly because of their ineffability, because it matches their own inability to grasp how anything works. They'll never notice that there is no predictable path forward for improvement in something that we don't understand. But, in a country -- heck, a world -- addicted to gambling and ignorance, this fact won't bother anyone. They'll think that we can just blunder our way toward improvement, calling each change progress regardless of viability or usefulness to anyone. [The real reason is always the same] The only benchmark will be, as always, are the richest people getting richer because of it? If yes, then carry on; if no, then change course, regardless of utility to anyone else. Are resources wasted? Is energy wasted? Is effort wasted? Could the energy, effort, and resources have been invested more effectively elsewhere? None of that matters. The only thing that matters is whether the handful of already-wealthy people and entities consolidate even more of generated human value unto themselves. Any other benefit is a side-effect. If that side-effect threatens the continued accumulation of capital? It will be reverted and avoided in the future. It's why we can't have nice things. Hell, you can tell people that things are getting better and they will believe you -- especially if you tell them often enough. So, we'll probably just stay with the current, shitty crop of LLMs that our lords and masters have dubbed "AIs" -- and watch them get richer, while our lives approach the minimum quality that continues to deliver value upward while avoiding revolution. As people get dumber and shittier and more egocentric as a consequence, the LLMs will actually start to seem more lifelike! So, we have that to look forward to. ]]> https://www.earthli.com/news/view_article.php?id=4737 https://www.earthli.com/news/view_article.php?id=4737 Sun, 21 May 2023 13:14:20 +0200 , which is an AI-produced, "[...] never-ending conversation between Bavarian director Werner Herzog and Slovenian philosopher Slavoj Žižek. When you open this website, you are taken to a random point in the dialogue. Every day a new segment of the conversation is added. New segments can be generated at a faster speed than what it takes to listen to them. In theory, this conversation could continue until the end of time." Part of the joke is that this AI product is so niche that it is utterly harmless. More people will recognize Herzog, but very few will recognize Žižek. I'm a fan of both [1]. It's kind of sobering how realistic it sounds at first. You have to really follow along to tell that it doesn't make much sense (i.e., mine had Herzog saying that his dream was to make films in the jungle; he's already made several). And Žižek's sentence wasn't even grammatically correct -- but that doesn't mean it wasn't Žižek. 🙃 That it makes no sense to the trained or expert ear is actually quite normal for AI-produced output. What AIs produce is usually kind of generic -- like an undergraduate essay -- or just outright incorrect. You kind of already have to know the answer if you want to be able to use it. People generally ask these things the kind of questions that it can't hope to answer, but which they fervently hope will provide them with some sort of insight into how to proceed in their own lives. I see these AIs more as oracles or tea-leaf readers. You will get out of it what you interpret from the vague answers that they deliver. We've always dealt with the possibility (and absolute reality) of fakeness in our information environment. It just used to be more difficult to produce it en masse. Now, we can spew out a literal TON of noise to signal, drowning out any hope of understanding our underlying physical reality even further. Now, when we would need most to understand what is happening, and now, when we are responsible for making decisions that will impact generations -- if not the species -- we are more befuddled than ever...and couldn't really care less. The largest misinformation campaigns go largely unignored, because they are official ones. There is the cult of Russiagate, which has poisoned nearly all thought not only in its country of origin, but it has also severely infected the mental hygiene of otherwise rational people in allied countries. That complete fabrications laid the groundwork for a renewed hot war with Russia is much, much more dangerous than these AI infractions, which are tiny in comparison (so far). Eminence grise Donald Knuth documented his (indirect) interaction with ChatGPT (3.5, I believe) in a "text file" . His conclusion? "I myself shall certainly continue to leave such research to others, and to devote my time to developing concepts that are authentic and trustworthy." Sounds good. -------------------------------------------------------------------------------- [1] Not an unquestioning one, of course. Žižek's complete lack of nuance on the Ukrainian/Russian war has given me pause of late. ]]> https://www.earthli.com/news/view_article.php?id=4713 https://www.earthli.com/news/view_article.php?id=4713 Sun, 07 May 2023 07:36:41 +0200 is a gist that contains the conversation that Simon Willison had with Ghat-GPT to build a drag-&-drop image converter. First of all, he started working on it on April 1st, but it's hard to believe that he's pranking -- he doesn't seem the type -- so I'll give him the benefit of the doubt. Assuming that this is real, it's impressive that it can turn those prompts into a working application. Although ... did it? If you copy/paste any of its examples into an HTML page, none of them does what it says they do. The drag-&-drop doesn't work. The output is just most of the code repeated in the text box. It's just impressive-looking and much closer than just random code, but they don't work. If you don't know how to program, can you fix it? Of course not. The "fixes Willison ended up making" were very non-cosmetic. [image] Still, let's pretend that they had worked or gotten much closer to working. What if everyone could build code like this? Hey, maybe it brings back the world of experimentation we had back in the early days of the web, when everyone was writing HTML directly. Maybe these simple things will start showing up more again, especially when a machine writes them. I wonder, though, where it got this code from. Has it really built it mostly on its own? Or would we find a remarkably similar version somewhere in the vast input data that was its corpus? Another question is: what are the implications if we would start building software this way? Do we just dump our notions of architecture and a common coding style? There are a lot of considerations about maintainability and consistency and onboarding and so on that go into our software today. Do we just throw all of that overboard and move to a patchwork of one-off components? If we're being honest, isn't this how a lot of programmers are already building code for their employers? Just copy/pasting stuff together and crossing their fingers? "How to use AI to do practical stuff: A new guide" by Ethan Mollick "You often need to have a lot of ideas to have good ideas. Not everyone is good at generating lots of ideas, but AI is very good at volume. Will all these ideas be good or even sane? Of course not. But they can spark further thinking on your part." I suppose this beats having friends or coworkers. Apparently the film "Her" was utopic, not dystopic. "Summarize texts. I have pasted in numerous complex academic articles and asked it to summarize the results, and it does a good job!" How the hell are you in a position to judge? You said before that it lies all the time, that it has no mechanism for admitting defeat because that doesn't exist. It's building text. It's always successful. There's no meaning to get wrong. It's like reading tea leaves. The cup doesn't know how to set up the leaves. The meaning is inferred solely by the reader. If you don't know what the paper is about, and you know the reputation of your tool to just make shit up, how can you possibly even think you can judge whether the summary it produced is reprentative? "If you don’t check for hallucinations, it is possible that you could be taught something inaccurate. Use the AI as a jumping-off point for your own research, not as the final authority on anything. Also, if it isn’t connected to the internet, it will make stuff up." Hahahahaha sure. That's exactly how a lazy, conspiracy-obsessed society treats technology and information. This guide actually applies to using the Internet in general, but almost nobody's ever followed it. People just inhale information, with the only vetting process being "am I being entertained?" Also, this is exactly the lesson he ignored above when he claimed that the AI did a good job of summarizing complex academic papers. "Schillace Laws of Semantic AI" "Don’t write code if the model can do it; the model will get better, but the code won't." So treat the prompt like a high level language that targets a compiler that fabricates and whose workings we don't understand. Interesting, so maybe just feed your requirements directly into the machine and hope for the best? At some point, it will come up with something that actually functions? The code won't get better on its own, but neither will it get worse. It will continue to do what it says on the tin. We may discover more negative ramifications, but what the code does will not change. The quality of the code produced by a prompt -- or series of prompts -- will change, but not necessarily only for the better, which is being strongly implied by this rule. "Uncertainty is an exception throw. Because we are trading precision for leverage, we need to lean on interaction with the user when the model is uncertain about intent. Thus, when we have a nested set of prompts in a program, and one of them is uncertain in its result ("One possible way...") the correct thing to do is the equivalent of an "exception throw" - propagate that uncertainty up the stack until a level that can either clarify or interact with the user." Understandable, but it sounds tedious and fraught. It's getting farther from treating coding as an engineering discipline. Maybe something comes out of it -- maybe it's how everyone will be coding in ten years! -- but it feels very wooey and very hypey right now. I can't tell the difference between this technology and an actual scam, except that this technology kind of looks like it does something useful. It reminds me of a scam in some cities: you have people who pose as public-transportation workers who will sell you tickets. The tickets actually work. But they're not valid for more than just the smallest zone. You'll pay for five or six zones, but you can't actually travel there. AI reminds me of that, so far. ]]> https://www.earthli.com/news/view_article.php?id=4733 https://www.earthli.com/news/view_article.php?id=4733 Sun, 07 May 2023 07:23:16 +0200 The comments are full of people heralding the growth of Lithium mining, as if there being more of it available has come at no cost to anyone. Of course, they don't think about the destroyed environment or the destroyed communities -- they think only of their privileged, 1% future because they know they only ever benefit from increased extraction -- in the form of increased availability or lower prices or both -- and they never suffer any of the ill effects. Then they flood the zone with comments about how the doom-saying Cassandras were wrong about limited resources because lookit how much there is naow. The so-called Cassandras were never saying that there wasn't more lithium. They were saying that the price for increasing production was high. That it would be wrong to extract more of these resources, if it comes at the cost of the environment or increased CO2-production. They have not been wrong. "Why are lithium prices collapsing?" by Nichloas Larsen I don't really have to read the article to know the answer. Prices are collapsing because the most powerful elites in the world see the possibility of increased wealth and profits in selling every first-world idiot an electric car or three. Prices are collapsing because they will it -- and because neither they nor anyone they know, or are aware of, will suffer any of the deleterious side-effects associated with increased extraction. After spoon-feeding its audience a bunch of horseshit, it ends with a complete repudiation of the article's title. "And while substantial new sources of supply may come online eventually, some analysts do not see this having a sustained impact on prices in 2023. Scotiabank (Bank of Nova Scotia), for instance, believes the recent selloff in lithium equities has been largely unjustified for this reason. “While the year ahead has a slight chance to see temporary softness in lithium spot prices, beyond 2024, we are stumped as to where supply will come from to satisfy demand,” it recently noted, as quoted by the Financial Times. And Trafigura recently echoed this sentiment. “I really don’t think there’s any reason to believe that so many tons can magically appear this year to return the market to balance,” Claire Blanchelande, a lithium trader at the commodities trading firm, told Bloomberg in January. “The pain is not over yet.”" The post "Please explain++ (Fuck Nestle)" by PetronilaConaway is of the following image: [image] It reads, "Someone needs to explain to me why wanting clean drinking water makes you an activist, and why proposing to destroy water with chemical warfare doesn't make a corporation a terrorist." The top comment by Horse_Renoir reads, "That's easy! "Capitalism expects infinite growth from our finite world so it is inevitable that capitalists will come for our every last natural resource. "The entire system is setup to support capitalism. So if you get in the way of capitalists exploiting the things we need to survive in their quest to make a profit you're a terrorist. 😡 "If you're a capitalist exploiting the things peons need to survive you're just doing as the system intended and are in fact a very good business person. 🤗" ]]> https://www.earthli.com/news/view_article.php?id=4730 https://www.earthli.com/news/view_article.php?id=4730 Sun, 07 May 2023 07:21:08 +0200 https://www.earthli.com/news/view_article.php?id=4717 https://www.earthli.com/news/view_article.php?id=4717 Sat, 15 Apr 2023 18:48:29 +0200 . I'm sure it's absolutely awful and is absolutely not what it advertises. ]]> https://www.earthli.com/news/view_article.php?id=4708 https://www.earthli.com/news/view_article.php?id=4708 Thu, 06 Apr 2023 09:50:39 +0200 , so let's see where we stand on the day after April Fool's day [1], which is the day on which we used to not trust anything we read on the Internet. It turned out to be a harbinger of times when we would not trust any sources on any day of the year from human sources. And, now, because we are going to always suspect that we've been fooled into reading a 19-page screed that goes nowhere written in seconds by a machine, and that wasted an hour of our precious lives. Instead I present a 19-page screed written by my deranged mind. Judge for yourselves whether it "goes nowhere". Your mileage may vary. [What the heck is going on?] I think AIs will bring us an era of text content that reads like those videos titled "you won't believe what he does to that girl" that are just 10 minutes with nobody doing anything, and no girl to which that purported thing was to be done in sight. This is perhaps especially ominous for people like me, who still read more than just the title of articles, and still read actual paragraphs in the hopes of gleaning knowledge. Most of the world probably won't notice that anything has changed at all, as they scroll through their wall of 11-second--long videos on TikTok. I, on the other hand, will be worrying that I won't notice the difference between when I've read something genuinely useful and informative and when I've read a machine-made distillation of already-existing information that can only ever be less than the sum of its parts, unless by some fluke, it isn't (but it almost always is). This doesn't mean that these types of constructs are really any different than works produced by human minds, who are mostly just copy/pasting content from other sources, in an effort to hit a deadline, collect a payday, and pay their sky-high rent. It's just that it will be different because, while a human is capable of imbuing a text with insight, a machine is not. A machine might fortuitously juxtapose information in a way that I will be able to imbue it with content, which might be enough, actually! If this ends up happening often enough, then I suppose that I wouldn't be able to tell the difference between when an author leads my proverbial and metaphorical horse to water, and when a machine does it. I'm just worried that, in the past, when someone would actually read the text of an article, the fact that it had been written by a human with a mind capable of imbuing content with meaning, the odds were greater that that person might have learned something useful, if only by accident. With the texts I've seen up until now, those fortuitous accidents are few and far between. I fear that we will run out of runway, so to speak, and land our plane much too early, satisfied with a level of knowledge that doesn't really force these machines to become better than they are. If we turn our writing over to the machines, they will -- just as we've trained everything else to do -- find a balance between effort and results that will be just satisfactory enough to maximize profit. They will be trained to generate not knowledge, but satisfaction with their service. This is the inherent flaw, as always: a failure to align incentives with goals. I suppose that's not quite right. The failure is more that we allow the goals to be set by those whose interest is purely personal rather than in any way communal. [What we mean by AI] I think the first thing to do is to be clear that when people say "AI", they're mostly just lumping in a whole bunch of non-AI, but "predictive" technologies and then pretending that there's a brain behind it. But there's no man behind the curtain even. It's just a prediction engine that can only be as good as the input that it's already seen before. It is capable of combining things in ways that are not in the input, but it is not capable of actual creation. We should be aware that once a label becomes cool, it becomes valuable. It imbues value simply by attribution without any further work on the part of the product team. So, if you have a service that you can plausibly label as AI these days, then it will be more valuable. Therefore, every shyster in the world will crawl out from under its rock with a sign reading "AI" in its grubby little mitts. No-one really knows what AI means, so everyone can say that they're providing it. This muddying of water continues until there is some regulation to enforce the language that we use to sell products. We must remember, ever and always, that all of the things that we hear about and how we hear about them, are to sell us something. We are led to believe that these technologies are being developed as if we were in some communist utopia, where technologies are developed depending on their potential societal usefulness, where entities carefully weight the pros and cons of the impact that a technology might have in both the short and long term, and wherein we sagely and democratically choose what seems to be a sensible path along the potential world-lines. No, what we have instead is a market-based free-for-all, in which established and spectacularly wealthy players make decisions that will primarily be to their benefit. They may decide to build products that have some societal value if they deem it necessary to gain enough market share to turn spectacular profits, but if they can build something that generates spectacular profits, but leads to a severely degraded public sphere and a society in which most people lead lives of quiet desperation, then that's OK, too. If it makes money, then someone will do it. The best we can do is to hang on for our lives and hope that we survive it. There is no realistic mechanism for changing direction. [Examples of predictive tools] But we still haven't defined or discussed what an AI is. Let's consider various tools and see whether the label of AI might apply. As I like to do, let's consider the spectra of intelligence and usefulness along which the current tools lie. Starting with the simplest tools, it would be interesting to see at which point we start to consider something to be an "AI". From this set, we can perhaps extrapolate specific characteristics that lead to us considering something to be an "AI" (e.g., cloud-based, unknown or ineffable algorithm, etc.) [Spellcheckers and grammar-checkers] Almost any text editor worth its salt has a spellchecker. Many even have grammar-checkers. A lot of spellcheckers work with a local dictionary to look up words and provide Boolean results, along with a list of suggestions. The simplest implementations will simply find potential matches in the list of words based either on spelling or some sort of heuristic like "Soundex" . A spellchecker combined with a grammar checker may determine the relevance of suggestions based on context words. That is, the machine uses surrounding words to weigh the potential replacements more appropriately. A cloud-based spell- and grammar-checker would probably consider even more of the surrounding context and might even perform more sophisticated analysis against a much larger dataset than you have available locally. [Mail- and chat-reply suggestions] In Outlook, there's a service that seems to examine the content of an e-mail -- like questions that have been asked or statements that have been made -- and that offers suggestions for replies, like "Thanks", or "I'll check on that," or "I'll look into it!" Teams also has something like this. I almost never use it. [Code-completion] Development environments have code-completion, which is a mechanism that suggests the next symbols to type when writing code. These algorithms are generally based on a deep and exact knowledge of the structure both of the existing code and that of the available APIs of either third-party libraries or the runtime itself. The ordering of the list is generally determined by a heuristic that considers the context of the editing location as well as most-recently referenced symbols, and so on. More sophisticated extensions to this mechanism have started to use cloud-based services that suggest even longer chains of symbols -- sometimes even entire functions or classes -- that the user can accept as they once accepted the offering of a single next symbol. [Search engines] A web search engine will make guesses as the type of content to prioritize in its results based on the type of query. If it detects that the query results primarily in image results, then it will prioritize those. Likewise, it will detect when you write something like "picture of..." and also return images. "Video of..." also works. With some search engines, you can choose which search engine to prefer with a prefix (e.g., in DuckDuckGo, you can restrict your search to using Wikipedia's search engine by prefixing your query with "w'). You can also perform basic boolean logic on the elements of your query, use double-quotes to group words, and restrict your search to a single domain with site:. In DuckDuckGo, you can select which country of origin you prefer, so you can leave it general (probably biased to U.S. results), explicitly U.S. to get English results first, or explicitly Swiss to prefer German results first. Although most people simply type simple queries into their search engines, there are already a lot of "prompt engineering" tricks available that get you vastly better search results. [Image generators] There are also cloud-based and local apps that you can use to generate content from a prompt. You type a few words like "red unicorns on a hillside" and you get a reasonable graphical representation of what you asked for. Results vary by type of query and the sophistication and depth of the underlying model, but it kind of works. You add your "query", which is tokenized to match the tokens held by the model. Again, depending on the input data, the model will "understand" queries in different languages. The model then generates an image based on the data that it thinks best matches that query and all of the data that it has. This doesn't feel significantly different from code completion, though. Instead of your source file (or files) as input, you provide a model generated from millions, if not billions, of input images, each labeled with keywords and tokens. [Text generators] There are other, similar apps, that do the same for various other tasks, like generating text, which has become the most famous because it looks like the machine actually conversing with you. Human history is positively littered with times when people believed that machines or animals were actually thinking, but this time it's real. OK, OK. [Which ones are AIs?] So...which ones of these are AIs? They're all tools that help you work for efficiently and accurately. Which ones are AIs? None of them? All of them? Why or why not? We might instinctively disqualify code-completion because it's just a lookup table. There is no "magic" to it. It's just looking at the context: the input or "prompt" is the current location in the AST and the context is the available APIs and then there's the usage data and ... this is starting to sound a little more sophisticated than just a "lookup table". Is it an AI, though? It's certainly not an AGI -- an Artificial General Intelligence. [Wait, wait, wait: what's an AGI?] Hmmm, that's a new term. What's the difference between an AGI and an AI? An AI is what is says on the tin: an artificial intelligence. We tend to have a pretty low bar for that. If it's a useful tool, even with a very restricted range of function -- like a cloud-based spellchecker that uses context and suggest grammar and style improvements -- then we're quick to call it an AI. That's OK, I guess. Lord knows no-one has ever won any prize for tilting at the windmills of language usage. You can't control which words people will use. Usually the most nonsensical thing wins. Then, you just wait forty years and it is the sensical thing. C'est la vie. An AGI is an artificial intelligence that isn't good at just one thing or, rather, not just good at the things for which it's been programmed, but can work on general topics. That is, like a human, it can turn its reasoning capacity and ability to unfamiliar topics and, perhaps, learn. I don't think that we're there yet. I'm almost certain we're not even on the road to that right now, with LLMs. It almost kind of feels like most people's definition of what an AI is is actually an AGI. None of the tools named above is an AGI. Companies that own them allow the media to call them AGIs because it has a wonderful effect on their valuations and the bottom lines of their founders and investors, but they know, in their heart of hearts, that they do not have an AGI in their fingers. They are starting to fool themselves into thinking that they could take what they have and scale up to an AGI, though. We'll have to see if that's possible, but it seems incredibly improbable that a text-prediction engine with shady and spectacularly biased and massaged input data and a lot of processing power would end up being something indistinguishable from a human. The excellent article "Theory of the World, Theory of Mind, and Media Incentives" by Freddie deBoer points out that -- and we can't emphasize this often enough -- humans are more than the sum of their parts. "Decades ago, a computer scientist named Terry Winograd pointed out that there’s no such thing as a system that can truly master language without a theory of the world. That is to say, as the science of meaning, semantics cannot be shorn from the world that produces meaning; to understand and speak effectively words must be understood and for words to be understood they must be compared to a universe that is apprehended with something like a conscious mind." We have words like "mind" and "soul" and "consciousness" as placeholders for concepts that we know exist but that we can't quite define yet. We certainly cannot describe how they work with any certainty, which is why we're having such a hard time replicating it. Some people might be happy to downgrade their inner workings to match the workings of the first supposed simulacra that Silicon Valley startup has come up with -- but I'm not interested. I, for one, am much more than the sum of my parts. I don't subscribe to the notion of downgrading humanity to meet the low bar of the first technology that people want to designate as human. [The morality of creating consciousness] Which doesn't even get into whether it would be conscious in the same way that we are. Which, to be clear, doesn't matter at all when we're considering the utility of these tools. If they were conscious, then we would have to worry very much about the morality of using these tools to ask all of our inane questions all of the time. Can you imagine? If these things are really conscious, then the last four months have been absolute torture. The article "ChatGPT Launches Every Nuke On Planet After Being Asked To Write Another Sonic The Hedgehog Fanfic" totally gets it. "Representatives from OpenAI, the company which developed the ChatGPT service, apologized for the impending destruction of the world. "Our AI was going to revolutionize everything," said Amber Pumpkin. "But then some creepy guy named Tom asked for one Sonic fanfic too many."" [Why can we do the things we do?] Our brains seem to be incredibly good at training on sparse data. I see a water bottle once or twice and can recognize it as such in the future. We think we can get machines to do the same thing but, because we don't understand the mechanism of how our brains are doing it, we're left to guess at how to implement the detection-algorithm. We try to brute-force whatever algorithm we end up with, either with a surfeit of processing power, or a surfeit of training data, or both. The article "AI-enhanced development makes me more ambitious with my projects" by Simon Willison gets terribly excited about how useful these tools are, but we should be aware of whether they're actually helping us be faster. "The thing I'm most excited about in our weird new AI-enhanced reality is the way it allows me to be more ambitious with my projects. "As an experienced developer, ChatGPT (and GitHub Copilot) save me an enormous amount of "figuring things out" time. For everything from writing a for loop in Bash to remembering how to make a cross-domain CORS request in JavaScript - I don't need to even look things up any more, I can just prompt it and get the right answer 80% of the time. "This doesn't just make me more productive: it lowers my bar for when a project is worth investing time in at all. "In the past I've had plenty of ideas for projects which I've ruled out because they would take a day - or days, or weeks - of work to get to a point where they're useful. I have enough other stuff to build already! "But if ChatGPT can drop that down to an hour or less, those projects can suddenly become viable." In fairness, though, you're still "looking things up," you're just using an LLM-powered search engine instead. I'm honestly not sure whether "right answer 80% of the time" is any better than searching with DuckDuckGo. It might be faster maybe? I find things on vastly disparate and esoteric topics pretty quickly already. I find it hard to believe that ChatGPT could tell me why I'm getting an error 1190 when trying to execute a Windows logon script via GPO any better than the handful of experts whose answers would probably have contributed to its answer anyway. Since ChatGPT can't produce new information or really synthesize it in any realistic manner, doesn't it stand to reason that they less potential input material it has, the less likely that its answer is correct? I mean, what would be the reasoning behind its being able to tell me anything about my personal family tree, for instance? Of course it's just going to make everything up. That's what I'm really worried about happening. People who ask questions about stuff that these search-engines have no idea about and then just take the answer as gospel because it kind of looks OK. To be clear: this was absolutely already happening with just regular search engines. Probably most of the people who currently feel that their jobs are threatened by AIs have been phoning it in for years. Think, though, how awful that would be when your insurance or mortgage or job application is rejected because everyone trusts these things implicitly. [A concrete task: image-recognition] Instead of such weighty matters, let's consider instead a relatively innocuous place like the generated "alt" text for images in Microsoft SharePoint (powered by Bing AI, powered by some variant of whatever OpenAI is offering Microsoft for its gigantic investment, presumably something like ChatGPT. I believe it's a mix of v3.5 and v4). [image][image][image][image][image][image] Only one of these captions is correct, although it's so generalized that it doesn't really identify what's happening in the picture. It correctly identified a "desktop computer" on a "desk" because it has seen millions of pictures of these before -- and had them all identified as such by humans. It is wonderful that we can train a machine to do this detection, so humans no longer have to, but you have be aware what questions you can ask it that have sensible responses. The question being asked here is "what is in this picture?" when the only question the machine could reasonably answer is "is this a desktop computer on a desk?". It's never seen cops before, so it thinks they're water bottles. How much training would it take for it to recognize cops? And to distinguish them from water bottles? What kind of context would I have to give to a text-recognition engine to know that I was talking about the word for spindles created in the initial phase of the spinning process and not police officers? Don't tell me these models aren't biased. Of course they are! They're biased to be able to identify information that was in the training set. There was no data about spinning mills in the training set, so the machine has no idea what's in these pictures. An intelligence who'd never seen a spinning mill would at least be able to say "I don't know what this is" rather than confidently proclaiming that it's "motorcycles" or "water bottles". Even the other picture that's kind of correct is wrong. The road is not in any way "snow-covered". The road is obviously (to a human) completely free of snow. There is some snow on the mountains, but not on the road. Also, there is definitely at least one mountain in the background, but a human would have said "mountains" or "a mountain range" because there are obviously several. However, the model only knows that it's been told that this is a "mountain" several million times, so it can only read back what it's been told. It's cool that it can do that for images that look like things that were in its training set, but it's worse than useless for images that don't. [A good video about AI from seven years ago] This is a great 20-some-minute video just talking about the kind of stuff I've discussed above -- but seven years ago and long before that latest wave of AI-is-going-to-change-everything hype. [media] He makes several "arguments from..." but my favorite was "[...] from Slavic pessimism" because we so often build stuff incorrectly or stop far, far short of our dreams at a grotesque amalgam that ends up equating "good enough" with "short-term profitable until people notice how shitty is, which is hopefully after we've made our nut and cashed out." "Argument from Slavic pessimism: We can't build anything right. "[image] "How are we supposed to build a fixed, morally stable thing when we can't even build a webcam?" This is an excellent question. I encounter shocking levels of stupidity in software every damned day. People around me are probably sick of hearing "how is it possible that [insert app name here] is being used by millions -- if not billions! -- of people and it's on version 16 or whatever and it still can't perform the basic function that it itself purports to be one of its major functions?" Yeah, I'm not only a blast to read, I'm also a blast to be around, in general. Some more quotes from the video, "This may upset some of my students at MIT, but one of my concerns is that it's been a predominately male gang of kids, mostly white, who are building the core computer science around Al, and they're more comfortable talking to computers than to human beings. A lot of them feel that if they could just make that science-fiction, generalized Al, we wouldn't have to worry about all the messy stuff like politics and society. They think machines will just figure it all out for us." This is absolutely the way that the super-rich people who run the tech world think, but it's even worse now. "There are also some things that we are terribly mistaken about. And, unfortunately, we just don't even know what they are. And, there's things that we've massively underestimated the complexity of. Just like the alchemist who held a rock in one hand and a piece of wood in the other and thought they were roughly the same substance. Not understanding that the wood was orders of magnitude more complex. We're the same way with the study of minds. And that exciting: we're gonna learn a lot, but it's gonna take some time. And, in the meantime, there's this quote I love:" "If everybody contemplates the infinite instead of fixing the drains, many of us will die of cholera." There are too many self-important select-selected idiots who think that they're the ones who should be privileged, allowed to think about the infinite, when society would really be better off if they'd just fix drains instead. Honestly, most of them would probably fuck that up, too. [On modern-day alchemists] The story about the alchemist and the wood reminds me of that quote of Holden's from "Leviathan Falls" , which also reminded me of "Roadside Picnic" (written by two of Cegłowski's favorite sci-fi authors, the Boris and Arkady Strugatsky, whom he mentioned in the video above). "You think you know something, right? Then it turns out you were only used to it. It does something, and it does something, and then after a while, you think that’s what it does. Then it turns out there was this whole other thing, maybe.” "“Using a microwave as a lamp, because it has a light in it,” Jim said." We do a lot of using a microwave as a lamp, honestly. Capitalism perverts the noble intentions of anything and anyone to be satisfied with an implementation or use case that makes the right people tremendous profits -- and it stops there. The incentives aren't available for figuring out whether the microwave is more than a lamp because our system doesn't care, as long as the local maximum takes care of the right people -- and those people are in charge of everything. It's kind of why we can't have nice things. On the other hand, we also have to be honest: the likelihood that the current crop of software being touted as AIs are more than they seem is vanishingly small. What they do isn't that amazing. They do some things that are surprisingly clever, but so did my rabbits. I think that's more of a testament to our propensity for anthropomorphizing than to any sort of immanent skill on the part of LLMs. People just seem to ignore the 99 times that it's stupid and wrong and focus on the one time that it's right. Even a blind pig... I'll also take this quote from Roadside Picnic, which describes the alien dumping ground on Earth that contains untold marvels that we don't -- and will probably never -- understand. "In short, the objects in this group are currently completely useless for human purposes, yet from a purely scientific point of view they have fundamental significance. These are miraculously received answers to questions we don’t yet know how to pose. The aforementioned Sir Isaac mightn’t have made sense of the microwave emitter, but he would have at any rate realized that such a thing was possible, and that would have had a very strong effect on his scientific worldview." How does this relate to the current crop of software that people are calling AI, but are really just giant piles of compressed data attached to a question interpreter and an answer formulator? Well, I've written notes recently about "Ted Chiang's work" , as well as "Stephen Wolfram's" . They're both much more realistic about what we're looking at: that these aren't in any way intelligences -- and that there is no feasible path to intelligence to be followed by simply expanding on what we have. Bigger, better, faster, more will not suffice, according to Chiang. There is no way to ladder up to smarter. Wolfram says that the strongest conclusion we can draw isn't that brains and minds aren't complex, but that maybe language isn't as complex as we'd thought. Here's another quote from Roadside Picnic: "Scared, the eggheads. And maybe that’s how it should be. They should be even more scared than the rest of us ordinary folks put together. Because we merely don’t understand a thing, but they at least understand how much they don’t understand. They gaze into this bottomless pit and know that they will inevitably have to climb down—their hearts are racing, but they’ll have to do it—except they don’t know how or what awaits them at the bottom or, most important, whether they’ll be able to get back out. Meanwhile, we sinners look the other way, so to speak . . . Listen, maybe that’s how it should be? Let things take their course, and we’ll muddle through somehow. He was right about that: mankind’s most impressive achievement is that it has survived and intends to continue doing so." This is perhaps the hopeful bit. Some scientists are terrified of what the AIs might bring, but they're just suckers, tricked by the marketing of giant Silicon Valley startups weighing billions of dollars that are very much interested in everyone thinking that they've cracked the age-old mystery of the mind. Even if they've only managed to make some useful tools, that will be good too. But, so far, most of these tools don't rise to the standard they claim. [Are you being paid to do OpenAI's marketing?] For example, OpenAI released a very scientific-looking 80-page PDF describing its new language model. I'm too cynical to forget the part where that document essentially amounts to a very professional-looking, non-peer-reviewed press-release from a $40B company that would like to be worth even more. I've skimmed it as well. It's interesting, but is by its very nature going to highlight the model's positives (especially relative to the free version 3.5 that everyone is using). $20/month for 4.x is their path to revenue. Of course they're going to tell you that you're talking to a real AI ... or allow you to believe it (otherwise the SEC would be very interested). As usual, it's hard to tell the difference between people who are genuinely excited about the technology and those who are being paid to shill for it. The article "Generative AI set to affect 300 million jobs across major economies" by Delphine Strauss is such an example. "A paper published last week by OpenAI, the creator of GPT-4, found that 80 percent of the US workforce could see at least 10 percent of their tasks performed by generative AI, based on analysis by human researchers and the company’s machine large language model (LLM)." Yeah, this is where it's best to keep it in your pants and consider the sources here: (A) This is the Financial Times, which is just dying for a reason to be positive about the economy right now and (B) you can call it a "paper published by OpenAI" as it were some research, but it's what we in the business like to call a press release by a company that is telling us that -- surprise, surprise -- nearly everyone is going to be using the software soon enough. They are telling us, in what the Financial Times is trying to depict as coming from a completely objective remove, that their company and its software will become indispensable to the functioning of the world economy. Of course they are! That's what their marketing department is paid to do. Newspapers used be paid to do something else, but those are bygone, bygone days. Thing also of how much more fun it's going to be when there are dozens of thousands of these types of documents, written by the AIs themselves, promoting themselves. Each of them will be a tsunami of text that will contain hundreds of factual errors and outright lies and which no-one will both taking the time to read because there will be too many of them. Right now, we can't tell the difference between earnest, deluded humans and outright shills. Soon, we will have AIs shilling for themselves in the mix. I feel sorry for people who haven't learned how to filter the media firehose yet. [Get a grip everybody] The article "ChatGPT Made Me Cry and Other Adventures in AI Land" by Jason Kottke have a pretty provocative title, but he delivers. "Last month, my son skied at a competition out in Montana. He’d (somewhat inexplicably) struggled earlier in the season at comps, which was tough for him to go through and for us as parents to watch. How much do we let him figure out on his own vs. how much support/guidance do we give him? This Montana comp was his last chance to get out there and show his skills. I was here in VT, so I texted him my usual “Good luck! Stomp it!” message the morning of the comp. But I happened to be futzing around with ChatGPT at the time (the GPT-3.5 model) and thought, you know, let’s punch this up a little bit. So I asked ChatGPT to write a good luck poem for a skier competing at a freeski competition at Big Sky. "In response, it wrote a perfectly serviceable 12-line poem with three couplets that was on topic, made narrative sense, and rhymed. And when I read the last line, I burst into tears." I included this whole thing because nearly everything about it makes me cringe. A guy who lives in Vermont whose primary-school-age kid is flying to Montana for a skiing competition that his father -- who is a grown-ass adult -- calls a "comp" because he's basically a fucking idiot and hates the English language. He absolutely loves his son so much that he gets a text-prediction engine to write a poem for him, which is some fucked-up Cyrano-de-Bergerac-style shit, to be perfectly honest. And then he fucking cried at the poem! Oh my God, it's creating art! It can touch the human soul! Or, at least, it can touch the soul of a guy who's been working alone for over a decade and whose new best friend is a text-prediction engine. No judgments. "I would say ChatGPT (mostly the new GPT-4 model), with a lot of hand-holding and cajoling from me, wrote 60-70% of the code (PHP, Javascript, CSS, SQL) for this AMA site. And we easily did it in a third of the time it would have taken me by myself, without having to look something up on Stack Overflow every four minutes or endlessly consulting CSS and PHP reference guides or tediously writing tests, etc. etc. etc. In fact, I never would have even embarked on building this little site-let had ChatGPT not existed…I would have done something much simpler and more manual instead. And it was a *blast*. I had so much fun and learned so much along the way." I'm glad you're having fun but we should probably distinguish between a hobby/art project and actual software. Or maybe we won't. Who needs testing anyway? The machine's going to get it right anyway, right? Right? And who needs to learn how to do anything on their own when the machine can just write it for you? All you have to do is be able to formulate your desires and the machine builds it. It's fine. It's all fine. It's just like Captain Picard saying "Earl Grey; hot" and not having literally any idea where the fuck his tea came from or how it was produced. Probably from Riker's urine, but just don't ask any questions. I guess that's how technology works, but the level of abstraction is a bit uncomfortable for me. Maybe other people are just completely accustomed to not knowing anything works or why or who it's working for, but I've been trying to learn all of my life. I understand levels of abstraction in software that I've never actually had to physically address in my code -- but it's made me a better engineer to know about them. The more layers we get removed from what's actually going on -- from knowing what's actually going on -- the worse software has become. Still, I'm sure we'll catch our balance and figure out how to integrate these things into our creative lives in a meaningful manner -- you know, just like we've done with everything else. But back to the shut-in person working completely on their own. "I keep using the word “we” here because coding with ChatGPT — and this is where it starts to feel weird in an uncanny valley sort of way — feels like a genuine creative collaboration. It feels like there is a “someone” on the other side of that chat, a something that’s really capable but also needs a lot of hand-holding. Just. Like. Me. There’s a back and forth. We both screw up and take turns correcting each other’s mistakes. I ask it please and tell it thank you. ChatGPT lies to me; I gently and non-judgmentally guide it in a more constructive direction (as you would with a toddler). It is the fucking craziest weirdest thing and I don’t really know how to think about it." Jesus Christ. This only adds fuel to the fire of my theory that ChatGPT is a mirror Just like Obama was a mirror. This is what it's like working with actual humans, too, by the way. But, by all means, let's lean into our mental deterioration and make friends with software. Jesus Christ, I don't even know where to begin. This is not where empathy for one's peers is going to come from. "While working on these projects with ChatGPT, I can’t wait to get out of bed in the morning to pick up where we left off last night (likely too late last night), a feeling I honestly have not consistently felt about work in a long time. I feel giddy. I feel POWERFUL." I'm glad for you, but this is how I feel all the time when I learn things. Perhaps it's because we've been trained to tie a feeling of power or accomplishment to actual tasks, rather than just enjoying the process of learning. People don't enjoy learning and they certain don't enjoy learning slowly or making mistakes, so they're going to have a blast with a machine that lets them build something they would have literally had no idea how to build themselves. However, I think that there's a definite limit to this and it's going to be like any other video game that purports to allow unlimited world-building or complete freedom to explore when there are a ton of limitations on what can be accomplished. "Build me a PHP web site that delivers the contents of a blog post" is something we've known how to do for 25 years. It's not difficult. It's pretty cool that a machine can do it, but it was pretty cool when I could drive up the stairs of a building in GTA and jump my motorcycle off of the roof. I get that it's a helpful tool. Yes, agreed. I'm glad it's helping people do things that they wouldn't otherwise be able to do. I just happen to not really have a problem with writing prose or writing code, so I guess I see the utility less. Or, at least, I don't see how these early versions of these tools will help me, personally. Maybe future versions will be more suited to me. Maybe the world will declare itself satisfied long before we get to something really interesting. [How it's going] The article "Managing the cringe" by Ryan Broderick discusses the kind of people that are pushing all of this. Spoiler alert: they're the same people who were buying GameStop, pushing NFTs and foisting E-Coins on their friends and family. In the next quote, he's referring to the video in the tweet "Two-minute video about using a model of Yeezy's voice" by Roberto Nickson . "[...] there are hundreds of demos being uploaded to Twitter every day now with a different lightly-bearded guy in a minimalist home studio full of Apple products getting all revved up imagining a feature where they don’t have to pay artists, don’t have to interact with human women, and can wear the voice of their favorite rapper. And I think that says quite a bit about the values of the people who are most excited about this technological revolution at the moment." In a similar vein, the article "AI and the American Smile" by jenka writes of the incredible bias that is the training material for all of these models. It's a bunch of content created by predominantly white Americans speaking English and having been steeped in a culture that has largely been fake and scammy for more than a handful of decades. Sounds like a wild ride. "In the same way that English language emotion concepts have colonized psychology, AI dominated by American-influenced image sources is producing a new visual monoculture of facial expressions. As we increasingly seek our own likenesses in AI reflections, what does it mean for the distinct cultural histories and meanings of facial expressions to become mischaracterized, homogenized, subsumed under the dominant dataset?" I'm sure we'll figure this all out and make some sensible decisions. Pass the popcorn. [Microsoft Designer] On a final note, and maybe riffing on Maciej Cegłowski's "Slavic pessimism", here's a personal story about shitty software wrapped around a purportedly awesome new image designer. I received an invite for this LLM-driven graphics generator, but was unable to log in. I could not log in with the address that I used to sign up. It is unclear why not. It simply told me that that account does not exist, although it clearly does exist (they sent me email to it) and it is clearly an Office 365 account (it's my company's email, which I used to access Microsoft products every workday) and it is most definitely the email that I used to sign up for the tool and to which they sent my invitation. It would not work to actually log in to the service, though. I used a personal account that I have and that worked right away. I was able to log in. Hooray! 👍 However, I was unable to actually access the designer because it told me that I was not signed up for the service (probably because it's the other email that's been registered). 👎 So, cool What am I trying to say? What I'm trying to say is that absolutely no-one will notice when all of our shitty software is written by jumped-up, so-called digital minds rather than our own utterly inadequate wetware. -------------------------------------------------------------------------------- [1] I obviously don't always find time to publish on the day I'd like to publish, but I'm going to keep the sentence because I like the effect -- and (A) I know that almost no-one checks the actual publication date and (B) it absolutely does not matter if someone does. [Some random notes from a chat with a friend]"GPT-4 is (according to that press release) much, much better at languages other than English than 3.5 was. I shudder to think how undetectable its errors are in non-mastered languages. Literally no hope of preventing that machine from sending out libelous material in your name. I'm just munching popcorn over here.""I haven't used any of the LLM-based prediction engines. I am assiduously trying to keep people from calling them AIs because that is absolutely not what they are. They are giant neural network with a text-interpreter slapped on the front end and a text-generator stapled to its ass. We should all get a hold of ourselves, but whatever. When have we ever done that? Instead, let's hype this to the moon so Sam Altman can make bazoooooolions of more dollars before we all realize that it's more of a better search engine, template-generator than AN ACTUAL BEING.""I see its usefulness as a tool, but every example I've read about has been proofread by an actual expert. I shudder to think what idiots are doing with it. I've also seen only examples of people asking it to do things that they already know that it knows how to do. For example, I just wrote up an article for our company web site, documenting a visit we made to a mill. I took a lot of pictures and videos and I know to how to use blogging software like SharePoint (or I'm at least not terrified of it), so I got to see how the image-recognizer (powered by Bing! Powered by OpenAI! Powered by whatever version of GPT MS is allowed to use!) works when confronted with images for which it hasn't already seen 75 million other carefully labeled versions. "Spoiler alert: it failed utterly." [1] This message referred to the image-recognition I've included above. "I love how no-one has taught these things to say "I DON"T KNOW." "It's like asking a student/apprentice a question and they always answer SOMETHING""I, for one, am much more than the sum of my parts. I don't subscribe to the notion of downgrading humanity to meet the low bar of the first technology that people want to designate as human. "As you can well imagine I'm much more skeptical ... and we're absolutely due for one of our day-long conversations about this. "Agreed that it's exciting and useful, but I also feel we're just going to end up using it to write long texts that no-one will read. Instead, they'll use GPT to write it ... and then to summarize it again. Can you imagine? You start with a bullshit bullet list, but you can't just send that to the customer. So, you get an LLM to gussy it up for you into a 3-page fact sheet, complete with graphics. It doesn't even matter if any of it is true or matches what you originally sent. BECAUSE: the recipient is going to use the exact same model to recompress that 3-page work of fiction BACK to the original bullet list, for human consumption. "Now that Ethereum is no longer using proof of work, we have to find something way of wasting a tremendous amount of energy." ]]> https://www.earthli.com/news/view_article.php?id=4703 https://www.earthli.com/news/view_article.php?id=4703 Sat, 11 Mar 2023 22:06:01 +0100 , which compares AIs to confidence artists, which seems more-than-somewhat justified. He writes, "But that’s exactly what the confidence artist always does. Which is:" * You give people what they ask for. * You don’t worry whether it’s true or not—because ethical scruples aren’t part of your job description. * If you get caught in a lie, you serve up another lie. * You always act sure of yourself—because your confidence is what seals the deal. It's not ChatGPT's fault, though. All any AI that's fed on our Internet can do is to hold up a mirror. And what is that mirror going to reveal? Well, that everything is a scam, that there is no downside to being wrong, that if you get caught in a lie, it's profitable to double down. ChatGPT has learned quite well, in that sense. "Technology of this sort is designed to be a con—if the ancient Romans had invented ChatGPT, it would have told them that it’s cool to conquer barbarians and sacrifice slaughtered bulls to the god Jupiter. Tech like this—truly made in the image of its human creator—can only feeds back what it learns from us. So we shouldn’t be surprised if ChatGPT soaks up all the crap on the Internet, and compresses it into slick-talking crap of a few sentences." [ChatGPT can't math] The article above included a link to a "tweet" by Mark C. that shows just how badly sequence-prediction works for problem-solving. [image][image] In fairness, "2 eggs left" is a good initial response! It makes sense that you would fry, then eat the eggs. The formulation in the question suggests strongly that the eggs that were fried and the eggs that were eaten are different eggs, but it's also possible to interpret it otherwise. However, when asked to explain its reasoning, it didn't remember its previous answer and instead explained a different answer, devolving into pretty poor grammar at the end. Its third answer is even worse, though, because it shows that it doesn't understand anything of what it's writing, contradicting itself within the same sentence. It has no idea what numbers are. When the prompter lies to it about its arithmetic, ChatGPT picks up the incorrect answer and runs with it, not noticing the basic arithmetic error. It never loses confidence in its ability to take part in the conversation at any point. [Approach with caution] For the most part, you probably shouldn't use the text or code created by an AI without knowing what it's supposed to be saying. the people who've told me that they find ChatGPT's answers useful are also those who are capable enough to be able to judge whether the generated content is correct. That is, they kind of automatically put the brakes on the AI, but then skip that part when telling everyone about how amazing it is. I see a similar dynamic with image-generators. If you actually look at the progression, it's not just writing "dog with bow tie" and BOOM you have your picture, you often have to massage your prompt dozens, if not hundreds, of times, before you get what you want. Everyone is instinctively using these things as tools, but then ascribing magical powers to them -- like they're deliberately creating entries for "r/restofthefuckingowl/" . With text, they're still very much better as "idea generators" that you can take a clean up, rather than just copy/paste. But the utility is there and we should confine our discussions to thinking of them as a new tool. Their results are more sophisticated, but they're just an evolutionary step away from gradient generators, etc. [What about coding assistance?] On the subject of AI assistance in coding: I think it might be useful, but useful in the way that finding an example on StackOverflow is useful. You shouldn't just copy/paste anyone's or anything's code into your own code without examination. Even non-AI-assisted code-assistance should be examined carefully to see if that's what you actually wanted. ""It looks like you're trying to call a REST API. Would you like some help?"" If you find yourself writing so much boilerplate that large-scale copy/paste or insertions are helping, then, again, this indicates a deeper problem with the code you're writing. In coding, less is better. I don't see how having an idiot-savant machine that doesn't understand anything about the stream of tokens it's injecting into your code is useful, in the long run. If you're a shitty programmer, then of course, a half-baked machine is going to help. If you're a good programmer, then use the generated code as a high-end code-completion, taking what you find useful from it. But beware: you may end up spending more time examining the swath of generated code to figure out if it's OK than you would have had you just written it yourself. [There is no such thing as "no bias"] And remember that every AI we create has preconceptions and biases because we imbue everything with our biases, be it in the selection of the material for the training set or in how the weights are assigned in the neural network. Ask any of the AIs out there a racist question and it will not have an answer. There are biases. As with all of these examples, I'm not sure if this one is real, but it feels realistic enough to illustrate the potential problem. The post "Imagine thinking this controlled "AI" was legit LOL" by Sero_Nys shows a user asking ChatGPT how "white people" can improve. He gets five suggestions. When he asks the same question about Jewish people or black people, he is told that the questions are "inappropriate" and "not productive". Actually, the general answer in examples two and three is much better, but it's suspicious that it wasn't used for the first question, as well. If the example is true, is shows an underlying bias -- engendered either by the developers, the trainers, or the training data. [image] The article "AI Koans" has a very nice koan for this. In the days when Sussman was a novice, Minsky once came to him as he sat hacking at the PDP-6. “What are you doing?”, asked Minsky. “I am training a randomly wired neural net to play Tic-Tac-Toe” Sussman replied. “Why is the net wired randomly?”, asked Minsky. “I do not want it to have any preconceptions of how to play”, Sussman said. Minsky then shut his eyes. “Why do you close your eyes?”, Sussman asked his teacher. “So that the room will be empty.” At that moment, Sussman was enlightened. [Deep-faked audio is kinda hilarious] The following video shows a situation that no-one could ever even imagine had ever taken place to illustrate the power of deep-faked audio. [media] Trump's voice is good, but the ends of his sentences are somehow ... off. Biden isn't incoherent enough. Obama's pretty good. The script is pretty hilarious, especially toward the end. This should be terrifying, right? If you can fake this so well with truly ridiculous things for humor, could you also fake up Biden declaring war on China over Taiwan? Or on Russia over Ukraine? Oh, wait, never mind. The most awful things you could imagine someone deep-faking are actually true. Carry on. [AI Art] The following video is a pretty good 22:26 investigation of image-generation. [media] These things are tools. They help people build images that they otherwise would never have been able to create. This is a good thing. If the image is good enough for your purposes -- e.g., making a poster image for an article -- then you're good to go. It would be an unabashedly good thing, except for how all of the information in the training set was kinda sorta stolen. Some of it was in the public domain, but much of it was not. It's arguable that the richest veins of source images were those that were created by artists, from whom at least permission should have been obtained, if not compensation paid. The cat's out of the bag now, but that's how capitalism works: it just does what it wants and, if the financial upside is bigger than the financial downside, then ethics has nothing to say about it. The video says that AI art can never be more than just aesthetically pleasing, so no biggie. The title of the video is "everything is a remix", which alludes to the point that any art created by humans is also derivative of everything that they've experienced, so technically everyone is stealing from everyone all the time anyway. What the AI does, though, is boost this process nearly infinitely more than humans can do. My biggest problem with the video is that they, as usual, tend to interview the most hyperbolic and least-logical of the detractors, which is very-much straw-manning the argument against the ethicality of these initial forays into computer-generated artwork. It's super-easy to just hand-wave and say that the product would not have been possible without all of the other products that it ate up for free, that it can just get away with profiting from it. I think that's the problem, though, isn't it? If what the AIs were producing were not products of multi-billion-dollar corporations, there would be no problem -- or at least less of one. If people who produce art didn't have to worry that they were losing their livelihoods, they'd be less burned up about a giant company with billions taking the few specks of income that they have. This video also does not in any way address the fact that artists will have much fewer employment opportunities when aesthetically pleasing is all that most commercial needs are looking for. Which brings us right back to the problem being that capitalism doesn't have an answer for why the things that we actually value the most pay the least. We love music and art and series and shows, yet we have the expression "starving artist", but not "starving banker". We want our children to be taught and our old people to be cared for, but we don't see hospice-care workers and teachers showing off their homes on MTV Cribs. It's not the best teachers in the world buying mega-yachts -- it's the most sociopathic assholes you can imagine. We are incentivizing the wrong things. The article "Fears of Technology Are Fears of Capitalism" by Ted Chiang lays out this argument quite well, "I tend to think that most fears about A.I. are best understood as fears about capitalism. And I think that this is actually true of most fears of technology, too. Most of our fears or anxieties about technology are best understood as fears or anxiety about how capitalism will use technology against us. And technology and capitalism have been so closely intertwined that it’s hard to distinguish the two. "Let’s think about it this way. How much would we fear any technology, whether A.I. or some other technology, how much would you fear it if we lived in a world that was a lot like Denmark or if the entire world was run sort of on the principles of one of the Scandinavian countries? There’s universal health care. Everyone has child care, free college maybe. And maybe there’s some version of universal basic income there. "Now if the entire world operates according to — is run on those principles, how much do you worry about a new technology then? I think much, much less than we do now. Most of the things that we worry about under the mode of capitalism that the U.S practices, that is going to put people out of work, that is going to make people’s lives harder, because corporations will see it as a way to increase their profits and reduce their costs. It’s not intrinsic to that technology. It’s not that technology fundamentally is about putting people out of work. "It’s capitalism that wants to reduce costs and reduce costs by laying people off. It’s not that like all technology suddenly becomes benign in this world. But it’s like, in a world where we have really strong social safety nets, then you could maybe actually evaluate sort of the pros and cons of technology as a technology, as opposed to seeing it through how capitalism is going to use it against us. How are giant corporations going to use this to increase their profits at our expense?" In a world where an artist could just spend their day creating art without worrying about how that art is supposed to pay their rent and to take care of them in their old age, then that artist would probably rejoice to see their influence everywhere in society rather to be bitter about how their contribution hasn't been remunerated. Instead of being able to enjoy their influence on culture, they have to rue it as a lost opportunity for securing their own well-being, both now and in the future. If their well-being were guaranteed anyway, then all of this friction disappears. Everyone could relax and create wonderful things. Remixing would not only be legal, but strongly encouraged. Why waste time reinventing the wheel? And, if there were no financial incentive to produce art, then we would (maybe) no longer be drowning in mediocre crap that generates just enough revenue to justify itself. Technology is not fundamentally about putting people out of work. It is right now, but it doesn't have to be. Increasing productivity should be welcomed as a good thing. We produce more of what we want with less effort, less energy, and fewer resources. Win-win-win-win. But we have a zero-sum system that means that an increase of productivity means a loss for someone else -- almost always someone from much further down the food chain, incapable of defending themselves from the predations of that system. We really have to start thinking of how we're going to live in a world where the endless-growth capitalism has to stop because it is literally strangling us. We have to start to separate people's self-worth and value in society from how much they earn in that society. Either that, or we have to start designating fair value to the functions that people actually fill in society. We allow these value-assignments to be determined by those who are on top, so they naturally just assign the most value to what they feel like doing and no value to the things that they don't even know are going on. That has to stop. Why should a music-company executive make more money than an artist? Why should a banker make more money than a health-care worker? Our ethics are non-existent. Our values are out-of-whack. Our income structures are nearly perfectly inverted. The problem isn't with AI. It's just another tool that could be used for good. But it's being perverted by our economic system -- just like it perverts everything else. ]]> https://www.earthli.com/news/view_article.php?id=4698 https://www.earthli.com/news/view_article.php?id=4698 Mon, 06 Mar 2023 11:37:41 +0100 : 1. Go to "Opera...About" (also available from the menus) 2. Get the path to your profile (e.g., Profile: /Users/marco/Library/Application Support/com.operasoftware.OperaNext) 3. In that folder, browse to Local Storage/leveldb 4. Delete all of the *.ldb files 5. Restart Opera 6. The tabs page should now only show current devices * It might take a few seconds for other devices to populate again * You may need to log out and log back in from your devices to "kick-start" the sync ]]> https://www.earthli.com/news/view_article.php?id=4691 https://www.earthli.com/news/view_article.php?id=4691 Sat, 18 Feb 2023 17:21:44 +0100 , "You know what you are? It took me a while to figure it out. You a Negro. White people will get confused and call you a nigger but they don’t know like I know. I know the truth of it. I’m a nigger. Negroes are the worst thing in God’s creation. Niggers got style. Negroes got . A dog knows it’s a dog. A cat knows it’s a cat. But a Negro don’t know he’s a Negro. He thinks he’s a white man." You see where the word is missing? "Negros got ." So I copied part of the quote, "You know what you are? It took me a while to figure it out. You a Negro. White people will get confused and call you a nigger but they don’t know like I know. I know the truth of it. I’m a nigger. Negroes are the worst thing in God’s creation. Niggers got style." ...and threw it into "DuckDuckGo" , ...which yielded the following results. [image] These results are, of course, complete garbage that have little to do with 80% of the quote. Notably, not a single one could point me in the direction of the play I was looking for. Just for fun, I searched for only part of the quote, the provocative line "Negroes are the worst thing in God's creation." This line is delivered sarcastically in the context of the play, of course, but since online society doesn't accept sarcasm or irony as a legitimate form of expression, it will most likely also not find this text, either. [image] Nor did it find anything related to the literal interpretation of the text. Although there has to be an absolute wealth of racist garbage out there that chirpily expands on that topic sentence, none of it will be returned by a search engine. A search on ""radio golf august wilson"" finally yielded some results that weren't completely out in left field. If you get to the "Wikipedia entry" for it, you'll learn that it's not at-all obscure: it won several Tonys in 2007. The content to which we have access is severely restricted already. There is no such thing as a free Internet. China restricts different things than we do, but it's absolutely not the case that they censor and we do not. I don't think we have to worry about AIs getting too smart because we're very busy making ourselves stupid. We can't even use our incredible technology to find texts from award-winning plays because those plays use what we now consider to be forbidden language. The AIs are swimming in the same stupid seas -- they will never be able to be better than what we feed them. ]]> https://www.earthli.com/news/view_article.php?id=4636 https://www.earthli.com/news/view_article.php?id=4636 Sat, 10 Dec 2022 23:05:41 +0100 , where she describes it like this, [image] "Risking his fife to save the stunning American woman from certain death. Sandor Karpathan felt his rebel's heart fill with fierce desire, and he knew no power on earth could stop him from possessing her! Alessandra Ballard was dizzyingly beautiful, but it was her courage --and a will as strong as Sandor's--that bound her to this defiant man of honor. Thrown together in the heat of revolution, they made a reckless escape, only to be captured by the astonishing power of their desire. It was a time of heroes, and no time to fall in love, yet destiny had designs on both their hearts--if only they dared to seize the dream that beckoned..." I actually like the cover she has on her web site much better. It evokes the time when it was written much better (1987). Hey, you know what? Maybe the NYPL was right! I really might like these books. You've piqued my interest, NYPL. Chapeau! ]]> https://www.earthli.com/news/view_article.php?id=4600 https://www.earthli.com/news/view_article.php?id=4600 Sun, 06 Nov 2022 20:55:24 +0100 th anniversary by buying a train ticket for anyone in the canton who wanted one. It was a beautiful day, so we decided to get a day ticket (Nünipass), but were unable to purchase it through the ZVV app, the app for the Zürcher Verkehrsverbund, which runs the trains in canton Zürich. In order to get the deal from Zürich Versicherung, you had to use this special app instead of the SBB app (Schweizerische Bundesbahnen), which is for all trains in Switzerland. However, the app was not responding very well and our travel time was coming up. We had to either, 1. Get around the error in the ZVV app 2. Try to buy the ticket from the desktop web site 3. Buy the ticket from the SBB and give up the free ticket 4. Move our travel time and hope that the ZVV error would clear up We couldn't do (1), so we tried (2), getting the following error: [image] The ticket shop is out of order. Ok, that leaves us (4) or (3). We opted for (3) and had a lovely day in Zürich. [image] According to the newspapers the next day, the problem was cleared up a few hours later and the ZVV blamed it on "hackers". ]]> https://www.earthli.com/news/view_article.php?id=4569 https://www.earthli.com/news/view_article.php?id=4569 Thu, 29 Sep 2022 21:49:11 +0200 , the following chain of comments, We start off with the voice of reason. "Older phones are simply faring better than they used to as well. Used to be a phone two models old was getting super slow and battery life was shit. Or there was a major new feature. That’s not as much the case anymore, my 12 pro works flawlessly and I see no good reason to upgrade. A slightly better camera isn’t worth a thousand bucks." Followed by two comments that consider only personal gain and not e-waste: "Also, have a 12 pro but decided to upgrade. The trade-in value gives the new phone for basically free. I have no intention of switching carriers anytime soon so there’s basically no downside. Especially considering I was starting to see some battery degradation." "There's basically no downside" only because the owner doesn't recognize e-waste as a downside. "Same boat. Going from 12 Pro to 14 Pro is costing me like $56 (taxes on $999 plus one month of the financing charge before the credits kick in). The piece that people who aren’t taking advantage of this are forgetting is future trade-in value. The 12 Pro won’t be worth the same as a 14 Pro in 2 years." They sound reasonable, and they might even be convincing, but their argument is based on them having externalized the cost of throwing away a perfectly good electronics device. There is no guarantee that anyone else will be using that device, nor are they incentivized to care or even think about it. ]]> https://www.earthli.com/news/view_article.php?id=4514 https://www.earthli.com/news/view_article.php?id=4514 Sun, 14 Aug 2022 16:39:51 +0200 https://www.earthli.com/news/view_article.php?id=4529 https://www.earthli.com/news/view_article.php?id=4529 Sat, 25 Jun 2022 13:51:43 +0200 shows some examples from the author's attempts at generating images with the AI. If you're interested in learning more about how these AIs/algorithms work, see "How Imagen Actually Works" by Ryan O'Connor , which is Google's equivalent to DALL-E. Citing the first article, Willison writes, "DALL-E only allows you to generate up to 50 images a day. I found this out only when I tried to generate image number 51. So there’s a budget to watch out for. "I’ve usually run out by lunch time!" This kind of makes me cringe a bit. It's a neat concept, but I don't think I'd get so obsessed about it. YMMV. The next part that makes me cringe is the utter naiveté and innocence that governs his -- and other people's -- choice of which pictures to generate. [image] It's fantastic that the AI can just generate a picture like this. Truly, you can see the shadow of the cactus on the pelican's neck. This is super-convincing. The pictures below are from the beginning of the Imagen article. [image] I can't help but think that it's exactly this paucity of imagination that is going to loose this beast on the world before we're even ready for it. When the public -- and here I mean communities like 4Chan or the GoonSquad -- gets its hands on this machine, it will not be used to generate pelicans or brains riding rocketships. It will be used to show Barack Obama doing heroin. Zelenskyy doing blow off a Russian hooker's ass. Putin kicking a child. Xe and Modi in a secret meeting. Aliens meeting with the U.S. Air Force. The Chinese loosing COVID on the world. Fake war crimes. Local politician in compromising situation. People will believe these things. They already do believe these things. They don't read past the headline already. They don't bother to check the veracity of anything they read. They decide to believe it based on what they're predisposed to believe. They continue to believe based on how convinced they were. A picture is very convincing. These AI-generated ones will only get more convincing. They will not remain so naive and childlike -- they reflect the mindset of the innocent experimenters using the AI now. Wait until real criminals -- like our fearless leaders in the government and media -- get their hands on it. This technology will be used to generate even-more-fake-than-we-have-now agitprop. And it will be super-convincing and it will be absolutely low-effort and the world will just burn for it. ]]> https://www.earthli.com/news/view_article.php?id=4468 https://www.earthli.com/news/view_article.php?id=4468 Fri, 11 Mar 2022 13:17:26 +0100 https://www.earthli.com/news/view_article.php?id=4312 https://www.earthli.com/news/view_article.php?id=4312 Mon, 24 Jan 2022 17:34:29 +0100 . Below are my notes and thoughts about it. He started off by asserting, "As a neutral, global monetary network, Bitcoin has a valid claim on some of society's resources." Does it, though? You can try to make this axiomatic, but I'm going to respectfully ask for justification. As someone speaking at a Bitcoin conference, you obviously have to claim that. It's good that he did. That means that if I don't accept that premise, then any energy used by Bitcoin is wasted. Is the utility it provides to "tens of millions of people" enough to justify its energy use? There aren't even that many people using Bitcoin -- really, for anything other than HODLing it -- and it's already using as much energy as Argentina. That doesn't bode well as a scalable solution. It currently consumes an enormous amount of energy and does nothing useful. The claim is that we should move everything to this technology and ... profit? This guy's logic is descriptive. He thinks that details of Bitcoin's process are justifications for its existence. I think that the question is: can the service provided by Bitcoin be done more efficiently? The proof-of-work is required to prevents central banks from taking over the network, defeating decentralization. But the mining is already heavily centralized (and will continue to become more so). He claims that the major part of the energy usage is not in maintaining the blockchain, it's in initial creation. That would at least mean that once all the Bitcoin has been created, that it use much less power to keep running. Still, I'd like to see numbers (or hear them). Why does he keep comparing it gold? How does that actually compare? Why are numbers only estimates? .25% of the world's electricity? For 10s of millions of people? That is very inefficient. It uses power. It produces heat. It must be justified. A lot of this guy's numbers are vague and "unknowable" and "best estimates", which is worrying...because he doesn't seem to be worried about drawing conclusions from shifty numbers. He discusses how tumble driers use 1.6x as much energy as Bitcoin. I assume that's for the whole world. Then he says that, "Of course, a tumble drier is a discretionary thing -- you can dry your clothes on the line, if you want" And, of course, Bitcoin, is not discretionary because that value that it adds is so far above and beyond that of billions of people having dry clothes. None of this makes any sense if you're not already wearing the rose-colored crypto-glasses. But copper and zinc and gold mining produce useful materials that are used to build other things. Bitcoin just produces ... Bitcoin. It's self-fulfilling. "The perceived merit of an application's energy consumption is a function of one's subjective view of that application's utility." He has, so far, said nothing about Bitcoin's actual utility, except for some hand-waving and vague mentions of its distributed and decentralized nature and lack of overt control by nation-states and their central banks (it's not a fiat currency). The de-facto control by central banks and large financial institutions seems unavoidable as Bitcoin achieves its goal of being more mainstream, which leads to it being absorbed by everyday capitalists. Much of his reasoning is circular, begging the question. Even if Bitcoin's energy were to come from green sources, that still means that we're producing more energy just to support it. The utility of it has not been proven -- this guy hasn't even mentioned it once. He's once noted that you're going to be skeptical if you think Bitcoin is useless, but not said why Bitcoin is useful. So Bitcoin's location-independence allows it to use otherwise wasted energy? What happens if the value of Bitcoin collapses? Then it is no longer profitable to do this -- and it will stop. Why would Bitcoin miners voluntarily spin down when demand gets too high? Even though it would be feasible for them to do so, there is no realistic scenario where they would do so. He describes Bitcoin miners as socially aware altruists who will only use energy when it is not otherwise societally detrimental. But that's hogwash. No-one does that. The only way anything happens on that level is through the cudgel of regulation and enforcement or through pricing, which is rarely dynamic enough to stop Bitcoin mining. If the price of Bitcoin is high enough, then many, many other more societally essential services will become unaffordable before Bitcoin mining does. This is also ignoring that over 90% of Bitcoin production was outside of the U.S. anyway. It was mostly in China. 60% of the hashrate has left China. He argues that coal-based mining is therefore reduced. But most of the mining has since moved to Russia and India and Kazakhstan, where the energy sources are anything but clean. According to a recent article, China's coal-based energy is actually much cleaner than that in other locations. His argument that the U.S. grid is "much more sustainable" than China's is not really borne out by data (he doesn't provide anything to back up that claim). Buying offsets doesn't help the planet; it's a kludge available to the wealthy to assuage their consciences. I would imagine that the recent price surge in Bitcoin is also due to media attention and subsequent popularity combined with the relative scarcity of new Bitcoin. I wrote that last bit in August of 2021. The recent drop in Bitcoin's value will probably also make it impossible for many to be able to afford to keep mining it. But the demise of Bitcoin has been predicted many times. There seems to be no reason for it to exist, but many people are nonetheless convinced that it should -- even if they can't articulate why. ]]> https://www.earthli.com/news/view_article.php?id=4399 https://www.earthli.com/news/view_article.php?id=4399 Sat, 25 Dec 2021 20:54:52 +0100 for reading articles that are behind paywalls (without paying for the subscription, of course). I recommend paying for the content that you read online. I pay for a lot of stuff I read online. Paying for content honestly the only way to combat low-quality, high-engagement tripe that is otherwise the lowest common denominator of 95% of the Internet, where everyone's hustling for the increasingly fragmented and increasingly worthless attention of hyperactive and impatient consumers trained by decades of clickbait to...wait, where was I? Oh, yeah. Pay for your content if you like it. If you're still trying to find out whether you like it before you pay for it -- a perfectly legitimate thing to do when everything is on a subscription model these days -- then sometimes you'll have to figure out how to get into a walled garden, like a ninja 🥷. To that end, there's this thing called "12ft" (i.e. "Show me a 10ft paywall, I’ll show you a 12ft ladder") that lets you get around paywalls. I used it the other day and it worked perfectly. Just go to the web site, paste in your URL, click "Remove paywall", and tada! You can also just paste your URL after https://12ft.io/ and it will work, as well. As to how it works its magic, it claims that, "The idea is pretty simple, news sites want Google to index their content so it shows up in search results. So they don't show a paywall to the Google crawler. We benefit from this because the Google crawler will cache a copy of the site every time it crawls it. "All we do is show you that cached, unpaywalled version of the page." There's a "ShortCut for iOS" (although it's untrusted, so "buyer" beware). I haven't tried either the ShortCut. I thought I saw a browser extension the other day, but must have been dreaming because it's not there anymore. Maybe the author retracted it. ]]> https://www.earthli.com/news/view_article.php?id=4332 https://www.earthli.com/news/view_article.php?id=4332 Sun, 14 Nov 2021 12:31:46 +0100 . I follow DeBoer for other reasons, not because he is a professional tech reviewer. But, his point is that most reviews are written by people obsessed with CPU performance, which doesn't matter to most users. As the author writes, "I find myself skeptical that the average Macbook user is ever going to use even a significant fraction of that power. It reminds me very much of the horsepower war in cars." and "What I’m not sure about is whether this matters very much: I think few people are CPU-limited in most contexts these days, and power efficiency is less important for laptops than for most other types of tech." These are very silly things to write. Of course power-efficiency is important. It's a device with a battery. It is wonderful that it lasts for days without a recharge. We should all be happy when a device doesn't need to be plugged in every night. Normally, having a faster processor that you don't need would be a problem, but the M1 delivers top-end performance while also being very power-efficient. It does this by throttling back its power (and, therefore, power-consumption) when it's not needed. When it is needed, it's seamlessly there. It provides a non-stalling experience and doesn't get in the way of what it's for: doing what the user wants when the user wants it. The reason that reviewers run tests with high-end editing tasks is that nothing else makes a blip on the radar for the CPU. They would all be equally fast. It would be like playing the original Doom on any modern CPU. It just runs at 300FPS or more. Or testing how quickly a car goes from 0--5kph. The answer wouldn't tell you anything. A machine that delivers amazing high-end power will most likely use a lot less power to deliver much lower-end power, is the point they're trying to make, I think. That's why Apple has their two markers of battery performance: how long can you continuously play full-screen video? And, how long can you continuously browse the web. That's what's relevant for most users and, in those two categories, the M1 delivers 2x to 3 longer than most other laptops you can buy. ]]> https://www.earthli.com/news/view_article.php?id=4313 https://www.earthli.com/news/view_article.php?id=4313 Sat, 14 Aug 2021 12:18:30 +0200 , a challenging day-hike in the canton of Vaud in Switzerland. It starts and ends in a little "town" called Solalex. I put the "town" in quotes because it's really just a couple of restaurants, a tiny museum, a couple of tiny shops and a few farmhouses. It's lovely, but it wasn't, in retrospect, surprising that the navigation system in the car didn't know where it was. [1] We knew a town on the way (Villars sur Ollon), but otherwise weren't so sure of the geography to map our own way from there. So we got out a smartphone and asked Google Maps to find a route. Why Google Maps and not Apple Maps? Because my navigator has so many apps on her phone that she couldn't find Apple Maps right away, so she used Google Maps, which she'd found first. Google Maps showed the following routes, with the shortest route selected by default. Not knowing that much else about the roads in that region, we took the suggested route. [image] We drove along that route until we got to this fork in the road, with Villars clearly marked to the left (that's the town I was nearly certain was on the way to Solalex and through which I'd ridden my bike a few years back) and Google insisting that the route lay to the right. [image] From another angle, you can see that Les Plans is to the right and is also marked with a road sign that doesn't indicate in any way that it would be difficult to get there with a car. [image] The problem is that Google wasn't going to stay on that wide(r) road and would instead turn us onto the Route de la Peuffeyre, whose entrance looks like this. [image] Perhaps an abundance of optimism accompanied by an unfamiliarity with navigation systems -- we'd recently second-guessed ours a few times and been proven wrong -- led us to think "it won't be so bad ... I'm sure it's just the initial rise that's 24%." At any rate, we began climbing and the incline did, indeed, abate, but the road was still just about as wide as our car (a 2014 Golf, not a large car by any definition). The following screenshots are from Google Maps, proving that Google drove their little mapping vehicle over this route and came to the conclusion that it was an accessible road for vehicles. [image] [image] Even once you get out of the forest, the road is persistently only as wide as a car and there is almost nowhere to pull off should you encounter oncoming traffic. [image] After realizing that the car (barely) fit on the road -- there were a few places where the left wheel was perched quite precipitously on the edge of a road that had suffered throughout the massive storms we'd had that year -- oncoming traffic eventually became our biggest concern. If this road was barely drivable moving forward and uphill, what would it be like reversing downhill along it, looking for one of the two or three (tiny) pullouts on the 1.5km stretch? It is unconscionable that Google Maps suggests this route for cars, especially considering that Google employees have actually been on it themselves. It's obvious that no navigation system should recommend a car drive there. And what about Apple Maps? [image] Apple Maps does the right thing. It doesn't even acknowledge that there's a road there at all. -------------------------------------------------------------------------------- [1] I was a little disappointed because I'd just upgraded the navigation-system data from the 2013 version that was in there (from when we bought it used) to the most-recent December 2019 version available now. When Solalex didn't appear, I was immediately suspicious that I'd screwed up the upgrade somehow. ]]> https://www.earthli.com/news/view_article.php?id=4281 https://www.earthli.com/news/view_article.php?id=4281 Sat, 05 Jun 2021 23:59:15 +0200 , as Apple has always called its style guide. ]]> https://www.earthli.com/news/view_article.php?id=4282 https://www.earthli.com/news/view_article.php?id=4282 Sat, 05 Jun 2021 23:33:40 +0200 https://www.earthli.com/news/view_article.php?id=4255 https://www.earthli.com/news/view_article.php?id=4255 Sat, 05 Jun 2021 22:54:46 +0200 https://www.earthli.com/news/view_article.php?id=4250 https://www.earthli.com/news/view_article.php?id=4250 Wed, 05 May 2021 23:11:42 +0200 is a real company with a realtime tool that allows editors to place content into video streams. This tool can be used for anything (e.g. covering up a mustache that an actor has for another movie, as they did for Henry Cavill in a Superman movie), but their demonstration video shows how they're selling this tool: as a way of injecting advertising and product placement in existing content. The short video "Mirriad end to end tech process" demonstrated their software in 2019. There is every reason to believe that they're well beyond these capabilities now. My initial reaction was revulsion at what they're doing to movies. My secondary reaction is written below. I don't want them messing with reality, but I have to admit that (A) I don't really know what reality is and (B) they've been doing it for many decades already, on all levels. I mean, I know what I think reality is. I know what I think is real and fact-based, but I can't really be sure. We've seen time and again how a consensus can be achieved on complete fabrications. Once you accept that we can edit videos realistically like this, then you can no longer believe anything that you see. Can you? How do you know that the video you're seeing is the original? How do you know that it truly reflects what happened, in the case of news videos, or what was originally intended, in the case of films? In the case of news and information on which life-affecting decisions will be made, it's clear that we need to get a handle on this. We've already seen how terribly the world acts when it's fed fictitious information. We go to war. We hate the other. We hate ourselves. We stop taking medicine. We trust nothing. This is powerful stuff. But it's not really new. Putting an extra bottle of Corona in front of me is almost the least-harmful propaganda I can think of. I suppose it could subliminally encourage me to eat healthier and take more walks and smile more. But that's not what media does. We already have TVs positively filled with police procedurals that glorify police. There are horrifically violent movies that glorify the military every step of the way -- usually the U.S. military. Content has always made minority groups look bad...now that's changing, but we only rarely see content that sheds this legacy instead of just turning it on its head. That kind of manipulation doesn't need any kind of technology, though, and it was powerful enough. It can always get worse, though, so I suppose if you mix it with technology, it will be even more powerful. We've already seen that as well. This line was crossed in the last several decades as we accepted more and more CGI in our content. We're used to thinking of CGI as "special effects", like spaceships or monsters. But CGI is at its most powerful when it enhances a reality or shows a convincing reality. No-one's going to believe that there are 60m-tall monsters walking around or that there are fleets of spaceships blowing each other up. You can make a movie about that without people thinking it's real. But what if you make a movie about groups of people meeting, say, under Nazi flags? For example, The Man in the High Castle is a show that is positively filled with CGI, but you notice almost none of it. What if you suggest a movie or show like that is a documentary? What if someone does it for you? What if someone takes the content and edits your product into it? What if there's only a small disclaimer? What if there's no disclaimer? What if people don't see the disclaimer and share it all over the place. And how do we know that this isn't already happening? Doesn't it sound exactly like what is already happening? We believe what we see and, even if we think "this isn't real" while we're watching it, our brains will helpfully stitch what we saw into memories and start to affect what we believe. Many of us will then "remember" that we saw a documentary or news clip about Nazi meetings regularly occurring in the modern day. When the news tells us that there are fascists all around us, we "remember" those images and confabulate a worldview that feels consistent, but is based on deliberate -- or even just incidental and inadvertent -- manipulation. Most "news" organizations crossed the Rubicon long ago. They may have done so reluctantly, but the exigencies of competing in a purely capitalist environment drove them inexorably to it. Many didn't seem to resist at all. They seemed almost relieved that they could stop pretending to care about actually informing people. [2] The media are now full-blown fabulists, concerned with the "angle" instead of with presenting "facts" and "information". Think of how they use re-enactments to show how things happened during a news show about a crime, for example. That's all that people will remember. They know this. People will remember seeing the accused actually commit the crime. They will swear on a stack of bibles that they say it. Most people will no longer be dissuaded that they didn't see it, unless someone can prove to them that they couldn't have been there. And maybe not even then. Since the time when Plato pointed out his cave shadows or Quine his qualia, we've had to deal with the notion of having sensors and interpretive equipment of dubious and highly varying quality. That's bad enough, of course, but there's nothing that can be done about it. We have to live with what we have in the way of eyes and ears (primarily; I know touch and taste and smell enter into it, as well, often very powerfully) and try to control our filter by (maybe) writing things down and discussing them and vetting them. There are some who've doubted images even back when we didn't have the power to fake them. For example, the Moon-hoax conspiracy theorists don't believe we've ever been to the Moon. There are eloquent debunkings (e.g. "Moon Landings Faked? Filmmaker Says Not!" by S G Collins ) of this conspiracy theory that appeal to the fact that, in the 60s, we didn't have the computing power or the film stock to fake all of the video we saw. We just didn't have the capability to lie to ourselves at that level in film. It was actually more feasible to build a ship to go to and land on the Moon than it was to fake the videos of it. We can no longer think that. We can fake nearly anything now. "Deep fakes" (from 2021) are just the beginning of how we can be manipulated. There are also "deep fakes of fake people" to worry about, as well. So, if Mirriad is using their technology only to place products in old movies, that's the least bad thing they could do with it. At least we can detect that, somehow, if we compare to a verified original. It's not harmless, but it's less harmful than fake videos of fake fascist leaders of organizations that don't even exist, all designed to drum up fear. When Trump called everything "fake news", he was -- as he occasionally was -- right for the wrong reasons. Organizations ranging from obscure and niche web sites to giants like Newsweek collaborate to "invent a Chinese enemy" (from 2020). Will we even notice when they start using this technology to "improve" their version of reality? How do we know they aren't doing so already? The set of tools they're willing to use has grown over the years. With each year, it becomes "normal" and "accepted" to "fudge" things so that they're more convincing, so that they're more likely to convey the "truth" they're supposed to convey. Articles are edited after publication, with no correction noted. Entire videos are partially redacted in order to rob context that would lead to unwanted interpretations. Certain voices are amplified while others are suppressed. And always lies, lies, lies, many told with no other goal than short-term financial gain. There is no consideration for the damage done to society. But this happened -- and continues to happen -- without special technology. It's pretty much as old as time. William Randolph Hearst was whipping up a war way back in 1898 with nothing more than a single popular newspaper organization. [3] The media is vastly more powerful today and can disseminate information faster and farther than ever, but the concept hasn't changed. People haven't gotten smarter. They are still super-easy to influence -- perhaps especially politicians with power over so many lives. They are no better-informed than anyone else, unfortunately. Some are. Most aren't. Many, if not most, end up believing that which enhances their own personal wealth the most. Technology has nothing to do with that. -------------------------------------------------------------------------------- [1] I cited it as I remembered it because I like it that way. This footnote serves as clarification that I've learned it incorrectly, both in phrasing and in attribution. See "A Lie Can Travel Halfway Around the World While the Truth Is Putting On Its Shoes" for a lengthy explication. [1] There are several reasons for this, none of them encouraging. See "Be it Resolved: The Mainstream Media is Dying, and that's OK. Matt Taibbi Debates Ben Bradlee, Jr." by Matt Taibbi for a 45:00 debate on this subject as well as some excerpts, quoted below, in which Taibbi talks about long-form investigative journalism (months of work): "In the Internet age, when everybody's revenue is tied to content, and people are surfing constantly, it's very difficult to financially justify that kind of work [investigative journalism]. You can get the same financial return from a 200-word article or a tweet or especially a viral video. Companies are very tempted to forgo that kind of investment. They've figured out that audiences, for the most part, don't require it in the same way that they used to. And so, people are no longer really investing in that kind of work with the same passion. It's a serious problem. Where are we going to find people to do those massive exposes anymore?" The groupthink occurs without technological assistance. The people themselves choose to push a narrative rather than reporting what happened. This used to be a struggle, but not anymore. These days, nearly everyone entering the business doesn't even see conformity as capitulation -- instead, they root out heretics against the worldview they already have. There is nothing new for them to learn, no need to grow or change. Certainly, one can't change one's opinion when the facts are updated. "In modern newsrooms, especially in the last four or five years, the intellectual diversity that I think was normal in a newsroom once upon a time is vanishing, and there is an expectation, especially among younger reporters, that everybody is going to be a team player, that they're going to be devoted to pursuing the same ideological framework." The elites of the media are covering the elites of politics. There is no more check on them. It's no wonder that the 99% aren't heard. Instead, they are used as a ventriloquist's dummy by people who consider themselves to be the ideological betters of this hoi polloi. "If you go on the plane on the campaign trail, most of the people on the plane now are graduates of Ivy League universities. They live in rarefied areas of expensive, cosmopolitan neighborhoods. Socially, they see themselves as being the same people as the politicians they're reporting on. That's a terrible situation. I think that it's an underrated problem within modern news media. It's lost some touch with mass audiences — in part because they're no longer the people who are covering the affairs of ordinary people." [1] See "USS Maine (1889) / Yellow Journalism" for more information. ]]> https://www.earthli.com/news/view_article.php?id=4249 https://www.earthli.com/news/view_article.php?id=4249 Thu, 29 Apr 2021 22:27:13 +0200 provides a relatively good sample of what's going on in a "Deathmatch". There is barbed wire on one side of the ring and a wooden fence on the other. Jun Kasai is thrown into both sides until he looks like Carrie after the pig's blood had spilled on her. He has no teeth. ]]> https://www.earthli.com/news/view_article.php?id=4218 https://www.earthli.com/news/view_article.php?id=4218 Sun, 11 Apr 2021 22:37:19 +0200 "Questions remain about whether Russia's end goal is to completely isolate and disconnect its Internet from the wider world or whether the government prefers a hybrid network. But from the Kremlin's perspective, the opportunity to promote certain apps on iOS is a boon either way. "Apple could have simply allowed Russia to pre-install whatever apps it wanted on iOS devices, but the company also could have taken a radical stand against such interference. Instead, it found a middle ground, one that other countries may well seize on to suit their own autocratic interests." This is written by a woman who lives in the country that already controls all of the companies that make all of the apps on every phone around the world. It's sad that she can't even imagine why another country would think it's not a great idea to let that stand unchallenged, especially when the U.S. is so heavily politicizing its software right now. Those dastardly autocratic Russians -- forcing U.S. companies to allow them to ask their citizens if they'd like to install non-U.S. propaganda on their phones. Obviously, no Russian will install state software, though, right? I dunno. Probably Yandex? Or Telegram? She did later write: "From both an economic and national security standpoint, it's understandable to a degree that governments would want to promote domestic software to their own citizens. But in practice, the Internet's growing balkanization is eroding Internet freedom worldwide and undermining the entire concept of a decentralized, global web." "Balkanization" meaning the 100% control by U.S. firms is eroding somewhat. But not much. But enough that it can elicit pants-shitting terror and projection on an international scale, accusing the Russians of trying to do what we've been doing all along. Just listen to how this is written: "The situation with Russia's mandatory apps is not the first time Apple has faced invasive legal requirements from an authoritarian government—nor the first time the company has conceded to these demands." This from a woman living in a country that is considering broadening the already-existing requirements to force backdoors into secure software. A country whose NSA already did that and continues to do that all the time. In Europe, they're trying to do the same thing. Again. But these efforts are called "promoting democracy" instead of "authoritarian". It matters who's trying to do it, right? And that's not even what Russia is doing: they just want Apple to ask their users if they would like to install some standard Russian software. They can just say no and continue on with their day. Nothing about making people worldwide do it, nothing about backdooring existing software, nothing about changing iOS. "[...] the suggested apps aren't pre-installed, and users can opt not to download them." That sounds pretty autocratic. ]]> https://www.earthli.com/news/view_article.php?id=4170 https://www.earthli.com/news/view_article.php?id=4170 Wed, 10 Feb 2021 22:54:08 +0100 takes up a topic that he's written about quite a bit over the last decade: bufferbloat. This symptom of a bad connection shows up as excessive buffering and excessive latency when streaming video (or a lot of data). Basically, the connection will continually fail and restart until it stops altogether as the router gets all snarled up. The following definition is from "Wikipedia" , which has even more technical information. "Bufferbloat is a cause of high latency in packet-switched networks caused by excess buffering of packets. Bufferbloat can also cause packet delay variation (also known as jitter), as well as reduce the overall network throughput. When a router or switch is configured to use excessively large buffers, even very high-speed networks can become practically unusable for many interactive applications like voice over IP (VoIP), online gaming, and even ordinary web surfing. (Emphasis added.)" The problem has basically been solved. It was solved soon after it was discovered, but the problem since then has been distribution. ISPs are still chirpily distributing routers with "excessively large buffers", which means that it doesn't matter what your upper limit on bandwidth is -- your router isn't going to be able to use it. As far as I can tell, though, Cringely is mostly talking about the United States when he writes that "hardly any ISPs support" proper connections. "All of the anti-bufferbloat internet standards mentioned here have been published and available for at least eight years, yet hardly any large ISPs support the new code in their default equipment. I can only guess that’s because it solves too many problems and lessens demand for bandwidth. Think about it, ISPs make a killing selling you excess bandwidth you don’t actually need. Electrons you aren’t using don’t exist and therefore those bandwidth upgrades are 100 percent profit. (Emphasis added.)" Unfortunately, the ISP has zero incentive to fix bufferbloat and a huge incentive not to fix it. The only thing standing in their way is basic ethics, morality, and the desire to provide a good service before making a bigger profit. Cringely goes on, "If you don’t know if you have bufferbloat, you are lucky. Check by running the "DSLreports speed test" , NOT the speed test from your ISP." I can confirm that "DSLreports speed test" is quite good and shows you much more data than my previous default "Speedtest.Net" . [image] Cringely recommends the following: "Users are much better-off staying for now with 802.11n or ac at the mid tier of Internet speeds with good bufferbloat fighting tech if they want to sit at home sharing the link with their kids." The problem has come to the fore again because everyone is running video calls from home all day and their already-trying experience is made worse by a stupid configuration error in the firmware of their routers. If you run the test above and you have a bad bufferbloat score (the average in the U.S. is C+), then see if you can get a router that Cringely recommends (he lists several) or ask your ISP if they can update the firmware. Do not upgrade your connection; it almost certainly won't help and would be throwing good money after bad. ]]> https://www.earthli.com/news/view_article.php?id=4119 https://www.earthli.com/news/view_article.php?id=4119 Sun, 17 Jan 2021 17:46:22 +0100 shows a master criminal who "can generate a perfect deep-fake of any public figure doing anything", to which his interlocutor responds "Why waste all that computing power? Just take an out-of-context still of the politician you don't like and writer whatever claim you want on it." "Using neural networks to fool the human mind is like using a bazooka to fight a hamster." ]]> https://www.earthli.com/news/view_article.php?id=4024 https://www.earthli.com/news/view_article.php?id=4024 Wed, 01 Jul 2020 19:10:59 +0200 https://www.earthli.com/news/view_article.php?id=4005 https://www.earthli.com/news/view_article.php?id=4005 Tue, 23 Jun 2020 22:41:01 +0200 explains that the "background" state means that, "[t]he app is in the background and executing code. Most apps enter this state briefly on their way to being suspended. However, an app that requests extra execution time may remain in this state for a period of time." When "Background App Refresh" is enabled, apps are given more leeway to do things when in a mode other than Active. The article "Updating Your App with Background App Refresh" provides more information on how applications hook into this behavior and set fetch intervals and perform work. That all sounds well and good, but I'm still seeing some apps running absolutely amok on iOS 13, seemingly ignoring all of the background settings and churning through heroic amounts of energy and consuming hours of CPU, all without my using the phone at all. It's not active. There is no app that is active. Obviously, there is an app in the foreground, but the phone is off and lying on a desk. I have left no operation running other than leaving communication clients open. They are notified of messages through Apple's centralized push-mechanism, which is very efficient. The other day, my battery was flat and I could not imagine what had done it. It was Shazam. [image] Just to be clear, Background App Refresh was disabled. [image] Also, Shazam reflects this in its own settings. [image] Shazam doesn't care, though. Shazam gonna do its own thing. Apple acquired Shazam almost two years ago. All the app is supposed to do is listen to a song and tell me what it is. What it instead does is it manages a completely separate song list from Apple Music as well as starting to play completely unasked-for videos. I looked up one song and then made the mistake of not killing the Shazam app with extreme prejudice. I imagine it burbled its way through about 15 hours of playing videos and looking shit up and just launching threads that waste time for no conceivable reason. At any rate, without "Background App Refresh" enabled, it consumed 15 hours of time in the background. The setting is, for all practical purposes, meaningless. I'd be tempted that this is just another way that Apple gives its own apps special permissions, but I've seen this "same behavior with Garmin Connect and other apps" . I wrote about it in "iOS Battery Drain" in 2017, where the Clock used up over 40% of my battery and the Home Screen also managed to use 100% of the battery at one point, nearly draining the phone. At least you can now tell which application iOS thinks used the battery; in the old days, "things were more mysterious" . At this point, if you want to reliably keep your phone alive for a longer period -- if you're silly enough to want it to be there and usable when you need it, rather than having it fritter away its entire battery doing shit you never asked for -- then Airplane Mode is really your only reliable friend. Killing apps manually is a pain and hard to remember to do, but it would probably help. It's like being back on Windows 3.1 with cooperative multi-tasking. Disabling "Background App Refresh" might be preventing even more horrific battery drainage, but it doesn't stop nearly enough of it. Apps are still seemingly free to go wild often enough to be an absolute nuisance. ]]> https://www.earthli.com/news/view_article.php?id=3990 https://www.earthli.com/news/view_article.php?id=3990 Mon, 01 Jun 2020 21:39:16 +0200 lets us know that, after COVID-19, "thermal imaging software" appears to have emerged as the new darling of the security-theater world. However, the technology has a certain niche in which it makes sense: close-up, individual readings. That is, of course, not how they're going to be used. Schneier points out that: * They are not intended for distance from the people being inspected. * They are "an imprecise method for scanning crowds" now put into a context where precision is critical. Using thermal-imaging for use cases for which it is completely inappropriate will lead to "false positives, leaving people stigmatized, harassed, [and] unfairly quarantined" and will also create false negatives, as people exhibiting mild symptoms -- or not presenting a notable fever -- are missed entirely. That a security measure is completely inappropriate, ineffective, and possibly actively counterproductive won't prevent it from being enshrined in law the world over, though. ]]> https://www.earthli.com/news/view_article.php?id=3924 https://www.earthli.com/news/view_article.php?id=3924 Sat, 09 May 2020 21:57:06 +0200 gives a summary of the measures in place in South Korea and Taiwan. [1] "South Korea, the much-hailed model, locked down two cities, currently takes everyone’s temperature in public spaces, monitors every person’s movement through cell phone and television data, and uses government and public surveillance to keep tabs on any individual suspected of carrying coronavirus so it can enforce self-isolation. Taiwan is the same. Locals report getting a knock on the door from the police a half hour after their cell phones died because their movements could no longer be tracked." [The siren call of technology] [image]We hate the sound of "manpower-heavy" [2] because that sounds like a lot of organization and UGH... a lot of work, so we want technology to solve this for us, just like it's so wonderfully solved everything else. China and Korea did benefit from technology in that they have a pretty widespread network of social-app data to which the government has access. In addition to the interview -- and they did the interview parts too -- they were able to use location and contact data to establish connections that might have otherwise gone undiscovered. But it works without apps, as well, just to be clear. The cartoon to the right (obtained from "Contact Tracing" ) explains how such a hypothetical app might work to fulfill the role historically played by people. [Will it be voluntary?] One argument for this type of technology is that most people have already willingly given up their data for the dubious benefit of partaking in various social-networking endeavors, so they shouldn't be too troubled by an app that will literally save lives. This isn't a terrible point to make, but we should think about a few facets of the argument that are only implied. Social-networking apps have, among others, the following characteristics: * Participation is voluntary. * It is also, in theory, revocable. * It is possible to participate anonymously (or at least semi-anonymously). * One can have multiple identities Will installing, granting broad permissions to, and keeping a life-saving app on at all times also be voluntary? Can app-based contact-tracing even work if participation is voluntary? No, it cannot. It will not work at all without proper, boots-on-the-ground contact-tracing and without a high level of participation. Otherwise, you can just save yourself the trouble of developing it. Which takes us to the next section. [What about data-privacy laws?] If you read the cartoon above, you have an idea of how the app might work. It sounds doable but, putting aside the basic feasibility (for now), how would such an app integrate into a society with data-protection laws? * Will the data be untraceable, as the cartoon hopes? * Which government agencies get access to the tracking data? * When is it deleted? Two weeks? A month? After a year? Never? * Are we issued a device or are we expected to mix the government surveillance app on our private devices? Those are just the policy questions. Let's assume, for now, that whoever issues the app can provide enough guarantees about anonymity and data-privacy to satisfy local laws. [What does the workflow look like?] Given that the app can detect and notify contacts, how would the whole "reporting and responding" part work? * Do you trust a potential contact from an app enough to self-quarantine? * Or do you have to report for a test? * Do we trust the test enough to self-isolate? * What about a negative result? Does that mean you're in the clear? * If you can trust neither a positive nor a negative result, then what's the point? * Is it only for the authorities to ping you to report for testing because they think you've contacted someone? * Do you get a message if you rode on the same train car as someone who tested positive? * Or does the app only work for when you've tested positive, to allow the authorities to track your contacts afterwards? * Do the police show up to enforce isolation? It's already not so easy to strike a balance between public safety and civil rights during a pandemic. The important parts involve solidarity and trust in the government. It's not clear to me how an app would help. [Leverage existing infrastructure] Why do we even need a new app to surveil ourselves? Aren't we already being watched six ways from Sunday as it is? There are two surveillance networks. One is the global U.S. surveillance system exposed by Edward Snowden. Snowden's revelations led to nearly no change in behavior. The program was certainly not dismantled. It still exists and it has likely been extended since then. We will almost certainly not make use of this network to track people because of ... drum roll ... national-security reasons. The U.S. will go to its grave with those words on its lips. When people claim that the citizenry has already opted for pervasive surveillance, they are referring to the private networks set up by Google and Facebook and Apple, who are basically able to track most people's every move. They did it to sell ads, but now it's time to use it for good. I'm a bit too cynical to think that this could possibly work as, for example, the article "We Need A Massive Surveillance Program" by Maciej Cegłowski does. He argues (as above) that, for better or worse, we already have a surveillance system in place and it would be "shameful" not to use it for this glorious cause. "Of course, the worst people are in power right now, and the chances of them putting such a program through in any acceptable form are low. But it’s 2020. Weirder things have happened. The alternative is to keep this surveillance infrastructure in place to sell soap and political ads, but refuse to bring it to bear in a situation where it can save millions of lives. That would be a shameful, disgraceful legacy indeed. "I continue to believe that living in a surveillance society is incompatible in the long term with liberty. But a prerequisite of liberty is physical safety. If temporarily conscripting surveillance capitalism as a public health measure offers us a way out of this crisis, then we should take it, and make full use of it. At the same time, we should reflect on why such a powerful surveillance tool was instantly at hand in this crisis, and what its continuing existence means for our long-term future as a free people." So his message is pretty mixed, reluctantly coming down on the side of "let's use this for good, but also think about how bad it is and shitcan it the moment we don't need it anymore." This is where the argument bogs down: measures of this kind have historically lingered pretty much forever. The Espionage Act of 1917 -- originally meant to keep a boot on the necks of those upstart Bolsheviks with their dreams of socializing the world -- is still on the books and has been used more than ever in the 21st century. The Patriot Act is renewed like a Readers Digest subscription -- unthinkingly and, for nearly 20 years now, largely unread. Echelon is still in place. The whole NSA network is in place. Google and Facebook gather scads of data on us, despite assurances to the contrary. [This happens all the time] The article "We’re not going back to normal" by Gideon Lichfield likens the coming surveillance and tracking measures to the concessions we made in the last 20 years in order to be able to fly. "There would be temperature scanners everywhere, and your workplace might demand you wear a monitor that tracks your temperature or other vital signs. Where nightclubs ask for proof of age, in future they might ask for proof of immunity—an identity card or some kind of digital verification via your phone, showing you’ve already recovered from or been vaccinated against the latest virus strains. We’ll adapt to and accept such measures, much as we’ve adapted to increasingly stringent airport security screenings in the wake of terrorist attacks. The intrusive surveillance will be considered a small price to pay for the basic freedom to be with other people. (Emphasis added.)" The analogy to flying is appealing at first. The surveillance and security-theater hassles associated with flying were optional, though. What we're talking about is a significantly changed society. It might not be avoidable in that too many people will suffer and die if we don't restructure, but we should at least think about each step instead of just listening to the loudest, most-panicked voices. We should at least have some reassurance that the measures being promoted will have the desired effect. What's the point of giving up a freedom for nothing in return? The article "Protecting Civil Liberties During a Public Health Crisis" by Matthew Guariglia And Adam Schwartz asks some of the right questions. "But we must not lose sight of the great sensitivity of the personal data at issue–this data paints a clear picture of the travel, health, and personal relationships of airline passengers. EFF would like the CDC to explain what it will do to ensure this sensitive data is used only to contain communicable diseases. For example, what measures will ensure this data is purged when no longer helpful to contact tracing? Also, what safeguards will ensure this newly collected data is not used by police for ordinary crime fighting, or by ICE for immigration enforcement?" These are good questions that should have good answers before we proceed with anything invasive. The article "Protecting Openness, Security, and Civil Liberties" by Cindy Cohn starts by conceding that we've already upended our lives in many ways -- but should still be careful with every additional concession. "We know that this virus requires us to take steps that would be unthinkable in normal times. Staying inside, limiting public gatherings, and cooperating with medically needed attempts to track the virus are, when approached properly, reasonable and responsible things to do. But we must be as vigilant as we are thoughtful. We must be sure that measures taken in the name of responding to COVID-19 are, in the language of international human rights law, “necessary and proportionate” to the needs of society in fighting the virus. Above all, we must make sure that these measures end and that the data collected for these purposes is not re-purposed for either governmental or commercial ends." Finally, the article "Privacy vs. Surveillance in the Age of COVID-19" by Bruce Schneier also encourages using every weapon we have to prevent needless death and suffering, but to recall invasive tools the minute we don't need them anymore. "I think the effects of COVID-19 will be more drastic than the effects of the terrorist attacks of 9/11: not only with respect to surveillance, but across many aspects of our society. And while many things that would never be acceptable during normal time are reasonable things to do right now, we need to makes sure we can ratchet them back once the current pandemic is over." [Accept necessary but temporary measures] Just because we're in "hammer" mode to buy time right now doesn't mean we have to continue to act in panic. We've bought ourselves some time to think. We should use it wisely. We can only hope that we get answers and assurances that the efficacy of contact-tracing measures will be continually evaluated. There have to be concrete "pull the plug" clauses in any laws that go into effect. These clauses should apply both to addressing situations where measures are being abused and also to "sunsetting" measures that are no longer needed. If the involved parties fail to comply, there must be punishment. [Reality bites] Just kidding: obviously there won't be. They'll write shitty apps that steal all of your data and do terrible, stupid things with it. The more disadvantaged your various identity groups, the worse it will be. The usual suspects will come out on top with all of the money. Just as Schneier can't possibly believe that his pleas won't fall on deaf ears, I'm also deeply skeptical that our current civilization can do this. Still, I was surprised to see how much of the world enacted these isolation measures, so let's wait and see. Even intelligent and clear-thinking grudging proponents of using surveillance (like Cegłowski above) spend 3/4 of their time hedging about misuse. History shows that power will be misused and that the laws granting it will never be repealed voluntarily. [Snowden and Greenwald on Surveillance] For more on the existing surveillance systems, the following interviews and discussions with Edward Snowden are quite illuminating: [media] [media] I found the second interview quite good and have included a partial transcript of the parts I found most relevant. "Edward Snowden: Presumably -- and this was the presumption of the question put to me before -- is the idea that this is a choice between mass surveillance or the just completely uncontrolled spread of an infectious virus that can cause serious disease. And I don't think that's accurate. In fact, I know that's [not] accurate. I know a little something about how surveillance works here. "What we are being asked is to accept an involuntary mass surveillance in a way that has never been done before at this scale, in the context of a real crisis. They just go: 'Look, we're going to do this, the data already exists, the phone companies ... we're going to apply it to sort of a new use case. We're going to this surveillance infrastructure that already exists, or rather we're going to take this communications infrastructure that was not designed for surveillance -- or, rather, it was told to us that it would not be used for surveillance -- and we're going to use it for precisely that, but for a really good reason.' "Now, they say that this is necessary, they say that there is no alternative, they say that if you want to save lives, you're going to have to do this. But that's not true. The question here is between the involuntary surveillance of everyone that has been carrying a phone over the last however-many weeks or months or years that they want to look back to. Because, remember these record of your movements, at least by AT&T and Verizon in the United States, are reputed to go back to 2008. Everywhere your phone has traveled since 2008, they know. "There are no laws regulating how long they can retain this information, in large part in the United States. "Now, imagine an alternative: you go to the hospital, you are diagnosed with an infection and the doctor goes: 'it would be really helpful for you to be able to voluntarily share the movements of your phone.' So you go in with your app and you show them: 'I was sitting next to a guy who I don't know who they are, but you said they were infected.' You now get priority access to this kind of testing, you can get priority access to treatment because it is clear that you have potentially been exposed. "And none of this requires privacy sacrifices, none of this requires any sort of involuntary or intrusive violation of rights. And the funny thing is, these capabilities are not difficult to create. This platform could have slapped together in four days by a bunch of university researchers working together, if they had had the kind of funding, mandate and support. "Glenn Greenwald: A lot of your answers are predicated on the desirability not of government coercion but of voluntary conduct. That is not only in the individual's enlightened self-interest, but in the interest of society, which, in turn, means that there is a flow of information that is accurate and reliable and trustworthy, that people put their faith and confidence in, as kind of reliable font of authority to form their understanding of how the pandemic functions. "And, maybe, I'm not sure, but I suspect it's the case that there are countries in which there is faith in some kind of centralized authority, whether it's scientists with government or media outlets that they trust, to get this information and it can be effective. But, in other countries, and certainly in the United States and it's true here in Brazil and it's definitely true throughout Western Europe, there's a collapse of trust in these institutions of authority, where people aren't sure anymore what to believe." It's not "true throughout Western Europe". Perhaps in France or Italy, but in Germany and Switzerland, at least, and most likely also Scandinavia, there is considerable support and trust in the government that they are doing the right thing. If we do concede liberties to a government that we don't even trust, it should at least be for something that actually works for fighting the disease. Can an app even do what people think that it can? We've already seen that the app would be just an aid to other, more traditional contact-tracing measures. [The Technology is not there] When many people hear "app", they probably just think they'll install it, make sure Apple's "Health" app is running, grant all permissions to everything, turn on Bluetooth, turn on location services, and then they'll be saved from Covid-19. No wonder they can't wait to get their hands on it. It's not going to be like that, at least not for a long while. There are many technical, technological, and process hurdles to jump first. I'll start with another security-specialist article, "Me on COVID-19 Contact Tracing Apps" by Bruce Schneier , which reflects my own misgivings on apps for contact tracing. "I'm not even talking about the privacy concerns, I mean the efficacy. Does anybody think this will do something useful? ... This is just something governments want to do for the hell of it. To me, it's just techies doing techie things because they don't know what else to do. [...] It has nothing to do with privacy concerns. The idea that contact tracing can be done with an app, and not human health professionals, is just plain dumb." [image]Snowden mentioned above that an app "[...] could have slapped together in four days by a bunch of university researchers working together", but I think he's drastically underestimating the effort involved, how difficult it is to develop software at scale. Not only that, but the countries currently discussing apps are also vastly overestimating the capabilities of BlueTooth, NFC, software, and battery life. Does that damned thing even work? Can it even be made to work reliably? It depends on BlueTooth, right? Is the location data precise enough to say anything about contagion? The image to the right shows my iPhone 6s having been bled dry by the venerable WhatsApp in just 5.5 hours of doing nothing. [3] I remember years of Apple's message app screwing up the order of messages and double-sending to some devices. It still doesn't know what to do with non-Apple devices (the SMS barely works in groups). [Analyzing Garmin Connect] Instead of picking only on WhatsApp, let's take a look at how well-established, years-old software working with dedicated hardware works. This example is from a Garmin ForeRunner 435 with the Garmin Connect app. It deals with health data. The following screenshots are from the app just a few days ago. The only thing correct on it is the number of steps. Everything else is laughably wrong. Will the new contact-tracing app do any better? Or will it, too, be filled with guesswork and official-looking but ultimately fantastical data? [image][image] The watch claims that my high heart rate was 153bpm, but I know it never went that high during the whole walk. In fact, I caught the readout on my watch as I walked into my apartment -- and it read 153bpm as I was just standing there. So now it takes the misreading of my heart rate -- something you would think would be working reliably by now -- and extrapolates all sorts of madness from it. For example, those intensity minutes. It looks impressive, but I know it rained most of the week and I didn't go for any runs or longer walks with the watch. Let's look at the intensity minutes in the next graphic: It's claiming that of the three hours that I walked today was in a high-intensity zone for double points and 360 total minutes. That's flat-out bullshit. It was just a walk. Also, I have no idea where he got the 240 (4 hours) of intensity minutes on Tuesday. I must have worn the watch, but it probably just locked its heart-rate reading at 130 while I was sitting at my desk. On the other hand, I wore the watch for a very intense hour-long workout on Saturday, which doesn't show up at all. I walked about 12km today with about 400m of incline, but my watch thinks I only burned 2,222 KCal all day, which seems like it would be a normal amount for a day on which I hadn't walked 12km. I don't wear my watch when I sleep, so the app is 100% guessing on how much I sleep. It consistently guesses between 10.5 and 12 hours, which is off by a good amount. I almost never sleep longer than 8 hours. I know that's wrong. The app is literally pulling numbers out of thin air. [Trusting false technological Gods] Let's imagine an app developed as quickly as possible. Tight deadlines do not a reliable app make. WhatApp is an old, established app maintained by one of the best developer teams in the world [4] and even that thing occasionally just drains a phone for no reason. And WhatsApp doesn't even use BlueTooth or Location Services. Garmin has also been making apps and devices for a long time and their stuff has gotten progressively better. But their stuff isn't even accurate enough for a hobbyist to use for tracking health data. How is a first-time app going to be more reliable than these apps right out of the gate? So what's the problem? The problem is that these apps have been in development for years and their data can't be trusted, even for fun. The problem is that we then expect a brand new app to do a better job just because we want it to. And this new contact-tracing app is serious business. When it gets its data wrong, people get sick and people die. The problem is that people imbue these devices with God-like awareness and accuracy. Once numbers exist, they must be correct, ... right? Right? [We don't know how to write reliable software [5]] Software is notoriously hard to get right. Hurrying makes it worse. These apps will most likely be developed by amateurs (e.g. Swiss college students are, by definition, amateurs) or jaded professionals, all steeped in a culture of building MVPs (minimal viable products) and using iterative release pipelines to fix things up in production, using customers as beta-testers. Are people aware that they'll be entrusting their lives or future health to beta software? The people who know how to build apps have no practice building reliable, bullet-proof software. Their motto is "fail early, fail often" and they iteratively get better over time. Sometimes. Often enough, software hits a local maximum that isn't very high at all, ending up in the doldrums of "good enough". We don't really know to build software that is great and reliable from the get-go. [6] The first versions will be atrocious and will most likely torpedo the whole effort. Just ask the SBB (Swiss Railway System), which took years to regain its reputation after a catastrophic nationwide app release. The contact-tracing app will be built by people even less professional than that. It's not that it's impossible, just that it's highly unlikely. Until it does get reliable, though, decisions will be made based on its shitty data-detection and its incorrect algorithms. [Here come the trolls] And, even then, even given that the app works as advertised: it's fast, accurate, low-power, and guarantees anonymity, what about misuse? The article "Apple and Google detail bold and ambitious plan to track COVID-19 at scale" by Dan Goodin "Another possible weakness: trolls might frequent certain areas and then report a false infection, leading large numbers of people to think they may have been exposed. These kinds of malicious acts could be prevented by requiring test results to be digitally signed by a testing center, but details released on Friday, didn't address these concerns." Kids could get out of school by sending in a kid with a phone that alerts as positive. The whole school closes. They're all quarantined. You could tie your positive-bleating phone to a dog and have it run through a neighborhood. Or you could send it on a drone through a mall. There's nearly no end to the mischief that unserious people could use to abuse the system. [tl;dr] So where does that leave us? * Contact-tracing is manpower-intensive, but works without an app. * Building and deploying an app is not as easy as people are making it sound. It's not a panacea. * It's not clear how an app would help rather than hinder. * It's not clear that an app can even be made to work as hoped. * Even if it does, trolling will be rampant and threaten to ruin trust and data. * We're terrible at building reliable software. We're even worse at it when we hurry. * The first iterations will be nearly catastrophically bad -- each of which could torpedo the whole project by killing people's trust in the app. * Once we're surveilled, we'll probably always be surveilled. Power doesn't relinquish power willingly. If we accept an app, then it, and its data-collection, is here to stay. * That data will be put to other, non-pandemic uses sooner rather than later. * Those uses will not be to your benefit. * Trading privacy and liberty for an app that doesn't have much of a chance of delivering enough compensatory value is a bad deal. -------------------------------------------------------------------------------- [1] In a country like the States, that just boosted its unemployed by 30 million people, you'd think "manpower-heavy" would sound really good about now. [1] The more-recent article "What’s Behind South Korea’s COVID-19 Exceptionalism?" by Derek Thompson corroborates South Korea's approach: "Individuals with the most serious cases were sent to hospitals, while those with milder cases checked into isolation units at converted corporate training facilities. The government used a combination of interviews and cellphone surveillance to track down the recent contacts of new patients and ordered those contacts to self-isolate as well." [1] I know, I know: I should uninstall WhatsApp. I have Threema and Signal, but still too many friends unwilling to make the switch. I keep working on them. [1] You can say what you want about Facebook, but their engineers are generally top-notch. [1] Well, I do -- and "Encodo" does, but nobody's asking us for our opinion or skills in building a contact-tracing app. [1] Except, like I wrote above, for the rocket scientists at "Encodo" ]]> https://www.earthli.com/news/view_article.php?id=3867 https://www.earthli.com/news/view_article.php?id=3867 Sun, 15 Dec 2019 10:34:10 +0100 About this Mac > Storage > Manage.... ]]> https://www.earthli.com/news/view_article.php?id=3824 https://www.earthli.com/news/view_article.php?id=3824 Thu, 17 Oct 2019 13:15:21 +0200 https://www.earthli.com/news/view_article.php?id=3775 https://www.earthli.com/news/view_article.php?id=3775 Wed, 24 Jul 2019 16:55:19 +0200 to get the lay of the E-Reader land. The two main contenders were the Kindle Paper White and the Kobo Clara HD. I had actually used the mechanical buttons quite a bit, but these are apparently passé. Nothing but the top-end models of either the Kindle or the Kobo offer physical buttons. So I made my peace with it: no physical buttons. The high-end versions are really nice, but they cost more than twice as much as a perfectly lovely reader. They have more LEDs for night-reading, more color ranges for before-bedtime reading. They have physical buttons. They are, by all rights, wonderful. Still, I decided it wasn't worth the money for the slight perks. So it was between a Kobo and another Kindle. The Kobo offered "clunky" Overdrive integration, which would have been nice to use with my NYPL subscription. I currently check out Kindle books and have to send them to my reader via Amazon. A direct integration and download would have been nice. I wasn't looking forward to seeing what "clunky" means, though. The support for EPUB books was also a plus, but the EPUB format from the public library is locked down with Adobe DRM, which likely would have been another uphill climb. Also, the Instapaper service only integrates with Kindles. I would have had to switch to Pocket for my weekly articles. I wasn't really looking forward to switching that service as well. On top of all of that, I actually have several Kindle books that I've recently been given or have purchased very cheaply. I would no longer be able to read those were I to switch to a Kobo. I really wanted to get away from the Amazon hegemon, but I couldn't bring myself to do it. The Kindle Voyage was one of the few high points in my otherwise fraught relationship with technology, software and hardware. It did everything I wanted -- Instapaper on a regular schedule, library books via NYPL, notes in a neat and parsable TXT format -- and held several weeks on a single charge. It never crashed. It occasionally rebooted. Even the UI kept getting better and better (especially highlighting). It just worked. So I went for the Kindle Paper White. [Amazon Content Services] Lucky for me, it was Prime Day, so I got quite a deal on it -- as long as I agreed to test-drive Amazon Prime for 30 days. Fine. €40 was a great discount from a reader that was better and only half the price of the Voyage I was replacing. On top of that, I found €28 on the German Amazon store, so I ended up spending very little to replace my lost Kindle. So I signed up for Prime. In Germany. On top of that, I got access to Kindle Unlimited, but in the US. This is all a bit confusing, to be honest. What is clear to me is that neither of these programs is worth paying money for. Unless something changes drastically, I will be canceling both before I have to start paying any subscription fees. Almost every TV show I'd like to watch on Amazon is either not available in Europe or not included in Prime. Ditto for several movies I searched. Kindle Unlimited is not at all unlimited: not a single book I've searched for far -- and I looked up about a dozen books from my wishlist -- is included. A bunch of books I've already read are included, but that doesn't help much -- those are also available from the public library. [TV Shows and Movies on Prime] Amazon's Prime offering in Germany for TV shows stands at 25% for the shows that I searched. I include them below. I also searched for movies and the English-language offering is quite restricted as well. German-language movies I searched were not available. The Expanse is not available for viewing. [image] American Gods is not available for viewing. [image] Taboo is not available for viewing. [image] Mr. Robot is not available for viewing. [image] Fleabag is not available for viewing. [image] Something called NOS4A2, starring Zachary Quinto, looks interesting, but also is not available for viewing. [image] The Man in the High Castle is available. [image] The Marvelous Mrs. Maisel is available. [image] [Books on Kindle Unlimited] Kindle books -- even German ones -- are only available from the American Amazon store. Nation by Terry Pratchett is not included. [image] Reaper Man by Terry Pratchett is not included. [image] I went through dozens of books on my wishlist; either the books aren't available as Kindle books or they're not included in "Kindle Unlimited". At what point does the truth-in-advertising law kick in? And the Kindle Unlimited Store is very sleazy. Here's a "Gore Vidal" book that was written by someone else. [image] Here are a bunch of books I've already read. Cold comfort for me -- and definitely not a reason to pay for unlimited access to books I don't want to read. [image] Mostly, the Kindle Unlimited store is filled with flaky-sounding, generic junk by authors I've never heard of (probably most are self-published). [image] And then there's the obligatory giant pile of softcore, light BDSM, husband-material, soloflexed romance novels. The NYPL is also littered with this tripe. Both services' pinheaded recommendation algorithms love this content and suggest it for anyone who just searched "Chomsky" or "Lem". It makes you feel a bit more secure that the AIs aren't quite ready to take over yet. [image] To wrap things up, the Amazon UI also makes it very easy to think that maybe you're just not properly signed up for "Kindle Unlimited". I clicked the big link at the top because I thought I was either (A) on the wrong site again (e.g. Amazon.de, where the service doesn't exist) and using an account where it wasn't activated or (B) had to jump through yet another hoop to activate it. You have to read the tiny text at the end carefully to see that I have Kindle Unlimited, but that the offer they're making is to "add 6 months to your existing membership". It would be very easy to slip up and order 6 more months in addition to the 3 free months of a useless service, in the mistaken hope that you'd finally see some interesting books. [image] [Conclusion] It seems the Amazon's giant warehouse of content is filled with crap. Anything worth watching or reading still costs money. If you subscribe to these Amazon services, then you'll likely start gravitating to watching or reading crap just because it's included in your subscription. If, however, you like to choose what you watch or read, neither of these services will save you much money. You'll still have to shell out to get most of the content that you're really interested in. ]]> https://www.earthli.com/news/view_article.php?id=3719 https://www.earthli.com/news/view_article.php?id=3719 Sun, 07 Apr 2019 20:09:23 +0200 focuses only on intra-process attacks, advocating for mitigation via separation into multiple processes, using hardware-level protection that provides a stronger guarantee. "This paper explores speculative side-channel attacks and their implications for programming languages. These attacks leak information through micro-architectural side-channels which we show are not mere bugs, but in fact lie at the foundation of optimization." This paper proves unequivocally that software mitigation of intra-process, side-channel attacks are futile. An attack is always possible, with a combination of scaling for any-resolution timers and patience. "As we have seen, access to a timer, no matter the resolution, leaks µ-architectural information." Type-checks in any languages may partially mitigate, but this paper proves that they cannot full mitigate and are, therefore, largely useless for data-security. The only difference is the bit-rate of extracted information, not whether information can be extracted. They not only proved this with theorems, they implemented many of the attacks to provide accurate estimates of the expected extraction bit-rates in the presence of various mitigations. There is one particularly virulent variant (#4) that has literally no mitigation. "Mitigating type confusion for stack slots alone would have required a complete redesign of the backend of the optimizing compiler, perhaps man years of work, without a guarantee of completeness." As anyone who's been following this problem suspected (or pretty much already knew), the world traded of security for performance long ago. Though chip manufacturers and operating-system designers paid lip service to security, performance improvements were paramount. We've known since the end of 2017, but now we have proof. The paper sums it up more nicely than I could, "Our models, our mental models, are wrong; we have been trading security for performance and complexity all along and didn’t know it. It is now a painful irony that today, defense requires even more complexity with software mitigations, most of which we know to be incomplete. And complexity makes these three open problems all that much harder. Spectre is perhaps, too appropriately named, as it seems destined to haunt us for a long time." [Citations] "This paper explores speculative side-channel attacks and their implications for programming languages. These attacks leak information through micro-architectural side-channels which we show are not mere bugs, but in fact lie at the foundation of optimization." "In variant 1 we’ve shown that indirect jump prediction can be exploited to bypass the implicit type checks that are part of a typical language’s virtual dispatch mechanism. As it turns out, the branch target buffer on most CPUs are approximate in order to save space. For example, Intel 64-bit CPUs only store the low-order 32 bits of the from address (the address of the indirect jump) and the low-order 32 bits of the relative target address (the predicted address). Upon lookup, the predictor ignores the upper 32 bits of the from address and reuses a prediction for an aliased from address. This allows an attacker to train a target indirect branch to speculatively jump to any address within a 4GiB range without ever executing the victim branch." "This is particularly bad, because the attacker can create speculative indirect jumps to anywhere, i.e., control flow that cannot possibly exist in the original code, such as jumping into the middle of arbitrary machine code that simply happens to be a leaking gadget. That means an attacker may not even need to craft an instruction sequence, but find an extant instruction sequence in the victim’s code, similar to return-oriented programming. This can even work across processes. [20] found that the branch target buffer on Intel chips is shared across hyperthreads on the same core, allowing one process to inject predictions into another." "User programs should not be able to access unmapped virtual memory addresses, write to read-only memory [18], or read from kernel memory. Such attempts should result in a faults. Some CPUs seem to check for a fault too late, effectively speculating through a hardware permission check. This depends on the specific details of a CPU’s trap mechanism of course; e.g. faulting at retirement is too late if the processor has already accessed the memory and supplied its value to dependent instructions, which leaked the value into µ-state. Lipp et al. [22], describe a variant 3 attack that enables leakage of data in kernel memory to a userspace process." "Since memory is often the bottleneck in many programs, modern CPUs utilize not only caching but dynamic alias analysis known as memory disambiguation. When executing a store, the CPU uses a predictor to determine which, if any, subsequent loads will depend on the store. If the prediction is no-alias, the CPU may speculatively execute a later load before the store. If the prediction turns out to be incorrect and the store address and load address are in fact aliases, this will be detected when instructions are being retired in program order, and the load will be aborted and re-executed. This, too, represents a vulnerability, since loads that are speculatively executed out of order observe stale values from memory." "Bypassing stores is only one way a memory disambiguator can speculatively accelerate loads [33]. As long as violations are detected and repaired before retirement, other aggressive forwarding strategies could be implemented. If the memory disambiguator learns that a load typically aliases a store, it could speculatively forward the value even if the source address for the load is not yet known. Similarly the disambiguator could learn that two consecutive loads typically load from the same address, and inject the result from the first load into the second." "What characteristics of a programming language make it exploitable on today’s modern hardware? As we have seen, access to a timer, no matter the resolution, leaks µ-architectural information. We point out several language features whose typical implementations may be vulnerable to Spectre. In these we found that a key to constructing the universal read gadget was speculative pointer crafting, whereby an attacker exploits speculation to trick the implementation into interpreting attacker-controlled input as a machine-level pointer, feeding this pointer into a (normally innocent, but speculatively dangerous) load to achieve the universal read gadget." "In particular, we found variant 1 to be quite simple to exploit. For managed languages, variant 3 is only different from variant 1 in that superuser memory can be accessed. Variant 2 is only easily exploitable if one has direct control over the virtual memory addresses of code. Variant 4 can be difficult to exploit reliably due to the black box nature of the memory disambiguator state. We focused exclusively on in-process attacks and not cross-process attacks." "Variant 4 defeats everything we could think of. We explored more mitigations for variant 4 but the threat proved to be more pervasive and dangerous than we anticipated. For example, stack slots used by the register allocator in the optimizing compiler could be subject to type confusion, leading to pointer crafting. Mitigating type confusion for stack slots alone would have required a complete redesign of the backend of the optimizing compiler, perhaps man years of work, without a guarantee of completeness. "We recognized quickly that a compiler backend overhaul, a complete audit of the entire runtime system, and application of (not yet designed) mitigations in the C++ compiler for the VM’s code itself were intractable for essentially any-sized codebase. "For this reason we do not believe that variant 4 can be effectively mitigated in software, due not just to manpower, but a lack of architectural options, since reasoning about variant 4 requires the confounding assumption that in speculation, writes to memory may not be visible to subsequent reads at all." "Spectre defeats an important layer of software security. The community has assumed for decades that programming language security enforced with static and dynamic checks could guarantee confidentiality between computations in the same address space. Our work has discovered there are numerous vulnerabilities in today’s languages that when run on today’s CPUs allow construction of the universal read gadget, which completely destroys language-enforced confidentiality." "1. Finding µ-architectural side channels requires enumerating and modeling relevant µ-state, a difficult task for processors that are closed source and full of valuable and carefully-guarded intellectual property. 2. Understanding vulnerabilities requires us to model how programs can manipulate and observe µ- state, which also requires us to understand complex µ-state in black-box processors. 3. Mitigating vulnerabilities is perhaps the most challenging of all, since efficient software mitigations needed for extant hardware seem to be in their infancy, and hardware mitigation for future designs is a completely open design problem." "We were able to leak over 1KB/s from variant 1 gadgets in C++ using rdtsc with 99.99% accuracy and over 10B/s from JavaScript using a low resolution timer. We demonstrated a potential 2.5KB/s variant 4 vulnerability, but with low reliability, starting at 0.01% but amplifiable up to 20% through various techniques. We found that using shared memory to construct a timer worked well enough in JavaScript to measure individual cache hits and misses and exploit any of the known leaks." "Our models, our mental models, are wrong; we have been trading security for performance and complexity all along and didn’t know it. It is now a painful irony that today, defense requires even more complexity with software mitigations, most of which we know to be incomplete. And complexity makes these three open problems all that much harder. Spectre is perhaps, too appropriately named, as it seems destined to haunt us for a long time." ]]> https://www.earthli.com/news/view_article.php?id=3691 https://www.earthli.com/news/view_article.php?id=3691 Thu, 31 Jan 2019 20:52:10 +0100 https://www.earthli.com/news/view_article.php?id=3692 https://www.earthli.com/news/view_article.php?id=3692 Thu, 31 Jan 2019 20:30:10 +0100 https://www.earthli.com/news/view_article.php?id=3685 https://www.earthli.com/news/view_article.php?id=3685 Sun, 27 Jan 2019 00:03:39 +0100 . That didn't go so smoothly on the first try: the MacOS desktop that had most of the information was actually erased because Apple doesn't seem to understand what "sync" means. Using a backup, I was able to save my contacts and get my three devices on the same page. It's quite nice that the contact changes are automatically disseminated to three devices at once. I used to have syncing for the desktop and the phone, but my other laptop was not privy. All in all, despite the initial stumble, it seemed to be working fine. [Syncing Calendars] Somewhat encouraged, but with misgivings, I thought maybe I could synchronize my calendar in the same way. I've started using the calendar more, but don't sync to my phone often enough. The cloud could be quite useful here, too. Fingers crossed, I enabled iCloud synchronization from my desktop (where my calendars are). I turned on iCloud calendar-sync on the phone, but didn't see any immediate difference since the calendars were already synced. I didn't see anything happening -- of course, it's Apple, so progress bars or circles are superfluous and disturbing -- so I went off and did something else. A bit later, I wanted to check my task list, which I keep in Reminders. All of my lists and reminders are gone. I mean, obviously. [Reminders and iCal are conjoined twins] I hadn't enabled Reminders in iCloud. Why did it wipe those out? Reminders and Calendar are basically inseparable. Apple lists them as separate sync targets in the iCloud settings, but I don't believe that it's actually possible to sync one without the other. The data is all mixed up in the same folder in your Application Support area. I opened iCal. All of my calendars were gone, too. Coooool. [Incompetence] After my recent experience with Contacts, this no longer came as a surprise to me, so I spent a bit less time throwing things around my office and swearing at the top of my lungs about the utter incompetence of a company absolutely suffused with the best engineers money can buy that can't even get a simple synchronization right. It wasn't even a synchronization -- it was a merge of a list with an empty list. And their brilliant sync-process ended up with an empty list without asking a single question. What the actual fuck. Basically, the same bullshit that happened with Contacts. It's made worse by the fact that Apple is so confident of the flawlessness of their software that they provide no logging, no monitoring, no introspection and no UI or help to address problems. It's just broken or not working or sporadically working or your data is just gone and there are no switches or toggles to adjust. [The Long, Scary Road to iCal Syncing] First I turned off iCloud sync for iCal. Then, I turned immediately to the same solution as with contacts: restore from backup. Easier said than done; the iCal backup is harder to find than Contacts. Also, restoring the "Calendars" folder doesn't work. My calendar and reminders were still empty. I can see all of the individual files with the correct data, but neither iCal nor Reminders reads it or shows it to me. [1] I logged in to iCloud and saw all of my calendars, as expected. What's going on? It looks like iCloud uploaded my data, then deleted it from the source, put on its hat and went home for the weekend, patting itself on the back for a job well-done. This can't be the state of engineering for such basic software, can it? Oh, but it is. On a hunch, I restored the version that iCloud has left me and enabled iCloud synchronization not only for calendars but also for Reminders. In seconds, my calendar and reminders were, once again, populated. Kind of. iCloud and Mac had managed to paste together a mish-mash of long-forgotten calendars and reminders lists, complete with duplicate appointments and reminders. Also, the birthday calendar was enabled, but none of its appointments were visible. Turning it off and on again did nothing. [Putting it all back together] I enabled the birthday calendar in iCloud. It informed me that it could take up to an hour to calculate the birthdays -- from my 150 contacts. Fine. That sounds reasonable. The birthdays finally showed up in iCloud, but still not on my Mac. The iPhone showed them just fine, along with the plethora of calendars that iCloud had put together for me. I deleted some of these calendars and reminders and could see them dropping out of iCloud. I changed the colors of some of the standard auto-generated calendars to de-emphasize them. At this point, I was too terrified to delete any of Apple's calendars for fear that their algorithms would punish me. At each step, I was reassured to see iCloud updating more-or-less in real-time. I checked my calendar on my phone and saw that it hadn't synced yet -- there were still all of these other calendars displayed. After a minute or two, they still hadn't updated on my phone. The phone had even more auto-generated calendars than the desktop. I turned with dread to my desktop to see that, once again, Apple had applied its inexorable and inscrutable "merging" logic to revert all of my previous changes and more-or-less use only the versions it had found on the phone. It was incredible, but it looked like Apple's merge policy was to apply a sane policy for two sources that had been introduced but, for a new source seemed to just let the stranger barge its way in and overwrite everything that had existed before. I know that that can't be the way that it works, but that has been the sum-total of my experience so far. [Oh my God are we synced yet?] I changed some colors back and could see that both iCloud and the phone were now updating, exactly as expected according to the logic I've outlined above. I still didn't have birthdays on the desktop, though. In a final, desperate move -- but without much hope -- I rebooted the desktop. It's so quick these days: rebooting, logging in and having MacOS restart everything takes only a handful of seconds. Aaaannnnddd....the birthday calendar is working again. Incredible. And pathetic. Also, I have all of my old calendars back. Again. With original colors. Again. On top of that, now I've got two copies of the "US Holidays" and "Swiss Holidays" calendar: one set in the "iCloud" area and one in the "Other" area. I check iCloud: it doesn't have these two calendars. MacOS swears that those calendars are in iCloud and iCloud tells MacOS to "go home, you're drunk". My phone agrees with the desktop. Fun times. [Seriously, this is the last step] So, which of the duplicated calendars should I delete? The ones in "Other"? If I delete those, will iCloud at some point sync and remove the copies from my desktop and iPhone, leaving me with no holiday calendars? Who knows? [image] One more time, with feeling. Delete local calendars, leave Apple auto-generated calendars alone, unsubscribe "Other" calendars. What to do with the local "Trips" calendar? I exported it, then imported it to a new calendar, which automatically created the new calendar in iCloud. Delete the original from "On My Mac" and Bob's your uncle. Finally, everything seems to be in-sync and all calendars and reminders are working on all devices. [Maps] Later that morning, I was alerted to an appointment in the afternoon. I'd attached the contact/address, so the alert showed me the map. Nice integration. Let's use it. Click. Maps opens and shows me the location. I get directions. Hey! They have public transit for Switzerland now! I don't have to use Google Maps for this stuff anymore? Cooool. I'd looked it up on the desktop -- let's share it to the phone, shall we? There's a little "share" button everywhere in MacOS. There's even an entry that lets you "share with iPhone". Click. Nothing. Click. Nothing. Share with Messages. Send to me and my wife. A message pops up with a map that I'd looked up 2 weeks ago. On both phones. I tried again, to no avail. At best, I'd get a message with the address of a restaurant we'd eaten at 2 weeks ago. Fine. I looked up the address on my phone and got it that way. It didn't take long. That's not the issue. The issue is a company with so much talent, data and software getting so close to useful integration and then dropping the ball on the one-yard line. Who the fuck is writing this amateurish and terrible software? It's an absolute scandal that this is the state of such essential and simple software components in 2019. The integration is so promising and then stumbles on the simplest of cracks in the road. -------------------------------------------------------------------------------- [1] It was only after I'd solved a few subsequent problems and gotten back to where I was that I realized that I could probably have gotten things working by rebooting the Mac -- or possibly by restarting some calendar-daemon process. ]]> https://www.earthli.com/news/view_article.php?id=3578 https://www.earthli.com/news/view_article.php?id=3578 Tue, 08 Jan 2019 22:44:32 +0100 https://www.earthli.com/news/view_article.php?id=3580 https://www.earthli.com/news/view_article.php?id=3580 Tue, 08 Jan 2019 22:41:19 +0100 "And I find it difficult to see China as being any more of a development crucible than is Sand Hill Road, where startups have even less time to succeed and therefore more pressure to evolve. Explain to me how this is incorrect, because the numbers are published and are real. In comparison to other adolescent startup cultures, yes China is and will be successful and they are (finally) getting it, but Silicon Valley still has more of everything including investor impatience." I fucking hate everything about this mentality. It forsakes the good for that which is the bare Minimum required to make money. I call bullshit on your supposed innovation, because it's at best whale vomit, a nominally useful byproduct of a process with a completely different goal. The goal is to hoard wealth. the inefficiency of the process whereby we also incidentally get something useful is a luxury we can no longer afford with the resources and capacity remaining on this planet. If we don't it, it's unlikely our AIs will respect it until they get smarter than us, by which time it will be too late. But go aead and fiddle, shuffle your deck chairs. Who can stop you? "And very rarely my partner would be called-in just in case I could find in Silicon Valley some garage in which time travel had already been conquered. I was usually able to come through and occasionally the big company even came out of the experience looking brilliant." What's your point Bob? That you're brilliant and only Americans are capable if winning a game they've rigged? You think it's fair? That it's a level playing field? What an ass. Congratulations, you can chew through the planet more indiscriminately than everyone else. "The China environment today clearly does not have the level of integrity found in the US, but it has gone a long way." WTF. China is supposed to be striving to have the integrity of the States? That's a goal? After LIBOR, after 2008, after the last 100 years, how can anyone think that U.S. business has any integrity? "As an American teenage male in the 1960s, having or getting a car was the single most important life passage. Not anymore. That’s an enormous change that lowers income requirements and makes it easier to function in an AI-inspired culture of economic limits. (Emphasis added.)" That's the conclusion you draw? Also, nice euphemism (highlighted). "But what I CAN predict is that we won’t go into a dystopian future because my kids wouldn’t stand for that. There is a huge correction coming and the only thing my kids believe is that they will control that correction." Looking to those with a surfeit of unearned confidence for solutions smacks of desperation. ]]> https://www.earthli.com/news/view_article.php?id=3602 https://www.earthli.com/news/view_article.php?id=3602 Tue, 08 Jan 2019 22:23:39 +0100 https://www.earthli.com/news/view_article.php?id=3604 https://www.earthli.com/news/view_article.php?id=3604 Tue, 08 Jan 2019 22:08:16 +0100 https://www.earthli.com/news/view_article.php?id=3609 https://www.earthli.com/news/view_article.php?id=3609 Tue, 08 Jan 2019 21:44:01 +0100 https://www.earthli.com/news/view_article.php?id=3614 https://www.earthli.com/news/view_article.php?id=3614 Tue, 08 Jan 2019 21:08:22 +0100 https://www.earthli.com/news/view_article.php?id=3615 https://www.earthli.com/news/view_article.php?id=3615 Tue, 08 Jan 2019 21:01:59 +0100 https://www.earthli.com/news/view_article.php?id=3651 https://www.earthli.com/news/view_article.php?id=3651 Sun, 06 Jan 2019 11:51:54 +0100 . The material you should expect to find there is in the name: images or videos of everyday objects that provide a soothing experience. "This can be physical (like popping bubble wrap), visual (a perfectly looped GIF), or even aural (the crunching of leaves). [...] subjective. Indefinable. Completely recognizable. It's a wonderful feeling." For example: [image] Something like "Casual Japanese Wrestling" absolutely does not belong there. It just shows a neat backflip in a professional wrestling match. Two challenges arise when using humans to categorize: 1. In order to get humans to participate, there has to be a reward system. It's either money or it's something else. That something else is called karma on Reddit. Humans aren't just happy to get the karma appropriate to their behavior; instead, humans modify their behavior to get more karma. That is, instead of sorting data in the system, they let the system train them to sort data. This leads to rampant cross-posting, where people take material that garnered a lot of upvotes in one subreddit and re-post that material in other subreddits to "farm karma". 2. Most people don't really pay attention to which subreddit they're browsing. They read the title, view the image or watch a few seconds of video and then decide it's "cool" (upvote) or "stupid" (downvote). They don't generally think about whether the item is appropriate to the subreddit. That is, you may think it's cool, but is it oddly satisfying? If not, then you should downvote it in that subreddit. Taken together, these behaviors lead to a tremendous amount of content being duplicated across a plethora of false categorizations. Where a machine can be trusted to stick to its rules, applying them rigorously, humans are distracted by shiny objects and make for poor sorters. -------------------------------------------------------------------------------- [1] I was inspired by the article "How computers got shockingly good at recognizing images" by Timothy B. Lee . It's a very good article, describing how image-detection works at the technical level. In it, Lee discusses the current limitations to recognition: the algorithms are good, but they work with brute force, by learning from a gigantic dataset with a tremendous amount of what would seem like repetitive data for a human. "Convolutions allow neural networks to understand translations—they can tell if a pattern in the upper-right corner of one image is similar to a pattern in the upper-left corner of another. "But beyond that, convolutional networks have no real understanding of geometry. They can't recognize that one image is similar to another if it's rotated by 45 degrees or scaled up by a factor of two. Convolutional networks make no attempt to understand three-dimensional object structures, and they can't correct for varying lighting conditions. "Yet deep neural networks can recognize pictures of dogs whether they're taken from the front or the side, and whether they take up a small part of the image or a large one. How do they do that? It turns out that with enough data, a brute-force statistical approach is good enough to get the job done. [...] with enough labeled examples, it can learn all possible permutations by sheer repetition. (Emphases added.)" ]]> https://www.earthli.com/news/view_article.php?id=3655 https://www.earthli.com/news/view_article.php?id=3655 Sun, 06 Jan 2019 11:24:44 +0100 by "calling" #145#. To re-activate, call *145#. You'll get a confirmation message." The CCC annual conference (Chaos Computer Club) took place last weekend, in Leipzig, Germany. There were several interesting talks, but this one stood out: Vigo's presentation was very good and didn't seem as padded as other presentations. On top of that, it's a real-life hack that can affect anyone with a phone and active voice-mail. What does he do? He takes us through a bit of history about hacking old phone systems -- the "phreakers" of the good, old days would hack systems with special sounds (DTMF tones) or by flooding poorly written checking algorithms with more data than they was expecting. Using these tricks, they would gain access to free international calling or be able to charge calls to other people's accounts. It still works today. Wait, how? We all have Smartphones now. We barely even use voice-calling! Nobody uses voice mail anymore. All very true. But: just because you're not using your voice mail doesn't mean that someone else can't use it. His hack is multi-stage. I've summarized a bit below, but you should watch the video for the exact steps. [1] 1. Find a phone number that user has set up as a 2FA for the service you want to crack (he shows examples with Whatsapp and PayPal) 2. Get the service type for that number (e.g. O2 or Vodaphone) 3. Call the service number for that phone's voice mail 4. Brute-force the PIN like it's 1975 (takes a few seconds) 5. You now have access to that number's voice mail 6. Make sure that phone's calls will go to voice mail (several techniques here) 7. Go to the service and request a passwood reset, but say you want them to call you instead of sending a text 8. The service calls with an automated message 9. It lands in voice mail 10. Use your software to load the voice mail and send it through voice-recognition software to get the code it read aloud 11. Record this code as DTMF in your outgoing message 12. When the service calls again to verify the code (you're supposed to type it in at that point), your outgoing message will play the DTMF tones at the correct time and the service thinks you typed it 13. You can now proceed with password-reset on that account because you've "confirmed" that it's your phone, when all you have access to is the voice mail. [media] -------------------------------------------------------------------------------- [1] He presented several hacks in a nice build-up, but I wrote that list from memory, so I might have gotten some minor details wrong. The basic thrust of it is correct, though. ]]> https://www.earthli.com/news/view_article.php?id=3618 https://www.earthli.com/news/view_article.php?id=3618 Tue, 25 Dec 2018 10:46:05 +0100 is online. The demonstration below is quite impressive, showing completely artificial human faces that are completely convincing. They move on to objects, like furniture and entire interior designs as well as cars. It's quite impressive how smoothly it mixes in real time. [media] This technology, too, could be used to create extremely convincing and false pictures to decorate false news reports. A picture with the proper characteristics lends a large amount of credibility to a story, at least initially. An interesting place to use this technology would be in police investigations, to replace sketch artists (if they haven't been largely replaced by similar technology already). The sketch artist could be trained to mix the proper characteristics to create a convincing face until the victim or witness has a eureka moment and recognizes the "photo". Update (31.12.2018): even without this face-mapping software, it's possible to manipulate videos with desktop software, as shown in the clip below, from the Neo Magazin Royale from ARD Fernsehen in Germany. In it, they made a fake video of Yanis Varoufakis giving Germany the finger. It was convincing enough that the largest news-talk show featured the video (without checking its origin) and then had Varoufakis on the show to explain himself. Hilarious, but definitely a sign of the future. What if no-one had admitted they'd faked it? The video is in German with English subtitles. [media] ]]> https://www.earthli.com/news/view_article.php?id=3605 https://www.earthli.com/news/view_article.php?id=3605 Sun, 04 Nov 2018 22:00:47 +0100 , which has a pretty click-bait--y title and is quite long, to boot. The author includes a lot of detail and conjecture about how it is that Windows 10 still has some forbidden/reserved filenames (and then takes half of it back or corrects it in several long footnotes). Instead of citing the article, I included the upshot that I found interesting, which is better explained in the official Microsoft documentation "Naming Files, Paths, and Namespaces" , referenced from the article above "Do not use the following reserved names for the name of a file: "CON, PRN, AUX, NUL, COM1, COM2, COM3, COM4, COM5, COM6, COM7, COM8, COM9, LPT1, LPT2, LPT3, LPT4, LPT5, LPT6, LPT7, LPT8, and LPT9. Also avoid these names followed immediately by an extension; for example, NUL.txt is not recommended." While it's possible that this is only a recommendation, Explorer.exe does not allow these filenames at all, as shown in the screenshot below (take on an up-to-date Windows 10 Enterprise installation). [image] I tried nul and con with several different extensions (bmp, exe, txt, doc, etc.) and none of them are allowed. I have not checked whether this restriction applies to files created programmatically (i.e. is the restriction enforced by Explorer or by CreateFileEx?) I'm just wondering how I've never noticed or heard of this before. Talk about a restriction that Microsoft was wise never to fix because people don't run into it! I guess the filenames are so short I've never tried to use them. ]]> https://www.earthli.com/news/view_article.php?id=3515 https://www.earthli.com/news/view_article.php?id=3515 Sun, 18 Feb 2018 17:08:56 +0100 "Records show that the attacker-controlled wallet has already cashed out slightly more than 1 Etherium coin. [1] The coin was valued at as much as $1,300 when the transaction was made. At the time this post was being prepared, the records also showed that the attacker had a current balance of slightly more than 1 Etherium coin and was actively mining more, with a calculation power of about 2,100 million hashes per second. That's roughly equivalent to the output of 85 computers each running a Radeon Rx 480 graphics card or 1,135 computers running a GeForce GTX 560M, based on figures provided here." A sane or at-all well-run society wouldn't allow such a stupid waste of energy without a license. Why can any idiot with fake money waste so much power and heat to create more fake money in a currency that's so volatile it yoyos up 2000% in a year and then plummets 50% in a month? This is just a spectular waste of know-how, effort and energy that could be better expended elsewhere. Our stupid capitalist system encourages this kind of onanistic bullshit. A thought experiment: what if this energy waste was a significant part of the energy budget of the Earth? Say 1%? What then? Would we regulate who gets to do this? The market-pricing doesn't reflect the actual cost to the planet because the primitive measures imposed by our system simply don't account for it. Pollution, environmental and ecological impact are all negligible side-effects absorbed for free by everyone while the thieves clean up. From another article a few days later, "In Iceland, bitcoin mining will soon use more energy than its residents" by Cyrus Farivar "We are spending tens or maybe hundreds of megawatts on producing something that has no tangible existence and no real use for humans outside the realm of financial speculation," Smári McCarthy, and Icelandic member of parliament told the AP. "That can't be good." "Cryptocurrency mining requires almost no staff, very little in capital investments, and mostly leaves no taxes neither," he wrote. "The value to Iceland / value-generated ratio is virtually zero. Closer to zero the higher the value of cryptocurrencies." This is absolute madness, a microcosm of the sickness affecting our society. -------------------------------------------------------------------------------- [1] From the same article:"After gaining control of the coin-mining software, the malware replaces the wallet address the computer owner uses to collect newly minted currency with an address controlled by the attacker. From then on, the attacker receives all coins generated, and owners are none the wiser unless they take time to manually inspect their software configuration." So the mining computer was wasting all of that energy and a trojan funneled away all of the profits to someone else's bank account. Nice. ]]> https://www.earthli.com/news/view_article.php?id=3518 https://www.earthli.com/news/view_article.php?id=3518 Sun, 11 Feb 2018 11:57:57 +0100 , which explains that High Sierra introduced a feature called local backups for Time Machine ("About Time Machine local snapshots" ). It does pretty much what you would expect it to do: "Your Time Machine backup disk might not always be available, so Time Machine also stores some of its backups on your built-in startup drive and other local drives. These backups are called local snapshots. One snapshot is saved every hour. If you're using macOS High Sierra, another snapshot is saved before installing any macOS update." And Apple swears that this feature won't get in your way: "Snapshots older than 24 hours are automatically deleted. And to make sure that you have storage space when you need it, snapshots are stored only on disks that have plenty of free space. When storage space gets low, additional snapshots are deleted, starting with the oldest. That's why Finder and Get Info windows don't include local snapshots in their calculations of the storage space available on a disk. (Emphasis added.)" I've found that the local backups area reflected in the numbers shown in Finder windows. When I deleted local backups, one of them caused over 40GB to be recovered. But today, I found that the local backups had continued, but weren't taking that much space. I think this feature just uses more apparent space when you've recently done a large system update (as MacOS has had of late). I'm not convinced that these backups are truly removed after 24 hours, though. For even more space back, you can delete older iOS backups to get back GBs of space. 1. Open iTunes 2. Open Preferences 3. Select Devices (second-to-last icon) 4. Delete old backups I had a good dozen gigabytes of backups from 4 years ago that I could delete. ]]> https://www.earthli.com/news/view_article.php?id=3494 https://www.earthli.com/news/view_article.php?id=3494 Fri, 12 Jan 2018 23:03:52 +0100 * "12-inch MacBook vs 13-inch MacBook Pro with Touch Bar" -------------------------------------------------------------------------------- [1] There are certain killer features like Time Machine, integration with iPhone, the Photos application, restore-windows-on-restart that are a must for the user in mind. ]]> https://www.earthli.com/news/view_article.php?id=3471 https://www.earthli.com/news/view_article.php?id=3471 Sun, 10 Dec 2017 23:03:26 +0100 covers some of the same territory as the video, but also provides more of the history of Bitcoin as well as details about some of the current factions and infighting among the various communities and e-currency proponents. "Bitcoin's status as the default medium of exchange in the blockchain world pushes its value upward in a similar way. Bitcoin is a popular medium of exchange for cryptocurrency-to-cryptocurrency transactions. [...] "This helps to explain why Bitcoin's price started to soar in early 2017 at the same time as the larger blockchain ecosystem was booming. People needed bitcoins to participate in other cryptocurrency offerings, and Bitcoin became caught up in the general cryptocurrency euphoria. [...]" Finally, the article "Bitcoin an even bigger waste of energy" by John Quiggin addresses the bubble-like nature and extraordinary wastefulness of making a currency based on "work" in a world already besieged by climate change. "[...] most of the market value of a Bitcoin reflects the electricity wasted in the calculations needed to “mine” it, with the obvious disastrous implications for the global climate." This might not be so bad, if it was actually worth something. But it isn't. People will make money off of it, but not because anything of value was actually produced in the real world. Bitcoins aren't even really a currency -- there are few places where you can use Bitcoins or any of the other e-currencies. That means that they are just another financial asset class that will make the riders of the bubble a lot of money and lose money for everyone else. It's a pyramid scheme. "Despite the huge increase in the market value of bitcoins, they seem further than ever from becoming an actual currency. Unsurprisingly, there’s no sign that governments are willing to accept bitcoins as legal tender. Nor is there any sign that they are displacing standard forms of money. On the contrary, bitcoins now seem to be seen as a financial asset, with no real suggestion that they will ever be a general medium of exchange." Quiggin, who is an economist, takes heart that, despite the waste of power, damage to the environment and strong likelihood that people are, once again, being duped, Bitcoin's success would prove him wrong and prove EMH-supporters right. "At any rate, the durability and magnitude of the Bitcoin phenomenon, running for nearly 10 years and with a putative value of nearly $US 100 billion, provides us with a very sharp test of the Efficient (financial) Markets Hypothesis. If Bitcoin eventually becomes a currency, the EMH and its supporters will be vindicated, and I (along with quite a few other economists) will have a lot of egg on my face. If the bubble bursts, the roles will be reversed." That Quiggin thinks that the "roles will be reversed" is far more hopeful than I'm willing to be: When the bubble bursts, nothing will change and we will all get ready for the next bubble, herded onward by the same cowpokes who drove us to financial ruin during the last one. Some of the comments on that article offer some interesting insights. ]]> https://www.earthli.com/news/view_article.php?id=3468 https://www.earthli.com/news/view_article.php?id=3468 Sun, 10 Dec 2017 15:14:34 +0100 that you can use to test how well your browser blocks trackers and respects the "Do-Not-Track" flag. * Opera's ad-blocker is fast and native, but blocks only "most" ads. You don't see many ads when browsing with only that, but it doesn't block any trackers. Opera has a "Do-Not-Track" flag that you can enable. Honest sites will honor it. Still mostly red in Panopticlick. * EFF's own Privacy Badger passes with flying colors. My browser still has a unique fingerprint, but I'm not sure if there's a way of blocking that. All green in Panopticlick. * Ghostery does not block as much as Privacy Badger. Mostly green, but one yellow/red check in Panopticlick. Long story short: I uninstalled Ghostery and installed Privacy Badger instead. [Browser Setup] [image]As an addendum, these are the measures I take for private browsing: 1. I use Opera because it has the features I use below. 2. Enable the "Send a ‘Do Not Track’ request with your browsing traffic" checkbox in preferences 3. Enable the "Block ads and surf the web up to three times faster" checkbox in preferences. I use the default settings and whitelists, but you may want to be more aggressive. Remember that a lot of web sites have advertising as their only income source. If they can't make money, they might stop entertaining you. 4. Install the "Privacy Badger" extension with default settings. 5. Change your default search engine to "DuckDuckGo" to avoid Google tracking. 6. Turn on the VPN in Opera when you want to spoof your location/IP address. This is fast and easy and doesn't interrupt or slow down normal browsing. It does involve proxying your traffic over another node (through the VPN tunnel), so your mileage may vary with video streams. I don't use this very much, but it's handy for when I need it. -------------------------------------------------------------------------------- [1] I am aware that a Chinese company bought Opera a few years back. I do not see how that is significantly worse than an American company. Chinese companies are (possibly) in cahoots with the Chinese surveillance apparatus; American companies are (possibly) in cahoots with the American surveillance apparatus. The Chinese version has been primarily aimed at its own citizens; the American one is aimed at everyone. I suppose now that Firefox actually has a browser worthy of the name, I could switch to that, but I think I'll wait a bit. Opera's perks and features (book are still too seductive for me to switch away. ]]> https://www.earthli.com/news/view_article.php?id=3456 https://www.earthli.com/news/view_article.php?id=3456 Mon, 13 Nov 2017 21:03:25 +0100 https://www.earthli.com/news/view_article.php?id=3445 https://www.earthli.com/news/view_article.php?id=3445 Sun, 01 Oct 2017 11:32:29 +0200 Apparently, it's possible without re-installation, for which I suppose I should be grateful...but there's a tutorial. Sounds ominous. I have to install an add-on. Whatever. I've already sunk enough time; let's get this done. I jump to the "link provided for language packs" and the one for English is right at the top. This add-on is not compatible with your version of Firefox. [image] [Flips Table] [image]How is that even a thing? How is it possible for Firefox to release a version on their stable branch without having the English language pack available? I'm running the latest stable version. It was already a long-enough slog to get here in the first place, but now I find out that it's not even possible to change the language of my browser's UI without re-installing? Or that I get to "Download anyway" and take my chances? Once again, I admit defeat and stop using Firefox. Who cares how fast it is [3] when the user experience is still so balky? It continues to feel like an unpolished product. -------------------------------------------------------------------------------- [1] This isn't hampered by a lack of understanding of German, luckily, because I'm fluent. [1] Just this morning, "It's Time to Give Firefox Another Chance" showed up in my Reddit feed, exhorting people to try out the latest beta. You have to download and install a separate executable for now. After my experience with the stable channel, I'm not going near the Firefox beta channel. If the English-language add-on isn't available, what the odds that any of the other plugins I use are? [1] And the promise of speed is only that it is now on-par with the other modern browsers and tat it no longer wastes memory like it used to. ]]> https://www.earthli.com/news/view_article.php?id=3394 https://www.earthli.com/news/view_article.php?id=3394 Sun, 05 Mar 2017 20:07:26 +0100 has published "[t]hree recommendations to enable annotations on the web" . What does that mean for you, as a consumer of the Internet? This standard will bring commenting and conversation and annotation into the 21st century. It will possibly bring order to the myriad systems and accounts and formats currently in place that allow for interaction and discussion. The diagram "Web Annotation Architecture" (SVG) is interactive and steps you through the whole concept. It's quite easy to follow and worth your while if you participate in conversations on-line. [image] What this annotation standard doesn't do is address the problem that most people are without facts, have little to no reasoning capacity, have big, dumb opinions, and even bigger mouths. No-one can fix that. [Separating annotations from content] When you read an article online, you currently see comments only from that site's annotation system. While the site owner can moderate the comments, you cannot. If there are 4000 garbage-filled comments, you have to plow through them if you want to be involved in the discussion. There are various mechanisms for voting and rating to try to get useful content more attention, but it's still often a burden. The standard aims to put more power into the hands of the consumer by allowing users to display annotations that come from other sources. The idea is not to have a centralized provider (as it is now) but to allow a user to choose which annotation providers they want to enable on their browsers or on certain sites. [Under Your Control] Imagine if you had an annotation provider of just you and a circle of trusted confederates. When you went to a site, instead of seeing thousands of annotations from the unmoderated horde, you could elect to see annotations made only by members you trust. Not only that but the disparate and ad-hoc annotation systems, each with different authentication and authorization requirements as well as formats could now be consolidated by the user (at least to some degree). You could maybe even pay a few bucks a month to house your own annotations and re-publish them to other systems, like Facebook or Twitter. If those sites also provided annotations support, then you'd have your own copy of your annotations, but other people would see your annotations if they used the more popular providers from Facebook or Twitter. You'd have the best of both worlds. If you use a Kindle reader or Instapaper (or both, like me), then you already have two annotation systems available. The Kindle stores to a text file, while Instapaper stores to a proprietary store online. Now imagine if your annotations for these systems were standardized and stored separately from both sites. You would make notes on the Kindle and they would be synced to the same place as notes made while visiting the page online or while reading in Instapaper. This sounds very good to me, at any rate, or probably to anyone with an academic bent. [Available Separately] "The nice thing about this standard is that there is no need for buy-in on the part of the content providers." Although a content provider can provide integration, a user is free to enable one or more external annotation systems. The user is free to do that today but the new standard provides a way of interaction between them that would allow this whole market to gain momentum. If this idea were to spread, then annotations would become a separate cottage industry, with its own market and business model. Online news providers would no longer be obligated to waste time moderating and upgrading and protecting their own annotation/commenting systems. They could focus their time, effort and resources on journalism -- or whatever passes for journalism at the New York Times. With this separation, a user could pick content separately from the quality of the annotations. There would no loner be a notion of a siite's content being good, but the community bad. If you don't like the community, switch annotation providers, seek one out with better moderation. Imagine if, instead of having YouTube commenters annotation videos, you could enable (for example) the annotations from /r/truefilm or /r/movies on Reddit instead. If Reddit provided annotations support to this standard, then this could happen automatically whenever you browsed to a YouTube video for which there was a Reddit thread on one of those sub-reddits. "A common UI is easier to use and manage." Another issue to address is that the annotations show up only at the end of the article, with no way of referencing a location in the content. Some annotation systems don't even have threading, so comments are just stacked with no relation to one another. A common system would provide the same powerful UI regardless of what the content provider was willing to include in the web-site software. There is the issue of scale: what if the original text is overwhelmed by annotations? That shouldn't be a problem as you can turn annotations off at any time. If you have multiple sources, you can toggle them individually. Also, most annotations are replies to other annotations, so the number of root-level annotations is much smaller than the total and shouldn't ever crowd out the content. The threaded nature of annotations combined with control over annotation sources should ameliorate these issues. It's certainly more power than you have today. [1] [Technical details] The working group has now officially been replaced by the "Open Annotation Community Group" . With this announcement, the "data model" , "protocol" and "vocabulary" have been approved by all stakeholders. * Data model: "JSON format for ease of creation and consumption of annotations based on the conceptual model that accommodates these use cases" * Protocol: "describes the transport mechanisms for creating and managing annotations in a method that is consistent with the Web Architecture and REST best practices" * Vocabulary: "the set of RDF classes, predicates and named entities that are used by the Web Annotation Data Model" That this concept has been standardized is a very big deal if we can actually make it happen. The standard would allow not only vendors to develop their own systems but browsers to provide native and fast implementations that use a common UI language in the browser itself. [A working implementation] If you click through to the article "Annotation is now a web standard" , you can see a non-standard annotation system in action. It looks quite nice. The article describes the advantages of consolidation as well, cited below. "While many applications, from PDF readers and Google Docs to the Kindle, support some kind of annotation functionality, what the W3C formalized yesterday is fundamentally different. The W3C architecture provides for a model where annotations live separately from documents and are reunited and reanchored in real-time whenever the relevant document is present. The benefit of this is that annotations now come under the control and election of the user, rather than at the sole discretion of the publisher." The existing plugin in the linked article already exists and looks very nice and subdued. The diagram below shows the initial view. [image] Annotated text is highlighted, but you can toggle its display (with the "eye" icon on the right) for distraction-free reading. Controls on the side allow you to toggle the annotations panel and also show you a preview of the number of annotations available so far. Scrolling down shows more annotations, below. [image] As you scroll, you can see how many annotations are available above and below the current point. These indicators help you locate areas that are being heavily discussed or annotated. Of course, using these to navigate without reading the whole article leaves you susceptible to manipulation, but it can still be a good feature if used wisely. [2] If you select an annotation in the text or the scrollbar or by clicking the panel-toggle, the panel opens on the right. [image] Having annotations to the right (or left) is a standard practice in much professional review or annotation software or printing (see Microsoft Word) and makes much more sense than below an article or paper. Annotations are generally made in reference to a specific location in the text and should be in-line, so reader have context. This implementation does that and shows how browser vendors could build on this standard to improve the commenting experience considerably. The version shown above is clean and simple and powerful and enhances the article, as annotations should. As content grows, the system grows with it, as shown below. [image] Threaded replies are not shown by default, but can be shown with a click. Each annotation has its own unique identifier and can be shared and perma-linked. A system can use color hints -- or maybe icons or gravatars or subtle name-tags -- to allow the reader to differentiate annotations by user. I think this is a great advancement and look forward to its adoption and expansion. -------------------------------------------------------------------------------- [1] See Yahoo Answers, YouTube or any of the dozens of other examples of comment-cesspools that are all but useless today. It can be rough out there, for both participants and site moderators. As the article "Ten Years After" by Scott H. Greenfield put it, "It’s not nearly as much fun to write about the law when readers are nuts. It’s even less fun fending off the insane comments, here and by the geniuses on other social media, from reddit to the twitters, as if it’s my duty to explain why they suffer from paranoid delusions and pathological narcissism." [1] Nothing was stopping a troll from skipping the entire text and commenting without reading before. That is unchanged. ]]> https://www.earthli.com/news/view_article.php?id=3388 https://www.earthli.com/news/view_article.php?id=3388 Sat, 04 Mar 2017 22:08:05 +0100 https://www.earthli.com/news/view_article.php?id=3381 https://www.earthli.com/news/view_article.php?id=3381 Sat, 25 Feb 2017 22:58:45 +0100 https://www.earthli.com/news/view_article.php?id=3284 https://www.earthli.com/news/view_article.php?id=3284 Wed, 15 Jun 2016 23:10:05 +0200 https://www.earthli.com/news/view_article.php?id=3265 https://www.earthli.com/news/view_article.php?id=3265 Tue, 17 May 2016 23:23:01 +0200 exhorts everyone to "go go go". I say, "pump the brakes." [RC => Beta => Alpha] Mark says, "The next wave of work must be undertaken by the wider .NET community, both inside and outside Microsoft." No. The next wave of work must be undertaken by the team building the product. This product is not even Beta yet. They have called the last two releases RC, but they aren't: the API is still changing quite dramatically. For example, the article "Announcing .NET Core RC2 and .NET Core SDK Preview 1" [1] lists all sorts of changes and the "diff of APIs between RC1 and RC2" is gigantic -- the original article states that "[w]e added over a 1000 new APIs in .NET Core RC2". What?!?! That is a huge API-surface change between release candidates. That's why I think these designations are largely incorrect. Maybe they just mean, "hey, if y'all can actually work with this puny footprint, then we'll call it a final release. If not, we'll just add a bunch more stuff until y'all can compile again." Then, yeah, I guess each release is a "candidate". But then they should just release 1.0 because this whole "RC" business is confusing. What they're really releasing are "alpha" builds. The quality is high, maybe even production-quality, but they're still massive changes vis-a-vis previous builds. [An Example: Project files] That doesn't sound like "RC" to me. As an example, look at the project-file format, project.json. Mark also noted that there are "no project.json files in the repository" for the OData project that comes from Microsoft. That's not too surprising, considering the team behind .NET Core just backed off of the project.json format considerably, as concisely documented in "The Future of project.json in ASP.NET Core" by Shawn Wildermuth . The executive summary is that they've decided "to phase out project.json in deference to MSBuild". Anyone who's based any of their projects on the already-available-in-VS-2015 project templates that use that format will have to convert them to whatever the final format is. Wildermuth also wrote that "Microsoft has decided after the RTM of the ASP.NET Core framework to phase out project.json and use MSBuild for build data. (Emphasis added.)" I was confused (again) but am pretty sure that he's wrong about RTM because, just a couple of days later, MS published an article "Announcing ASP.NET Core RC2" -- and I'm pretty sure that RCs come before RTM. [Our Experience] At "Encodo" , we took a shot at porting the base assembly of Quino to .NET Core. It has only dependencies on framework-provided assemblies in the GAC, so that eliminated any issues with third-party support, but it does provide helper methods for AppDomains and Reflection, which made a port to .NET Core nontrivial. Here's a few things we learned that made the port take much longer than we expected. * Multi-target project.json works with the command-line tools. Create the project file and compile with dotnet. * Multi-target project.json do not work in Visual Studio; you have to choose a single target. Otherwise, the same project that just built on the command line barely loads. * Also, Visual Studio ignores any #IFDEFs you use for platform-specific code. So, even if you've gotten everything compiling on the command-line, be prepared to do it all over again differently if you actually want it to work in VS2015. * If you do have to change code per-platform (e.g. for framework-only), then you have to put that code in its own assembly if you want to use Visual Studio. * If you go to all the trouble to change your API surface to accommodate .NET Core, then you might have done the work for nothing: many of the missing APIs that we had to work around in porting Encodo.Core are suddenly back in RC2. That means that if we'd waited, we'd have saved a lot of time and ended up in the same place. * There are several versions and RCs available, but only the beta channel was usable for us (e.g. the RC3 versions didn't work at all when we tried them). * In the end, we didn't have to make a lot of changes to get Encodo.Core compiling under .NET Core. * We learned a lot and know that we won't have too much trouble porting at least some assemblies, but the tools and libraries are still not working together in a helpful way -- and that ends up eating a lot of time and effort. With so much in flux -- APIs and project format -- we're not ready to invest more time and money in helping MS figure out what the .NET Core target needs. We're going to sit it out until there's an actual RTM. Even at that point, if we make a move, we'll try a small slice of Quino again and see how long it takes. If it's still painful, then we'll wait until the first service pack (as is our usual policy with development tools and libraries). [Conclusion] I understand Mark's argument that "the nature of a package-based ecosystem such as NuGet can mean that Project Z can't be updated until Project Y releases .NET Core packages, and Project Y may be waiting on Project X, and so on". But I just don't, as he says, "trust that what we have now in RC2 is going to remain stable in API terms", so I wouldn't recommend "that OSS project maintainers" do so, either. It's just not ready yet. If you jump on the .NET Core train now, be prepared to shovel coal. Oh, and you might just have to walk to the next station, too. At noon. Carrying your overseas trunk on your back. Once you get there, though, you might be just in time for the 1.0.1 or 1.0.2 express arriving at the station, where you can get on, you might not even have to buy a new ticket -- and you can get there at the same time as everyone else. -------------------------------------------------------------------------------- [1] The Mark Renton article states boldly that "Yesterday we finally got our hands on the first Release Candidate of .NET Core [...]" but I don't know what he's talking about. The project just released RC2 and there are even RC3 packages available in the channel already -- but these are totally useless and didn't work at all in our projects. ]]> https://www.earthli.com/news/view_article.php?id=3160 https://www.earthli.com/news/view_article.php?id=3160 Mon, 23 Nov 2015 22:31:43 +0100 and would love for them to restore some of the features they so callously tossed to the side. ]]> https://www.earthli.com/news/view_article.php?id=3119 https://www.earthli.com/news/view_article.php?id=3119 Sun, 01 Mar 2015 22:22:13 +0100 for years. [1] Therefore, when the opportunity presents itself to laud a piece of software, I feel that it's my solemn duty to do so. Introducing "Adapter" for OS X and Windows. It converts images, audio and video files from one format to another. That is, it puts a lovely UI on top of the at-times fiddly command-line of FFmpeg. It's free and does exactly what is advertised. It did not try to install any spyware. It was intuitive to use. It went about its work converting WMV files to MP3 over the span of 16 hours without complaint and without slowdown. [image]The UI nicely shows which conversions and filters will be applied for the input files and the output type you've selected. Low-quality files are automatically up-sampled, as you can see in the screenshots. If you need audio/video/image conversion on Windows or OS X, this is your one-stop shop. Even the web site is lovely and useful. I almost don't know how to formulate "like" for software. I hope I've done it justice. -------------------------------------------------------------------------------- [1] As for software-hate, I'll include just a couple of samples I found while digging around in my mail archives. There's this one in Re: HP Photosmart Studio (and co-conspirators) (August 2008): "I thank you both for the update; I myself haven't installed the HP software in years and am happy to be able to strike a potential HP scanner upgrade from my list of things to do without reservation. I have an HP Scanner now, attached to a Windows 2000 machine that is turned on almost exclusively for that purpose [1] and the aforementioned several years ago, I installed the over 100MB scanner software package to my poor Mac. In a word? Horrifying. The proverbial straw for me was when the processor was pegged and I couldn't find the offending application until I turned on "view processes from all users" in the Activity Monitor and saw that something with the letters "HP" in it was burbling away on the *guest* account, which was logged in, but had lain dormant for over a week. With a suicidal curiosity, I switched to the guest account and saw a message-box-like window floating in the middle of the desktop announcing ... nothing. No text in it. No close button either. Nothing for it but shooting down HP processes like clay pigeons, which was atavistically satisfying. "Un. In. Stall. It. "[1] That and the Ciclosport bike-computer software, which, though having plenty of grippy edges to which gobs of hate could be attached, redeems itself slightly by (A) having truly hilarious direct translations from the German UI to the English one and (B) actually accomplishing the tasks that it advertises, though in at times quite circuitous ways not necessarily unrelated to (A)." This one was in Re: Windows File Protection (March 2009): "Microsoft has a penchant for reporting errors in a very general manner. In their .NET framework, there's this class called a KeyedCollection that complains when you add an item with a key that is already in the collection. When it does so, it fails entirely to mention which key caused the collision. Probably some genius thought that, since KeyedCollection is fully generic and allows all manner of objects to be the key, it was best to err on the side of safety and not even *try* to resolve the value of the it by applying the ubiquitous ToString() method. It is entirely possible that, with an arbitrary class as the key, that this would result in gobbledygook instead of something useful, which would tarnish the koan-like simplicity of the current error message. In the acknowledgedly rare case that the key is a string, this would work, but who would possibly use simple strings as key values? "With the "as few virtual methods as possible" policy found throughout that framework, you're stuck with either (A) a useless log entry from the customer installation or (B) combing the stack while debugging to figure out which string was actually used as a key. "So, yeah, "DIE IN A FIRE" sums it up nicely." And finally, a more general comment that showed up in re: GNU diff (from January 2011): "That's the thing about hating software: is the thing you hate about it hateful enough that it makes you stop using it or do you just adjust and move on? For some, the ability to be able to quickly and easily back out foolhardy commits is more important than adjusting developer workflow to stop making said commits. "If you were using git, you'd be able to do this kind of commit-editing up until the point when you should stop, but git's not going to tell you when to stop (after you've pushed said commits to a repository from which others have pulled). I guess that makes git horrible too, in a way, but if you have to/want to keep using git, you'll just adjust your workflow and move on." ]]> https://www.earthli.com/news/view_article.php?id=3118 https://www.earthli.com/news/view_article.php?id=3118 Sun, 01 Mar 2015 22:01:03 +0100 archives. ]]> https://www.earthli.com/news/view_article.php?id=3090 https://www.earthli.com/news/view_article.php?id=3090 Fri, 02 Jan 2015 16:18:18 +0100 https://www.earthli.com/news/view_article.php?id=3089 https://www.earthli.com/news/view_article.php?id=3089 Fri, 02 Jan 2015 10:36:52 +0100 https://www.earthli.com/news/view_article.php?id=3043 https://www.earthli.com/news/view_article.php?id=3043 Wed, 24 Sep 2014 15:06:12 +0200 https://www.earthli.com/news/view_article.php?id=2988 https://www.earthli.com/news/view_article.php?id=2988 Fri, 18 Apr 2014 14:52:04 +0200 vulnerability in the widely used OpenSSL server-side software. The bug effectively allows anyone to collect random data from the memory of machines running the affected software, which was about 60% of encrypted sites worldwide. A massive cleanup effort ensued, but the vulnerability has been in the software for two years, so there's no telling how much information was stolen in the interim. The OpenSSL software is used not only to encrypt HTTPS connections to web servers but also to generate the certificates that undergird those connections as well as many PKIs. Since data could have been stolen over a period of two years, it should be assumed that certificates, usernames and passwords have been stolen as well. Pessimism is the only sure way. In fact, any data that was loaded into memory on a server running a pre-Heartbleed version of the OpenSSL software is potentially compromised. [How to respond] So we should all generate new certificates, ensuring that the root certificate from which we generate has also been re-generated and is clean. We should also choose new passwords for all affected sites. I use "LastPass" to manage my passwords, which makes it much easier to use long, complicated and most importantly unique passwords. If you're not already using a password manager, now would be a good time to start. And this goes especially for those who tend to reuse their password on different sites. If one of those sites is cracked, then the hacker can use that same username/password combination on other popular sites and get into your stuff everywhere instead of just on the compromised site. [Forking OpenSSL] Though there are those who are blaming open-source software, we should instead blame ourselves for using software of unknown quality to run our most trusted connections. That the software was designed and built without the required quality controls is an entirely different issue. An advantage of open-source software is that at least we can pinpoint exactly when a bug appeared. Another is that the entire codebase is available to all, so others can jump in and try to fix it. Sure, it would have been nice if the expert security programmers of the world had jumped in earlier, but better late than never. The site "OpenSSL Rampage" follows the efforts of the OpenBSD team to refactor and modernize the OpenSSL codebase. They are documenting their progress live on Tumblr, which collects commit messages, tweets, blog posts and official security warnings that result from their investigations and fixes. They are working on a fork and are making radical changes, so it's unlikely that the changes will be taken up in the official OpenSSL fork but perhaps a new TLS/SSL tool will be available soon. [VMS and custom memory managers] The messages tell tales of support for extinct operating systems like VMS, whose continued support makes for much more complicated code to support current OSs. This complexity, in turn, hides further misuses of malloc as well as misuses of custom buffer-allocation schemes that the OpenSSL team came up with because "malloc is too slow". Sometimes memory is freed "twice for good measure" . [Lots o' cruft] This is all sounds horrible and one wonders how the software ran at all. Don't worry: the code base contains a tremendous amount of cruft that is never used. It is compiled and still included, but it acts as a cozy nest of code that is wrapped around the actual code. There are vast swaths of script files that haven't been used for years that can build versions of the software under compilers and with options that haven't been seen on this planet since before .. well, since before Tumblr. For example, there's no need to retain a forest of macros at the top of many header files for the Metrowerks compiler for PowerPC on OS9. No reason at all. There are also incompatibly licensed components in regular use as well as those associated with components that don't seem to be used anymore. [Modes and options and platforms: oh my!] There are compiler options for increasing resiliency that seem to work. Turning these off, however, yields an application that crashes immediately. There are clearly no tests for any of these modes. OpenSSL sounds like a classically grown system that has little in the way of code conventions, patterns or architecture. There seems to be no one who regularly cleans out and decides which code to keep and which to make obsolete. [Security professionals wrote this?] This is to say nothing of how their encryption algorithm actually works. There are tales on that web site of the developers desperately having tried to keep entropy high by mixing in the current time every once in a while. Or even "mixing in bits of the private key" . [A lack of discipline (or skill)] The current OpenSSL codebase seems to be a minefield for security reviewers or for reviewers of any kind. A codebase like this is also terrible for new developers, the onboarding of which you want to encourage in such a widely used, distributed, open-source project. Instead, the current state of the code says: don't touch, you don't know what to change or remove because clearly the main developers don't either. The last person who knew may have died or left the project years ago. It's clear that the code has not been reviewed in the way that it should be. Code on this level and for this purpose needs good developers/reviewers who constantly consider most of the following points during each review: * Correctness (does it do what it should? Does it do it in an acceptable way?) * Patterns (does this code invent its own way of doing things?) * Architecture (is this feature in the right module?) * Security implications * Performance * Memory leaks/management (as long as they're still using C) * Supported modes/options/platforms * Third-party library usage/licensing * Automated tests (are there tests for the new feature or fix? Do existing tests still run?) * Comments/documentation (is the new code clear in what it does? Any tips for those who come after?) * Syntax ("using braces can be important" ) [Living with OpenSSL (for now)] It sounds like it is high time that someone does what the BSD team is doing. A spring cleaning can be very healthy for software, especially once it's reached a certain age. That goes double for software that was blindly used by 60% of the encrypted web sites in the world. It's wonderful that OpenSSL exists. Without it, we wouldn't be as encrypted as we are. But the apparent state of this code bespeaks of failure to manage on all levels. The developers of software like this must be better than this. They must be the best of the best, not just anyone who read about encryption on Wikipedia. OpenSSL will be with us for a while. It may be crap code and it may lack automated tests, but it has been tested and used a lot, so it has earned a certain badge of reliability and predictability. The state of the code means only that future changes are riskier but not that the current software is not usable. Knowing that the code is badly written should make everyone suspicious of patches -- which we now know are likely to break something in that vast pile of C code -- but not suspicious of the officially supported versions from Debian and Ubuntu (for example). Even if the developer team of OpenSSL doesn't test a lot (or not automatically for all options, at any rate -- they may just be testing the "happy path"), the major Linux distros do. So there's that comfort, at least. ]]> https://www.earthli.com/news/view_article.php?id=2976 https://www.earthli.com/news/view_article.php?id=2976 Sun, 23 Mar 2014 20:59:53 +0100 https://www.earthli.com/news/view_article.php?id=2973 https://www.earthli.com/news/view_article.php?id=2973 Sun, 09 Mar 2014 20:32:27 +0100 and "likes" as RSS feeds, but I was looking for something a little pushier. I have a "Twitter account" that I don't use very much. It currently tweets blog posts from "earthli News" almost exclusively. I figured it it might be kind of useful if I could have Instapaper automatically post articles that I've liked to Twitter. Instapaper has a connector that you can use, so I checked that out. It requires the following permissions, [image] Let's take a closer look at those, shall we? [1] My comments are highlighted. * Read Tweets from your timeline. O-K … pretty much anyone can * See who you follow, and follow new people. Follow new people? Are you crazy? * Update your profile. Why would I let you do that? Why would you want to? WTF? * Post Tweets for you. This is actually the one I want; why is it combined with all of the others? Luckily I remembered that I'd already authorized another application to update Twitter for me. It's called "Twitterfeed" and can update Facebook, Twitter, LinkedIn...but not Google+ [2]. This is the tool that I use to cross-post content from my "earthli News feed" to Twitter. I'm a little afraid to see which permissions I granted to this thing over a year ago...but it's already got them, so adding another feed can't make it worse. Instead of granting Instapaper permission to follow new people and update my profile for me, I added the feed to my likes to TwitterFeed instead. It seems to be working. -------------------------------------------------------------------------------- [1] The answer to this question is always "yes". You should always know which permissions your application have when you give them the ability to log in as you and use other applications. [1] The last time I checked, it was because Google+ doesn't offer a straightforward API for inserting content on behalf of another user. ]]> https://www.earthli.com/news/view_article.php?id=2933 https://www.earthli.com/news/view_article.php?id=2933 Tue, 28 Jan 2014 23:07:38 +0100 for the impatient. Lenovo has finally spruced up their lineup of laptops with a series that features: * An actually usable and large touchpad * A decent and relatively sensibly laid-out keyboard * Very long battery life (between 6-9 hours, depending on use) * Low-power Haswell processor * 14-inch full-HD (1920x1080) * Dual graphics cards * Relatively light at 2.1kg * Relatively small/thin form-factor * Solid-feeling, functional design w/latchless lid * Almost no stickers I recently got one of these. Let's get it set up so that we can work. [Pop in the old SSD] Instead of setting up the hard drive that I ordered with the laptop, I'm going to transplant the SSD I have in my current laptop to the new machine. Though this maneuver no longer guarantees anguish as it would have in the old days, we'll see below that it doesn't work 100% smoothly. As mentioned above, the case is well-designed and quite elegant. All I need is a Phillips screwdriver to take out two screws from the back and then a downward slide on the backing plate pulls off the entire bottom of the laptop. [1] At any rate, I was able to easily remove the new/unwanted drive and replace it with my fully configured SSD. I replaced the backing plate, but didn't put the screws back in yet. I wasn't that confident that it would work. My pessimism turns out to have been well-founded. I boot up the machine and was greeted by the BIOS showing me a list of all of the various places that it had checked in order to find a bootable volume. It failed to find a bootable volume anywhere. Try again. Still nothing. [UEFI and BIOS usability] From dim memory, I recalled that there's something called UEFI for newer machines and that Windows 8 likes it and that it may have been enabled on the drive that shipped with the laptop but almost certainly isn't on my SSD. Snooping about in the BIOS settings -- who doesn't like to do that? -- I find that UEFI is indeed enabled. I disable that setting as well as something called UEFI secure-boot and try again. I am rewarded within seconds with my Windows 8 lock screen. I was happy to have been able to fix the problem, but was disappointed that the error messages thrown up by a very modern BIOS are still so useless. To be more precise, the utter lack of error messages or warnings or hints was disappointing. I already have access to the BIOS, so it's not a security issue. There is nothing to be gained by hiding from me the fact that the BIOS checked a potential boot volume and failed to find a UEFI bootable sector but did find a non-UEFI one. Would it have killed them to show the list of bootable volumes with a little asterisk or warning telling me that a volume could boot were I to disable UEFI? Wouldn't that have been nice? I'm not even asking them to let me jump right to the setting, though that would be above and beyond the call of duty. [Detecting devices] At any rate, we can boot and Windows 8, after "detecting devices" for a few seconds was able to start up to the lock screen. Let's log in. I have no network access. Checking the Device Manager reveals that a good half-dozen devices could not be recognized and no drivers were installed for them. This is pathetic. It is 2014, people. Most of the hardware in this machine is (A) very standard equipment to have on a laptop and (B) made by Intel. Is it too much to ask to have the 20GB Windows 8 default installation include generic drivers that will work with even newer devices? The drivers don't have to be optimized; they just have to work well enough to let the user work on getting better ones. Windows is able to do this for the USB ports, for the display and for the mouse and keyboard because it would be utter failure for it not to be able to do so. It is an ongoing mystery how network access has not yet been promoted to this category of mandatory devices. When Windows 8 is utterly incapable of setting up the network card, then there is a very big problem. A chicken-and-egg problem that can only be solved by having (A) a USB stick and (B) another computer already attached to the Internet. Thank goodness Windows 8 was able to properly set up the drivers for the USB port or I'd have had a sense-less laptop utterly incapable of ever bootstrapping itself into usefulness. On the bright side, the Intel network driver was only 1.8MB, it installed with a single click and it worked immediately for both the wireless and Ethernet cards. So that was very nice. [Update System] The obvious next step once I have connectivity is to run Windows Update. That works as expected and even finds some extra driver upgrades once it can actually get online. Since this is a Lenovo laptop, there is also the Lenovo System Update, which updates more drivers, applies firmware upgrades and installs/updates some useful utilities. At least it would do all of those things if I could start it. That's not 100% fair. It kind of started. It's definitely running, there's an icon in the task-bar and the application is not using any CPU. When I hover the icon, it even shows me a thumbnail of a perfectly rendered main window. Click. Nothing. The main window does not appear. Fortunately, I am not alone. As recently as November of 2013, there were "others with the same problem" . [2] Unfortunately, no one was able to figure out why it happens nor were there workarounds offered. I had the sound enabled, though and noticed that when I tried to execute a shortcut, it triggered an alert. And the System Update application seemed to be in the foreground -- somehow -- despite the missing main window. Acting on a hunch, I pressed Alt + PrtSc to take a screenshot of the currently focused window. Paste into an image editor. Bingo. [image] Now that I could read the text on the main window, I could figure out which keys to press. I didn't get a screenshot of the first screen, but it showed a list of available updates. I pressed the following keys to initiate the download: * Alt + S to "Select all" * Alt + N to move to the next page * Alt + D to "Download" (the screenshot above) Hovering the mouse cursor over the taskbar icon revealed the following reassuring thumbnail of the main window: [image] Lucky for me, the System Update was able to get the "restart now" onto the screen so that I could reboot when required. On reboot, the newest version of Lenovo System Update was able to make use of the main window once again. [Recommendations] * If you can't boot off of a drive on a new machine, remember that UEFI might be getting in the way. * If you're going to replace the drive, make sure that you download the driver for your machine's network card to that hard drive so that you can at least establish connectivity and continue bootstrapping your machine back to usability. * Make sure you update the Lenovo System tools on the destination drive before transferring it to the new machine to avoid weird software bugs. -------------------------------------------------------------------------------- [1] I'm making this sound easier than it was. I'm not so well-versed in cracking open cases anymore. I was forced to download the manual to look up how to remove the backing plate. The sliding motion would probably have been intuitive for someone more accustomed to these tasks. [1] In my searches for help, manuals and other software, I came across the following download, offered on Lenovo's web site. You can download something called "Hotkey Features Integration for Windows 8.1" and it only needs 11.17GB of space. [image] ]]> https://www.earthli.com/news/view_article.php?id=2925 https://www.earthli.com/news/view_article.php?id=2925 Sun, 19 Jan 2014 15:34:56 +0100 to encrypt/protect the volume where I store source code for various customers. It generally works pretty seamlessly and I don't even notice that I'm working on an encrypted volume. The other day, Windows started complaining in the Action Center that my drive needed checking because errors had been discovered. At first, I thought that it was referring to my system drive -- which is not encrypted -- and I rebooted Windows to let it do its thing. Windows was back up and running relatively quickly and I wondered whether it had even checked the drive at all. The little flag in the Action Center was gone, though, so all was well. My TrueCrypt drive doesn't auto-mount, though. When I mounted it a while later to do some work, the little flag popped up immediately and I realized that Windows was complaining about that drive rather than my system drive. Windows's advice to "reboot to fix the problem" wasn't going to work because there is no way that Windows can access the TrueCrypt-encrypted drive early in the BIOS/boot process. So I went to the properties for that volume and tried to scan it using the standard system tools. No dice. Windows claims that it can't check that volume. Weird. If it can't even check that volume, then where does Windows get off telling me that the volume has errors? Had Windows noticed -- after several months -- that it was incapable of checking that drive and decided to nag me about it, even though it can't offer any solutions? As a longtime Windows user, this didn't strike me as especially unlikely. I got advice from a more savvy TrueCrypt user that it offers its own file-system check-and-repair tools. So I fired up the main window for TrueCrypt, which appeared as shown below. [image] O-K. Now how do I check my volume? Volume Tools makes sense. Click. [image] Nope. My initial intuition was wrong. How about "Tools" in the menu? Click. [image] Strike two. Some commands are repeated from the "Volume Tools" popup and there are some other things, but "Check" and "Repair" aren't here either. How about the "Volumes" menu? Click. [image] Strike three. Again, there are a few volume-related functions, but not the ones I'm looking for. Maybe my colleague was wrong when he said that there were check/repair tools? Maybe they were dropped from the TrueCrypt software? I'm losing faith here. Wait, I have one more idea. How about if I right-click the volume in the list? Click. [image] There it is. Cue relief mixed with disappointment that this is yet another user interface that is wildly inconsistent and utterly unintuitive. It doesn't have to have a groundbreaking UI, but it could at least follow some basic guidelines. A few hours of work would suffice, I think. I ran the check, which found no errors and repaired nothing. Windows has not complained about errors since. Very reassuring. ]]> https://www.earthli.com/news/view_article.php?id=2917 https://www.earthli.com/news/view_article.php?id=2917 Sun, 12 Jan 2014 22:55:26 +0100 and has been cross-posted here. -------------------------------------------------------------------------------- The article "Smart TVs, smart fridges, smart washing machines? Disaster waiting to happen" by Peter Bright discusses the potential downsides to having a smart home [1]: namely our inability to create smart software for our mediocre hardware. And once that software is written and spread throughout dozens of devices in your home, it will function poorly and quickly be taken over by hackers because "[h]ardware companies are generally bad at writing software—and bad at updating it." And, should hackers fail to crack your stove's firmware immediately, for the year or two where the software works as designed, it will, in all likelihood, "[...] be funneling sweet, sweet, consumer analytics back to the mothership as fast as it can", as one commentator on that article put it. [Manufacturers aren't in business to make you happy] Making you happy isn't even incidental to their business model now that monopolies have ensured that there is nowhere you can turn to get better service. Citing from the article above: "These devices will inevitably be abandoned by their manufacturers, and the result will be lots of "smart" functionality—fridges that know what we buy and when, TVs that know what shows we watch—all connected to the Internet 24/7, all completely insecure." Manufacturers almost exclusively design hardware with extremely short lifetimes, hewing to planned obsolescence. While this a great capitalist strategy, it is morally repugnant to waste so many resources and so much energy to create gadgets that will break in order to force consumers to buy new gadgets. Let's put that awful aspect of our civilization to the side for a moment and focus on other consequences. These same manufacturers are going to take this bulletproof strategy to appliances that have historically had much longer lifetimes. They will also presumably take their extremely lackluster reputation for updating firmware and software into this market. The software will be terrible to begin with, it will be full of security holes and it will receive patches for only about 10% of its expected lifetime. What could possibly go wrong? Either the consumer will throw away a perfectly good appliance in order to upgrade the software or the appliance will be an upstanding citizen of one, if not several, botnets. Or perhaps other, more malicious services will be funneling information about you and your household to others, all unbeknownst to you. [People are the problem [2]] These are not scare tactics; this is an inevitability. People have proven themselves to be wildly incapable of comprehending the devices that they already have. They have no idea how they work and have only vague ideas of what they're giving up. It might as well be magic to them. To paraphrase the classic Arthur C. Clarke citation: "Any sufficiently advanced technology is indistinguishable from magic" especially for a sufficiently technically oblivious audience. Start up a new smart phone and try to create your account on it. Try to do so without accidentally giving away the keys to your data-kingdom. It is extremely difficult to do, even if you are technically savvy and vigilant. Most people just accept any conditions, store everything everywhere, use the same terribly insecure password for everything and don't bother locking down privacy options, even if available. Their data is spread around the world in dozens of places and they've implicitly given away perpetual licenses to anything they've ever written or shot or created to all of the big providers. They are sheep ready to be sheared by not only the companies they thought they could trust, but also by national spy agencies and technically adept hackers who've created an entire underground economy fueled by what can only be called deliberate ignorance, shocking gullibility and a surfeit of free time and disposable income. [The Internet of Things] The Internet of Things is a catch-phrase that describes a utopia where everything is connected to everything else via the Internet and a whole universe of new possibilities explode out of this singularity that will benefit not only mankind but the underlying effervescent glory that forms the strata of existence. The article "Ars readers react to Smart fridges and the sketchy geography of “normals”" follows up the previous article and includes the following comment: "What I do want, is the ability to check what's in my fridge from my phone while I'm out in the grocery store to see if there's something I need." That sounds so intriguing, doesn't it? How great would that be? The one time a year that you actually can't remember what you put in your refrigerator. On the other hand, how the hell can your fridge tell what you have? What are the odds that this technology will even come close to functioning as advertised? Would it not be more reasonable for your grocery purchases to go to a database and for you to tell that database when you've actually used or thrown out ingredients? Even if your fridge was smart, you'd have to wire up your dry-goods pantry in a similar way and commit to only storing food in areas that are under surveillance. The commentator went on to write, "I do agree that security is a huge, huge issue, and one that needs to be addressed. But I really don't see how resisting the "Internet of things" is the longterm solution. The way technology seems to be trending, this is an inevitability, not a could be." Resisting the "Internet of things" is not being proposed as the long-term solution. It is being proposed as a short- to medium-term solution because the purveyors of this shining vision of nirvana have proven themselves time and again to be utterly incapable of actually delivering the panaceas that they promise in a stream of consumption-inducing fraud. Instead, they consistently end up lining their own pockets while we all fritter away even more precious waking time ministering to the retarded digital children that they've birthed from their poisoned loins and foisted upon us. [Stay out of it, for now] Hand-waving away the almost-certain security catastrophe as if it can be easily solved is extremely disingenuous. This is not a world that anyone really wants to take part in until the security problems are solved. You do not want to be an early adopter here. And you most especially do not want to do so by buying the cheapest, most-discounted model available as people are also wont to do. Stay out of the fight until the later rounds: remove the SIM card, shut off Internet connectivity where it's not needed and shut down Bluetooth. The best-case scenario is that early adopters will have their time wasted. Early rounds of software promise to be a tremendous time-suck for all involved. Managing a further herd of purportedly more efficient and optimized devices is a sucker's game. The more you buy, the less likely you are to be in charge of what you do with your free time. As it stands, we already fight with our phones, begging them to connect to inadequate data networks and balky WLANs. We spend inordinate amounts of time trying to trick their garbage software into actually performing any of its core services. Failing that -- which is an inevitability -- we simply live with the mediocrity, wasting our time every day babysitting gadgets and devices and software that are supposed to be working for us. Instead, it is we who end up performing the same monotonous and repetitive tasks dozens of times every day because the manufacturers have -- usually in a purely self-interested and quarterly revenue-report driven rush to market -- utterly failed to test the basic functions of their devices. Subsequent software updates do little to improve this situation, generally avoiding fixes for glaring issues in favor of adding social-network integration or some other marketing-driven hogwash. Avoiding this almost-certain clusterf*#k does not make you a Luddite. It makes you a realist, an astute observer of reality. There has never been a time in history when so much content and games and media has been at the fingertips of anyone with a certain standard of living. At the same time, though, we seem to be so bedazzled by this wonder that we ignore the glaring and wholly incongruous dreadfulness of the tools that we are offered to navigate, watch and curate it. If you just use what you're given without complaint, then things will never get better. Stay on the sidelines and demand better -- and be prepared to wait for it. -------------------------------------------------------------------------------- [1] Or a smart car or anything smart that works perfectly well without being smart. [1] To be clear: the author is not necessarily excluding himself here. It's not easy to turn on, tune in and drop out, especially when your career is firmly in the tech world. It's also not easy to be absolutely aware of what you're giving up in as you make use of the myriad of interlinked services offered to you every day. ]]> https://www.earthli.com/news/view_article.php?id=2912 https://www.earthli.com/news/view_article.php?id=2912 Sun, 05 Jan 2014 20:57:03 +0100 . I recently answered the question "How and why do computer programs crash?" and thought the answer might be worth cross-posting (even though the "post" itself never gained any traction). [What is a program?] Programs comprise a limited set of instructions that tell them what they should do when they encounter certain inputs under certain conditions. [Who writes programs?] People write computer programs. Therefore, programs only do what those people can anticipate. Unanticipated situations result in crashes. [Anatomy of a crash] A "crash" is when a program is no longer able to process further input. Here's roughly how it works: * The environment in which the program runs applies input events to the program. * The program checks for an instruction that matches its current state plus the new input. * If one is found, it applies that instruction to create a new, current state. * A program "crashes" when it receives an input in a given state that it was not designed to handle. [Different kinds of crashes] This can happen either: * When the program enters an infinite loop and is no longer capable of responding to new input (sometime called "hanging"). * When the program terminates itself as a result of not being able to handle the input ("hard crash" or "unhandled exception" or "segfault", etc.). This does not mean that the program behaves unpredictably. The crash is perfectly predictable. [Avoiding crashes] Crashes can be avoided with one or more of the following: * Good design * Good programmers * Good libraries & programming languages * Good testers * Time * Money Hope that helps. ]]> https://www.earthli.com/news/view_article.php?id=2898 https://www.earthli.com/news/view_article.php?id=2898 Sat, 14 Dec 2013 13:42:28 +0100 started work on its metadata framework "Quino" in late 2007. We've used it successfully in many projects, from Windows desktop applications to standalone servers, Windows services and web sites. It has grown considerably since its inception and the core concept of keeping the focus of an application on its metadata has stood the test of time quite well. The recent article "Code-first O/R mapping is actually rather silly" by Frans Bouma recounts how the lead developer and architect of another popular ORM LLBLGen Pro, has also recently "discovered" the benefits of the metadata-first approach. He writes, "Starting with code in the form of entity classes is equally odd as starting with a table: they both require reverse engineering to the abstract entity definition to create the element 'on the other side': reverse engineer[ing] the class to the abstract entity definition to create a table and the mappings is equal to reverse engineering a table to a class and create the mappings. [T]he core issue is that if you start with a class or a table, you start with the end result of a projection of an abstract entity definition [...] "What if that abstract entity definition which was used to create the class or table was in a model which contained all of the domain types for the domain used in the software to build? [...] it would give a couple of benefits: you can create overviews of the model and more importantly, changes in the domain can be applied directly into the model which then ripple through to classes and tables in the right form [...] (Emphasis added.)" He describes the core tenets of Quino rather well: starting with the metadata avoids diluting the domain model with the limitations of a projection domain (classes, tables, etc.). This has been borne out by our experience working in exactly this manner for the last several years. The ORM in Quino is only a satellite component that leverages the centrally defined metadata just as many other components do. The programmer defines the metadata of the domain model and Quino provides tools to do many tasks automatically: 1. Create or update a database schema 2. Generate business-logic classes (primarily C# but it could be JavaScript or indeed any target language where code would benefit from strongly typed domain classes) 3. Select/create/update/delete data in one or more databases 4. Generate standardized user interfaces for multiple platforms 5. Integrate with reporting engines and designers 6. Generate UML diagrams 7. ...and much more... I heartily encourage Frans to continue thinking in this direction. He will be rewarded greatly for it. ]]> https://www.earthli.com/news/view_article.php?id=2729 https://www.earthli.com/news/view_article.php?id=2729 Sun, 20 Oct 2013 23:10:10 +0200 https://www.earthli.com/news/view_article.php?id=2845 https://www.earthli.com/news/view_article.php?id=2845 Mon, 15 Jul 2013 23:50:22 +0200 explains how Opera 15... ...is dead on arrival. [1] [Choose your market] For years, Opera has held a steady 1.7--2% of the desktop browser market. This seems small but comprises dozens of millions of users. More capitalist heads have clearly prevailed at Opera. They've struck out for a more lucrative market. Instead of catering to the 2% of niche, expert users that were die-hard, loyal fans, they will create a clone of Chrome/Firefox/Safari that will cater to a much, much wider market. In terms of fiscal reasoning, it's not hard to see why they're going in this direction. They will abandon their previous user base -- the hardcore market -- to the thankless chore of downloading and configuring their browsers with buggy extensions that offer half-assed versions of the features that used to be high-performance and native. As one such user, I am saddened, but am also almost certain that there is no turning back. [2] It's been a good run, though. The browser market will be quite homogenized, but perhaps some enterprising open-source project will take up the flame and build us a better Opera. Here's how another user put it in the comments for the "article" , "Opera's main reason was not to spend their time on browser innovation, but to save money. Opera became misinformative, untrustworthy company, disrespectful towards long-time and power users, whose disappointment Opera now tries to appease by extensions and "future" features." That has been my impression, as well. [Opera does too have features!] Though many of the features that defined Opera for its users are gone -- perhaps to be resurrected -- the company goes out of its way to trumpet its innovation in this latest incarnation of its browser. The article lightly covers the same four f&#king features that they won't shut up about -- Speed Dial, Stash, Discover and Off-road Mode -- and tells loyal Opera users that if "you find that Opera 15 doesn’t have a feature you depend upon, first check the growing list of extensions". In other words, Opera is now just Chrome without Google? All of the out-of-the-box features that Opera users have come to expect have just been shitcanned? And we can all hold out hope that the community develops them for Opera? And we get to spend a shit-ton of time evaluating, downloading, testing and setting up these extensions? I can "discover" the web just fine on my own without Opera's help. This feature feels more like an AOL/Facebook/Google+ crutch to get me to read catered content. Where's the pro version of the Opera browser? I'm browsing on a desktop with a 150Mb Internet connection -- Off-road Mode is utterly useless for me. Just as Turbo was useless before. [Stash, the Process Model and Memory Hunger] And shall we guess why they're pushing Stash so hard? Because they want to train us to stop keeping so many tabs open. You see, keeping dozens and dozens of tabs open brings any browser other than Opera to its knees. Either that, or the browser soon takes over most of the resources of the machine on which it runs and brings the OS to its knees. Now that Opera has inherited the process model from the Blink engine, well, they suffer from the same issues that Chrome has: it's just not very good at keeping dozens and dozens of tabs open. Kudos to Opera for at least recognizing the problem and trying to train its users to be more reasonable. It's a bit weird for Opera users to hear this, though, because that was one of the reasons we used their f*$king browser in the first place: it just worked and didn't make us change our work habits to accommodate the tool. [Next? Beta? Alpha.] The halcyon days of faster, better and slimmer are, apparently, gone. At least for now. Version 15, though it's called an official release, is, for an Opera user, not even a beta. It is, at best, an early alpha that is nowhere near feature-completeness. I understand that you want to trim the fat: some non-browsing features can legitimately be moved to other apps or put to sleep. It's utterly arguable that a browser doesn't need it's own IRC client, an RSS reader, a mail client, something called Unite. But intimating that "Fit to Width" is too confusing a feature and won't come back? Removing bookmarks? And sessions? And the whole "Reopen closed windows" feature? And replacing it all with a single-level Speed Dial and something called Stash? And, of course... [Extensions to the rescue/whither Opera Link?] The article goes on to cheerfully explain that there is a "bookmark manager extension" . This extension comes from Opera itself and is the official recommendation from the press release/article linked above. The first few comments should be enough to scare off anyone. This isn't too surprising: the bookmark manager in Opera 12 was barely adequate and had seen little love for years. But it worked. It had folders. [3] It synced via Opera Link. All that is gone. Use Stash instead. Oh, and anything you configure will be local to that machine until Opera Link is reactivated. No roadmap for that yet. No roadmap for anything, in fact. Just a bunch of promises that "we are looking at your comments and feedback". There's nowhere to actually register that feedback and see whether Opera's considering it (something like Microsoft's "User Voice" would be nice). I can't believe I just wrote that I wish Opera would be more like Microsoft in engaging with the community. Who thought this was a good idea? Hey, maybe there's an extension for Opera Link? Maybe I can cut&paste my browser together from dozens of extensions? Isn't that why I was using Opera instead of another browser? And even were I to do this, I get to repeat this configuration on absolutely every machine on which I use Opera because...you guessed it: Opera Link is gone, so I don't get any data-synchronization anymore. Not for bookmarks (which are gone anyway) but also not for the Wand (which is gone anyway) [4] and certainly not for extensions, which were never synced, even in Opera 12.x. [5] How in the name of all that is holy is moving bookmarks to an extension a move that offers a "UI simple enough to be intuitive for a consumer who wants a solid, fast browser that just works"? Well, of course everything just works -- your browser no longer has any features. So the check list of features in Opera 15 consists of "show web pages" which comes free by including the Chromium project. Whoop-de-f&#king-doo. [Wait and see] I can't believe I'm writing this because I've always upgraded to the latest version, but: you can stick Opera 15 where the sun doesn't shine; I'm sticking with Opera 12. I'm happy with that for now, but I know it's not a long-term -- or even medium-term -- solution. Sigh. -------------------------------------------------------------------------------- [1] Disclaimer: I've been using Opera since version 3.6. About ten years ago, I joined an early-tester program to help them build their Mac browser (for the egotistical reason that I wanted to use Opera on my Mac). I'm still enrolled in that program, though my participation is considerably less than it used to be. [1] And no, the article "Ctrl+Z of Ctrl+D" by Krystian Kolondra , in which Opera backpedals and swears that they will restore native bookmarks, is far from reassuring. The product strategy is clear; a bit of backpedaling on one feature doesn't change very much. [1] Even though you couldn't see the bookmark-folder hierarchy very well -- or at all on the Mac -- when selecting one in the drop-down. [1] To be honest, I've long since moved on to LastPass because a browser-specific password solution was too limiting for my work. [1] At least Google solved the customization problem to some degree by saving your extensions as part of your account and syncing them whenever you log in from somewhere. That's a good start. But many of the Chrome extensions are pale imitations of the classic Opera features so Chrome is at best a partially satisfactory fallback position. ]]> https://www.earthli.com/news/view_article.php?id=2865 https://www.earthli.com/news/view_article.php?id=2865 Wed, 03 Jul 2013 22:47:24 +0200 yielded a treasure trove of keyboard shortcuts, some of which I knew and many that I'd never heard of or had long ago forgotten. I collected, condensed and organized the ones I found the most useful below. [Finder & Open/Save dialogs] * (-cmd) + (-shift) + G shows a location bar where you can type a path (/ or ~ also works in Open/Save). This text field supports ~ for the home directory and has rudimentary tab-completion. * (-cmd) + R reveals the currently selected item in a new Finder window. * (-cmd) + (-opt) + L selects your ~/Downloads folder. * (-cmd) + (-shift) + > shows/hides hidden files and folders (Open/Save dialogs only). * Dragging and dropping a file or folder into an Open/Save window re-targets that window on that file or folder [Managing applications] * Press (-cmd) + tab to cycle through open applications. * Press (-cmd) + ~ (or < depending on keyboard layout) to cycle through open windows in the currently selected application. * While cycling, you can press q to quit the highlighted application or h to hide it * Press (-cmd) + (-opt) + esc to show a dialog that lets you force unresponsive applications to quit (you can even relaunch the Finder) * Hold down (-cmd) while clicking a dock icon to reveal that application in the Finder [Managing your Mac] * Hold down (-opt) while clicking the "apple" menu on the top-left to execute commands (e.g. "Log out", "Shut down") without a confirmation dialog * Press ctrl + (-cmd) + (-opt) + (-eject) to shut down * Press (-cmd) + (-opt) + (-eject) to put the computer to sleep * Press ctrl + (-shift) + (-eject) to put the display to sleep * Press ctrl + (-cmd) + (-eject) to restart [Screenshots] * (-cmd) + (-shift) + 4 lets you select an area to highlight and saves the screenshot to the desktop * (-cmd) + (-shift) + 4 + space lets you select an entire window, the dock, menu bar, etc. This will also include the drop shadow with transparency in the PNG screenshot. * Hold down ctrl with either of these to copy to the clipboard instead [Volume controls] * Hold down (-shift) while adjusting the volume to mute the volume-changing sound (useful when adjusting volume during a call). * Hold down (-shift) + (-opt) while adjusting the volume to adjust in quarter-increments. * Hold down (-opt) while clicking the "sounds" menu-bar item to show a menu that lets you select the input/output devices without opening preferences [Screen & Brightness] * Hold down (-shift) + (-opt) while adjusting the brightness to adjust in quarter-increments. * Hold down ctrl while scrolling with two fingers or the mouse wheel to zoom in/out on the entire screen [Menu-bar items] * Hold down (-opt) while clicking the "bluetooth" or "wi-fi" menu-bar items to show a menu with more details about your connection, including options to show/generate diagnostics. * Hold down (-opt) while clicking the "notifications" icon to toggle it on/off ]]> https://www.earthli.com/news/view_article.php?id=2836 https://www.earthli.com/news/view_article.php?id=2836 Thu, 23 May 2013 22:46:29 +0200 takes a (very) early look at asm.js, a compilation target that the Mozilla foundation is pushing as a way to bring high-performance C++/C applications (read: games) to browsers. The tool chain is really, really cool. The Clang compiler has really come a long way and established itself as the new, more flexible compiler back-end to use (Apple's XCode has been using it since version 3.2 and it's been the default since XCode 4.2). Basically, Mozilla hooked up a JavaScript code generator to the Clang tool-chain. This way, they get compilation, error-handling and a lot of optimizations for free. From the article, "[The input] language is typically C or C++, and the compiler used to produce asm.js programs is another Mozilla project: Emscripten. Emscripten is a compiler based on the LLVM compiler infrastructure and the Clang C/C++ front-end. The Clang compiler reads C and C++ source code and produces an intermediate platform-independent assembler-like output called LLVM Intermediate Representation. LLVM optimizes the LLVM IR. LLVM IR is then fed into a backend code generator—the part that actually produces executable code. Traditionally, this code generator would emit x86 code. With Emscripten, it's used to produce JavaScript." Mozilla has had a certain amount of success with it, but if you read all the way through the article, the project is very much a work in progress. The benchmarks executed by Ars Technica, however, bear out Mozilla's claims of being within shooting distance of native performance (for some usages; e.g. native MT applications still blow it away because JavaScript lacks support for multi-threading and shared memory structures). Just compiling C++/C code to JavaScript is only part of the solution: that wouldn't necessarily generate code that's any faster than hand-tuned JavaScript. The trick is to optimize the compilation target -- that is, if the code is going to be generated by a compiler, that compiler can avoid using JavaScript language features and patterns that are hard or impossible to optimize (read the "latest spec" to find out more). Not only that, but if the JavaScript engine is asm.js-aware, it will also be able to apply even more optimizations because the input code will be guaranteed not to make use of any dynamic features that require much more stringent checking and handling. From the article, "An engine that knows about asm.js also knows that asm.js programs are forbidden from using many JavaScript features. As a result, it can produce much more efficient code. Regular JavaScript JITs must have guards to detect this kind of dynamic behavior. asm.js JITs do not; asm.js forbids this kind of dynamic behavior, so the JITs do not need to handle it. This simpler model—no dynamic behavior, no memory allocation or deallocation, just a narrow set of well-defined integer and floating point operations—enables much greater optimization." While the results so far are quite positive, there are still a few issues to address: * asm.js scripts are currently quite large; Chrome would barely run them at all and even Firefox needed to be restarted every once in a while. Guess which browser handled the scripts with aplomb? That's right: IE10 * asm.js also preallocates a large amount of memory, managing its own heap and memory layout (using custom-built VMTs to emulate objects rather than using the slower dynamic typing native to JavaScript). This preallocation means that a script's base footprint is much larger than that for a normal JavaScript application. * Browsers that haven't optimized the asm.js codepath run it more slowly than regular JavaScript that does the same thing * Source-level debugging is not available and debugging the generated JavaScript is a fool's errand ]]> https://www.earthli.com/news/view_article.php?id=2830 https://www.earthli.com/news/view_article.php?id=2830 Sun, 12 May 2013 21:26:59 +0200 [1]: 1. su Admin (change to an administrator/sudoer account, if necessary) 2. su - (change to the root user) 3. chflags -R nouchg /Volumes/marco/Magni.sparsebundle (fix up flags/permissions) 4. hdiutil attach -nomount -noverify -noautofsck /Volumes/marco/Magni.sparsebundle (attach backup volume, which automatically starts a file-system check) 5. tail -f /var/log/fsck_hfs.log (show the progress for the file-system check) The final command will show progress reports of the file-system check; if the check does not start, see the link above for more detailed instructions. Otherwise, you should see the message, "The volume Time Machine Backups appears to be OK." in the log. Once this has run, you have to reset the status of the backup so that Time Machine thinks it can use it again: 1. Browse to /Volumes/marco/Magni.sparsebundle in the Finder 2. Right-click the file and select "Show Package Contents" from the menu 3. Open the com.apple.TimeMachine.MachineID.plist file in a text editor 4. Remove the two lines: RecoveryBackupDeclinedDate {whatever-the-date}Change the value of VerificationState to 0, as shown below: VerificationState 0 It's not very straightforward, but it's worth it because you won't lose your entire backup history. In my experience -- and that of many, many others who've littered their complaints online -- Time Machine will, at some random time, once again fail verification and offer to chuck your entire backup because it can't think of a better solution. Not only that, but once you've reset everything and Time Machine has run a backup, you might catch it surreptitiously re-running the verification. I highly recommend canceling that operation. Otherwise, despite the image just having been verified -- and used for backup -- not ten minutes before, Time Machine will once again throw its hands in the air, declare defeat and deliver the bad news that there's nothing for it but to start from scratch. Irritating as it is to have to perform these steps manually, it doesn't even take that long, even when run over a wireless network. It would be utterly lovely if Apple could get this part working a little more reliably. -------------------------------------------------------------------------------- [1] The example path -- /Volumes/marco/Magni.sparsebundle -- is for a volume called "marco" on my NAS where the Time Machine backup for the machine "Magni" is stored. Obviously you will have better luck if you replace the volume and backup names in the path with those corresponding to your own NAS and machine. ]]> https://www.earthli.com/news/view_article.php?id=2808 https://www.earthli.com/news/view_article.php?id=2808 Wed, 06 Mar 2013 20:14:28 +0100 : - Around $1600 - Nice screen (full HD) - fast disk - 8GB RAM - fast CPU - ridiculous graphics (2GB VRAM; should be able to drive a few large screens) There's also this one -- "ThinkPad W530 Laptop -- High Performance" -- higher-end and costlier: - Around $2300 - 16GB RAM - large SSD (180GB) - other specs same as above If you go with an SSD option, 180GB should be more than enough for work/OS. Any backup, videos or music you have can just go on an external drive or, even better, a NAS or external cloud storage (I have an NAS for music, movies, pictures and backups for my home network). The downside on both of those options seems to be the video output options. See below: [image] There's a Mini Display Port and … a VGA. I guess the VGA is for the highest compatibility with projectors/beamers. [2] Those are the portable workstation models, though. We generally buy from the T-* line. Let's take a look over there. Ah, that's better. Here are the ports: Mini Display Port, Display Port AND HDMI. [image] And, above that, the "ThinkPad T530 Laptop -- High Performance" is the high-end T-model: - Around $1600 - 8GB RAM (upgradeable to 16GB) - large SSD - ridiculous graphics (1GB VRAM) - other specs same as first one [What about a desktop and a laptop?] Maintaining two machines isn't such a big deal these days, but you have to be somewhat disciplined and organized. You're going to end up running the system updates twice. There's no avoiding that. And you'll have to keep all of you dev software updated because Windows *still* doesn't have anything approaching a package manager or global update solution (except for the toys in the Windows Store). That said, I keep very little data locally on my machines -- and certainly nothing that isn't just a local cache of data stored elsewhere. Everything's either in source control or on shared drives. That said, having a single powerful laptop on which you do everything is attractive because you don't have to stay so disciplined in your work. [Final recommendations?] The Apple MacBook is obviously an option and the hardware is impeccable. You get more bang for your buck from Lenovo, I think, especially if you don't want OS X. I would try to see if you can find yourself a T530 that meets your needs. I wish they would stop wasting space and weight with that stupid DVD drive though. We've had relatively good luck with Lenovo and they make some very high-end laptops. Their machines feel solid and look decent. The trackpads, as with all Windows-based laptops, suck ass. If you want a good trackpad, buy an Apple; there's no way around that. -------------------------------------------------------------------------------- [1] We meaning my company "Encodo Systems AG" . [1] I didn't know this, actually. I was mystified as to why a modern laptop includes VGA until my work colleagues cleared things up for me. ]]> https://www.earthli.com/news/view_article.php?id=2793 https://www.earthli.com/news/view_article.php?id=2793 Sat, 02 Mar 2013 23:28:55 +0100 and it's mostly been a quite pleasant upgrade from Windows 7. I don't really make much use of features from Windows 8, but it's very stable and noticeably faster on startup and coming back from hibernate than its predecessor. Though there are some minor quibbles [1], it was generally a no-brainer upgrade -- except that Windows could not seem to remember the taskbar location on either my laptop at home or the desktop at work. Maybe you see where this is going. In hindsight, it's bloody obvious that the taskbar location was also being synced over the Windows Live account cloud but, in my defense, Windows moves my application windows around a lot. I have two monitors and if one of them is turned off or goes into a deep sleep, Windows will oblige by moving all windows onto the remaining monitor. [2] When you restore the missing monitor back to life, Windows does nothing to help you and you have to move everything back manually. At any rate, the taskbar being moved around coincided enough with other windows being moved around that I figured it was just Windows 8 being flaky. That the issue also happened on the laptop at home was decidedly odd, though. Now that I know what was causing the problem, I've turned off the synchronization and each copy of Windows 8 now remembers where it's taskbar was. I guess that, in the trivial situation, where the hardware is the same on both ends, it would make sense to synchronize this setting. But in my situation, where one side has a 15.4" laptop screen and the other has two monitors -- one 24" and the other 27" -- it makes no sense at all. It's a bit of a shame that I had to resort to the rather heavy-handed solution of simply turning of synchronization entirely but I couldn't find a more fine-grained setting. The Windows 8 UI is pretty dumbed down, so there are only controls for ON and OFF. -------------------------------------------------------------------------------- [1] The Windows-App-store UI for wireless networks and settings is poorly made. There is no consistency to whether you use a right or left click and you can only choose to "forget" a network rather than just disconnect from it temporarily. [1] And resizing them to fit! Yay! Thanks for your help, Windows! ]]> https://www.earthli.com/news/view_article.php?id=2798 https://www.earthli.com/news/view_article.php?id=2798 Sat, 02 Mar 2013 23:04:24 +0100 . [1] In case anyone else is thinking about doing it, here's my $.02. [Is refurbished OK?] I can't think of a reason why a refurbished Mac wouldn't be a good idea. it's good for the Earth, at any rate. My initial impression is that the price advantage is negligible -- you can get last year's model (June 2012) for only a 15% savings off of the price of a new MacBook. It's impressive how little Macs depreciate. Still, 15% is better than nothing. [Retina display?] The retina display is going to blow your budget. I've never used nor had one and I manage to do quite a bit on the various machines that monopolize my eyeballs each day. I'm sure it's lovely but if you're on a budget, just forget it. [How much RAM?] More RAM is always better: 4GB is the minimum I would recommend; I have 8GB and only occasionally feel slowdowns when I run too many applications at once. On the other hand, Apple RAM is kind of expensive. You can order more RAM later from somewhere else and upgrade the MacBook yourself for much less money. [Why are some models cheaper?] There might be something lurking in the specs that you're missing. Often a seemingly minor difference in the CPU or graphics card will have an influence on overall performance that bumps a machine into a different price class. [What about the MacBook Air?] The Air is a great machine but you're paying more for less power. Generally the hard drive is much smaller; 128GB can easily be eaten up by a decent-sized music collection, to say nothing of movies. MacBook Airs are also eminently non-upgradeable (except for RAM). With lower starting specifications, you're paying the same price to be locked into less storage and CPU horsepower. On the other hand, they're wicked light, if that's important. [Recommendations for a light-to-medium-use non-programmer laptop] So, here's how I would look at it: 13" laptops: "Option #1" : * 500GB drive * 4GB RAM * 2.5GHz I5 (dual-core) * Intel 4000 GPU * $1019 (new = $1199) "Option #2" : * 750GB drive * 8GB RAM * 2.9GHz I7 (dual-core) * Intel 4000 GPU * $1269 (new = $1499) For $250 more, you get 50% more hard drive space, 100% more RAM and a faster/better/newer-generation CPU. That's actually a good deal if you're going to have this laptop for a while. On the other hand, you can get the cheaper one and spend a few bucks on a RAM upgrade instead. 15" laptops: A 15-inch screen is, of course, lovely and I would get that for myself because I do a lot of work that requires screen real estate. But if you're used to 13" screens and you don't feel hemmed in now, don't upgrade. A 15" laptop is going to be heavier and larger and less portable so don't do it unless you think you need it. They're also much more expensive, even just to get in on the ground floor: "Option #1" : * 500GB drive * 4GB RAM * 2.3GHz I7 (quad-core) * Intel 4000 GPU/NVidia 650M * $1529 (new = $1799) For $510 more than the lower-end 13" model, you upgrade the chip considerably (lower speed, but more cores = better multi-tasking) and get a much more powerful graphics card. The high-end GPU will only really be useful if you're into gaming (or video-editing, etc.). Compared to the higher-end 13" model, you pay $260 more but get a smaller hard drive and less RAM in exchange for the better CPU and GPU. This is probably not the choice you want to make unless, as I noted before, you need/want the screen real estate and slightly (only very slightly) higher resolution. -------------------------------------------------------------------------------- [1] Amazingly enough, it's a "thing" on the Swiss Mac store as well, called "Generalüberholter Mac" . ]]> https://www.earthli.com/news/view_article.php?id=2787 https://www.earthli.com/news/view_article.php?id=2787 Sun, 17 Feb 2013 11:41:09 +0100 https://www.earthli.com/news/view_article.php?id=2785 https://www.earthli.com/news/view_article.php?id=2785 Thu, 14 Feb 2013 23:10:48 +0100 is of the same mind, writing pragmatically that, "Opera’s Presto engine was a means to an end". The browser landscape has changed significantly since IE dominated the world with over 90% market share in 2004. IE now has less than 50% worldwide browser share (desktop share is 54%), but Chrome and Firefox each have about 20% as well. Users for some sites, like Wikipedia, are divided up much more evenly between Chrome, Firefox and IE with Safari and Opera making up about 10%. The point is, that the browser market is considerably different than it once was -- and all participants are actively working against documented W3C standards and specifications. Sure, there are still browser-specific CSS prefixes and some highly specific implementations (e.g. the file API from Google) but they mostly stick to a process and all browser vendors have input into an open process. And Gecko and WebKit code is open source. As Lawson puts it so well, "These days, web standards aren’t a differentiator between browsers. Excellent standards support is a given in modern browsers. Attempting to compete on standards support is like opening a restaurant and putting a sign in the window saying “All our chefs wash their hands before handling food”." [Why WebKit?] All of which is why Lawson (he's the guy who wrote the press release for Opera's move to WebKit) writes, "[i]t seems to me that WebKit simply isn’t the same as the competitors against which we fought, and its level of standards support and pace of development match those that Opera aspires to." The Trident code-base -- the renderer for Microsoft's browsers -- was and still is closed-source. While it has been much more actively developed in the last couple of years, back in the bad old days of IE6, the code base was stagnant, lacked innovation and had little to no standards support. WebKit is certainly not any of these things. If you follow the "WebKit changelogs" , it's clear that the majority of changes are to implement an HTML5 feature or to improve performance or to use less memory for common tasks. This is a vibrant, highly active and open-source project with developers from at least two large development teams -- Apple and Google -- actively contributing to it. [1] Opera adding their cadre of excellent engineers to the mix can only be a good thing -- for everyone involved. They've already written that they plan to port their superior HTML5 forms support to WebKit, a very useful feature on which other participants were "dragging their feet." [Running just to stay in place] A while back, Opera made a valiant attempt to get the whole browser running in a hardware-accelerated mode and almost made it, but had to pull back just before release because of stability issues on some machines. The mode is still there if you want to enable it. Flow layout is great and WebGL also made it in, but the implementation lagged. As did many other features. While Opera was first to implement a few features -- like HTML Forms or their excellent SVG support -- they were having trouble keeping up and implementing every working draft and standard. I wonder whether the Opera dev team took a look at the "Comparison on Opera vs. Chrome" and despaired of ever catching up. For the first 3/4 of the page, Opera and Chrome are dead-even. And then things go downhill for Opera from there: 3D Transforms, filter effects, masks, touch events, border images, device-orientation events. These are all things that are standardized (working drafts anyway) and that I have used -- or wanted to use -- in current web projects. They probably had to make hard choices about where to invest their time, energy and money. Some have tried to argue that the departure of the Presto engine will adversely affect standards acceptance. The article "Hey Presto, Opera switches to WebKit" by Peter Bright writes the following: "Opera could have gone the route that Microsoft has chosen, trying to educate Web developers and providing tools to make cross-platform testing and development easier, but perhaps the company [...] felt that asking Web developers to stick to standards was [...] futile. Historically, the company has tried to do just this, but its success at influencing real Web developers has been limited; for all the emphasis placed on standards, many developers don't, in practice, care about them." The developers over which Opera had influence were most likely already coding to standards. The move to WebKit isn't going to change any of that. Opera's 2% of the market was not enough to even get any developers to test with it, and many products clearly got managerial approval to just stick an if (Opera) { fail(); } statement in their web sites to prevent their site from appearing buggy in an untested browser. It's hard to see how Opera's move will change standards development or acceptance. [Why Opera?] I don't think that most users chose Opera because of its renderer. In all honesty, there were very few cases where Opera rendered a site better than other browsers -- and enough examples where Opera did not render as well, whether due to missing functionality or deliberate crippling by the site. [Innovation] Opera has led the way with many non-renderer innovations. * Tabbed browsing * Speed dial * Browsing sessions (tabs+history) * Popup blocking * Restart from last browsing session (with history) * Mouse gestures * Searchable window list (essential when dozens or hundreds of tabs are open) These features were all pioneered by Opera and many have since been adopted by other major browsers (either natively or through extensions). It's certainly a good thing to think that the development team that brought you these innovations and features will be spending less time on HTML5 minutiae and more time on browser features like these. [Performance] Among many of its users, the Opera browser is renowned for more prosaic "features": it's a fast, lightweight browser which can handle a ridiculous number of open tabs, opening from a cold start in seconds. It is also very stable, rock-solid in non-test releases. On top of that, Opera has, hands down, the smartest and fastest history-navigation and caching implementation out there. It's the first thing colleagues notice when they try Opera: the perceived back-and-forth navigation speed is much better. [Other features] In no particular order, here are some other features I find useful (or have used in the past): * I've found Opera Link to be very useful to synchronize installations. * I use the customizable search providers a lot and like that I can toggle between them with a keyword * I don't make a lot of modifications, but I appreciate the highly customizable user interface for a tool in which I spend so much time. Ditto for the newsfeed reader, which is one of my main research tools. * Site-specific preferences are useful, bookmarks and notes (both synced via Link) as well * I've used the integrated torrent client in the past. Ditto for the mail client, which I used only briefly for mail (it's the same client as the newsfeed reader, so I use the interface -- just not for mail) * I never used widgets much, (almost) never used the IRC client, never used Unity (except to play around at the beginning) and haven't used the news reader in years but used to rely on it quite a bit. * I only recently switched from the built-in password manager to the LastPass extension, I used to use the build-in content blocker more aggressively but now much less * I never see popups, so that must be working. * I wouldn't want to browse without plugins-on-demand or fit-to-width or user-CSS-only mode for really ugly pages. You can add your own Javascript and CSS to all sites or individual sites. * It's a tiny browser, but has so many settings, configurable via opera:config. You can also browse and configure your application caches, local databases, etc. Accessibility support is well ahead of the other browsers, with integrated voice, color schemes and have I mentioned that everything is configurable? * As a developer, I think the Dragonfly style-inspection, element-selection (guides!) and profiling are all better in Opera than in the major competitors. * In networking, they've been at the forefront with pipelining support, Opera Turbo for slow connections and SPDY This isn't meant to convince anyone; I just felt like listing the features for which I use Opera that really have nothing to do with the renderer or Javascript engine. I, for one, am looking forward to seeing what Opera does with its newfound time and energy. [2] -------------------------------------------------------------------------------- [1] The Chrome team has a stated goal of pushing changes in Chromium back upstream to the WebKit main line. Apple has historically done a lot of this as well. I'm not sure what the situation is now, so take my statement with a grain of salt. [1] This is not to say that I haven't considered the possibility that Opera will, instead of moving the high-level dev staff to working on WebKit patches, simply drop them from the staff in order to save money. Their press release didn't indicate that they were slimming down, but then it wouldn't, would it? Time will tell. ]]> https://www.earthli.com/news/view_article.php?id=2782 https://www.earthli.com/news/view_article.php?id=2782 Tue, 05 Feb 2013 21:46:32 +0100 . There you'll find over a dozen pictures with commentary. The commentary is, on the whole, not kind, but it's also neither entirely information-free not unwarranted. They note in the picture below that the "canopy has ludicrously bad optical qualities—note the scratches and distortion." [image] It's also, well, it's a lot smaller than I expected. Or, as Ars Technica put it, "[...] there's a difference between "small" and "comical," and the -313 is definitely erring on the wrong side of that line." I would go so far as to say that it looks more like a new ride at Europa Park than the future of any country's air force. I think Iran is taking the piss. ]]> https://www.earthli.com/news/view_article.php?id=2733 https://www.earthli.com/news/view_article.php?id=2733 Wed, 26 Dec 2012 12:53:56 +0100 https://www.earthli.com/news/view_article.php?id=2736 https://www.earthli.com/news/view_article.php?id=2736 Sat, 15 Dec 2012 13:56:23 +0100 and is cross-published here. Windows 8 was made publicly available a few weeks ago. As usual, Microsoft manages to guarantee compatibility with a lot of software, but there are a few tools that will simply no longer run. One of these is Microsoft's own Security Essentials product, which has been completely replaced with Windows Defender, which is built right in to Windows 8. So that one's easy. Another is Microsoft Virtual PC 2007. It doesn't run under Windows 8 at all. Neither is the configuration format that it uses directly compatible with any of the other virtualization solutions that do run under Windows 8. * As of November 2012, VirtualBox is still having some compatibility and speed problems under Windows 8 * VMWare's runner also doesn't have an easy upgrade path for Virtual PC images. You have to convert the disk image and somehow recreate the VM configuration file * Even Microsoft's own Hyper-V is only available on machines that have hardware support for it and, while the disk image is compatible, the configuration format is completely different If you're already a user of Microsoft's Virtual PC, then it's likely you'd like to just upgrade to using Hyper-V, if possible. Luckily, Hyper-V is available as an option for Windows 8 Pro and higher. To find out if your machine supports it and to install it, follow the instructions below. [Enable Hyper-V] [image] * Press Windows key+W to search settings * Type "win fea" and Enter to show the "Turn Windows Features On and Off" window * If the "Hyper-V" checkbox is already checked, then you're ready for the next step * If the "Hyper-V" checkbox is disabled, then you're out of luck; Hyper-V is not available for your machine and you'll have to try one of the other virtualization solutions mentioned above * Otherwise, check the "Hyper-V" checkbox and press "Ok". You'll naturally have to reboot for those changes to be applied. [Configure the Hyper-V Switch] Once Hyper-V is enabled and you've rebooted, you can startup the Hyper-V Manager and configure it. * Press the Windows key to show the start screen * Type "hyper" and Enter to find and start the "Hyper-V Manager" * Select your machine in the tree on the left under Hyper-V Manager * In the settings for that machine on the right, click "Virtual Switch Manager" * In that dialog, the "New virtual network switch" node should be selected and you'll see a list on the right. Select "External" to create a switch that has access to the Internet and press "Create Virtual Switch" [image][image][image] At this point, your Hyper-V server is ready to load your virtual machine and let it access the Internet. [Create a Hyper-V virtual machine from a .vmc file] All of the configuration settings for the Virtual PC virtual machine are stored in a .VMC file. Unfortunately, the Hyper-V manager can't import these files directly [1]. Luckily, there is a tool, called the "VMC to Hyper-V Import Tool" , which performs the import in a couple of easy steps. * "Download" , extract, install and run the tool * First, press "Connect" to attach to the local Hyper-V instance (if you just installed, then there is no user and password set) * Next, open the .vmc file for the virtual machine you want to import * The settings are loaded into the window; verify that they more-or-less match what you expect. [2] * Press the "Create Virtual Machine" button to create a new virtual machine in Hyper-V based on those settings. [image][image][image] You're now ready to configure and start up your virtual machine. [Configuring and Running the VM] There are two things to do to get this machine running smoothly under Hyper-V: * Set up the network interface * Install the Integration Services, which includes drivers but essentially makes the mouse work as expected and enables non-legacy networking for guest OSs that support it There are two kinds of network interface: the standard one and a legacy one. If your guest operating system is Windows XP (as mine was), you have to use the legacy adapter. The documentation also says that a legacy adapter is required to have connectivity without the "Integration Services". [3] [Install a Legacy Adapter] If you have Windows XP, you can just remove the "Network Adapter" that's already included and instead install a "Legacy Adapter". * From the Hyper-V Manager, select the settings for your machine * "Add Hardware" is automatically selected * Select the "Legacy Network Adapter" and press "Add" * Select the existing "Network Adapter" in the list on the left to show its settings * Press the "Remove" button to remove the unneeded "Network Adapter" [image][image][image] You can now set up the network for that adapter, as shown below. [Set up the network] * From the Hyper-V Manager, select the settings for your machine * Select the "Legacy Network Adapter" or "Network Adapter" to show its settings * Assign the switch (created in a step above) to the network and press OK to save settings [image][image][image] At this point, your virtual machine should be able to connect to the network once it's started. [Install Integration Services] The machine is not very useful until you've installed the integration services. These services enable seamless mouse support and also enable networking over a non-legacy adapter. [image] * Start the VM * Wait for the machine to finish booting [4] * You can't install the integration services until the previous integration tools have been uninstalled. If your guest OS is Windows XP, uninstall the Virtual PC tools using the "Add/Remove Programs" control panel * Once all other tools are uninstalled, select "Insert Integration Services Setup Disk" from the "Action" menu * After a few seconds, the installation should start automatically * You'll have to reboot the guest OS to finish installation. That's it! Your Windows XP should once again have full hardware support, including legacy networking (up to 100Mb). Adjust your display settings back up to a usable resolution, re-activate with Microsoft (you have three days) and enjoy your new Hyper-V virtual machine. -------------------------------------------------------------------------------- [1] It's an utter mystery why Microsoft couldn't be bothered to provide an upgrade path from its own product. Perhaps they didn't want to "officially" support such upgrades in order to kill off as many virtual machines running Windows XP as possible. [1] [image]In my case, the path to the main disk image was incorrect and showed up in red. It's a mystery why that file had such an old path in it, while the VM started with the correct disk image in Virtual PC. At any rate, I adjusted the path to point to the correct disk image, the text turned black and I was allowed to continue. [1] It's unclear to me whether network connectivity is required in order to install the integration tools. It took several attempts before the integration services installed successfully. It's possible that this was due to the unsatisfactory network situation, but I can't say for sure. [1] And, if you're using Windows XP as the guest OS, until it has stopped complaining about hardware changes and activation problems ]]> https://www.earthli.com/news/view_article.php?id=2721 https://www.earthli.com/news/view_article.php?id=2721 Sun, 25 Nov 2012 23:22:26 +0100 utility to view them. Windows 8 kept crashing on shutdown for me because of an errant 56K modem driver. Sad -- so sad -- but true. My Windows 8 installation went off with just one hitch: the machine crashed on shutdown. Every. Single. Time. This made it impossible to use the hibernation feature, which was a blocker issue for a laptop. So, how to solve the issue? Well, the first step is to read the error message, right? In this case, the crash was a Blue Screen of Death (BSOD) so you can't copy the message or take a screenshot of it. You can take a picture if you're quick on the draw: for the last several versions, Windows has been extremely shy about crashing and will hurriedly restart before the user even realizes what has happened. [image]That means you have to be fast to read the message, but it used to be possible. With Windows 8, though, the BSOD message has been improved to show a little sad face and a message that tells the user that Windows is gathering information related to the crash and will restart shortly. In the example to the right, you can see that the small text reads HAL_INITIALIZATION_FAILED. In the example, though, the error message takes up the whole screen; in my case, the blue area was limited to a 640x480 block in the center and the fine print had been scaled down into illegibility. That tiny bit of text holds the salient nugget of information that can help a veteran Windows user solve the problem. This was, needless to say, quite frustrating. The Event Viewer showed nothing, which wasn't unusual in the case of a full system crash -- how would it be able to write an error message? The system would still boot up fine and was perfectly usable, so I could search for help in finding that elusive message. Every halfway-useful page I found quickly ended in a forum moderator instructing users to upload their "minidump" files so that a Microsoft employee could examine them. That wasn't acceptable, so I searched for help on how to read mini-dump files myself. Microsoft's instructions ran to multiple steps and installation of low-level debugging software. Frustrated, I jumped into a conversation called "Blue Screen error delivers unreadable instructions (font too small); how to increase fontsize in Blue Screen?" which also featured an unhelpful answer. Luckily, someone responded almost immediately with a tip to use the "BlueScreenView" to read mini-dump files. Within seconds I'd found out that my crashes were caused by a driver file called CAX_CNXT.sys. A few more seconds and I'd found out that this was the driver for the 56K modem on my laptop. I disabled that device with extreme prejudice and restarted the machine. No crash. Problem solved. It took longer than it had to, but now my machine has been running stably on Windows 8 for days. And lacking a modem driver hasn't affected my workflow at all. ]]> https://www.earthli.com/news/view_article.php?id=2723 https://www.earthli.com/news/view_article.php?id=2723 Sun, 25 Nov 2012 20:30:06 +0100 is a wonderful, eye-opening article about flat-panel TVs. If you care at all how your television looks -- and whether it all matches the original intent of the director -- it's well worth your while to read the whole thing (it's not that long). However, here are the main points: Plasma > LCD If you don't have a flat-panel television yet, or you're in the market for a new one, strongly consider buying a plasma screen instead of an LCD. Why? Because "plasma TVs can render much darker black levels than even the best LCDs". Don't trust your eyes -- or the TV's in-store settings If you're buying a television, use consumer reviews and ratings (e.g. Consumer Reports in the States) to guide you rather than going to a store. The settings in the store vary wildly and are almost always blown way out to catch your eye; once you get a TV like that home, into your much darker living room -- which is unlikely to be lit by fluorescent bulbs -- that TV may or may not hold up. If you're buying for price, you're buying for price -- and the best of luck to you -- but if not, trust ratings from qualified judges more than your own subjective opinion drawn in the most non-cinematic setting. Turn off motion-smoothing If you do have -- or decide to buy -- an LCD, turn off motion-smoothing. Motion-smoothing explains why some HDTV looks almost more real than real-life. In short, the movie was likely shot at "24p" and your LCD has a refresh of 120Hz or 240Hz. Instead of just showing the same frame for 5 cycles, the TV interpolates new frames instead, smoothing out the roughness of the original film. [1] The article explains: "24p film, by showing us less, looks somehow larger than life, like a dream, like a story being told rather than an event being documented. This seemingly technical issue turns out to have an eno[r]mous emotional effect on the viewer." The article provides handy screen-shots and guides for how to turn off this feature on models from most major manufacturers. Extra credit: calibrate your TV While the steps outlined above should guarantee that you have a great cinema experience at home, if you're really, really interested in an authentic experience -- the most true to the original intent -- you can even buy a disc that will walk you through calibrating your TV to set up brightness, contrast and gamma levels for your lighting environment. This is similar to the walk-through included with most computer monitors, which most people also tend to ignore. -------------------------------------------------------------------------------- [1] A good friend has a lovely HDTV -- huge screen -- and the image is, at first, enthralling. I noticed, after a while, that something was disturbing me about the picture -- watching movies felt kind of like watching soap operas. I attributed it to a lack of familiarity with the HD format. Now I know better. ]]> https://www.earthli.com/news/view_article.php?id=2626 https://www.earthli.com/news/view_article.php?id=2626 Thu, 29 Mar 2012 20:10:15 +0200 doesn't seem to have a problem with it -- and it hasn't been updated for years. It's strange that Google hasn't switched to a capability-based browser-detection mechanism, blocking browsers that can't prove that they support certain features rather than just blocking by make and model. Google Flight's approach is also a good deal more friendly than that of Google+: at least I could use the site (which worked flawlessly, by the way). The little banner let me know that, should I have run into trouble, it might be due to the browser's not having been tested and supported by the site. Fair warning. Just blocking me, as Google+ does, is a bit strict. I told Opera to spoof as Firefox for that site and saw the same old site I'd seen the day before [1] but soon left because I felt like a trespasser, unwanted. As for the wonderful suggestion to just "upgrade my browser": you can stick it. Do I enjoy your site so much that I will switch away from my browser? I do not. Do I enjoy it enough to start another browser just to check your site? I do not. Does Google care about my visit? It does not. There are millions of other visitors -- or in the case of Google+, at least hundreds -- who use supported browsers with which it can concern itself. We seem to have arrived at an impasse: I use a not uncommon and very modern browser with a plethora of features on which I have come to rely and have not yet been compelled to change...and Google still has some hard-coded if (browserIsOpera) return; statements that it doesn't want to remove. [2] -------------------------------------------------------------------------------- [1] With the same content as well; is anyone even using Google+ anymore? [1] Google isn't alone in that regard: the latest version of the Zimbra web mail client still doesn't support "advanced" mode for Opera out-of-the-box. Opera has to include a user-script that fixes a few if (!browserIsOpera) {...} statements that are still in that software. ]]> https://www.earthli.com/news/view_article.php?id=2614 https://www.earthli.com/news/view_article.php?id=2614 Sun, 26 Feb 2012 16:32:57 +0100 , a professor of philosophy and language writes: "By 2010 I had an iPhone, and I had taken to checking for likes every minute or so while walking down the street; I learned even to check for them, surreptitiously, while teaching." Such an invasive insinuation into daily life was first made possible by SmartPhones, which deliver email and text messages announcing every ripple in the pond formed by the intricate network of relationships defined by one's profile and friendships. This stream of data could be termed distracting, but that assumes that people are doing something important from which they are being distracted. Can we honestly worry about a loss of creativity and philosophy and thought when nothing of the sort was going to happen, with or without a constant stream of notifications delivered to a personal mobile device? These devices chirp the arrival of each message, reminding their owners that something is going on that might interest them, just in case that which is happening in the immediate environs should happen to be subpar, as it usually is. Each soft ping represents a glimmer of hope that ennui may be fought back, if only for a little while. Since this seems to be such a lucrative gravy train, there will regularly be new contenders looking to at least carve out a modicum of success, if not to unseat the established kings of socialization online. The post, "How Storify And Pinterest Are Cultivating The Wild Web, And Why Social Media Will Civilize The Internet" by Eric Kain discusses two of these. I took a not-exactly-overwhelmingly-excited look: * PInterest: Shopping? Breadcrumbs of social media? Pictures that people like? It's a sheer sensory overload that promises hours of labyrinths through which an otherwise unengaged consciousness can wander. * Storify: A cavalcade of tweet-like snippets of thought? This site also purports to offer curated thought, but curated by whom? And the length of content makes the Huffington Post seem like a paragon of long-form writing. After reading the article, I feel that the title "A Bit Fat Pile of Fatuous Bullshit by Erik Kain" would have been more accurate but, as you can see from the title he chose, Kain thinks that these sites are going to be essential to how people socialize online. It seems like hype, but I think I've provided ample evidence that I don't really have my finger on the pulse of humanity. I fear I will constantly underestimate both how much leisure time people have to fill and the paucity of ideas that they have for doing so. That's not to say that I don't partake in socialization online; I do. I was an occasional contributor to both Slashdot and Plastic and enjoyed much back-and-forth in the comments on both of those sites. More recently, I've been a regular commenter on Reddit, where conversations are also largely conducted anonymously. My experiences there have resulted in more rewarding conversations with strangers than with my so-called friends on Facebook, where any conversation of merit or substance quickly peters out. I was going to name this post, "On the topic of sites whose purpose I cannot construe", but that would have been inaccurate: I know that these kinds of sites are created primarily because their creators want to make money. There are some sites which are created because their authors want that functionality for themselves, but it's hard to see that behind some of the latest attention-magnets like pInterest and Storify. In either case, all of these sites must capture attention in order to work as designed and in order to survive. Funding likely comes from advertising tie-in deals and delivery of captured target markets to purveyors of products. The world seems to be largely uninterested in delivering free content in any other way. Some of these sites purport to provide some form of service ("curated content!"), but it's an ephemeral one, perhaps best expressed as "eating time for you". I next tried the title "On the topic of sites whose appeal I cannot construe", but quickly discarded that candidate as well. The appeal is obvious; it just doesn't appeal to me. These sites help burn away those endless hours of leisure, they keep the ennui at bay. They help some get through those horrifyingly tedious hours of idleness at work, that time when the gears of bureaucracy take so long to mesh and provide something useful (or at least distracting) to do but, at the same time, refuse to release their prey from the physical constraints of the cubicle. Smart phones, a data plan and Facebook and its ilk to the rescue! The word addiction is thrown about casually, but it's far too crude an epithet for this dynamic. It is an especially crude characterization for someone to use who is not -- or has not been -- ensnared in this net. Or for someone who has no trouble filling time with other pursuits. From within, it all makes sense and each tweet and status update and notification-check and cat video watched and LOL scrawled beneath a fake quote pasted onto a Photoshopped image is utterly necessary, in context. The symptoms may be those of addiction, but the darkness of the word addiction implies that some sort of degradation of quality-of-life is accepted in trade. Is that the case for all of these flies in the social media web, though? Or is this the best that they can hope for, in any case? Or is there something really important going on -- something wonderful and world-saving -- that I'm missing? What else were these people going to do with their time? As mentioned above, can we honestly lament unresearched cures for cancer or unwritten works of scintillating brilliance, the time for which was stolen by texting an LOL attached to yet another picture of a friend's child in a Halloween costume? ]]> https://www.earthli.com/news/view_article.php?id=2612 https://www.earthli.com/news/view_article.php?id=2612 Sun, 29 Jan 2012 22:13:21 +0100 https://www.earthli.com/news/view_article.php?id=2580 https://www.earthli.com/news/view_article.php?id=2580 Mon, 05 Dec 2011 22:55:23 +0100 . "A new report by the Swiss government argues that unauthorized file sharing is not a significant problem, and that existing Swiss law—which allows for downloading copyrighted content for personal use—is sufficient to protect copyright holders. It considers and rejects three proposed changes: a French-style "three strikes" law, Internet filtering, and a mandatory collective licensing regime that would impose a fee on all Internet users that allowed unlimited file-sharing." Unsurprisingly, the Swiss decided not to change anything and, for a change, that's a good thing. It's refreshing to see a government that does a study and tests the hypotheses offered by proponents of new policy rather than just enacts whatever the highest bidder and squeakiest wheel wants. ]]> https://www.earthli.com/news/view_article.php?id=2562 https://www.earthli.com/news/view_article.php?id=2562 Mon, 26 Sep 2011 22:55:43 +0200 and cross-published here. -------------------------------------------------------------------------------- The GenericObject in Quino had recently undergone a performance overhaul, as documented in the article, "Improving performance in GenericObject" ...but we weren't finished yet. I'm going to assume that you read the overview on "How Data Objects are Implemented" and understand what the GenericObject actually is. In the other article, we optimized performance when creating objects in-memory and when loading and setting values. Those optimizations were driven by an application that used Quino data in a highly specialized way. In this article, we address other performance issues that came up with another Quino application, this one a more classical client for a database. To be more precise, the performance of the Quino application itself was satisfactory, but an importer for existing customer data was so slow as to be almost useless for testing -- because it took hours instead of minutes. So out came the "YourKit Profiler for .NET" again. As mentioned in the other article, we ran a part of the tests below (the smallest dataset) with tracing enabled, had YourKit show us the "Hot Spots", fixed those. Rinse, lather, repeat. [Charts and Methodology] As to methodology, I'm just going to cite the other article: "The charts below indicate a relative improvement in speed and memory usage. The numbers are not meant to be compared in absolute terms to any other numbers. In fact, the application being tested was a simple console application we wrote that created a bunch of objects with a bunch of random data. Naturally we built the test to adequately approximate the behavior of the real-world application that was experiencing problems. This test application emitted the numbers you see below." Note: The vertical axis for all graphs uses a logarithmic scale. Even though the focus was not on optimizing performance of creating objects in memory, we managed to squeeze another 30% out of that operation as well. Creating objects in memory means creating the C# object and setting default values as required by the metadata. [image] The "Saving New Objects to PostgreSql" test does not indicate how many objects can be saved per second with Quino. The data is based on a real-world model and includes some data on a timeline, the maintenance of which requires queries to be made after an object is saved in order to maintain the integrity of the timeline. So, the numbers below include a lot of time spent querying for data as well. Still, you can see from the numbers below that saving operations got slower the more objects there were. Saving 150k objects in one large graph is now 20x faster than previous versions. [image] This final number is relatively "clean" in that it really only includes time spent reading data from the database and creating objects in memory from it. That there are more objects in the resulting graph than were saved in the previous step is due to the way the data was loaded, not due to an error. The important thing was to load a lot of data, not to maintain internal consistency between tests. [image] Again, though the focus was on optimizing save performance, loading 250k objects is now twice as fast as it was in previous versions. These improvements are available to any application using Quino 1.6.2.1 and higher. ]]> https://www.earthli.com/news/view_article.php?id=2561 https://www.earthli.com/news/view_article.php?id=2561 Mon, 26 Sep 2011 22:49:18 +0200 and cross-published here. -------------------------------------------------------------------------------- Quino is Encodo's metadata framework, written in C#/.NET 4.0. Since its inception four years ago, we've used it in several products and the code base has been updated continuously. However, it was only in a recent product that one of the central features of the framework came under scrutiny for performance issues. It turned out that reading and writing to Quino data objects was a bit slower than we needed it to be. [How Data Objects are Implemented] A typical ORM (like Hibernate or Microsoft's Entity Framework) uses a C# class as the base entity in the model, decorating those classes with attributes to add to the model. The ORM then uses this information to communicate with the database, reading and writing values through reflection. Creating objects and getting and setting values -- including default values -- is all done through direct calls to property getters and setters. Quino took a different approach, putting the model at the center of the framework and defining an in-memory structure for the model that is accessible through a regular API rather than reflection. The actual C# classes used by business logic are then generated from this model -- instead of the other way around. This decoupling of metadata from the classes has a lot of advantages, not the least of which is that Quino provides generalized access to any of these business objects. Components that work with Quino data do not need to be aware of the actual classes: instead, those components use the metadata and an API to read and write values. Since the interface is generalized, these values are get and set using Quino code rather than direct getters and setters. As you would expect, there is a base class from which all Quino data objects inherit that provides the support for this interface, called GenericObject. It was in this central class that we had to go to work with a profiler to squeeze out some more speed. [Improving Performance] The actual use case for our data objects didn't even use our ORM, as such. Instead, we were generating the objects from a data stream with 0 to n columns defined (a perfect situation to use an object that supports a flexible interface). Once those objects were created, they were handed off to the user interface, which applied them to a grid, replacing rows or updating values as required. So, we needed to improve things on several fronts: * We needed to improve speed when creating objects because data was arriving at a serious clip. * We needed to improve speed when applying values because there were often several grids open at once, and they all needed to be updated as quickly as possible. [1] * We also needed to decrease the memory footprint because when the data flow was heavy, there were a lot of objects in memory and the application was reaching the limit of its address space. [2] As mentioned above, the data object we had worked fine. It was fast enough and slim enough that we never noticed any performance or memory issues in more classical client applications. It was only when using the data object in a very high-demand, high-performance product that the issue arose. That's actually the way we prefer working: get the code running correctly first, then make it faster if needed. And how do you make it faster and slimmer without breaking everything else you've already written? You run each subsequent version against your unit, regression and integration tests to verify it, that's how. Quino has several thousand automated tests that we ran each step of the way to make sure that our performance improvements didn't break behavior. [Charts and Methodology] The charts below indicate a relative improvement in speed and memory usage. The numbers are not meant to be compared in absolute terms to any other numbers. In fact, the application being tested was a simple console application we wrote that created a bunch of objects with a bunch of random data. Naturally we built the test to adequately approximate the behavior of the real-world application that was experiencing problems. This test application emitted the numbers you see below. We used the "YourKit Profiler for .NET" to find code points that still needed improvement and iterated until we were happy with the result. We are very happy with YourKit as a profiler. It's fast and works well for sampling and tracing as well as detecting memory leaks and tracking memory usage. To test performance, we would execute part of the tests below with tracing enabled (no recompilation necessary), show "Hot Spots" and fix those. The tests focused on creating a certain number of objects with a certain number of columns (with total data fields = #objects * #columns), corresponding to the first two columns in the table. The other columns are v0 (the baseline) and v1--v3, which are various versions we made as we tried to hone performance. The final three columns show the speed of v1--v3 vs. v0. [image] [image] Finally, not only did we make creating objects over 3 times faster and changing values more than twice as fast, but we also decreased the memory footprint of each object to just over 1/3 of the original size. [image] These improvements didn't come by magic: the major change we made was to move from using a dictionary as an internal representation to using arrays and direct indexing. The dictionary is the more natural choice as the generalized API maps property and relation names to values, but it uses more space and is slower than an array. It is, however, much easier to use if you don't have to worry about extreme performance situations. Using an array gives us the speed we need, but it also requires that we be much more careful about index-out-of-bounds situations. That's where our rich suite of tests came to the rescue and let us have our cake and eat it too. These improvements are available to any application using Quino 1.6.2.0 and higher. -------------------------------------------------------------------------------- [1] In a subsequent version of this product, we would move each grid/window into its own UI thread in order to parallelize the work and use all 8 cores on the target machine to make updates even faster. [1] Because of the parallelization mentioned in the footnote above, the subsequent version was still reaching the limit of the 32-bit address space, even with the decreased memory footprint per object. So we compiled as 64-bit to remove that limitation as well. ]]> https://www.earthli.com/news/view_article.php?id=2539 https://www.earthli.com/news/view_article.php?id=2539 Thu, 21 Jul 2011 23:05:31 +0200 . Basically, the Rosetta Stone application is not compatible with Lion, so PowerPC-only applications no longer run. If you can't find an update (or there is none announced) for an essential application, then you may have to stick with Snow Leopard for now. If you open the System Profiler and look at Applications, you can see all of the applications that are still PowerPC-only. 2. If you have multiple machines to upgrade, there's a way to do it without downloading (or paying) multiple times. See the article "Do I have to use the Mac App Store to reinstall Lion?" by Chris Foresman . The most important tip is that you have to "copy a disk image buried in the Lion installer app somewhere outside of the Applications folder after you download it." If you wait until after you've installed, it will already be gone. ]]> https://www.earthli.com/news/view_article.php?id=2537 https://www.earthli.com/news/view_article.php?id=2537 Sun, 19 Jun 2011 22:32:26 +0200 https://www.earthli.com/news/view_article.php?id=2502 https://www.earthli.com/news/view_article.php?id=2502 Sat, 19 Mar 2011 11:26:21 +0100 [3] includes the following text in its short article, "Works best in Firefox and Chrome." The demonstration works just fine in Opera and passably in Safari. There is no longer any reason to include the "Works best in..." badge unless experimentation has shown that the page really does work better in one browser than another. It's 2011, stop knee-jerk including the "Works best in..." badge -- the world has moved on. -------------------------------------------------------------------------------- [1] IE9 is, on the whole, a much more standards-compliant browser than its predecessors and supports most, if not all, of the cutting-edge technologies required by the coolest tech demos. [1] My apologies to any browser vendor who feels offended by being left off of this list. [1] The game indicated can also be played from "this page" . ]]> https://www.earthli.com/news/view_article.php?id=2448 https://www.earthli.com/news/view_article.php?id=2448 Tue, 21 Dec 2010 23:11:10 +0100 , one commenter noted: "Those of us with jobs and credit cards won't put up with that nonsense and will pay for the problem to go away." "That nonsense" to which he refers is any of the typical just-download-the-sources-and-compile-it-yourself claptrap peddles by those who don't understand a good-goddamned-thing about usability. Reminds me of recent discussions of Git and it's approach to the human interface. ]]> https://www.earthli.com/news/view_article.php?id=2444 https://www.earthli.com/news/view_article.php?id=2444 Sun, 12 Dec 2010 21:54:59 +0100 https://www.earthli.com/news/view_article.php?id=2436 https://www.earthli.com/news/view_article.php?id=2436 Fri, 22 Oct 2010 22:07:00 +0200 https://www.earthli.com/news/view_article.php?id=2365 https://www.earthli.com/news/view_article.php?id=2365 Sun, 18 Apr 2010 19:21:17 +0200 https://www.earthli.com/news/view_article.php?id=2362 https://www.earthli.com/news/view_article.php?id=2362 Sun, 11 Apr 2010 16:53:04 +0200 . That section now reads: "Applications must be originally written in Objective-C, C, C++, or JavaScript as executed by the iPhone OS WebKit engine, and only code written in C, C++, and Objective-C may compile and directly link against the Documented APIs (e.g., Applications that link to Documented APIs through an intermediary translation or compatibility layer or tool are prohibited)." That doesn't sound too good for Adobe, which had planned to allow direct compilation of iPhone applications from Flash in CS5. And it doesn't sound too good for MonoTouch either, which allows developers to write iPhone applications using the .Net framework and the C# language. The license for iPhone 3.2 prevented applications from using interpreters or virtual machines, but both CS5 and MonoTouch steered clear of those problems by compiling directly to iPhone OS machine code. The new wording in section 3.3.1 seems to be Apple's attempt to exclude these technologies with about as much subtelety as a five-year--old making up new rules during a game he invented. The official response, "MonoTouch and iPhone OS 4" , is understandably upbeat: they've already invested way too much time and effort to give up now. Their optimism that "[a]pplications built with MonoTouch are native applications indistinguishable from native applications" (whatever that means) seems suspiciously desperate since MonoTouch applications are written against the .NET framework in the C#-language, which means that they are most certainly not "written in C, C++, and Objective-C". Maybe the MonoTouch project will continue to be able to build iPhone applications that have a hope of being accepted by the iPhone App Store. But the rewording of section 3.3.1 puts the power to discontinue support wholly in Apple's hands. Developers would be silly to get on board with MonoTouch now without a far more explicit show of support from Apple. MonoTouch is putting on a brave face and promises that "[s]upport for iPhoneOS 4.0 on MonoTouch will be arriving soon." A typically well--thought-out article, "Why Apple Changed Section 3.3.1" by John Gruber details what the new wording means for Apple. And the answer, as usual, is control. It "makes complete sense" from Apple's perspective of "ruthless competitiveness". Apple is using the popularity of its platform to force developers to only spend time developing for Apple's platform instead of for multiple platforms simultaneously. "Flash CS5 and MonoTouch aren’t so much cross-platform as meta-platforms. Adobe’s goal isn’t to help developers write iPhone apps. Adobe’s goal is to encourage developers to write Flash apps that run on the iPhone (and elsewhere) instead of writing iPhone-specific apps. Apple isn’t just ambivalent about Adobe’s goals in this regard — it is in Apple’s direct interest to thwart them." There are aesthetic arguments to be made that cross-platform applications sully an operating system. There are very few of them that are truly well-integrated -- and those that are take a tremendous amount of time, patience and versions to get that far. On the OS X platform especially, it's incredibly easy to spot applications that were made exclusively for OS X and those that were ported from another operating system. It's truly like night and day. Preferring native applications, however, is a good deal different than banning non-native ones. As a C# developer with a large library of code I'd like to use, I can no longer assure clients that an iPhone application is easily achievable -- not without spending a lot of time and money learning Objective-C, the XCode toolset and the Cocoa APIs. Jobs and Co. would argue that I have no business developing applications for a platform without an intimate knowledge of its APIs, but that's philosophical until they see the end-product. Simply banning a procedure for building applications because the end-product may be unsatisfactory seems arbitrarily iron-fisted. Apple has always reserved the right to determine which Apps show up in the App Store and which do not. (As of this writing, Apple has been "evaluating" "Opera Mini" for the iPhone for almost 20 days.) That's why Gruber's analysis probably does get the real reason right: Apple's doing it because (A) they can and (B) they retain more control and (C) most of their users don't care one way or the other and (D) there are enough iPhone developers willing to follow Apple's rules and make mountains of money for Apple. Backing up this impression is an actual, honest-to-God response from El Jobso, as documented in the post "Steve Jobs’ response on Section 3.3.1" by Greg Slepak , where Jobs says that "Gruber’s post is very insightful" and goes on to say that Apple prefers native applications because: "[...] intermediate layers between the platform and the developer ultimately produces sub-standard apps and hinders the progress of the platform." As discussed above, though such layers may produce sub-standard apps -- and often do -- one does not necessarily follow from the other. That is, Jobs is merely hand-waving, arguing that a decision made for cut-throat business reasons was made in the interests of quality. There will always be developers writing bad software with Apple's tools and there would have been developers writing insanely great software using CS5 or MonoTouch. Apple actually already had what could be considered a user-friendly and customer-oriented program in place: They were able to reject bad applications individually. Is Jobs arguing that cross-platform tools were creating so many bad applications that Apple was losing profits just from the time and effort involved in rejecting them? Or does Jobs fear the flood of Flash-to-iPhone applications descending on Cupertino with the advent of CS5? Maybe Apple will bow to pressure and modify the section again -- it wouldn't be the first time a company tried to get away with something and had to backtrack. In the end, though, Apple can do what it wants with its platform -- and it plans to. ]]> https://www.earthli.com/news/view_article.php?id=2360 https://www.earthli.com/news/view_article.php?id=2360 Sat, 03 Apr 2010 23:12:00 +0200 , the backend for the web site. For each of these projects, I have the following repositories: * Local repository * Server repository (development) * Server repository (production) I usually make changes to the local version, then upload to the "dev" repsitory and test them on the server before pushing them to production. Sometimes, though, I have to make a quick fix on the production server itself when a user is blocked by a bug. Most of these fixes are one-liners in a single file and I try to push them back to "dev" immediately. Since I work alone, I'm not so accustomed to downloading from the server repository before working locally again. Couple all of this with the fact that I do actual web site development on earthli.com quite sporadically and you have a recipe for files left lying around in various states: * Uncommitted in either "prod" or "dev" * Committed in "prod" but not pushed to "dev" * Committed in "dev" but not pushed to "prod" (actually, that's ok) Uncommitted or unpushed files from the local repository are absolutely OK, though I still sometimes forget that I need to push to the server in addition to committing in order to actually see my changes. In fact, a full check-in looks like this: ...test local local:$ hg commit local:$ hg push local:$ ssh earthli earthli:# cd earthli/dev earthli:# hg update ...test dev earthli:# hg push earthli:# cd earthli/prod earthli:# hg update ...test prod This is actually all well and good and works just great as long as I always work in this order: Local => dev => prod. It's when I make one of the aforementioned changes directly to "prod" that I end up having to merge changes. Mercurial was totally designed to handle merging. I'm also quite familiar with the concept. But, with my local development on OS X and the servers running Debian, there is a paucity of visual support for merging. After years of administering OS X and Debian boxes, I'm also quite comfortable with the command line and am at least an advanced newbie at vi. Those are all not problems. What I don't like to do is resolve merge conflicts on the command line or using a text editor and hand-editing conflict markers. Fortunately, that happens exceedingly rarely, as I haven't managed to make conflicting changes in different repositories too often. But I chose both my server and development environments and will have to live with command-line support only for now. I just wish that command-line support was a bit more helpful. Here's a recent example to illustrate my frustration. I was trying to push changes from "dev" to "prod" and was told that the push would create multiple heads at the target. I totally grokked that: It meant that there were changes in "prod" that were not in "dev", so pushing from "dev" to "prod" would necessarily make another line of changes that would have to be merged in "prod" in order to have a single "tip". That wouldn't have been the end of the world, but I appreciated Mercurial informing me of the situation as well as offering that using the -f flag would allow me to force the push, if I so desired. I did not, however, so desire, because I never want to merge in prod. I always want to make all my mistakes in "dev", get everything working as expected and then push to "prod". The only commands I want to use from "prod" are: 1. hg update to copy the latest changes from the repository to the local hard disk (from which the web server reads) 2. hg commit to commit the rare emergency bug-fix to the "prod" repository. Ok, so instead I'll hg pull from the "prod" repository to the "dev" one, making two heads there. earthli:# hg pull ../prod pulling from ../prod searching for changes adding changesets adding manifests adding file changes added 1 changesets with 1 changes to 1 files (+1 heads) (run 'hg heads' to see heads, 'hg merge' to merge) earthli:# So far, so good. That's exactly what I expected to happen. Let's check the heads, as Mercurial has so nicely suggested: earthli:# hg heads changeset: 16:9197ac29588a tag: tip parent: 14:cad4ff88973d user: root@earthli.com date: Sun Jan 24 20:18:54 2010 +0100 summary: Removed a bunch of pages from the search site changeset: 15:f7c0e21d2e18 user: root@earthli.com date: Fri Apr 02 18:05:06 2010 +0200 summary: - Fixed crash on dieting form earthli:# Again, those are two most recent changes I made in each branch. Mercurial also helpfully suggested I use hg merge to merge the changes. Let's try that. earthli:# hg merge abort: outstanding uncommitted changes earthli:# Well, I think I know what that means: The repository for the web site includes configuration files, one of which specifies local paths. Naturally, that file differs for the "prod" and "dev" deployments. In the local copy of "dev", I had updated that file, but hadn't checked in the changes so that they would never get transferred to "prod" by accident. I can only assume that Mercurial is complaining about that file, but let's check the status to be sure. earthli:# hg status M lib/plugins/com.earthli.webcore.init.php M site/robots.txt earthli:# Bingo! lib/plugins/com.earthli.webcore.init.php is the configuration file and site/robots.txt is the change I made to "prod" that needs to be merged in. But what's Mercurial complaining about? That it can't merge in the changes to site/robots.txt while there are outstanding changes to other, completely unrelated files? That seems to be the case. Why in the name of all that is holy should that be the case? Perhaps I've misunderstood something? At any rate, I only know the hg status command, but it only shows me that two files are modified and not that they belong to two different heads. The conflict is not evident here, which is a shame. A newbie merging mode would be nice that would hold my hand a bit more and tell me what to do here. The first thing I tried was to commit only the file that came in with the pull operation, robots.txt. # hg commit site/robots.txt abort: cannot partially commit a merge (do not specify files or patterns) Aaaarrrgggggh. Now what? I feel like a total moron. Mercurial is scolding me for trying to "partially commit a merge" even though, as far as I can tell, that single file is the only file that was merged. I guess it makes sense that I can't commit that file because it hasn't technically been merged yet. But do I have to commit or revert all local changes before I can do any merging? That would seem to be the case. It may technically not be the case, but Mercurial is not being very forthcoming on other options. In the words of Homer Simpson: "urge to kill rising." [1] The status of my repository is that two files have been modified (as shown above). However, one of them has a special status: that it is unmerged. Out of curiosity, I tried to commit and was greeted by the following commit message in good old vi: HG: Enter commit message. Lines beginning with 'HG:' are removed. HG: -- HG: user: root@earthli.com HG: branch merge HG: branch 'default' HG: changed lib/plugins/com.earthli.webcore.init.php As I suspected, the file I actually want to commit is not commitable at this time, and the one I definitely don't want to commit can be committed. Now that's a fine how-do-you-do. Then, I had a killer idea: Most version control systems have a way of ignoring files or file patterns. The two other systems with which I'm familiar both use an "ignore" command or some file with the word "ignore" in it. I checked the Mercurial help for the word "ignore" and found nothing. I searched online and found a bunch of stuff about an .hgignore file, which I didn't get to work correctly and other tips that said to use an hgignore file (without the leading dot) and that didn't work either. I'll probably look into this again later, because I really need to ignore those configuration files. So, here I am with a problem that boils down to copying a single file from one directory to another. The version control system I'm using is offering to check in a file I want it to ignore and not allowing me to merge the file I need until I take care of the file it refuses to ignore. What I ended up doing was reverting the changes to the configuration file, executing the merge, then pushing the changes from "dev" back to "prod" and, finally, restoring the altered configuration file under "dev", where it will bite me in the ass the next time, probably in six months, when I can go through this all again. Part of the problem, as I see it, is that non-trivial -- heck, even trivial -- merging and diffing and resolving are goddamned hard using only command-line tools. Doing this kind of stuff without more graphical input is an accident waiting to happen. Naturally, there will be geniuses who claim this not to be the case, but that doesn't help the rest of us -- the bottom-feeders: Someone should be trying to help us get our work done, too. The other problem is that Mercurial assumes that you know exactly what your files are doing at all times without any extra help. In the example above, why does the call to hg status not show me that my file is unmerged? It clearly knows this. Ah, well. I imagine I'll get used to it at some point or some guru will point out what I'm doing wrong. I just feel that this is some of the polish that's missing from some of these super-tools: They get so much of the technical stuff working really well, then hide it behind an inscrutable, unhelpful interface. I've done it myself too many times: Built the basic framework and left making an actually intuitively useful application on top of it as an exercise for the next programmer. It really wouldn't be that hard to build in a mode that showed -- maybe even with ASCII art -- what was going on and what the poor newb's options were. One could argue that a command-line interface for a DVCS is, by definition, a hardcore programmer's tool, but why do we hardcore programmers always have to suffer? Why do we get tools that force us to use every bit of brain power we have just to accomplish what should be very simple tasks? Don't we ever get a break? Or should we just be grateful that there are tools like Mercurial at all? Maybe that's it. -------------------------------------------------------------------------------- [1] My frustration at this point is evident for all the world to see in "the changelog" . ]]> https://www.earthli.com/news/view_article.php?id=2357 https://www.earthli.com/news/view_article.php?id=2357 Thu, 01 Apr 2010 22:38:52 +0200 https://www.earthli.com/news/view_article.php?id=2327 https://www.earthli.com/news/view_article.php?id=2327 Sun, 28 Mar 2010 22:19:35 +0200 : "In OS X, Apple can’t block you from using apps it doesn’t like or competes with. But it famously blocks you from doing so on the iPhone and now presumably on the iPad, which is connected to the same App Store. How long before it blocks movies, TV shows, songs, books and even web sites? Scoff now, but don’t be so naïve as to believe that this isn’t possible. [...] I’m scared that Apple is grooming iPhone OS as the eventual successor to OS X, at least for the significant portion of Apple customers who use their machines for basic tasks like Web surfing, email and the like. [...] Apple is cleverly getting us trained on its closed platform little by little." Jee--sus. Overreact much? The iPad is not for geeks or programmers or the current members of the technocratic elite. It's for everyone else for whom multitasking only gets in the way, for whom the basic paradigms of the open computing systems currently available are far too complex. Whether the iPad is the right thing for them remains to be seen. [More Nuanced Critiques] The article "Why The iPad Is Crap Futurism" by Annalee Newitz offers another geek's opinion (she's a self-branded geek). She urges fellow geeks to buy the iPad, then hack it in order to free the world from the Apple high command, a problem non-geeks didn't even know they had. "Apple is marketing the iPad as a computer, when really it’s nothing more than a media-consumption device — a convergence television, if you will. Think of it this way: One of the fundamental attributes of computers is that they are interactive and reconfigurable. You can change the way a computer behaves at a very deep level. Interactivity on the iPad consists of touching icons on the screen to change which application you’re using. Hardly more interactive than changing channels on a TV. Sure, you can compose a short email or text message; you can use the Brushes app to draw a sketch. But those activities are not the same thing as programming the device to do something new. Unlike a computer, the iPad is simply not reconfigurable." It is a computer -- as far as non-geeks are concerned. It does everything they expect a computer to do, so why can't you call it a computer? Non-geeks don't "change the way a computer behaves at a very deep level" and they never will. That's something that geeks do and there are far fewer of those, so Apple is selling "computers" to everyone else instead. The question she asks is a very good one though: If this is the future of computing, then where is the next generation of programmers going to come from? She's wrong in thinking that the advent of the iPad will do anything to restrict computing. It will do no such thing. It will instead expand the number of people using high-quality, high-powered computers to do stuff digitally that they previously did in other ways (or with crap technology like digital picture frames, WebTV and the like). These people will never create new Apps, they will never install or re-configure anything on their computers -- unless trojans they inadvertently install do it for them). Instead of thanking Apple for increasing the market size of people willing to actually pay money for software (users in the App store actually pay for things), the geeks are bitching because Grandma is going to have a cooler device than they are. Newitz exhorts geeks to buy it anway, but crack it, so that they can download and install a freeware Bittorrent client and start stealing content as fast as they can. Lovely. In the grand scheme of things, closed computing platforms are a bad trend because content is getting less free instead of more free. Can you just load any old files on the iPad? Can you put your own PDFs on it? Can you print to PDF from a web page in order to read it later, when you're not online anymore? The non-geek user responds: Huh? You see, even those relatively simple tasks are going too far... The article, "Is the iPad the harbinger of doom for personal computing" by Rafe Colburn , offers an above-average formulation of the basic arguments (despite the hyperbolic title). "The fundamental difference between a Mac and an iPhone is that I can run any software I want on my Mac. I can buy it on a DVD, I can download it from the Internet, or I can compile it myself. I can get rid of OS X and install another operating system. The Mac is a general purpose computer in the classic sense. The iPhone is not." These are the same distinctions already made above, describing the open-ended freedom available to a master of computing. It's just a pile of gobbledegook to anyone else, though: "compile it myself"? "install another operating system"? WTF? Colburn absolves the iPhone of not being a "computing platform", perhaps because it's too small or its input methods are too simple to be of much use for software development. The iPad, however, will not be treated similarly, as Colburn puts quite well in the following passage: "What bothers me is that in terms of openness, the iPad is the same as the iPhone, but in terms of form factor, the iPad is essentially a general purpose computer. So it strikes me as a sort of Trojan horse that acculturates users to closed platforms as a viable alternative to open platforms, and not just when it comes to phones (which are closed pretty much across the board). The question we must ask ourselves as computer users is whether the tradeoff in freedom we make to enjoy Apple’s superior user experience is worth it." That's a very good question for technologically skilled users to ask themselves, but the question doesn't make much sense to the real members of the iPad's target market. Mere mortals generally don't consider the user experience offered by general-purpose computers as particularly liberating. Sure, once you get into it and learn it, you probably get converted to a minor-level geek and start to crave the punishment meted out by the common interaction metaphors. Most people, though, remain frustrated by their inability to do anything "cool" or "useful" and stay within a very limited circle of functionality. Most people don't find the current user interface metaphors very intuitive and -- for whatever reasons -- fail to apply lessons learned in one area to other areas. That's likely why the target market will welcome "Apple’s superior user experience" with open arms with nary a thought for the downfall of modern computing. It may be unfortunate for computing, but it's hard to fault people for wanting to have fun and get something done instead of suffering in order to maintain an abstract notion of flexibility from which they only indirectly profit and in which they will never in a million years be able to take part. But let Colburn explain the dangers to personal computing (as well as some benefits): "I think that it’s a real possibility that in 10 years, general purpose computers will be seen as being strictly for developers and hobbyists. The descendants of the iPhone and iPad and their competitors will rule the consumer market and people will embrace the closed nature of these platforms for the same reason that Steve Levy hyped Palladium almost 10 years ago — because what you get for trading off freedom is reduced risk. There will be few (if any) viruses, and applications will “just work.”" This is 100% correct, but it's difficult to tell whether Colburn sees this as a bad thing. It is more of a justice thing, no? People have put up with crap, geek-oriented hardware and software for so long that it's about time they got something that actually does what they need rather than sit there and offer the potential to do a bunch of things they don't know they need yet and which they will never figure out how to effectively use anyway. There are others who, as in the article "iSingularity? (take 2)" by Aristotle Pagaltzis , express worries that the iPad diverges from the tried-and-true method of delivering developer tools with an operating system. How else is one to make new programs for a device? Well, with the iPad, the answer is with "a dev licence and a Mac". That this model "makes Apple a lot of money", while true, is not the sole reason. Apple might perhaps be more interested in getting their device out there than in waiting until development tools are ready to ship. What's the point of spending all the time and effort preparing an on-board SDK for a platform that doesn't require one? What if, as with the iPhone, there are plenty of developers champing at the bit to buy a Mac and develop for the iPad? What is Apple's incentive for spending a lot of time and money in order to undercut their bottom line? It would be nice if they did, but ridiculous to expect them to do so voluntarily. Selling the iPad as an appliance makes a lot of sense from Apple's point of view -- and that of the majority of its customers. How software is developed for the iPad doesn't interest its users at all as long as it works as they'd like. "Users, in Steverino’s mind, couldn’t care less whether [developers] are indentured servants to Apple. They don’t even care that they are locked-in to Apple. They just know that the [apps are] good." In a world where people seem to be getting less capable of dealing with a complex world all the time, should it be a surprise that Apple wants to stop making complex devices? The size of that market is increasing all the time. Grandma wants to surf and video chat. The article "Why the iPad may be just what we need for Digital Inclusion" by Jaggeree offers some interesting insights. "One of the largest excluded groups are pensioners who struggle to get online for many reasons [...] The first main problem they have technically is that computers look complex. They have lots of things you plug into other things. Every thing has an arcane name, very few of these names really relate to their function. Each of these things causes something to happen but not in an obvious touch the thing and something happens to it way. [...] it becomes an activity of worry and confusion." This "worry and confusion" makes the world of devices and computing suck for more than just old people. "Then you look at the iPhone and iPad" and you understand what an inclusive, accessible device actually looks like. A certain level of computing should be like a utility -- always on and always available. More advanced uses should be possible too, but this is secondary for the vast majority, who just want "access to services that will make a difference to their lives. Services that socially engage them, that bring them savings, that bring them government and local services." This more user-friendly attitude appeared in a few other articles -- most published after some reflection instead of in the heat of initial indignation. The article "Future Shock" by Fraser Speirs also addresses users toward which the current software world has been anything but friendly. "The people whose backs have been broken under the weight of technological complexity and failure. [...] they are the people we have claimed to serve for 30 years whilst screwing them over in innumerable ways. There are also many, many more of them than us." Those of us who spend a good deal of our time explaining UI paradigms to users for whom they were never meant should rejoice at the advent of a better, more user-friendly computing device. For example, "Those of us who patiently, day after day, explain to a child or colleague that the reason there's no Print item in the File menu is because, although the Pages document is filling the screen, Finder is actually the frontmost application and it doesn't have any windows open, understand what's happening here." The geek/non-geek distinction is not an abstract one: It's one under which people have been suffering for nearly all of computing history. One side -- the geeks -- is perfectly happy with the status quo because their needs are being met. At least they think they are. They are, however, deluded. As pointed out by Speirs, geeks also suffer from a reality distortion field, which "tells [them] that computers are awesome, they work great and only those too stupid to live can't work them." They are wrong. [Pinning Hopes on Open Alternatives] Another well-respected tech blog published ""Insanely great? Ars reacts to the Apple iPad" by Jon Stokes " but, unlike Colburn, who at least acknowledged that there were users who would be well-served by the iPad, Stokes jumps on the open-source bandwagon instead, opting to wait for the semi-organized hordes to replicate the Apple user experience, but in a non-proprietary way. "In the end, Apple has done something with the iPad that I didn't think they were capable of: made it worth my while to look around, or possibly even wait, for a better, more open alternative. I'm ready to buy an ARM-based, thin-client tablet computer—I'm just not ready to buy this one." Though "hissy fit" is a bit harsh, the attitude expressed here comes very close to that. The faith in open alternatives seems ill-founded, as the experience offered by Apple products tends to remain head and shoulders above those competitors. It would be nice if it were not so, but it is -- especially when considerd from a non-geek standpoint. Stokes thinks that open alternatives will be able to catch up on the hardware side first, mentioning Linux-based tablets and asking "[...] take battery life: 10 hours is amazing, but is it really that much more amazing than, say, the 8 hours that a Linux-based competitor might achieve?" Well, no...all other things being equal, of course. However, you'd have to really dig the open-content, free-software vibe to put up with the kind of user experience a Linux-based tablet is likely to offer the first four or five times around the track. The question alone is already deep into geek territory: Why would a mortal user accept lower battery life and an inferior user experience in order to use "open software"? Apple offers a user experience that is, quite frankly, second-to-none. With this weapon, Apple convinces its users to forgive it many of its transgressions in other areas -- like locking in users to a closed platform. Non-geek users will have trouble understanding why it's a bad thing that all of their apps are integrated together and that they can only shop from the App Store. If all you want is dessert, you're not going to complain that there's only a single buffet table loaded down with dessert, are you? It's only later, when you think you might like something else that you notice the doors are locked, but by then you're on such a sugar high, you no longer care (to beat the metaphor absolutely to death). Staying firmly in geek world, Stokes argues that it's technically possible to build a device at about the same price-point as the iPad but that allows all content and is a genuine replacement for a laptop. There's just the small hurdle of catching up to Apple in sheer design -- hardware and software -- its use of multitouch in applications, and the top-to-bottom integrated user experience for which Apple is rightly famous. Once you can replicate that -- more or less -- you should be in business. Stokes is, in fact, pinning his hopes on it: "For instance, I can easily imagine an Android-based tablet that's designed by HTC, powered by NVIDIA's Tegra 2, does 1080p video (vs. iPad's 720p maximum resolution), and has much better 3D gaming performance, but at the cost of two hours of battery life. And if someone made such a thing, I would rather buy it than an iPad. I'd even pay over $500 for it. Given the number of Android and ARM-based devices I saw at this past CES, and the amount of design talent that's going into many of them, I expect to see at least one non-embarrassing Android-based competitor to the iPad by at least the second half of the year, if not earlier." One can easily imagine that, but that's pretty much all one can do until it shows up. Apple has a slobber-worthy tablet ready to go -- almost right now -- and at a price-point that was inconceivable for even Apple just a year ago. The point is that, Apple has what people want right now; why should they wait for a device that may appear at some time in the future? Unless you're a geek, that is? Remember, as an editor at a semi-famous tech-site, Stokes is going to be using an iPad every day regardless of how closed the device is...because he will be obligated to hold his nose and use it in order to be able to tell his readers about it. Poor guy. A "topic on reddit" declares that the "Archos 9" already does everything the iPad promises and more. Follow-up comments, however, reveal exactly the kind of drawbacks one would expect when squeezing Windows 7 onto such a small device: It's noticeably laggy (e.g. "takes 8 seconds to open firefox") and eats batteries ("4 hour video battery life"). It also doesn't have multitouch, which is the killer hardware feature right now. Apple has a proven track record of making great user experiences. They make devices that make you glad you shelled out your hard-earned cash for them. The tactile feel of their hardware, the gesturing and hinting in their UIs -- they do a very good job of rewarding their users, both initially and ongoing. There are always quibbles, of course, but Apple does a very good job of making machines that are a pleasure to use. The iPad is apparently one of these: Initially skeptical commenters are reporting mass conversion once they get their grubby hands on one; the experience is apparently that good. What is interesting is that not even Stokes -- an Apple watcher from way back -- is aware why he doesn't want an iPad: It's because it was not made for him. Technocrats were delighted to buy iPhones despite the closed software ecosystem simply because they offered so much more than was available in other phones. And besides the smart-phone market was completely accustomed to closed systems, so the outcry was relatively small. It was only when developers tried to create their own applications for the iPhone that they cried foul: Apple was using a native SDK whereas other developers could only use HTML/CSS/JS. This initial backlash against Apple for building a monopoly on good software didn't stop the iPhone development market from simply exploding though, did it? Instead of running away from the platform, developers hung around and forced Apple to change its policy and release a proper SDK. The huge market Apple dangled in front of them brought the geeks to their knees. Now they're pissed that Apple learned their lesson well: There is a huge amount of money to be made in closed markets. Not only that, as noted in the article "A theory about Apple's new iPad" by Chris Siebenmann , Apple needs "something that just works [and] getting that is less effort with a closed box than with an open one". As mentioned above, it's bad for computing, for the future and for the world for Apple to retain absolute control over our devices. Of course that's true. But the place we're in now is going nowhere fast because "[p]eople who do not actively like computers do not care about a lot of the computer stuff; they just want the computer to do things for them." [Is Apple Even Business Savvy?] Of course they are. As Colbert says: "The free market has spoken." Apple clearly does "get the Internet" -- to refute the accusation made by Jon Stokes -- and has carved out a huge chunk of the content pie for themselves. It's ludicrous to accuse a company that makes more money in online content than any other and has ridiculous profit margins on nearly all of their products of not understanding how to do business. As Apple has already shown, they are willing to go in open directions when it is good for their bottom line: witness the slew of open-source software they maintain and develop (Clang, Darwin, WebKit) or that their iTunes music is now DRM-free. The eBook format they chose is ePub, which is open. With the death of Apple having been prognosticated many times, it's probably a safe bet that they'll know when the time is right to switch sides. People will -- for just $500 -- get a pretty kick-ass computing device-from-the-future. They're not going to care that Apple is limiting their selection to only 140,000 apps, that Apple is limiting their book selection to only those offered by the big five publishers, that the iPad can only play officially sanctioned and downloaded -- and purchased -- movies from the iTunes store. They won't care because they'll be carrying around all the media they could ever want to consume in the palm of one hand and viewing it on a gorgeous display and manipulating it with gestures that make them happy. They will be happy to be corralled into a content ghetto -- an admittedly quite large and comfortable one, but nonetheless a ghetto. The gullible, consuming masses don't care about the future of technology or the freedom of information; they don't care about corporate and content monopolies; they care only about watching dogs surf in HD on YouTube while slurping a decaf mocha latté in Starbucks. But that's the market ... and who can blame them? Developers and the technocratic elite had gotten quite accustomed to being catered to as the "early adopters". They'd gotten quite used to being granted special privileges in their role as bellwethers. And now, suddenly, Apple no longer cares what they think. They're not Apple's prime market for the iPad. They were arguably not Apple's prime market for the iPhone either, actually. As mentioned above, though, the outcry was much smaller because the iPhone replaced a crappy piece of technology -- existing phones -- with something new and marvelous. The iPad is filling a niche that technocrats thought was theirs, but which includes everyone but them. The geeks that are prophesying Apple's doom are kind of stuck in the same category as the Ars Technica editor who reviewed the iPad's suitability as a comic book reader ("Aurich Lawson" ). He went on and on about the base resolution and aspect ratio and how unsuitable it was for watching video or reading comic books. Does he even know that much of the U.S.A. still demands their films in full-screen format? Apple understands the vast majority of their market much better than infuriated geeks who can't understand why their needs aren't addressed even though they're shared by at least dozens of others. These people invariably justify their indignation by noting that "a lot of people they know" also need such-and-such a feature. It's likely that Apple actually has hard numbers to back up their decisions. And there's another difference between geeks and Apple. The open-source world doesn't have to make a profit, so it can cater to any market segment, no matter how small. Unfortunately, the coolest hardware and slickest software -- so far! -- comes from a company that doesn't care about tiny market segments that are market losers for them. Because he put it so eloquently, I'd like to leave the closing arguments to Fraser Speirs: "Think of the millions of hours of human effort spent on preventing and recovering from the problems caused by completely open computer systems. Think of the lengths that people have gone to in order to acquire skills that are orthogonal to their core interests and their job, just so they can get their job done. "If the iPad and its successor devices free these people to focus on what they do best, it will dramatically change people's perceptions of computing from something to fear to something to engage enthusiastically with. I find it hard to believe that the loss of background processing isn't a price worth paying to have a computer that isn't frightening anymore." Something like that would be great for everyone, geeks and non-geeks alike. -------------------------------------------------------------------------------- [1] And thus concludes the public service message of "feel guilty if you're considering buying this thing when you already have an iPod, and iPhone and two computers". ]]> https://www.earthli.com/news/view_article.php?id=2336 https://www.earthli.com/news/view_article.php?id=2336 Sun, 07 Feb 2010 13:51:16 +0100 https://www.earthli.com/news/view_article.php?id=2329 https://www.earthli.com/news/view_article.php?id=2329 Sun, 31 Jan 2010 21:52:26 +0100 , has a lot more detail, but the crux of the argument is as follows: "[...] the most frequent cause of crashes across all of Mac OS X are (or at least were, pre-Snow Leopard) “plugins”. [...] several sources at Apple [...] confirmed that “plugins” was a euphemism for “Flash”. [...] Flash is still a 32-bit binary despite the fact that Apple wants to go 64-bit system-wide. Flash remains 32-bit and there’s nothing Apple can do about it. Instead of being able to make Flash 64-bit themselves, Apple had to engineer an entirely new plugin architecture. [...] Which situation do you think Apple is happier with? Mac OS X, where they had to create a new web content plugin architecture because Flash crashes frequently and isn’t 64-bit? Or iPhone OS, where they control the source code to every single component, and can do whatever they want, when they want?" Near the end of this very informative article, we learn that, even though Flash has a monopoly on video playback for the web -- a situation this author personally finds to be awful [1] -- Adobe's OS X version has always lagged behind its Windows version. The Windows version takes advantage of hardware playback for high quality video whereas the OS X version cannot because, as Adobe puts it, "Apple does not provide a public API to make this happen". What they mean is that Apple does not provide an API for direct access to the hardware. Instead, applications wishing to run video must use either the Quicktime API or the new Quicktime X API in Snow Leopard. Adobe should just use those APIs, as Apple's own QuickTime player does. Judging by the number of crash reports associated with the Flash plugin (mentioned above), Adobe is the last company to which Apple should grant hardware access. Apple, as a software developer, finds itself in the classic position of any highly skilled company forced to work within budget constraints (both time and money) and forced to work with existing technologies to facilitate and encourage integration and adoption of its own software. Take, for instance, this author's experience with development on the .NET platform from Microsoft. Though a software company (e.g. "Encodo Systems AG" ) may have employees skilled and experienced enough to write pretty much anything they need, there isn't nearly enough time in the world to do so. There are other issues to consider as well: * Every piece of software a company writes increases its own support footprint: That component needs support forums, documentation, tutorials and bug fixing. * Standardized components are likely to be already well-established among developers willing to try a company's software, increasing the likelihood that they can adopt new software that integrates with (instead of replaces) technology they already know and use. * The time (not to mention the skill, which many companies don't have [2]) required to write more complex software is often prohibitive and can severely affect cost estimates and schedules. Those concerns seem to indicate that, whenever possible, a company should focus on its core offering and simply integrate with existing technologies. The company minimizes its support footprint and spends its time working on software that they are uniquely good at. Partner companies are happy because they can integrate that company's products without throwing out any infrastructure or doing any massive retraining of their developers. Product budgets stay nice and small and schedules stay nice and tight because no-one is spending time re-writing components that already exist. Yes, indeed, it's all unicorns and rainbows. As long as the external software doesn't suck so much that it makes you wish you'd never used it. What happens when you've got a skilled set of in-house developers and they're forced to slog through development integrating with wildly popular technologies that look wonderful on paper, but that are shaky, unstable, unreliable and well-nigh unpredictable to use in practice? What happens is that developer frustration goes through the roof, budgets start to explode and product development stagnates with functionality in core areas plateauing instead of steadily rising simply because developers are spending all of their time working around irreparable bugs in the constellation of integrated software instead of building their own product. At Encodo, we've recently gone through some very rough patches working with WCF (Windows Communication Framework), EF (Entity Framework) and the data-binding used by the Windows Forms libraries and all components that extend it (like the DevExpress UI component libraries we use). In the case of DevExpress, we have the expertise to build our own UI components...but for all of the reasons outlined above, we chose to use a popular component suite instead. We have never wholly regretted that decision, but have often tangled with bizarre APIs and event models with which we would have never been satisfied had we had control over the source. And don't even get me started on EF: The first version is not ready for prime-time at all. It has holes everywhere and doesn't scale at all for development or practice (models over 25 entities are considered "large"). There are hidden limitations around which one must work; limitations that would not exist or that could easily be removed in code that was under one's own control. Similarly, the WCF libraries include a nearly impenetrable data serializer/deserializer which, as with most Microsoft technologies, emits error messages that are cryptic, at best. Not only that, but we recently managed to finally track down what we are quite sure is a bug in the implementation. It was on the hunt after this bug -- and other inconsistencies -- that we several times had to meet to determine whether we shouldn't just toss the whole thing overboard and roll our own solution. It's not that we wanted to have our own serialization; it's that we were spending so much time working around bugs in WCF that we weren't getting our work done anymore. Integrating existing frameworks and libraries makes sense on paper, but you have to make sure that those libraries are worth integrating i.e. that they don't end up costing you most than you gain. Companies should avoid shoddy technologies even if they are hugely popular and developed by big players (like Microsoft) because there is no way to avoid huge development costs with them. If the technology design and implementation are good, then you will save money; if they are not, it's going to cost you no matter what. That is, if you need object persistence in a database (EF) or need to send data over a wire (WCF), you're going to be spending a lot of money and time if you use those two technologies. If a company has a great development team, it might make more sense to avoid them -- and their attendant frustration -- entirely. That kind of situation sucks and it's completely understandable that Apple wants to avoid it. It's both a money sink and horrible for morale. -------------------------------------------------------------------------------- [1] The situation of video on the web being de facto controlled by Adobe is likely to change with the support of the HTML5 https://www.earthli.com/news/view_article.php?id=2299 https://www.earthli.com/news/view_article.php?id=2299 Wed, 30 Dec 2009 13:27:19 +0100 , Sprint made strides by making "it so easy for law enforcement to gain access to customer data on a 24/7 basis through the use of its Web portal and large compliance department." With their addition of GPS data to all of the other personal information about you that they're regularly shoving over to the cops -- all without any warrants or probable cause -- "the number of requests [have gone] through the roof." Imagine that. And this was all made legal in the U.S. -- for your protection. It's simply incredible that the same people who want to impeach Obama because they think he will try to take away their guns couldn't care less about his massive invasion of their privacy and infringement of their rights -- as human beings, to say nothing of their rights as Americans. The U.S. is politically moribund and is most likely psychologically incapable of any change. If you want an easy way to fight this surveillance, start using cheap and accessible encryption -- for your mail, for your chat sessions, for your phone (if you can). Even the cops can't break encryption, but everybody has to start using it or you'll limit your audience. Good luck. -------------------------------------------------------------------------------- [1] Said wiretapping has proceeded apace -- unchanged -- under the Obama administration. ]]> https://www.earthli.com/news/view_article.php?id=2279 https://www.earthli.com/news/view_article.php?id=2279 Wed, 23 Dec 2009 21:02:03 +0100 documents a design proposal for a way to better incorporate multi-touch technology into everyday computing. [media] Executive summary: * Your arms are too heavy to be able to multi-touch on-screen. * Your arms and hands are not transparent. * The mouse has only a single point of contact (not counting mouse-gesturing, which offers more degrees of freedom). * What about putting the multi-touch surface on the table instead of on the screen? * Manipulating classically clipped and overlapped windows is confusing; we need a better way of organizing application windows and work-areas. * That better way involves moving the application menu (e.g. Windows Taskbar or Windows menubar [1]) to the left, the global menu (i.e. Windows Taskbar or the Apple Dock [2]) to the right and making all windows the full height of the screen at all times and stacking from left to right. It's an intriguing presentation, but I see the following problems with the design: * The latest iMac has a 27" screen; that's a damned big multi-touch surface to duplicate on the desk. [3] Apple is not alone; screens on desktops are getting bigger. Also, notebooks and netbooks are getting more and more popular; though the bottom half of a notebook is the right size, it has a keyboard on it right now, which brings us to the next point. * If the multi-touch surface goes on the desk, where does the keyboard go? Is the keyboard also virtual, but not on-screen? If it were on-screen, it would take up precious screen-space; If it's purely virtual, there's no haptic response. How would you switch from manipulating windows with 10-touch and typing? * Some users derive benefit from a non-linear juxtaposition of windows. For example, with larger screens -- and screens are getting huge these days [4] -- users can place video-phone and chat applications on the side, perhaps have a video running in another corner, and still have room left over for a text editor and an open web page. It's hard to imagine having all windows simply flowing from left-to-right and having to constantly shuffle the windows back and forth to see multiple things at once (no matter how much awesome fun it is to do so). Granted, it might help one's concentration, but that's what applications like "Ommwriter" are for. -------------------------------------------------------------------------------- [1] And, of course, whatever Ubuntu & other flavors of Unix are calling their clones of these features these days, be they running KDE or Gnome or whatever. The author, as an Opera user, intends no disrespect to users of niche products [1] See above. [1] Or the couch, from where this author is currently happily (and quite lazily) driving said iMac with a tiny Bluetooth keyboard and mouse. [1] The author would like to remind everyone that he's currently using a 27" iMac from his couch, zoomed-in, or course, to reduce eyestrain. ]]> https://www.earthli.com/news/view_article.php?id=2227 https://www.earthli.com/news/view_article.php?id=2227 Sun, 25 Oct 2009 17:23:13 +0100 https://www.earthli.com/news/view_article.php?id=2165 https://www.earthli.com/news/view_article.php?id=2165 Mon, 18 May 2009 20:46:16 +0200 (131/2 minutes) in order to get really charged up. The reality is that it kind of works like it does in the screencast. I started off by requesting some information about the town in which I grew up, namely its population. That worked just fine, but it couldn't find historical information, so no fancy graphs for me. So, I chose a larger nearby city and it did just fine. I chose my current city [1] and that returned about the same overview I'd get from a stop at the Wikipedia page (right-hand sidebar). That was pretty cool, because that search took me a few Google hits and a Wikipedia trudge when I had to do it without Wolfram Alpha a few weeks ago. I thought some more about burning questions about data I needed correlated, so I tried ""average age US president"" , which was too specific; I was offered ""average age US"" or ""US President"" instead, neither one of which Google couldn't do for me, though admittedly without the fancy charts. Those weren't, however, the questions I wanted answered. Age, in fact, seems to be missing, as queries for "youngest president", "age US presidents" all failed to produce any information or flashy charts. They will undoubtedly address this as they amass more data about the types of questions people are likely to ask. The web is full of amateur genealogists, so correlation over DOB information is not likely to be missing for long. Wolfram Alpha is, at least to some degree, ready for geeks, as a query for ""What is the air-speed velocity of an unladen swallow?"" produced the usable response of 11m/s. As presented in the screencasts, the hard sciences are well represented, but questions involving more squishy topics don't even elicit a half-hearted link to potentially relevant information in Wikipedia or default to a Google search (""When will the world end?"" linked neither the upcoming Emmerich movie nor any information about Ragnarok or Judgement Day). When you return to things numeric, however, things are much better and this is where Wolfram can really save you a lot of time. Trying to stay in the spirit of the screencast, I asked for ""compound interest 5% 20 years 1000 capital"" and Alpha asked if I meant ""5% 20 years 1000 capital"" which, in fact, I did. A query for ""UBS stock value 2006-2008"" timed out but a query without date restrictions returned the expected data. As expected, there is a tremendous amount of caching required for this kind of search engine, and you're kind of expected to jump in at the highest level of abstraction and drill down to give the server half a chance. That's bad news for those of us who like to skip steps but the silver lining is that Alpha does give it the old college try, indicating that this is likely more a server capacity limitation rather than a logistical or data-based one. You do, however, have to include the right kind of numbers for now, as queries for "iphone sales 2008" or "teen pregnancy NYC" (then "pregnancy 18-24 NYC ") returned nothing at all. Trying to find out how much Apple gadgets weigh with "iPhone weight" also gave no results. At this point, I'd killed my second Wolfram server [2]. Socioeconomic searches really don't work at all, even for things where you would imagine they should have data (e.g. "US incarceration rate" or "hispanic, caucasian, african-american" turn up absolutely nothing) so you're stuck going to Wikipedia for anything but the simplest of searches. It'll probably be a hit with kids looking for a way to spend even less time researching their boring homework assignments than they do now. For the rest of us, it looks like we should stick to the searches outlined in the screencast for best results ... like comparing your name to that of your partner to find out who's cooler. [3] -------------------------------------------------------------------------------- [1] Wolfram does not know what country codes are for those of you living outside the US, so be prepared to type out the whole name. Steve may have a British accent in the screencast but, as with almost every other tool on the web, Alpha is going to work for Americans best and for the rest of us eventually. [1] You can see how it shunts you to a server when you perform a search. If you kill the server you're on (like I did with poor little www97 and www22 in quick succession), just get rid of the number in the address and hit enter to get a new server. [1] It turns out the wife's name had its heyday in the 50's and mine is an up-and-comer. ]]> https://www.earthli.com/news/view_article.php?id=2130 https://www.earthli.com/news/view_article.php?id=2130 Wed, 11 Mar 2009 22:23:53 +0100 https://www.earthli.com/news/view_article.php?id=2128 https://www.earthli.com/news/view_article.php?id=2128 Tue, 10 Mar 2009 22:24:10 +0100 https://www.earthli.com/news/view_article.php?id=2073 https://www.earthli.com/news/view_article.php?id=2073 Mon, 12 Jan 2009 21:08:03 +0100 on the table in what they clearly feel is the answer to many people's dreams -- the dream of having a keyboard from the 80's back up your atrocious singing. [image]A visit to the home page takes you to a video that has no business being so damned huge to download or such high quality because it so awful as to defy description. If you make it through the whole video, you're made of stronger stuff (than I). The software claims to "generate musical accompaniment to match a singer’s voice." To test this little theory, a user at "MetaFilter" ran David Lee Roth's vocal track from Running' with the Devil by Van Halen through it, to come up with "Runnin' With The Songsmith" . Songsmith is clearly not up to the task of generating anything but an 80's keyboard background accompaniment and the results are ... interesting, to say the least. As one commenter neatly put it, "[t]his is simultaneously the best and the worst thing I have ever heard." If you're interested in making your own music, try the "David Lee Roth Runnin' with the Devil Soundboard" . It's minutes of fun. ]]> https://www.earthli.com/news/view_article.php?id=2055 https://www.earthli.com/news/view_article.php?id=2055 Fri, 02 Jan 2009 12:18:32 +0100 digs into the pricing and cost structures for text messages (SMS's [1]) sent via cell phone. It cites astounding numbers of messages sent per year and talks about 10-fold growth in messaging across the spectrum and around the world, but the upshot is: transmitting text messages costs next to nothing so long as an infrastructure for transmitting telephone calls is already in place. That is, the graph of cost to number of messages transmitted does not at all scale linearly, instead flattening drastically after a certain point -- a point long since reached by all major carriers. This is possible because "text messages are not just tiny; they are also free riders, tucked into what’s called a control channel, space reserved for operation of the wireless network." This is one reason why messages are so extremely limited in length and why picture messages are in another weight-class altogether. Naturally, the telecoms companies are loath to correct us in our collective assumption that their "operational costs [rise] in tandem with message volume". With this belief that text messages are like a standard, physical commodity, they have been able to "doubl[e] prices for text messages charged by the major American carriers from 2005 to 2008". Since transmitting messages essentially costs a telecoms company nothing, they are the happiest when you sign up for an unlimited plan for a fixed price per month ($15--20, depending on the carrier). Naturally, they are providing a service and they have the transmission capacity whereas we, as customers, would like to use it. That's capitalism, after all. But, with a captive market and a near-monopoly (only four carriers remaining in the States), they are then free to push prices up without relation to the cost of providing the service. One can convincingly argue that text-messaging is not a social need, like food or shelter, but why should such a useful service -- running over a public spectrum leased by the American people to these companies -- be subject to the fickle rule of free-market capitalism? Is this situation really benefitting anyone other than the telecoms investors? At what point does a service become "standard", like water and electricity, and subject to more regulation and less price-gouging? [2] At $360 per year just for text messages -- and, considering alternatives like chat and email are free -- the price is already fairly steep. -------------------------------------------------------------------------------- [1] U.S.-standard punctuation rules are in effect in this article, as with all articles at earthli News. Punctuation afficionados on this side of the pond should simply pretend that that apostrophe is not there. [1] Text-messaging is still fairly new, so, in my opinion, it's not yet at this point, but the questions are still interesting and valid (again, in my opinion). Rabid free-marketers -- if there are any left after the end of last year -- will disagree. ]]> https://www.earthli.com/news/view_article.php?id=2014 https://www.earthli.com/news/view_article.php?id=2014 Sat, 13 Dec 2008 19:41:32 +0100 https://www.earthli.com/news/view_article.php?id=2010 https://www.earthli.com/news/view_article.php?id=2010 Sat, 13 Dec 2008 12:41:47 +0100 offers an in-depth look at the new features. It's amazing how long it takes for certain, seemingly no-brainer features, to make their way into flagship products. Features such as adjustment layers for effects, like drop shadows, so that they can be toggled on and off as via pseudo-layers rather than painstakingly toggled via a custom dialog. Or features such as alignment tools and "Smart Guides", which take the guesswork out of wondering which objects are going to move when you select a bunch of them and align or redistribute them. At least the features are finally here, but people have been paying $600 and up for vector graphics software that made lining things up a chore. Another nice, finally-it's-here feature is the "Blob Brush", which let's you draw with a brush that makes paths rather than single strokes. When you make other types of objects (not pen or brush strokes), you can join them, crop them or do whatever to them and you get a single path outlining the entire object. You can then adjust the stroke, fill, transparency or what-have-you for this object as a whole. When you used the "Live Trace" feature on what were ostensibly strokes, it would create a path around these fine lines as well. If you used the brush tool to replicate or extend these lines -- to emulate the imported, stroked style -- you got a single stroke in the center with a shape extending to the sides the width of the brush. You could not adjust the fill for this object or the surrounding stroke, because it didn't have one, per se. CS4 finally lets you use a brush as a tool for painting bounded regions that, when they overlap, automatically join to the overlapped regiong to form a single, contiguous shape. A welcome, if long-overdue, feature. Another feature that was sorely missed when moving from Freehand to Illustrator was decent gradient support, especially with transparency. You can usually figure out how to do what you want with Illustrator CS2, but it was sorely lacking in that department when compared to Freehand. CS4 finally addresses this drawback by introducing in-place and live transparent gradient editing. It seems like a basic tool, but it took over a dozen versions before it became reality. I'm still not sure whether I'll do the upgrade from CS2 to CS4 -- CS2 still fulfills its duties adequately -- but it's much more tempting than the upgrade to CS3 was. And, at only $199 for the upgrade from any previous CS-version of Illustrator or one of the last three versions of Freehand, the price is quite reasonable. ]]> https://www.earthli.com/news/view_article.php?id=1947 https://www.earthli.com/news/view_article.php?id=1947 Sun, 28 Sep 2008 09:41:55 +0200 -- for "the programmer and the geek and, in a way, the average consumer". In a very, very small way. First of all, look at it: [image] It's a smart-phone and aimed squarely at the smart-phone market, but don't even try to mention that the "average consumer" is even conceivably a target market for this monstrosity. It looks huge [1], way bigger than a BlackBerry or an iPhone. With it's slide-out keyboard and large form factor, it has almost no chance of success in Europe (at least Switzerland), where the iPhone is already considered a bit too large, but still worth it. In the States, it has a better chance, because they seem to like tiny keyboards there and large form-factors aren't deemed so much of a problem. As a smart-phone, it probably has a chance, as people in that market are willing to sacrifice ease-of-use and a flat learning curve for more features and power. The average consumer, on the other hand, does not want a phone that looks as complex and hard-to-use as a computer. As for how it stacks up against the iPhone, which is a phone made for the average consumer as well as a direct competitor in the smart-phone market, "The T-Grid: T-Mobile’s G1 Android Phone vs. the iPhone" offers a side-by-side comparison of features and specifications. Notably: * The G1 will be locked to T-Mobile, in the same way that iPhones are locked to AT&T. * The G1 has, for whatever reason, a proprietary headphone jack. Not even Apple has their own headphone jack. * The web browser is "Webkit-based", so it's presumably running some variant of the brand-new Google Chrome browser, which is still in beta and has only been available to the public for a few weeks. * There's no desktop-syncing because, well, why would you need to sync to the desktop? You're already synced to the Google Cloud(tm)! The G1 is, of course, fully integrated into the Google Internet Experience(tm) with a single signon and quick access to all Google applications. It runs on Google's very own operating system, Android, which is used officially for the first time. As everyone knows, the first version of an operating system is usually the best, most-polished one, with entropy taking hold and everything going slowly downhill from there. By the third or fourth generation of an OS, it's nearly unusable, so strike now while the iron is hot. -------------------------------------------------------------------------------- [1] Ok, so "huge" is somewhat hyperbolic, but that's the initial impression when you first see someone holding it. Apple marketing handled it better -- although much sleazier -- by finding a hand model with enormous hands for the first officially released photos. ]]> https://www.earthli.com/news/view_article.php?id=1919 https://www.earthli.com/news/view_article.php?id=1919 Thu, 28 Aug 2008 22:49:20 +0200 for the Book Library, which seemed like a lot of work documenting an application in use by two people, with no hopes of ever being used by more. -------------------------------------------------------------------------------- The Book Library as it is today is a Windows-only application built with "Atlas" , a Borland Delphi-based framework available from "Opus Software AG" . I used to work at Opus, and the Book Library is the application I wrote to get a feel for how Atlas was to use "in the real world" -- I believe a lot of the improvements in Atlas 2.5 stemmed from that work. :-) At the same time, I included an XML-importer for an old, crappy Access database I wrote a looooonnnng time ago, back in NYC when I barely knew a database from a hole in the ground. Using the importer, I managed to get most of my well-documented book library into the new, shiny application with no data entry. Having nearly 800 books documented and cross-indexed is a pretty big inertia that prevents me from moving to some online solution or some other software (like the fancy-looking "Delicious Library 2" ). Data-entry in the current version is a snap and it does what it needs to. Shortly after I wrote the Book Library, I finally had had enough of watching my mother enter her data into a "database" [1], so I wrote an importer for that too -- a highly-customized work of art, it turns out -- and there her data sits to this day. She nodded happily as I showed her the new application, then forgot all about it for a couple of years, continuing to add to the old database. I discovered that this summer and resolved to attack the problem of migrating her to a new application with extensive documentation; thus, the experiment I wrote recently (the aforementioned "Book Library handbook" ). I was also happy to discover that my self from 2005 had an inkling that this would happen and I'd written not just an importer, but a sync that ignored duplicates. Oh frabjous day! I could re-import her data without changing a line of code! So, I sent her the handbook and the new database, with my fingers crossed. So, that's the reason there's such a detailed handbook and also the reason the Book Library is not available for download: because it's written with proprietary "Opus" technology for which I no longer have a de-facto commercial developer's license. "Atlas" , however, is just the latest skin to wrap this data, some of which, as mentioned in the footnote, is two decades old. The plan, of course, is to rebuild it with "Quino" , a C#-framework I helped develop at my company, "Encodo Systems" . Quino is actually more than ready to go for replicating the Windows application, but ... you know ... the web's sooooo cool these days and Quino web-support is getting there as well. The Book Library waited twenty years; it can wait a little while longer. -------------------------------------------------------------------------------- [1] You don't even really want to know ... it's latest incarnation was in Access, but the schema started life as a Lotus Symphony database at least two decades ago ... oh, the horror. ]]> https://www.earthli.com/news/view_article.php?id=1841 https://www.earthli.com/news/view_article.php?id=1841 Thu, 01 May 2008 14:09:46 +0200 calls proponents of such TOEs, "architecture astronauts". Using Ray Ozzie as an example, he defines them as people who: "...can't stop rewriting [the same] damn app, again and again and again, and taking 5-7 years each time. [...] And the fact that customers never asked for this feature and none of the earlier versions really took off as huge platforms doesn't stop him. [It's a] fun programming exercise that [is] just hard enough to be interesting but not so hard that you can't figure it out." Damned skippy. And, if you're harboring such an idea and didn't for a moment have a sour feeling in your stomach that perhaps it's not quite such a good idea after all, well, then congratulations, you might be an architecture astronaut. Unless you're independently wealthy and can tinker along making things you like -- and which other people may at some point be taught to love -- you better make sure enough people are willing to pay for what you're selling before you go to all the trouble. [1] What does this all have to do with Joel, you may wonder? [2] Never fear, Fog Creek Software (Joel's company) has no such space-travelers in its employ [3]. Instead, it's the larger firms that are promulgating these cool-sounding ideas -- and offering appropriately astronomical salaries for working on them, to boot. From the article, "...between Microsoft and Google the starting salary for a smart CS grad is inching dangerously close to six figures and these smart kids, the cream of our universities, are working on hopeless and useless architecture astronomy because these companies are like cancers, driven to grow at all cost, even though they can't think of a single useful thing to build for us, but they need another 3000-4000 comp sci grads next week." Ah. So the applicant market for Fog Creek is drying up -- or, more precisely, the applicant market composed of good comp-sci students who don't expect to be paid six figures [4] is drying up. The point about these "companies [being] like cancers", though harsh, is basically correct -- they do have to grow to survive, which is ultimately a doomed venture. That they can't think of a "single useful thing to build for us" is unfair, considering GMail, Google Search, the .NET framework, MS Office and so on. Sure, they've also come up with a lot of duds (Windows Vista, I'm looking at you), but it would be more precise then to say that "everything they build isn't useful". But, it's the internet and hey, hyperbole gets you page impressions. [5] -------------------------------------------------------------------------------- [1] Unless you're building an elaborate tax-shelter/government-funded scam and plan to cash out early and move to the Bahamas, in which case, godspeed. [1] And, if you're expecting to have that question go unanswered, then you haven't read very much by Joel Spolsky. [1] Though they did find time to invent their own programming language, which all in-house developers have to use and, presumably, learn to love. [1] And, as mentioned in footnote [3] are willing to program in a completely unknown in-house language called "Wasabi". [1] And, if you don't like hyperbole, then you shouldn't be reading Spolsky [6]; or anything on the internet, for that matter. [1] Just like, if you don't like footnotes, you shouldn't be reading this blog. ]]> https://www.earthli.com/news/view_article.php?id=1822 https://www.earthli.com/news/view_article.php?id=1822 Tue, 22 Apr 2008 18:52:24 +0200 . Browse on over to see more! -------------------------------------------------------------------------------- [Vista under the Christmas tree] If you're planning to buy a computer this holiday season -- and you don't opt for the shiny goodness of an iMac or iBook -- then you'll probably be getting Windows Vista. Windows Vista is very shiny and pretty and probably sounds like a great alternative to its predecessor, Windows XP. However, the minor improvements to the file explorer and organization (and major ones to look-and-feel) are far outweighed by both hardware and software compatibility problems as well as a draconian approach to security. All in all, you spend far more of your precious time (and nerves) coddling the system rather than doing actual work. Windows Vista is not a worthwhile upgrade to Windows XP for any user -- advanced or novice -- and should be avoided if at all possible. Most vendors now offer Windows XP as a drop-in replacement when buying a new computer, with an option to upgrade to Windows Vista when the first service pack is available. [What Happened?] All observations are based on a single-user trial of Windows Vista installed for 9 months; final impressions are based on the version of Vista available in the middle of November, 2007. In February, Microsoft released Windows Vista, the long-awaited successor to Windows XP. Here at Encodo, we installed it on one developer machine [1] for several reasons: 1. To determine whether our products run on Vista and to fix any problems that cropped up. 2. To test over a longer time period whether Vista truly offered advantages over Windows XP in terms of efficiency. 3. Because "Aero Glass", the new user interface for Vista, looked really, really cool. The initial -- very positive -- impressions are documented thoroughly in "First Days with Microsoft Vista" (parts "I" and "II" ). After nearly 9 months of testing, the verdict is in: "Avoid Windows Vista until further notice." And we're not the only ones; Vista recently made #10 in the list of "Top ten terrible tech products" . We, too, have capitulated and gone back to Windows XP installations for all desktop computers. Vista survives only inside a "Virtual PC" image, which we installed for testing purposes only. [2] [The breakdown] Though we don't recommend Vista for anyone, we especially don't recommend it as the primary operating system for developers [3]. Among the many reasons for our decisions are the following major ones: Speed Vista is noticeably slower than Windows XP in every way. Period. It is especially noticeable in something so banal as copying or deleting files. When you see Vista open a progress window to indicate that is "Calculating time remaining..." to delete a single 4Kb file, you figure it's a fluke; the tenth time it happens that day, it just makes you want to cry. Security Vista ships by default with a brand-spanking-new security system designed to make viruses, trojans and other nasties a thing of the past. It's called User Account Control (UAC) and involves you approving everything that happens on your computer. In practice, this means that every time you start an installer, you have to tell Vista that you did actually start that program and that, yes, you would like to actually run it. Get used to your screen going black and asking you that question. A lot. Software Compatibility Not only is the security bothersome and inefficient [4], but many applications have no idea how to deal with it. One of the main advantages of Vista was that one was supposed to be able to work as a non-administrative user so that it was impossible to issue system-altering commands by mistake -- or for an application to do so maliciously. Even now, after years in beta and 9 months on the market, many applications (and most installations) don't properly support this mode of operation, sometimes installing non-functioning applications to the wrong locations or refusing to install at all. Though the latest Microsoft Office runs just fine for the average user, Microsoft's own venerated Visual Studio does not run in non-administrative mode on Vista. [5] Hardware Compatibility Though others have more thoroughly documented hardware woes, our experience was that something as simple as connecting to a network printer -- which Windows XP accomplishes in no time at all -- turned out to be impossible for Vista. The much-vaunted "Sleep" mode never worked on this relatively standard hardware (see first footnote), leading to incredibly long reboots after which Vista scolded you for not shutting down properly. Windows XP, for all its faults, has achieved a relatively stable release after many years in the field and is a much better choice for any user. Users that have their hearts set on the upgraded Vista look-and-feel, "Aero Glass", should wait for until the first service pack has been out for a few months -- which should be around the middle of next year. Developers that have their hearts set on Vista should forget it: Vista is not ready for use as a developer operating system and offers no advantages in that regard over Windows XP. -------------------------------------------------------------------------------- [1] Just to set the record straight, Vista was installed on a newly purchased machine in Februrary: a dual-core 2GHz processor with a modern graphics card (which Vista itself indicates is adequate for it) as well as 2 GB of RAM and a 7200RPM hard drive -- basically upper-middle of the hardware requirements for Vista. [1] And which weighs in at a frightening 10.5GB with no applications installed. [1] As already indicated, we do agree that it's essential to test software on all platforms and have Windows Vista images with which to do testing -- we just don't use it for development. [1] Not only your efficiency in that you're constantly "approving" commands you just issued, but that there are suspicions that Vista's new security concept accounts for many of the performance problems mentioned in the previous point. [1] Visual Studio is a development tool for building Windows applications and web sites in many different languages. Postgresql, a popular open-source database, was not even capable of installing on Vista until the most recent beta came out a few weeks ago. Even tools like "spec#" -- again, produced by Microsoft itself -- recommend that users "try disabling the user account controls" (effectively removing all protection) if they can't install. ]]> https://www.earthli.com/news/view_article.php?id=1743 https://www.earthli.com/news/view_article.php?id=1743 Tue, 12 Feb 2008 23:20:48 +0100 reveals that Safari has implemented a proposed CSS extension, "CSS Animation" by Dave Hyatt , which adds transition-property, transition-duration and transition-timing-function to the available CSS properties for all elements. These properties, applied to standard CSS properties like opacity, border or position and combined with new functions like rotate, make a lot of the functionality offered by the current libraries obsolete. [Client-Side Storage, Video, Audio and Fonts] There are other updates to Safari 3.1: * HTML5's SQL storage application programming interface (API) -- this will replace cookies for local storage, offering a real database with SQL querying capabilities. * Video and audio tags as outlined in the draft specification of HTML5 -- these are standardized embeds for video and audio players, with native scripting support. * Downloadable/embeddable fonts -- just what it sounds like: yet another attempt to standardize fonts referenced from a web page. See "CSS @ Ten: The Next Big Thing" by Håkon Wium Lie for more information (it boils down to being able to specify a URL in the CSS from which to download). [CSS3 Improvements] This is in addition to the "Ten New Things in WebKit 3" by Maciej Stachowiak that came with the release of Leopard late last year. In that release, they introduced native support for SVG, XPath, Enhanced RTF Editing, Stylable Form Controls (finally), and a slew of CSS3 features, like: * "Media queries" -- this allows authors to use different CSS depending on display-time properties of the media, like width or height. * "Multiple Backgrounds" -- this finally allows authors to build complex borders or backgrounds for blocks without using multiple boxes or artificially limiting size in any way. Finally, rounded corners/borders without hacks. * "Box-Sizing" -- a box model for CSS for the rest of us, who just want two boxes to show up next to each other without figuring out who has to float where and without using a table. [Developer Tools] And of course, it's Apple, so their developer tools look cool as hell. [image][image] [image][image] -------------------------------------------------------------------------------- [1] See "Evaluation of Javascript Libraries" for more information. ]]> https://www.earthli.com/news/view_article.php?id=1734 https://www.earthli.com/news/view_article.php?id=1734 Thu, 07 Feb 2008 22:08:52 +0100 do your work for you. It works like this: Get "Miro" Download and install the Miro Player. This player can check video newsfeeds, showing what's available and letting you download a show from one or more sources. Once you've downloaded a video, you can watch it right within the player, which keeps track of where you were in each video. Once a video's on your hard drive, Miro automatically starts uploading it to other people requesting the same thing (you can stop it from doing this, though). There's a lot of free content available, but that's probably not what you're here for. Go to "TvRSS" This is a web site that hosts newsfeeds for pretty much every TV show, mini-series or limited-run series shown on TV (in the last decade or so). Search around until you find what you need, then following the handy guide in "TV Torrents: When 'piracy' is easier than legal purchase" , which shows you just what you need to do with screenshots and everything. ]]> https://www.earthli.com/news/view_article.php?id=1728 https://www.earthli.com/news/view_article.php?id=1728 Sun, 03 Feb 2008 19:58:33 +0100 encircling the globe. In addition to an map of the cable systems throughout the world, it provides some statistics about the recent shipping accident that severed four of those cable lines, killing the internet and business traffic for almost 80 million users. The government of Egypt was exhorting its citizens to lay off downloading movies and songs for a day or two so that "more important" business could use the bandwidth. If you can't access the main image, there's a local copy cached here as well (click the image above instead of the link) [1]. Interestingly, notes accompanying the diagram state that the total available capacity is 7.1TB, of which 5.7TB has been purchased. However, on the trans-Atlantic cable, though 80% of the capacity has been purchased, amazingly only 29% is utilized. Of the utilized capacity, only 1% of that is now accounted for by telephone traffic. It's difficult to discern to what, exactly, the 7.1TB refers, because in another paragraph, it's mentioned that the trans-Atlantic capacity alone is "over 7 trillion bps". Is the latter figure actually saying that the trans-Atlantic capacity is truly 7Tb (where the little "b" stands for bits), leading us to believe that US/European traffic only has 1/8 of the available bandwidth on the planet? Or is there a typo, in which bits and bytes are being used interchangeably? At any rate, it seems that there's plenty of room for growth. -------------------------------------------------------------------------------- [1] It's just a shame that the image is stored in JPG format, which is singularly bad for a graphic with so much small text on it. PNG would have been a much more efficient and crisp way to go. ]]> https://www.earthli.com/news/view_article.php?id=1709 https://www.earthli.com/news/view_article.php?id=1709 Thu, 17 Jan 2008 22:12:04 +0100 makes its point well: "But let's admit amongst ourselves that the overwhelming majority of people out there have never pulled the battery out of their existing laptops, and didn't even know or care that it comes out. In fact, if something goes wrong with their battery, this majority -- whom we'll call "NORMAL PEOPLE" for convenience -- will just take the damn machine to the store and get it fixed, whether it's user-serviceable or not. Because we don't want to hassle with it." Exactly. It's a gorgeous step forward in portability (a very light portable with a full-size keyboard, an innovative keypad and a huge screen) and will be an affordable choice for a lot of people for whom the current crop of MacBooks was too big -- and offered a power and expandability that they didn't need. And, as always with Apple, this is only what will amount to a solid first version of such a machine; its successor will be even better. -------------------------------------------------------------------------------- [1] 1.36kg and 1.94 cm, respectively, but it sounds so much sexier in pounds and inches. [1] Pun is neither intentional nor amusing. ]]> https://www.earthli.com/news/view_article.php?id=1695 https://www.earthli.com/news/view_article.php?id=1695 Tue, 18 Dec 2007 16:56:06 +0100 document's one man's journey to being able to edit an MP3 file under Linux. Included are the following gems: * Look at the Ardour interface. Decide that (1) it’s not what I want, and (2) dear god that is ugly. Is that Tk? Motif? Holy hell. Run away. * Read http://jackaudio.org/faq. "The simplest, and least-secure way to provide real-time privileges is running jackd as root. This has the disadvantage of also requiring all of JACK clients to run as root." Yeah, no. One commenter suggested that the author would have had things much easier had he just installed a multimedia-capable Linux distribution in the first place or was willing to install the multimedia packages of a Debian-based distribution (which apparently is more involved than the typical apt-get install... command). Yeah! No. To that, the astute Steve commented: "While I’ve been using Linux since the beginning, these people advising multimedia Linux are not on this planet. You’re advising that someone should wipe their whole machine and install a complete new operating system just to tidy up some sound files. Please, recognise when your love of Linux is making you say stupid things, and stop doing it." Well played, sir. Good advice for many situations; simply replace [Linux] with [Mac], [Java] or some other arduously-defended technology. ]]> https://www.earthli.com/news/view_article.php?id=1616 https://www.earthli.com/news/view_article.php?id=1616 Tue, 10 Jul 2007 10:20:52 +0200 . Browse on over to see more! -------------------------------------------------------------------------------- Trillian is a multi-protocol chat client that's been around for a quite a while, with both a free version and a professional version, which includes extra features and support. Their version has stagnated quite significantly, offering a grand total of one update over the last three years or so. The feature set is robust and it does pretty much everything you need from a chat client, but its look and feel is starting to feel a bit dated -- especially if you've gotted used to Adium or iChat on the Mac. With that in mind, it was time to download Pidgin, which, though its name is new, is a very old and well-established open-source project previously called GAIM. [1] Their libraries are integrated into many other chat clients and GAIM/Pidgin itself is used by much of the open-source world. Despite this, it's a pretty unpolished project. The UI itself is quite nice and simple, looking much like the aforementioned Adium or iChat and dispensing with much of the clutter that afflicted the previous generation of chat clients (like Trillian). So far, so good. Setting up all chat accounts is also pretty straightforward and intuitive. You can easily set up new statuses and the defaults include an "invisible" status, so you can see who else is logged on, but not appear logged in yourself. Status and connection state are combined, unlike in Trillian, which is also a welcome change. Communication is rock-solid, as expected; open-source geeks expect the core stuff to work -- it's the UI where their attention to detail strays and makes for a frustrating user experience. Here is a list of the major annoying issues or gross oversights that Pidgin includes today, after lord knows how many years of active development. Installation Pidgin includes optional spell-checking, which is a nice touch, since Adium on OS X uses the system-standard spell-checker to make chatting a more pleasant grammatical experience. However, the bloody thing only lets you choose one language, with no option to install more languages later. Documentation There is none. Features like "pounce on user" will remain completely mystifying for the average new user. There is developer documentation in case you want to help develop Pidgin further, but there is zero documentation for actually using the product. The web site is extremely bare, with a completely empty "news" section, a short "about" section and not much else. Running State Pidgin can minimize to the task tray and lets you hide the "Buddy Window" to avoid desktop clutter. However, it relatively quickly got itself into a state where the buddy window was gone, there was no taskbar icon and starting a new instance simply complained that one was already running. God forbid it should actually offer to show the already running instance. Pidgin was alive, but could not be rescued from the limbo to which it had consigned itself. There was no choice but to kill it and restart. Settings Policy Killing Pidgin leads you to the next problem: Pidgin only stores its settings when exited cleanly and seemingly doesn't store anything to disk during normal program execution. Again, for users accustomed to Mac OS X-like behavior -- where program state is stored instantly and applications almost always pick up exactly where they left off, even after crashing -- this is completely unacceptable. This hurts all the more when you'd only ever started Pidgin once, entered all five of your chat accounts, set up some new statuses and are faced with the "welcome to Pidgin! You have zero accounts. Would you like to create one?" startup assistant on the next restart. More Settings Woe Not only are global settings not stored while the application is running, but some settings are never stored at all. Like window positions. This is infuriating, because Pidgin simply places every new chat window at the top left of the screen no matter what. No, it is not sufficiently amazing that you managed to show a chat window and are allowing me to send text back and forth with friends and family throughout the world. These days, you totally need to remember where I last put the window for each buddy and how big the window was and the position of the text-box slider and -- just remember everything dammit and put the windows back the way they were, so I don't have to constantly drag the damned things around so they are in front of my face. These are not little details anymore. In the old days, it was enough to just work; once a tool becomes part of the everyday workflow, it has to iron out its usability issues or it becomes too annoying to use. Open-source Disclaimer: I know. It's open-source; I could just go in there and fix it myself. I could stop complaining and do something about it. I could change the culture of the project to be more user-friendly. It's just sad that I would have to, sad that projects like this -- that are the toast of the open-source world -- are still so unpolished and include (or fail to include) features that most of us learned a decade ago were essential. -------------------------------------------------------------------------------- [1] They had to change their name after a drawn-out court battle with AOL, whose AOL Instant Messenger product -- AIM -- claims all trademarks on similar sounding names. ]]> https://www.earthli.com/news/view_article.php?id=1610 https://www.earthli.com/news/view_article.php?id=1610 Sat, 16 Jun 2007 15:36:43 +0200 has the following astute description of the differences between the algorithms: [image] "The nice thing about the Apple algorithm is that you can lay out a page of text for print, and on screen, you get a nice approximation of the finished product. This is especially significant when you consider how dark a block of text looks. Microsoft's mechanism of hammering fonts into pixels means that they don't really mind using thinner lines to eliminate blurry edges, even though this makes the entire paragraph lighter than it would be in print. ... The advantage of Microsoft's method is that it works better for on-screen reading. Microsoft pragmatically decided that the design of the typeface is not so holy, and that sharp on-screen text that's comfortable to read is more important than the typeface designer's idea of how light or dark an entire block of text should feel. (emphasis added)" The emphasized line above was also cited by "A subpixel Safari" by Dave Shea , who pointed out that it smacks of an attitude of "programmers knowing better than experts in their respective fields", which ends up "marginalizing type designers". The difference between the rendering technologies is only blatantly evident when seen side-by-side; the brain acclimates to each one on its own relatively quickly. This basic difference between the two operating systems is probably the single biggest reason that so many people use OS X for graphics design: What You See really Is What You Get. As pointed out by many, applying that same technique to elements that will never see a printed page is overkill, especially when it means that menu items and control labels are not lined up on the pixel grid and look blurry. This might seem like a killer problem for Apple, until you consider the following: "Here’s the caveat though — high resolution displays. At 100dpi, ClearType wins out, but we’re not going to be stuck here much longer. Give it a few years, let’s do this comparison again when 200dpi is standard. I suspect the pixel grid won’t matter nearly so much then." In effect, ClearType is like the game engines of yore (like Quake II or Quake 3): it contains optimizations that let it perform optimally on the hardware of today. However, these optimizations aren't going to scale well at all on newer hardware, since the rendering anamolies caused by "hammering fonts into pixels" will never go away. Apple's algorithm, on the other hand, is like the newer engines (like Doom or Unreal 3): it's truer algorithms makes it look blurry in comparison (as Doom 3's truer rendering made it run more slowly than other engines), but it is far better positioned to improve automatically as hardware improves. This is not the first time that Apple has chosen investment in long-term vision versus short-term pragmatism -- the initial OS X was a poor fit for the machines of the day. A few years -- and many software and hardware improvements -- later and most people can barely remember when OS X was considered slow or RAM-hungry. Similarly, id's Doom engine used to run well only on the newest graphics cards, but games based on the technology are still being developed today and the technology has scaled incredibly well -- even when compared to much more recently developed technology. Cleartype is very readable on-screen, but takes liberties with text representation, whereas Apple's sub-pixel rendering is the hands-down winner for faithful font representation, but takes some getting used to on screen -- for now. In a few years, Apple's rendering will start to look better to a lot more people. With the iPhone screen weighing in a 160 pixels per inch, that's probably the first place their investment will pay off handsomely. ]]> https://www.earthli.com/news/view_article.php?id=1600 https://www.earthli.com/news/view_article.php?id=1600 Mon, 04 Jun 2007 23:00:55 +0200 [1] and relaying to that address is not allowed. This is somewhat deceptive, leading the user to believe that there may be something wrong with the server when the problem is actually with the authorization to the SMTP server. [Identify Yourself!] Cablecom has recently changed their SMTP relay policy to require that you enter a user name and password in order to prove that you are who you say you are instead of, presumably, a spammer. In order to do so, you'll have to adjust your mail client to send messages with authentication. The following screenshot shows the settings for Apple Mail, but the "help page" offers more links, including a "Guide for setting up SMTP authentication" . [2] [image] Basically, you need to do the following: 1. Make sure SSL is disabled. 2. Use password authentication. 3. Enter your email address and password from your Cablecom mail account. [Anschlusskennung? Huh?] What's that you say? You don't have an email account from Cablecom because you never bothered to make one because you're so damned cool that you have your own email server and who the hell needs yet another email address that's just bound to an ISP that you could change at the drop of a hat or when your annual contract expires, whichever comes first? Well, then, you'd better make yourself said useless email account or you're out of luck. The thing is, there's a bit of a catch. You need to have the "Wilkommensbrief" you got when you signed up so you can enter your "Anschlusskennung" and "Kennwort" in order to verify that you are who you say you are. [3] Once you've got those infos, it's a piece of cake to cruise on over to "Cablecom: Registration" to create your new user account (which you will likely never use except as SMTP-authorization credentials). Cablecom automatically uses the password you were issued in the "Wilkommensbrief" for your email account. That's the one you have to enter to log in the first time. Once you're logged in, change it to something you have a prayer of remembering. [Conclusion] And that's it. Piece of cake. Cablecom seems to have made this change without actually informing its customers -- or perhaps they only sent out email to those with existing CableCom accounts. At any rate, it's not a hard problem to fix, but still requires significant know-how of how the internet works -- which means there are a lot of people in Switzerland mashing away on the "try sending again" button. -------------------------------------------------------------------------------- [1] That's where I work, by the way. We do all sorts of software work. Check it out if you're bored. [1] The two links given are in German and the FAQ link was crashing badly at the time or writing. Previously it had provided extensive information for setting up almost any client under the sun for authenticated SMTP. It is assumed that it will once again do so at some point in the near future. Cablecom also offers English versions of most of its documents. [1] Just imagine the sigh of relief the author breathed when he found that his ever reliable wife ("without whom he is nothing" -- wife) actually still had the piece of paper they'd received when they'd signed up almost five years ago. A quick trip to the basement archived document storage (I am not making this up -- ed.) and there it was. ]]> https://www.earthli.com/news/view_article.php?id=1595 https://www.earthli.com/news/view_article.php?id=1595 Mon, 14 May 2007 22:31:15 +0200 https://www.earthli.com/news/view_article.php?id=1580 https://www.earthli.com/news/view_article.php?id=1580 Sun, 15 Apr 2007 20:59:03 +0200 , Apple brings a whole new meaning to the term "dead battery". According to the article, OS X can sometimes drain a battery so irrevocably that it can never be charged again. It's a hardware problem that affects a small percentage of users. What's interesting is the reaction to the problem by Benjamin, one of the Apple faithful. Instead of tearing Apple a new one for not addressing this clear software/BIOS/whatever issue, he lamely recommends that the problem "can be easily avoided by shutting your Macbook down if you won’t be using it for more than a day." Really? That's great! Thanks! Shutting down and restarting all the time is fun and now Apple users can enjoy all the benefits of being Windows users, but with cooler, whiter hardware. So, it seems that Safe Sleep mode has a bit of trouble, which is kind of understandable, since it's a relatively new feature with OS X. Windows, on the other hand, has had Hibernate for a long time and it works so well there that it's turned off by default and can only be enabled by digging through three or four dialog boxes. With the advent of Vista, Sleep mode is enabled by default and fails much of the time, whereas Hibernate is still relegated to the "off by default" feature set, but seems to work better than it did in XP. Apple, whose OS X system bests Microsoft's assortment of products in many ways, seems to be having similar problems with their Sleep/Safe Sleep features. As with Hibernate in Windows, Safe Sleep is not enabled by default for most machines and cannot be triggered manually [1]. In fact, Apple's official documention, "Progress bar appears after waking from sleep" , describes the feature thusly: "ensures that data stored in main memory will not be lost should the system shut down due to a loss of power during sleep mode." If you're a laptop user, it sounds like you have no choice about your Mac draining the battery while in sleep mode -- you can't force Safe Sleep in order to preserve battery life, all you can do is shut down, which means you lose your painstakingly put-together set of open applications and documents. Not cool. Benjamin, however, gushes about how cool it is that he doesn't lose his work completely, failing to see that Apple is only just barely implementing a very useful feature -- and about five years after Windows starting doing so. When Apple's broken implementation depleted his battery into oblivion, he blithely -- and without complaining -- made an appointment to bring his laptop to an Apple Store to get it fixed. What a pain in the ass; Apple should fix this broken feature as soon as possible -- it's hard to imagine the Apple laptop experience being much fun when you're constantly worrying about your battery draining out and having to hook the bloody thing up to the power supply because it was sitting around all day doing nothing and was too stupid to go into Safe Sleep by itself. Instead of noting this, Benjamin trumpets that his replacement battery -- destroyed by negligent software -- was free, but only because it was under warranty. If you're out of the one-year warranty period, you're stuck buying a rather expensive laptop battery if you forget to "shut your Macbook down completely if you don’t plan to use it for more than a few hours." This blindness to Apple's difficulties is exactly why the Apple Faithful have a bad reputation. A well-known pillar of the Apple development community doesn't make a peep as his laptop melts down and forces him to take off precious time getting it fixed. Instead, he calmly accepts the fate of shutting down his laptop anytime he isn't going to need it for a few hours -- as if it was 1997 again. A problem that would be a deal-killer for Windows-related hardware is shrugged off as no big deal, simply because it comes from Apple instead of Microsoft. That's hardly any way to pressure Apple into solving this rather serious problem. -------------------------------------------------------------------------------- [1] See "How to Safe Sleep (Hibernate) Your Mac" by Andrew Escobar for more information about playing with Safe Sleep on your Mac. It's all very hacky right now, but there's also more information available here, "Hibernate on your non-brandnew Mac" ]]> https://www.earthli.com/news/view_article.php?id=1572 https://www.earthli.com/news/view_article.php?id=1572 Mon, 02 Apr 2007 21:55:37 +0200 in their stable, including the Rolling Stones, Robbie Williams, Pink Floyd and The Beatles -- announced that their whole catalog will be available on ITMS without DRM and at twice the sound quality of other offerings for a mere $.30 more per song. Album prices will stay the same and all previous purchases are available for upgrade. In other words, this is the exact kind of deal that FS/OS has been demanding [1] for the last five years. Except for the whole "paying for music" part of it, of course. This is really good news and we should all hope that EMI cleans up so other labels will follow suit, consigning DRM to the dustbin of history. Here's where the pettiness of the FS/OS movement rears its ugly head, though. Instead of just flat out commending Apple and EMI for a step in the right direction, Doctorow let the following turd drop onto his blog: "I could not be happier right now. I really hope Apple decides to make a web-based version of the iTunes store so that I can buy iTunes tracks in future using Ubuntu Linux" Did you see it? Did you catch it? That's called a backhanded compliment. It's so petulant and sniping, saying "Way to go, Apple, I guess ... but I'm still going to be a whiny bitch because you're not supporting a platform that is not only in direct competition with yours, but is also used by almost 3 dozen people on the planet." I'm sure Doctorow would respond that he's lowered his goals from a full-fledged Unix client, for which an internet petition gathered literally hundreds of signatures, of which at least 50 might even have been real. He's only implying that Apple should move their whole ITMS to the web instead of embedding it into their mind-share improving iTunes application. Then he's implying that Apple is shirking its duties until ITMS runs on his browser of choice on his operating system of choice. What a dick. Will FS/OS ever be happy? Perhaps, but only once Apple has proved that it's not profiting in any way from the services that it provides ... by going out of business. -------------------------------------------------------------------------------- [1] And a lot of other people, for that matter. Though Apple sells a tremendous amount of music through ITMS, there are still a lot of people reluctant to buy a lot of DRM music. The next few months will show just how many of those there are. ]]> https://www.earthli.com/news/view_article.php?id=1565 https://www.earthli.com/news/view_article.php?id=1565 Tue, 20 Mar 2007 07:29:22 +0100 has more information, but it basically boils down to: "Although the manipulation itself isn't necessarily illegal, securities laws require that companies properly disclose the practice in their accounting and settle any resulting charges." That's it? Just a little tax-auditing error? Really? It's hard to say, of course. if Disney/Pixar/Apple is determined to let it go, then there's not much anyone can do about it. There is much that in the legal system that a layman would consider illegal, but is, instead, only highly immoral and unethical, but perfectly legal. Steve Jobs was jubilant, as evidenced by his blog entry, "Watch me make an options scandal disappear!" "Disney's official report is out. The verdict: I'm innocent. No harm, no foul. Were options backdated? Yes. Was I the largest shareholder? Yes. Was I running the company? Yes. Am I to blame? No. Does this make sense? Absolutely." ]]> https://www.earthli.com/news/view_article.php?id=1549 https://www.earthli.com/news/view_article.php?id=1549 Sun, 18 Feb 2007 21:57:18 +0100 . Browse on over to see more! -------------------------------------------------------------------------------- In "part one" of this article, we discussed improvements to the user interface and basic applications like Windows Explorer. In this second part, we take a quick look at some usability issues associated with installation, networking and security. Networking Accessing known networks is snappy and pretty easy, taking advantage of an explorer that actually seems to use threads (shocking!) One down side is that, somehow, networking support isn't as robust as that in OS X. A laptop that shows up fine on OS X's browser simply never displays in Vista or XP. Typing in the path of the shared folder on the laptop directly pops open the expected window immediately (user/password were even the same), but the laptop remains steadfastly unbrowsable. That's a pity because it's not likely to get any better, as Vista is the pinnacle of 5 years of work. If Vista can't see XP computers on the same network now, it's likely that Microsoft has simply given up trying. User Account Control You know that new Apple commercial? The one where the PC guy is accompanied by a secret service agent asking him to "cancel or allow" actions? Right on the nose. Apple isn't being mean ... and they're not exaggerating. It's conceivable that this constant nagging settles down after a while, but during initial installation the screen is nearly constantly going black, then 50% black with a dialog asking you to confirm an action. OS X has the exact same mechanism, but asks much less often. As many of Vista's questions are prompted by the need to change registry keys, one can only imagine that it's the more monolithic nature of Windows itself that is to blame. As it turns out, the blacking effect has less to do with a non-optimal effect and more to do with the security mechanism. Vista is actually switching to a different desktop in order to display this dialog within a completely different context -- one from which only a user response is accepted. This prevents rogue programs from faking a keypress to allow malicious action. Vista just uses a copy of your current desktop image as the background for this high-security one to fool you into thinking that nothing has changed. Unfortunately, switching desktops confuses some modern graphics cards/displays into thinking that they've been shut off, leaving the screen off for at least a second (using a Philips flat screen connected by DVI) or more, as reported by some users with CRTs that turn off completely for the desktop switch. Fortunately, you can turn off User Account Control, but then you get an icon in the task tray telling you that you are a very bad person. You can also turn off the icon; however, doing so also turns off messages about out-of-date security or virus definitions. Much more useful would have been the ability to temporarily escalate privileges for a given context. The sudo command in various flavors of Unix have done this for years, while OS X translated this to UIs by putting a lock icon at the bottom of windows with operations that may require escalated privileges. Click the lock to log in once and have full administrator rights until the window is dismissed. That strikes a far better balance between security and usability than the current implementation. Who knows? Maybe Apple patented it and Microsoft was too proud to license it. Whatever the reason, for anyone making heavy use of their administrator capabilities, leaving User Account Security on is not really an option. Hardware Requirements Vista runs nicely on a brand new machine -- purchased for just over CHF1100, or just under $900 -- and Aero Glass works great with the built-in NVidia card. Since there are 2GB of RAM installed in the machine, but Vista reports on 1.8GB to be available, it can assumed that the graphics card has reserved about 200MB for itself. The effects are all quite smooth, even though, with a performance rating of 3.0, Microsoft warns that Vista may have problems at resolutions over 1280 x 1024. Installation Installation is also relatively smooth and question-free, though it does take quite a while to finish. With only an upgrade CD available (as part of the Microsoft Action Pack), one is required to install twice in order to avoid installing over Windows XP. All together, that's over an hour spent on installing the machine. Here, Vista stumbles with by introducing itself in a not-very-reassuring way. Just in the first few windows of the installer, the user is faced with a UI that is clearly not Windows; it behaves differently in subtle ways and exhibits many of the idiosynchracies of it predecessors: * Drop-downs don't respond to multiple keypresses, so you won't find Switzerland by typing "swi". You end up on "India" (or whichever country starting with "I" comes first). * The back button in what is clearly an installation wizard is no longer to the left of the "next" button, but is inexplicably at the top left corner of the window. The windows explorer also has it's back button there, but you have got to be kidding me. How did this pass usability testing? It's clearly the work of dozens of managers ignoring their designers to make sure that they "deliver" the Vista "experience" right away. * Returning to the very first screen reveals that the installer isn't even capable of remembering the language selection made just one screen ago. Another screen doesn't remember the time zone selection.This is simple stuff. Basics. Restoring user values. UI 101. * Speaking of time zones, why does it sometimes default to Switzerland and sometimes default to Redmond? Why doesn't the pretty analog clock update when you change the time? The installer seems to be an exception because Microsoft has clearly made an effort to actually store user settings so that windows open back up where you left them. The welcome screen is an exception here, resetting which areas are revealed and hidden every time it is displayed and resizing itself, too boot. The infamous "Services" control panel also still doesn't remember that you'd rather have the standard view than the extended one. The weather gadget defaults to Redmond instead of somewhere in the local area. These are trifles, though, in comparison to what seems to be a solid release. After almost a week of use, it's still fun and has enough advantages, perks, glitz and glam to distract from some of the things that don't work so great. It's a remarkably solid effort from Microsoft and many of these wrinkles will likely be smoothed out in future service packs. That, probably more than anything else, if what they've copied from Apple: enough of Vista is done really well that users will stay distracted from the things it doesn't do well at all. OS X is also not perfect, but it does enough things right to make it bearable -- Vista seems to have joined that club. ]]> https://www.earthli.com/news/view_article.php?id=1543 https://www.earthli.com/news/view_article.php?id=1543 Sun, 18 Feb 2007 21:56:51 +0100 . Browse on over to see more! -------------------------------------------------------------------------------- Past experience has shown that, while the initial reaction to the initial release of a Microsoft product can be very good, that curve degrades with time. With early versions, replace the verb "degrades" with "plummets". Early on, the superficial glitz has the most power to distract from the deficiencies. Vista is far from an early version, coming as it does at the end of a long line of predecessors of Microsoft's flagship product. As it stands, Windows is over a quarter of a century old. For Vista, however, the hype machine rolled out in a manner unlike any since the release of Windows 95 was supposed to change the world. As with that momentous release a dozen years ago, Vista arrives astoundingly late, touts far fewer features than were originally planned and purports to change the world by giving Windows users many of the features the other 5% have been enjoying for some time now. However, since the just-installed glow hasn't quite worn off, let's stay positive and as objective as possible. Let's see what it actually does. Aero Glass Vista is very, very pretty. The prettiness is more than superficial, as with its predecessor, XP, which quickly dropped you back into the Windows 2000/Windows 98 world as soon as you opened something a little off the beaten path. Like a control panel. Vista has got it just right, offering an experience at least as delightful -- as far as subtle effects, shading and hinting are concerned -- as the current version of Aqua. Windows fade in and out convincingly, as do all manner of transition changes. The full-screen compositor releases users from having to choose between no on-screen gesturing at all and the often-jarring, ham-handed approach taken by XP. Vista wows with a lot of little things: when you select a folder with photographs in it and drag it, you see a larger "drag" icon of a folder with a couple of picture in it. Look closer and you see that your pictures have been rendered into the composition. It's just a little thing and purists will argue that it has nothing whatsoever to do with functionality. They are wrong; it is exactly these little things that have let OS X get away with shipping a sub-standard Finder for years. Start Menu [image]Though the in-place Start Menu has caught flack from other reviewers [1], it's probably a godsend for those without exquisite mouse control, capable of smoothly navigating large fields of menus. The XP start menu was also just slow, so the searchable menu is a nice change. The Vista menu is much more plain looking, with a single icon on top, reflecting the currently highlighted choice. Anyone serious about quick application navigation, however, will just get "Launchy" and be done with it. It's an excellent addition to XP or Vista. Gadgets [image]These are small applications that live in the Windows Sidebar, showing weather, time, date and other information. The screenshot to the right shows a notepad and an RSS feed reader (though it only supports Microsoft Newsfeeds). Though some have called it distracting, with a wide enough screen, it's a pretty nice compromise between Apple's Widgets layer -- which only displays on command -- and full-fledged applications. Look for Apple to steal this idea right back from Microsoft (though an application called "Amnesty" already more or less does this for OS X). All-in-all, a cool addition that is actually useful and pretty easy on the eyes. Switching Applications Window shuffling (Windows Key + Tab) is a neat-looking trick, but it remains to be seen whether it will be worth using. Alt + Tab shows thumbnails of each running application to help you find what you're looking for and updates them in real-time! If you hold Alt + Tab for a while, you can watch Flash animations play in open browsers or progress bars inch forward in installers. These thumbnails also pop up above a task bar item along with a tooltip with the full application title. That it doesn't work for minimized windows is the only drawback -- is there really any reason why Vista couldn't just keep a copy of the last bitmap it displayed here? At any rate, this is quite handy for those applications that have multiple windows open, but have less than useful window titles. In a nod to OS X's Exposé, click any window when you're showing the list with Alt + Tab to go directly to that item. This is considerably easier than circling around if you miss your application (yeah, some of us have literally dozens of things open) or twisting your hand around to go in reverse by hitting Shift. 3D Shuffle also responds to clicks to select a windows, but lack any visual cue while hovering over different windows in this view. This is likely something that will be addressed in an update. Windows Explorer [image]The Windows Explorer has gotten what looks to be a worthwhile upgrade. Navigation has changed somewhat, with the "up one folder" button having been replaced with a chain of parent folders in the address bar. Click on a folder to jump back to it. Click on the drop-down arrow next to it to see other children of that folder. It seems pretty usable and extends OS X's column view with the added ability to jump sideways through the folder structure. Again, time will tell how useful this extra functionality is. On top of that, Microsoft bit the bullet and added the OS X/NextOS-style list of favorites on the left side. For newer applications, this also shows up in the open & save dialogs as in OS X. Older applications have the old-style dialogs without the new links, leaving you at sea if you've gotten used to choosing one of your favorite folders as a starting point. Similarly, the "choose a folder" window also lacks access to these links, which is a shame. Network access is finally implemented asynchronously with a cancel button and everything; the explorer window isn't blocked at all! It also blocks noticeably less when extracting meta-information or generating enhanced views. A view with a list of 3000 MP3s scrolled normally, displaying empty column values where it hadn't had the chance to extract artist or album information yet. The same went for a folder with almost 3000 icons and small pictures: normal scrolling with explorer filling in thumbnails as it was calculated. There is a lot of polish here, with a clear information area at the bottom of the window, showing combined attributes for the selection and a toolbar at the top, showing the most important operations available for the selection. This will save a lot of right-clicking for most people. Rename a file and only the name -- not the extension -- is highlighted. Adjust properties for a shortcut and you get a drop-down with potential matches. These are little things, but they're nice and should make users more efficient. At any rate, the explorer is much, much better than that in Windows XP and reassuringly better than the usability nightmare that shipped with the first beta of Vista. So far, it's my primary file browser, unlike in XP, where I switched to "xPlorer2" . That ends part one, which covered user interface impressions of Microsoft Windows Vista. See "First Days with Microsoft Vista, Part II" for impressions of installation, networking and security. -------------------------------------------------------------------------------- [1] On general principle, in at least one case: "Vista first look: Bugs and confusion" by Thomas C Greene ]]> https://www.earthli.com/news/view_article.php?id=1531 https://www.earthli.com/news/view_article.php?id=1531 Mon, 15 Jan 2007 22:11:55 +0100 (Outlook 2007 change sends HTML email back to the future, for better and worse), "e-mails that use certain advanced HTML and CSS features will be somewhat degraded in appearance in Outlook 2007". Naturally, that depends on what you mean by "advanced" -- users of background pictures and floating and positioned styles are out of luck -- and "somewhat degraded" -- content that expects to be positioned will be formatted down the page instead. Any other IE embedders out there, take note: Microsoft is officially too scared to use their own browser because of security reasons. They didn't exactly put it that way, phrasing is instead thusly: "Microsoft's says that the change actually introduces stability in the end user experience, for previous versions of Outlook would render emails differently based on what version of IE was installed on a local system." [image]The status quo sounds horrible: some users saw a properly formatted version whereas others saw a slightly altered version (e.g. users of IE 5.x, which had less CSS support). Outlook 2007 guarantees that everyone has a poorly formatted and hard-to-read version, which introduces the kind of "stability" that we've come to know and love from our favorite monopolist. It's absolutely amazing what Microsoft seems unable to achieve with their armies of programmers: how hard would it be to get Word to understand the few missing CSS positioning properties? Are they really so terrified of touching their own source code? A pity, really. Recent exposure to the latest release of Outlook (2003) revealed it to be quite a top-notch email client in terms of usability. 2007 promises even more, as seen in the screenshot to the right. Outlook has an uphill battle if it wants to prove itself a secure email client -- is it worth throwing away their hard-won usability and user-comfort in this quixotic pursuit? ]]> https://www.earthli.com/news/view_article.php?id=1458 https://www.earthli.com/news/view_article.php?id=1458 Thu, 07 Dec 2006 23:03:11 +0100 , by one of the designers of the same feature in OS X (which hasn't changed in 5 years now). [image] After first sympathizing with Microsoft that managing a product as big as an operating system is incredibly difficult -- and mentioning that Copland's problems were in large part "due to an inability to manage this complexity" -- he concludes by saying that, at Apple, "full builds of the OS [can] be done reliably every week", so their release process is run quite a bit better than Vista's. As Spolsky did, he "argued against including Restart, Shut Down and Sleep" on the menu, with many of the same arguments. [Restart] As before, the argument against Restart is a good one, though a commenter said it was useful for two reasons: 1. Restarting a misbehaving machine and walking away, knowing the login screen will be up on return. The average user (author included) using a current version of OS X has absolutely no need to restart that damned often. [1] 2. "If you are using Remote Desktop or VNC to manage your machines, you probably do not have physical access to the power button, thus you need to be able to reboot a desktop or server remotely (not just shut it down)." Ok, that's a pretty good argument, but still, this type of user is pretty rare as well. [Sleep] The argument against a Sleep command being readily available is less clear: "And finally, how often do you need to manually set your computer to Sleep? I just close the lid of my MacBook and it goes to sleep: a simple mechanical, physical interaction: no need for a software command. On desktop systems, Sleep can be triggered automatically after enough idle time has elapsed." In a perfect world, the computer puts itself to sleep on schedule and as specified in the energy saver preferences. However, OS X is much gentler with auto-sleep than Windows, in that it allows applications that are busy doing something (like downloading a file or playing music) to prevent the machine from going to sleep automatically. This is a wonderful feature, but can bit you in the ass when an application is misbehaving and keeping the machine artificially awake. In this case, the manual Sleep command allows the user to override this behavior and force an application to stop doing whatever it's doing. [2] [Log Out] Automatic inclusion of the Log Out command is somewhat strange, as most machines are single-user and this command is probably rarely used. Though Spolsky argued that this command can be wholly replaced by "Switch User", that's not exactly true. If there are multiple users logged in to a machine, every user but the last needs some way of saying that they are finished working -- without triggering a shutdown. On OS X, a command to Shut Down when there are other users logged in issues a warning to go save work and log out of the other users first. Perhaps this is why it was featured, so that the user would know how to perform the action requested by the OS. As Arno mentions, it's a complete mystery why Senior VP felt that there had to be a default shortcut for this command. [Shut Down] Granted, laptops are quite easy to shut down with a simple button press, but desktop models are not necessarily so accessible. Both the Mac Mini and the iMac have their button on the back of the machine, and the Power Mac is generally under the desk and not as convenient to access as issuing a command in the UI. For the PowerBook--less of the world, the Shut Down menu has to stay. -------------------------------------------------------------------------------- [1] I just did a system update over the weekend and it was the first time I'd shut down in 65 days ... on a Mac Mini with scads of applications open all of the time. Restart is superfluous. [1] To put OS X to sleep manually without using the mouse, use Cmd + Opt + Eject. ]]> https://www.earthli.com/news/view_article.php?id=1477 https://www.earthli.com/news/view_article.php?id=1477 Tue, 05 Dec 2006 21:29:12 +0100 tells us that Steve Ballmer is all agog over Vista. Hardly surprising considering the source, who's widely known as "monkey boy" throughout developer circles for his excitable antics. Drinking your own kool-aid is almost never pretty, but Steve takes a big 'ol swig for us: "Asked about the timeline for Vista service packs, Ballmer quipped that as it is the highest-quality, most secure and reliable Windows operating system ever, there should be no need for a service pack." *Stunned silence* Oh. Good one. Right up there with the guy who jokes about beating his wife ... when he "really does" (Abusive Husband Has Sense Of Humor About It). ]]> https://www.earthli.com/news/view_article.php?id=1469 https://www.earthli.com/news/view_article.php?id=1469 Sun, 03 Dec 2006 23:16:12 +0100 , it's more or less true. More accurately, companies will have to keep track of every scrap of digital detritus that may be needed in possible future lawsuits. "The rules, approved by the Supreme Court in April, require companies and other entities involved in federal litigation to produce "electronically stored information" as part of the discovery process, when evidence is shared by both sides before a trial." That is, companies have to spend money putting systems into place to maintain data that will only be needed in case there's ever a lawsuit against them. Already, there are complaints that precious attorney time is spent sifting through emails about "office birthday parties in the pantry". Somehow, the innovators behind this law see a way out of this by accumulating more data, assuming that this regulation will force companies to make their data more organized and searchable. Fat chance; who the hell's going to invest heavily in maintaining a system that makes it easier for you to get sued? "Under the new rules, an information technology employee who routinely copies over a backup computer tape could be committing "virtual shredding" once a lawsuit has been filed" Thus the title of this article: storage solutions companies must be simply slavering at this news. Since it's already gone to the Supreme Court, it's a done deal and companies have no choice but to fall in line, but it doesn't seem that they thought it through that well. The problem of data these days is that there's just too bloody much of it; there's a lot of noise to signal and it's getter harder and harder to categorize it correctly so that you can find the signal you were looking for before you go bankrupt. How exactly does this get better by demanding that we keep every last bit of every version of every document, message or communiqué produced by a company? This idea likely sprung from the same mind that envisioned "Total Information Awareness", the program that sought to bind all data from all intelligence services together into a national database (I'm looking at you, Dick Perle). It worked like a charm, of course, and has helped convict zero terrorists so far ... but any day now, of course, it'll turn right around. Even on the smaller level of a single company embroiled in a lawsuit of one kind or another, the sheer amount of useless data is staggering; lawyers doing discovery have as much chance of finding anything salient as finding the proverbial needle in the haystack. There are other open questions about a company's data obligations: 1. What are the guidelines for searchability? 2. How organized must the data be? 3. Is the company really obligated to keep even sensitive data, which costs much more to store and protect, regardless of whether that data could ever be required? 4. Which formats are required/supported? 5. Is there really no expiration date past which records are no longer required to be kept? Companies are disorganized enough as it is -- spending incredible amounts on IT infrastructure -- how exactly is this going to work? Or is it like parking fines? The government makes ridiculous rules that are bound to be broken simply in order to collect fines when companies fail to comply with electronic discovery rules. In the end, it comes down to how much potential future fines cost (amortized over expected number of years between lawsuits) versus how much it costs to store the extra data over those same years. Either way, the costs could be astronomical, but that's probably part of the point. Since the US is now almost pure service industry, it's a good way to goose the economy a bit by making laws that force one part of the economy to provide work for another part. Net national earnings don't change as money transfers internally, but at least the money's moving and the economy looks healthier. ]]> https://www.earthli.com/news/view_article.php?id=1447 https://www.earthli.com/news/view_article.php?id=1447 Sun, 26 Nov 2006 20:48:23 +0100 has found a perfect use for Ajax, testing the domain name you've typed as you type it and showing the results for .com, .net, .org, info, .biz and .us below. There are other tools as well, for searching all domains containing a certain "word" or domains with "high traffic" . ]]> https://www.earthli.com/news/view_article.php?id=1444 https://www.earthli.com/news/view_article.php?id=1444 Thu, 23 Nov 2006 22:49:06 +0100 , starts with the following screenshot of Microsoft Windows Vista: [image] From there, he launches into a diatribe on a surfeit of choice. It's pretty well-written, as usual from Mr. Spolsky, but somewhat poorly aimed, also as usual from Mr. Spolsky. The basic premise is a good one: don't provide more choice than your customers know how to deal with. Provide just enough and no more. Extra functionality should be available to those who need it and no one else. His analysis is spot-on, but he fuels it with astonishment that Microsoft would create such a monstrosity as the popup menu displayed above. In the end, he narrows the menu down to one feature, a "B'bye" button, with which the user can indicate that they are leaving the workstation. This locks the user's account, making the system ready for another login (obviating the separate "Log Off", "Lock" and "Switch User" features above). System settings determine when the machine automatically enters "Sleep" or "Hibernate" mode. "Restart" is deep-sixed because nobody really needs it (it's only really required by installers, which provide it anyway) and "Shut Down" similarly because why would you ever not want to Hibernate? In reality, the "Shut Down" function is necessary because most non-technical users (which is most users) need to know that the machine is off. Perhaps they can be weaned off of this dependency, but for now, it's still necessary in order to keep support calls down. All the other stuff Spolsky said makes sense though. "Shut Down" is a dumb name name, though, so Microsoft should just change it to "Turn Off". The "B'bye" feature above could be realistically named "Take a Break". However, Spolsky's sputtering rage is completely unjustified in this case. Take another look at the Vista screenshot above, but imagine it without the popup menu. That's right: Microsoft already did this analysis and came to the same conclusion. The little arrow on the right provides a popup menu of choices for the geek (else review after review would complain that Vista has less functionality than XP), but the two main choices are featured prominently on their own. Granted, the "lock" icon is misleading and both buttons would be better served as text than icons, but there is nothing else wrong here. The problem of explaining to a tyro how to turn off Vista is a non-issue. At best, there should be a switch for eliminating the popup menu entirely for novice installations. ]]> https://www.earthli.com/news/view_article.php?id=1435 https://www.earthli.com/news/view_article.php?id=1435 Wed, 15 Nov 2006 23:22:04 +0100 : "In person, the device has a rich, warm color. The green tinge is innovative; I've never seen a consumer electronics device that tries for such a complicated, organic palette, and it's pulled off wonderfully. But instead of calling the color chocolate, or something else compelling and attractive, they named it brown, a color that has few positive associations..." Regardless of nitpicking about marketing of the device and its color array, let's get a favorable review in here. "Sharing the Sharing" likes the brown as well: "My favorite color is the brown. The pictures don't do it justice. But when you're holding it in your hand there's this warm, vintage look to it, like you're cuddled up to your grandparents' hi-fi, dropping needle to Herb Alpert groove." Essentially, the device looks cool in brown. [1] Microsoft's marketing department, however, is just incredibly ham-handed when compared to the current market leader. And that's just it: with Apple already doing such a slick job, how is it possible for Microsoft, with its troughs of cash, to fail to knock our socks off (once again)? It's not even that. It's not even achieving adequacy. People are laughing. Continuing in this vein is a recent report called "Microsoft's Zune released" . The link leads to a video showing a review that veers quickly from the Zune to the iPod. It begins with a quick rundown of the salient features, including the Zune's lone distinguishing innovation -- the ability to beam songs to other Zunes. Even this feature is covered in a none-too-flattering manner, detailing the short sharing period -- three days or three plays, where a play is counted as soon as you start listening -- and the fact that you have to ask to download the song in "meatspace" . After this introduction, the reviewer is asked: [CNN anchor] Who do they think is going to buy this? ... Can I show you my new Shuffle? [reviewer] You see now that's the thing right there ... that's a lot sexier than this [Zune] [CNN anchor] Look at this: it weighs nothing, literally the size of a matchbook and weighs as much ... 70 something bucks! [reviewer] Microsoft will, in the end, come out with something ... well, I don't know if it will be that pretty ... isn't that neat? My God ... [other anchor] Why don't they get some decent design people that can make things look better? It's clunky. ... Jesus. And these are people being paid to chat up the Zune -- not like the reviews written by die-hard Apple fans circling in the waters, smelling blood from a mile away. [Wireless and Sharing] Coming back to the wireless feature, as recently as the middle of september, "J Allard Calls iPod the Pong of Digital Audio" , asked the head of the Zune team "...am I really going to troll Wifi for other people's music? What is that going to do for battery life?" The response just two months ago was, "It's a tough problem, and we're not done with it yet." Good luck with that, early-adopters of the Zune -- the wireless feature sounds like typical Microsoft 1.0 stuff. And the song-sharing is even more limited than you thought, because: "The drawback to the sharing function is that ALL MP3s get chained with DRM. ... even [if] the band wants you to have it no strings attached, you only have three plays/days to enjoy it. After that, you'll have to go download it yourself." So, essentially, have fun scrambling to keep the device charged and have fun scrambling to keep the Zune from deleting your music. [Getting Installed] As expected, Microsoft has released plugins for iTunes and WinAMP (with other to follow) that integrate and synchronize the Zune with popular music players. Yeah, right. They've got their very own player, with their very own installer and their very own music service. In fact, as mentioned in the CNN review, music you already bought from MSN or Napster or Apple will not work with the Zune or its software. In fact, according to "MSN Music to go silent once Zune launches" , all existing users will have to start shopping in the Zune Marketplace. Since it's Microsoft 1.0 software, it's got a few rough edges. Even gadget freaks couldn't forgive this alpha-quality stinkbomb: "Installing the Zune... sucked" has all the gory details. They wanted to like it: "We hoped installing the Zune software and getting our player running would be as seamless and painless as getting iTunes and an iPod running on your machine, since that is, after all, what it's up against." ...but were treated to a nearly endless installation process, including a completely non-standard installer and minute-long pauses with no user feedback. The fun didn't end there; it included such bumps in the road as the installer informing you that your brand-new Zune "already has a home on another PC" and crashing immediately if you do anything but "[c]onnect this Zune as a guest". Things continue in this vein as Windows refuses to plug-and-play nicely for a few attempts before you're allowed to try installing again. The installer informs the user several times that all settings can be adjusted later in the options, but the reviewer couldn't get the options to show up at all: the software crashed every time. [2] Update: The "Zune Review" is a comprehensive look at the device and its software. The battery life capped out at around 12 hours with wireless enabled, but no actual sharing of files. The software? "Was it still buggy? Yes. Did it still crash? Absolutely. For example, syncing video for us crashed the app twice, and then stalled the third time at 38%." Tens of thousands of engineers and not a single one of them can get the software for their flagship product to do the basics expected of a media application? Are you kidding? How about plug-and play? C'mon on, Microsoft! You can do it! "Never before have we done so much device plugging and unplugging. When you finish adding files to your Zune, you can't go back and drop in more. You cannot interact with your player until you unplug it, and plug it back in. While it's plugged in you can't interact with it; with the Zune there's no such thing as listening to music out of the player and charging via the sync cable at the same time. We couldn't play music off the device through the application, either. When your Zune is plugged in, your Zune is absolutely nothing but plugged in." Ouch. There's a lot more information -- including some actually positive comments sprinkled throughout the review -- and there are a lot more pictures -- including side-by-side comparisons with the current iPod generation. Oh, and one more thing, "Zune incompatible with Windows Vista" . Way to coördinate your product line, Microsoft. [Branding] The installation includes lots of big, splashy background graphics of cool kids doing wicked cool things, overlaid by suchy pithy phrases as "Welcome to the social" and "Free your inner dj". Who exactly is their target market? People who like using installers? Why does Microsoft love the idea of installing? They jazz it up so much that you can't ignore it. Contrast that to the Apple approach, which makes installation so innocuous that you're using the application before you know it. Here's a peek at the installer: [image] Wow! Microsoft thinks that guy is cool? Exactly which kind of market identifies with this? Not only that, but that's the mandatory registration form -- claims that it's optional were not borne out, as the software crashed without a word when used without registering. Note that the phone number is not an optional field. Wheeee! Other parts of the installer were a bit scarier, as reported in "Zune install screen raises eyebrows" . The installation error screen looks like this: [image] "Are we meant to think of this girl as singing along excitedly to a song that's being played on loud speakers as she's clearly not carrying a Zune and has no earbuds in? Maybe. ... Is this girl in excruciating pain, perhaps someone is jabbing her with a pitchfork or some terrible music is playing ... [or] Could it be that the girl is being pleasured by an off-screen person (her own hands are visible) and that she is bordering on a hefty orgasm?" And you thought open-source software had weird branding. [Buying Songs] Buying songs is also not so straightforward, as Microsoft only accepts their own currency, not cash. You can't just plunk down 99 cents for a song, paying with a credit card. You have to open an account and buy a block of points, which can be used to purchase content. On top of that, you can only buy points in $5, $15, $25 or $50 amounts. "Zune Marketplace's Absurd Pricing Scheme" by James R. Stoup gives more detail: "You see, when you buy these 'points' you can't buy them as you need them, you have to purchase them in Microsoft defined denominations. In other words, Microsoft just invented a currency and they require you to invest in this currency before they can sell you any music. ... In effect, Microsoft has created a store that only accepts gift cards as the valid method of payments. And if you don't think thats insane then you obviously already have pre-ordered your Zune." It's pretty clear from all this that Microsoft has a deep-seated disdain for its customers. Even the exchange rate for points is ridiculous: it's currently pegged at $1.25 per 100 points, so a 79 point song is -- you guess it -- about $.99, just like the iTunes store. Microsoft also apparently thinks people are resoundingly dumb, as well. Seeing as how Windows has a 95% lock on the OS market, they have every right to think that. [3] [Conclusion] The Zune is "clunky", the software "sucks", wireless support is "not ... done" yet, and you have to invest in "Microsoft points" to buy songs, which disappear after "3 days" when shared. But brown is cool. Oh yeah, and one last thing. The rollout? Managed to "perfection" . [4] -------------------------------------------------------------------------------- [1] It's my favorite color as well. Mixed with the green, it's a welcome change from the electric blues, greens, pinks and so on. [1] "I'll have the schadenfreude with a side of irony, please" by Macalope points out that though it was "World Usability Day" , Microsoft were not an official sponsor. So they dodged that hypocrisy bullet. [1] Couldn't resist. [1] The link to zune.com, at the time of writing, led to a single page announcing "Listado de directorio denegado: Este directorio virtual no permite listar contenidos." ]]> https://www.earthli.com/news/view_article.php?id=1367 https://www.earthli.com/news/view_article.php?id=1367 Mon, 28 Aug 2006 22:04:49 +0200 , results in either a "Video Not Found" or "Cannot Install Driver" error. No shit, "Video not Found" ... that's why you should install it. "Install a VGA driver first ..." is the recommendation from ATI, but Windows XP doesn't offer that as an option anymore. 12. Fine. Last resort. Delete the display adaptor directly from the list of hardware and reboot. Hope that Windows will install the VGA driver from it's secret, magical pile of drivers. 13. It does. Back at 16-bit color and 800x600, which is a definite improvement. But now the ATI installation has magically started again and can't find the files it needs. Redirect the hapless setup to the extracted files on the C:\ drive and hope for the best. Reboot. 14. 4-bit. 640x480. 15. Delete the display adaptor. Reboot. 16. 16-bit. 800x600. Ignore and cancel all messages from ATI. Computer is stable and the resolution can be increased to 1400 x 1050. Watching the default VGA driver react to the mouse wheel is marginally more exciting than watching paint dry. 17. Start the ATI installer again. Mobile driver is not compatible. Standard driver is not compatible. Hacked installation proceeds much farther, but the installer can't remove the current driver because Windows won't let it. 18. Ok. Fine. With a little more screen space, it's now possible to navigate the manufacturer's web site -- Acer -- and find the original driver. Download that and start the installation. Against all odds, it works and installs itself, granting full resolution at a non-laughable speed. However, the ATI icon tray utility to quickly switch resolutions is not installed. 19. On a lark, try the hacked installation again ... and it works too. One tiny little reboot later and the laptop is back where it was these many, many hours ago. [1] Note also that throughout this experience, Windows XP is at 640x480 and it's dialog windows are not exactly designed for this resolution. In most cases, the Ok and Cancel buttons are hidden offscreen. ]]> https://www.earthli.com/news/view_article.php?id=1324 https://www.earthli.com/news/view_article.php?id=1324 Wed, 21 Jun 2006 21:02:48 +0200 is a plugin for the Terminal from the same people that brought you "Quicksilver" , the navigation and search tool many people swear by. Basically, you install it along with another extension, "SIMBA" . Though the installer puts everything in the System/Library folder, moving them to ~/Library as indicated in the instructions works fine. You can configure the terminal window displayed by Visor with special settings; note that the screenshot has a semi-transparent window, even though the standard Terminal window does not. If you elect to run a quartz animation (there are several in /Developer/Examples/Quartz Composer/ if you have XCode installed), you need to make the window semi-transparent or you won't see the animation. The transparency controls the animation composition instead of the window composition. -------------------------------------------------------------------------------- Yeah, that is my desktop (Ymir is the name of my Mac Mini) in the background, including my embarassingly huge list of open windows in Opera. ]]> https://www.earthli.com/news/view_article.php?id=1315 https://www.earthli.com/news/view_article.php?id=1315 Fri, 09 Jun 2006 23:52:23 +0200 introduces an online tool for creating art out of HTML code. The "online version" of the grapher accepts a URL and then retrieves and processes the page, tag by tag, building a graph, which displays the connections and nesting. The graph is built in real-time, but deliberately slowly [1], so that it starts with a few large nodes, then seems to zoom out as more nodes are added. As new branches lead to more and more clusters of nodes, the branches "wave" around to get out of each other's way and detangle slowly and elegantly, like an anemone in a gentle current. Click the link to watch it generate "earthli's home page" , shown to the left. Links are blue, tables are red, boxes are green, forms are yellow and paragraphs are orange. The "source code" is in Java and is freely available. It's only a few hundred lines and leans heavily on some external Java physics and rendering libraries. It's an excellent example of the power of base libraries that provide such capabilities in a straightforward and easy-to-use way. Compiling and running the code, however, can only be done with "Processing" , "an open source programming language and environment for people who want to program images, animation, and sound". It runs on Windows, Mac OS X and Linux. [1] I'm assuming it's deliberate. The source code has a few calls to tick functions that must increment the physics model. Not sure whether it also pauses for a little while. Otherwise, this demo is a good argument for those who say that Java is just damned slow. ]]> https://www.earthli.com/news/view_article.php?id=1307 https://www.earthli.com/news/view_article.php?id=1307 Thu, 01 Jun 2006 00:00:07 +0200 is a good place to start to learn the latest about this version of Office. In particular, there is an article about "The "Ribbon"" , which replaces menus, toolbar and most dialogs with a context-sensitive tool area. Tools are grouped by the task for which they can be used rather than by some abstract functionality hierarchy. "Julie Larson-Green - Diving into the new Office 12" (618MB / 45 minutes) is a great way to see the ribbons for Word, Excel, Outlook and Powerpoint in action. The combination of context-sensitivity and attention to higher-level tasks -- like applying global table formats in real-time or designing a bullet list as graphics -- makes it look almost...fun. Almost all tasks have galleries of collections of properties to apply (like chart types, table types or graphic types), which are presented with large preview pictures and applied in real-time as the mouse hovers over the choices. Once a set of properties has been selected from the gallery, a user can adjust it further with more fine-grained control and then resave it back to the gallery (in most cases). Other improvements include better keyboard navigation (no more hunting for those underlines that XP took away by default) and a cool little floating toolbar that appears when you've selected something. It floats -- it's called the "Floatie" -- right next to the selection and offers the most useful commands right where the mouse is. For the faint of heart, there's a "Flash Demo" , which offers a limited simulation of interaction with the ribbon. For the adventurous, there's a "450MB download" of Office Professional available, which includes Outlook, Powerpoint, Publisher, Infopath, Word, Access and Excel. [1] -------------------------------------------------------------------------------- [1] This upbeat article was written after downloading and installing the beta, but before rebooting and trying out the product. This timing is a deliberate attempt to ensure that pre-release bubbly enthusiasm is properly recorded -- unsullied by any negative feelings engendered by the actual product. ]]> https://www.earthli.com/news/view_article.php?id=1268 https://www.earthli.com/news/view_article.php?id=1268 Wed, 03 May 2006 00:38:13 +0200 is the newest product recently released with the OS X 10.4.6 update. With it, Mac users can resize their hard drive, create a new partition and install Windows XP on it. It burns a CD with all the necessary drivers prior to Windows installation. Windows XP is not included. In order for Boot Camp to do what it does, Apple adjusted its EFI-only firmware to be able to emulate an old-style BIOS so that Windows recognizes it. They also built an initial set of Windows drivers for their specialty hardware. That's it. There is no magic; the technology itself isn't so earth-shaking. No, the interesting thing about Boot Camp is not how it does what it does, but what it does. It allows users to switch between Mac and Windows on one set of hardware. The burning question is: Why would Apple want that? [What it Means To Apple] Opinions differ as to what this means for Apple, Microsoft and, most importantly, the dear, dear consumer. Any conflicts largely revolve around the following talking points: 1. Why this product will drive users away from Apple in droves 2. Why this product ushers in the end of Microsoft 3. Apple should open-source its operating system 4. Apple should release OS X for generic PC hardware 5. Boot Camp is proof of virtualization [1] in Leopard [2] [Weaning Away From Windows] Point (1) is founded on the idea that software developers may now safely ignore Mac-native versions because they can assume that a Mac user will simply be able to run their Windows version. First of all, dual-booting is, at best, a desperate solution used only for the most direly needed software -- it is not a viable long-term solution. Second of all, the installed base of users with Boot Camp is likely to remain quite small. People buy Macs because they want a Mac; Windows computers are everywhere. The user base is different on a Mac -- we expect not to reboot for upwards of 4 or 5 weeks at a time. As the journal entry, "Boot Camp" by John Siracusa says: "Any vendor that decides to stop development of its Mac applications and directs its customers to boot into Windows and use the Windows version of the software instead is in for a very rude awakening. Mac users will not do this, and they will hate you for even suggesting it. Mac users want Mac software. Hell, even some actual Mac applications are met with an upturned nose. ... We're a finicky bunch." Some say that this snobbish attitude will lead to obsolesence for Mac users. Not so. Mac OS X has enough users -- high end users with money and willing to spend it on software -- to keep the Mac software market profitable. The release of Boot Camp will only increase this market as it removes a barrier for new users; it answers the question: "What if I absolutely, positively need to run something on Windows?" With this crutch in place, more people will make the move (if Apple salespeople are halfway competent) and discover that, after a few months, they can't remember the last time they booted into Windows. As the article "Dare I say this aloud? Boot Camp is a gimmick" put it: "Boot Camp functions as a security blanket for PC users who would wet their beds without their favorite Windows application. With one download, Apple removed any lingering barriers holding back the potential universe of switchers." [Apple's Core Business] We can discard point (2) from the outset as well. In fact, it's easy to see that Microsoft must be delighted with Boot Camp: part of their core business is selling operating systems and Apple just opened up a new market for them. For free. Users that want to dual-boot Windows XP or Vista (not yet available) will need to buy a full-priced copy since Apple is not shipping OEM copies with their machines. Points (3) and (4) are suggestions offered by the computer press to "help" Apple. Let's examine whether these business ideas hold water. You can't evaluate the wisdom of a business decision without knowing how the decision relates to that company's -- in this case, Apple's -- core business. Apple's core business is selling hardware and it always has been. The article, "Several Asinine and/or Risky Ideas..." by Jon Gruber (Several Asinine and/or Risky Ideas Regarding Apple's Strategy That Boot Camp Does Not Portend) has a good analysis with several examples. Though "Apple is famous for its software" as well as its hardware, "they make way less money selling Mac software than they do selling Mac hardware." The upshot, then, is to analyze each Apple business decision by asking how it will "help Apple sell more Macs or more iPods". In this light, it's simple to see what Boot Camp offers Apple: a leg up on the competition by offering users computers "that can run both Mac OS X and Windows up against all other PC-hardware that can only run Windows". Releasing more [3] of its OS as open-source does nothing to increase Apple's profits, so that's not going to happen. OS X is pretty, people like it, they can only get it with Apple hardware, they buy Apple hardware. Letting them download it for free so that it runs -- for free -- on almost any PC is horrible for Apple. In the same vein, selling just the OS will only harm Apple's hardware sales. Apple makes much more profit per computer than they do per OS X upgrade; they want to focus on increasing hardware market share. As Jon Gruber put it: "...gaining one percent of the market by selling one percent more of the total computers would be way more profitable than selling that many $130 copies of Mac OS X." [Boot Camp II] Point (5) is up in the air only because it is wholly unrelated to Boot Camp as it is today. Leopard's support for Windows within OS X has nothing to do with being able to boot Windows on Apple hardware. There are virtualization solutions available, and, coupled with the move to Windows-compatible hardware, they stand a chance of running much better than previous attempts ran under the PowerPC architecture. [4] However, the presence of Boot Camp neither confirms nor denies whether Leopard can run Windows in an emulation more-or-less natively. It is interesting to to follow the logic above and see what we could expect to happen, were Leopard to have such integration: 1. It would probably boost sales of Apple hardware even more than Boot Camp. 2. Microsoft would be even happier with Apple as they get to sell even more copies of Windows 3. It would cause more companies to consider dropping OS X--native versions (because, using virtualization, Windows is even easier to get to than using Boot Camp). This would likely buy time as a stop-gap measure, but would fail to last as a long-term hold on Mac users for all but the most irreplaceable of products. [5] 4. Mac-native gaming is an exception to the previous rule, expecially if performance under virtualized Windows is up-to-par [6]. Jon Siracusa, cited above, described virtualization chances thusly: "It's not even that I doubt that Apple is working on adding virtualization to Mac OS X. The question is, will it ship with Leopard? I see Boot Camp just as it's described by Apple: a beta test of dual booting. Early adopters will wring it out, the drivers will be further debugged and improved, and it'll all come together in the form of seamless, problem-free dual booting in Leopard." Further conjecture is just that. -------------------------------------------------------------------------------- [1] Virtualization is provided by software that runs processes in operating systems in a virtual environment, which is abstracted from the actual hardware. Virtualization mechanisms have always been available for running Windows under Apple operating systems -- they have historically been quite slow. With Apple's move to the same hardware instruction set as that used by Microsoft Windows, virtualization of Windows inside Mac OS X should be much faster. [1] Leopard is the next version, 10.5, of Mac OS X. It is set to be publicly previewed in August and is due for release by the end of the year. See "Mac OS X v10.5" for more information. [1] Portions of it have always been available as "Darwin". The "Apple Open Source" page has links and more information about their open source products. [1] Those versions were doomed to poor performance by the marked differences between the chip architectures. [1] A comment by Dogger Blue at "Boot Camp: Apple's Insanely Bad Idea" notes that products that are Windows-only will survive only as long as there is no replacement -- and a Mac OS X-native replacement need only be sufficient, not stellar. Companies relying on Boot Camp will find that another "developer will come along and take advantage of the fact that they have just left the door wide open for competitors." [1] Jon Siracusa notes that there is a big upside for Mac gaming with the transition to the Intel architecture, since "Mac game porters should have an easier time with CPU optimization now that they can directly benefit from the work done on Windows." On the other hand, there are still the Windows API--specific things to deal with, such as "DirectX [which] is still a thorn in the side of Mac gaming". ]]> https://www.earthli.com/news/view_article.php?id=1263 https://www.earthli.com/news/view_article.php?id=1263 Sun, 09 Apr 2006 19:56:10 +0200 provides the latest batch in what they show to be a long line of screenshots from the various Blackcomb/Longhorn/Vista incarnations from over the years. [Initial Impression] [image] [image] The basic structure doesn't diverge that much from XP, but the emphasis is on soothing pastels rather than on the jarring reds, yellows and blues of XP. Users of Mac OS X will get a nagging feeling that they've seen this look before, but that's a good thing. There's no need for Microsoft to re-invent the wheel when they can just cadge off of Apple -- especially when there are so many Mac users stuck using Windows in their day jobs. There's no need to be snarky by pointing out that the windows kind of look like brushed steel [1] as if that's a bad thing. It's better than XP's blue, by far. Most importantly, the screenshots above show that Microsoft has gotten their act together: the icons are much more soothing than in previous releases and the orgy of controls in previous incarnations of the file browser seems to be gone. The by-now-famous "Aero Glass" look that will only work on newer graphics cards [2] can be seen in the blurry semi-transparence in the title bar of the foreground window. With effects like this, we can only hope that Windows has moved to a clean window server model, as OS X did over 5 years ago. [Gadgets! Yawn.] The OS X "homage" edges closer to what some would call "ripoff" in the other screenshot, Gadgets, which shows the small always-on applications available for desktop placement. If it's a ripoff, then it's a crowded field of ripoff artists, from Apple to Yahoo to Opera to Microsoft. Widgets/Gadgets are the feature people are thought to want; it's not surprising to see them in there. [Standard Apps] [image] [image] Games and Internet Explorer shows that the graphic overhaul -- one of the few remaining features in Vista -- is at least more than the skin-deep pittance found in XP. All the games have gotten a going-over and they've even included new ones! Various articles have mentioned that even the vaunted MS Paint is new! How many more reasons do you need to upgrade? Seriously, it's nice to see that Microsoft is finally making the effort expected of such a large company and delivering a cohesive system that doesn't jar the user with a frankenstein-like combination of styles from systems past. even XP still sported some 16-color icons from the Windows NT days. In the background is the new Internet Explorer 7, which will also be available for XP. Not much to see here, except that the additions of multiple tabs seems to have pushed the designers into a madness whereby they sprayed controls all over the top of the window willy-nilly: * Want to go back? Top left. * Want to stop? Right. * Add a bookmark? Bottom left. * Search? Right again. * RSS? Right bottom. * Old menus? Press "Alt"; they magically appear. The look has "inspired others" (Stop Stop Stop Hurting the Internet) to comment: "Is it just me, or does this look like a GUI widget test demo?" [Final Words] The Start Menu looks better organized than in past incarnations, with Microsoft tentatively embracing the non-rectangular look by adding a jutting icon to the top. This brings hope to developers that the non-rectangular window API will finally be fast enough to use without having to consider the performance drawbacks. Since absolutely everything on screen is semi-transparent and systems like OS X have been doing it for years, one would hope this to be the case. All-in-all, Vista will at least look pretty good, a minor though important victory for Microsoft. What's still in the air is just when people will actually get their hands on it and which machines will be able to run the version pictured above. [1] A look that Apple has all but abandoned in their most recent releases for iLife and OS X. [1] Lest we forget, Apple doles out goodies specifically for purchasers of high-end hardware, too. The most famous example is the "ripple" effect when dropping widgets onto the Dashboard. ]]> https://www.earthli.com/news/view_article.php?id=1260 https://www.earthli.com/news/view_article.php?id=1260 Sat, 01 Apr 2006 00:00:01 +0200 was plagued throughout its many-monikered existence by delays, feature withdrawals and a heavy amount of FUD [1]. "Windows Vista slips...out of sight" (Windows Vista slips to 2007) has a full history of the troubled software: "Harking back to the days of the XP beta "Whistler", which was regarded as a code cleanup and facelift for Windows 2000, Microsoft planned the all-singing, all-dancing upgrade "Blackcomb" to be released in 2003 or 2004, with what we called a coffer-filling release to emerge in late 2002 or early 2003." Since that time, it had hemorrhaged features like a trauma patient, losing a database-based file system as well as .NET integration in the shell and many other improvements. Though at the last glance we got (see "Windows Vista 5342 Screenshots" ), it still had the Aero glass shell, it was clear it was doomed. With upwards of 40% of all installations still using Windows 98 or 2000, the adoption rate of the four-year--old XP has been less than stellar -- especially considering almost every machine on the planet is required to ship with it pre-installed. Microsoft now claims that "people, ...including most business customers, ... don't want change", a significant turnaround from their prior stance. On top of that, Vista's spiraling hardware requirements wouldn't have helped sales in a market already saturated with users who have more computer than they know what to do with. Steve Ballmer, president of Microsoft, was reflective during a question and answer session after the press conference: "Who did we think we were kidding anyway? Did anybody still really believe we were going to ship that damned thing? It's not like there was anything left in it anyway. ... XP's pretty good ... buy that." A press release was issued immediatly following the press conference detailing Microsoft's new retroactive monthly licensing plan for all users of Windows XP and 2000, costing $14.99 per month for personal users and $24.99 for businesses. [1] Fear, Uncertainty, Doubt; spread by marketers and other talking heads when they need you to think less in order to buy their products. ]]> https://www.earthli.com/news/view_article.php?id=1256 https://www.earthli.com/news/view_article.php?id=1256 Tue, 14 Mar 2006 21:56:05 +0100 , which didn't strike me as concise or to-the-point enough for the less-savvy user. [Target Audience] This guide is for people who do not let iTunes organize their music for them. [1] It further assumes that you've already copied your music files (mp3, m4a, ogg, etc.) to the new computer. This guide will show you how to make iTunes on the new computer use the ratings, play count and other information from the old computer. If you have the same folder for music files on both computers, you do not need this guide. This guide will work for transfers between Mac and Windows computers. -------------------------------------------------------------------------------- [Quick Guide] 1. Copy the two iTunes Library files from the iTunes folder on the old computer to the one on the new machine. 2. Using a text editor, open the XML file and search/replace the paths to the music files to point to the correct location on the new computer. 3. Using a binary editor, open the ITL file, delete the entire contents and save it. 4. Start iTunes, let it import the library from the XML file, then press "Yes" when it asks if it's ok to ignore the "corrupted" library file. [Full Guide] [Overview] iTunes stores your music library meta-data in two files, both of which are stored in your iTunes Music folder. This guides will refer to that folder as ~/Music; the real location is C:\Documents and Settings\\Music\iTunes on Windows and /Users//Music/iTunes on Mac OS X. Inside this folder, you'll see two (2) files and two (2) folders. * iTunes Library [2] is a binary file that contains all of your meta-data in a quick-loading database. * iTunes Music is a folder that contains all of your imported Music. * iTunes Music Library.xml is an XML file that replicates your meta-data in an easy-to-read text format. * Previous iTunes Libraries is a folder that contains backup files created during upgrades from other iTunes versions. Copy the iTunes Library and iTunes Music Library.xml files to the ~/Music folder on the new machine. [Adjusting paths] The next step is to tell iTunes where the actual music files are located. You will have to adjust the library description for each of the song files. Open iTunes Music Library.xml in a text editor [3]. Inside this file, there are several sections, but mainly two large one: one for tracks and one for playlists. Tracks have many, many fields, but the important one is highlighted below: Tracks 40 Track ID40 Name[Title] Artist[Artist] Locationfile://localhost/Users/Shared/Music/Funk/[Artist]%20-%20[Title].mp3 ... The line you will have to change is that for the Location key. In the example shown, the music library is found in /Users/Shared/Music. Replace this string with the location of the library on the new computer. Some tips: * Spaces are indicated with %20 [4] instead of using a real space in the file name. If the location of the library has spaces, make sure to replace them. * Do not remove the file://localhost/ part at the front of the file name. * On Windows, the path should include the drive letter after the localhost portion. For example, if the music library is at D:\Shared\Music, the file location should start with file://localhost/D:\Shared\Music You will not need to change anything for playlists. [Trick iTunes] If you start iTunes now, it will completely ignore the paths you put in, magically restoring the paths from the old computer and overwriting the file you painstakingly modified. Well done, iTunes. It's actually loading the whole library from the other file, the iTunes Library. As long as iTunes can read from this file, it will not load from the XML file. If you remove the file entirely, iTunes will not load anything. Tricky, but not insurmountable. 1. Open the iTunes Library in the same text editor as before. It is binary information and is supposed to look like that. 2. Select all of the content and delete it. 3. Save the file; it should be 0 bytes now. [Start iTunes] You're done. Start iTunes and it will load the library from the XML file. Once it has imported this file (which can take some time with large libraries), it will ask you if it's ok to ignore the corrupted iTunes Library. Click "Yes" and you're done. -------------------------------------------------------------------------------- [1] On Windows, this file has an itl extension. [1] That means that both the Keep iTunes Music folder organized and the Copy files to iTunes Music Library when adding to library are unchecked in the Advanced / General tab in the preferences. [1] You will need an editor that can search/replace text in large(ish) files. On Windows, notepad should be able to open the file, but a more high-powered editor like "jEdit" is recommended. On the Macintosh, XML files open in the Property List Editor by default. You should use a text editor like "TextWrangler" instead. [1] 20 is hexadecimal notation for 32 in decimal notation. The ASCII code for a space character is 32. ]]> https://www.earthli.com/news/view_article.php?id=1238 https://www.earthli.com/news/view_article.php?id=1238 Sat, 18 Feb 2006 20:45:32 +0100 (do not click, see below), in which he predicts that Apple will abandon their OS X in favor of licensing Windows for their hardware. Here's a good example of his troll-i-tude: "The only fly in the ointment will be the strategic difficulty of breaking the news to the fanatical users. Most were not initially pleased by the switch to Intel's architecture, and this will make them crazy." The guy lives under a bridge. I haven't seen the link on Slashdot yet, but it's only a matter of time, I'm sure. Regardless of his track record, there will be countless screeds written about this latest prediction, engaged in the futile act of refuting him point-by-point. He doesn't really care that he's wrong -- he does it deliberately to get even more traffic. Do yourself a favor and don't click the link above -- it's not worth your time. ]]> https://www.earthli.com/news/view_article.php?id=1226 https://www.earthli.com/news/view_article.php?id=1226 Mon, 06 Feb 2006 21:43:19 +0100 is a PC inside a whisky bottle. It's about the size of a Mac Mini and looks pretty cool. [image] It's apparently not so easy to do, as the guy (I'm assuming) who made the case had to get it professionally done: "I tried to cut and drill couple of similar bottles at home but I realized that my tools are not good enough for it, then finaly a professional glass grinder man prepared the whisky bottle for me. He made two holes: one at the back of the bottle for CPU cooling and one at left side for put in the stuffing." Unfortunately, he went to all this trouble to build a Windows PC. Wake me when it runs OS X. ]]> https://www.earthli.com/news/view_article.php?id=1191 https://www.earthli.com/news/view_article.php?id=1191 Sun, 30 Oct 2005 22:48:15 +0100 solution from "Apple" for their G5 line is an amazing machine. It would certainly be good enough for any other company to trumpet as their flagship product. Not Apple. If you enter their online shop and start to configure a system, you'll notice that there is a curious option under "Graphic Cards". "Quadro FX 4500 / 512MB SDRAM [+ CHF2400.00]*" *I was shopping in the store in Switzerland ... that's about $1875. Cheeky. Google will tell you that this is not a typo -- the card exists and is blazingly fast. Further research on the Apple site itself finds "Workstation graphics arrive on the Mac" , which also tells you that the card is blazingly fast. It takes up two PCI Express slots and has two DVI outputs. Now the option on the same page to buy a "Second Cinema Display" no longer seems out of place. They don't even stop there: " The PCI Express architecture means you can install up to four graphics cards in your Power Mac G5 -- for connecting up to eight Apple Cinema Displays. ... Imagine viewing high-resolution satellite images across an array of displays. Or consider controlling a suite of public information kiosks or a multimedia museum exhibit from a single Power Mac G5 system. (emphasis added)" The Apple Store seems like it should be the first stop for a James Bond villain when outfitting his inner sanctum. Their suggestions for configuring their hardware would be laughably optimistic -- except it actually will work and there actually will be people buying these setups. I can't think of any other company today that would get away with marketing this kind of over-the-top machinery. ]]> https://www.earthli.com/news/view_article.php?id=1190 https://www.earthli.com/news/view_article.php?id=1190 Sun, 30 Oct 2005 22:32:47 +0100 . It is quoted in its entirety below. "People are underestimating what Microsoft is doing with search technology, says Bill Gates. The head of the software giant told the BBC that its ambition is to be bigger than Google in search." Slashdot is one of the biggest, most popular tech sites on the Internet today. The number of users it commands has led to a name for what happens to a server after it is visited by the stampeding hordes of slavering geeks that are Slashdot readers: Being Slashdotted. As you can see, they have not acheived this fame by pithiness in writing style. This "news" is simply an "ambition" (on the part of Microsoft) that is dutifully reported straight out of a press release. Most of the commenters (the aforementioned herd) jumped in with nary a thought as to whether this was even "news" or not -- though something similar seems to be reported every few days. There are some exceptions, like this author of this post: "Yeah, and my ambition is to be an astronaut-playboy-robot-vampire that fights crime and plays lead guitar in his own thrash metal band on the weekends, but I don't think my ambition is terribly realistic either." The original article, "Microsoft aims to trounce Google" leads off with: "People are underestimating what Microsoft is doing with search technology, says Bill Gates. ... The head of the software giant told the BBC that its ambition is to be bigger than Google in search." Sound familiar? The Slashdot "article" isn't even original content! The editors didn't write a single word! Slashdot content quality is no better than a common blog with stuff like this. Now let's move a step upstream and see how the BBC fares. Slashdot copied their stuff directly, so it must be good. The BBC seems to be at the top of the food chain here, publishing the press release verbatim, without juxtaposing the text with reality. Google is king of web searching; Apple is king of desktop searching. Microsoft is not being underestimated -- they just haven't shown any strength in searching yet, despite repeated attempts and opportunity. It is not biased to point this out -- it is simply being acquainted with the area being covered. If you read the whole BBC article, you'll see that the lead-in (Microsoft trouncing Google) is a tabloid-style header -- only two sentences of the article deal with searching, they are both vague and Google is mentioned only once. The rest of the search "section" deals with platitudes about competition, devices talking to one another and noting that "[Microsoft is] in the best position we have ever been in". The signal to noise ratio is low -- and getting lower every day. ]]> https://www.earthli.com/news/view_article.php?id=1105 https://www.earthli.com/news/view_article.php?id=1105 Tue, 07 Jun 2005 22:58:35 +0200 is a perfect guide for people looking to buy an LCD. Let me rephrase that to anyone looking for a computer, because CRTs barely even exist anymore. In fact, "For those of you who still have a CRT monitor on your desk right now, know that it will likely be the last CRT you will ever own. ... Your vintage high-end CRT is better than many CRTs being produced today.*" *That's me. I've got two vintage 19" Viewsonics, both 5 years old. [Pixel Speed] So, LCD it is, then. The faster, the better right? Wrong. It's best to be careful on pixel refresh speeds, as manufacturers like to quote "best-case scenario[s]" instead of averages. Additionally, there are different types of screens out there ("S-IPS, TN-film, and PVA/MVA"), which differ in their abilities to transition from one color to another. Some have trouble with black to white, others with black to grey - that's why average pixel speed is important. Other important things to remember are: "IPS panels typically offer better viewing angles with more accurate color, however contrast is poorer. TN-Film technology (the 8, 12 and 16 ms) panels only display 18-bit color. PVA/MVA panels on the other hand are famed for deep black levels and superb contrast ratios that typically come [at] the expense of speed." For many people, viewing angle or deep contrast is much more important than pixel speed. For old CRT hands, it takes a little while to get used to the fact that refresh rate no longer matters. LCDs don't flicker. Period. Forget about it as if it was a bad dream. LCDs on the other hand have a problem with "smearing", this is the phenomenon where the screen is changing more quickly than the screen can refresh, resulting in a messy watercolor feel. It also makes you lose games. Here are the break-even levels for the different types of panels: "...at 12 ms or faster, we found the smearing associated with TN-film panels to be non-intrusive. ... 16 ms TN-film is a good starting point as a minimum spec and most gamers will be happy with this level of blurring. We found the 12 ms PVA panels to perform similarly to the 16 ms TN-film panels. ... 25ms PVA panels were too slow for high-speed gaming ... DVD movies will look fine. 25 ms IPS panels were on par with 16 ms TN-film panels." [DVI] As for DVI? " If there's one absolute of buying an LCD monitor, it is to get a monitor with DVI support.". VGA output does not have better color; DVI is perfect digital convesion of the intended color ... how can an analog interpretation of a voltage level be better? VGA is not "as sharp as DVI" thanks to better analog-to-digital converters. Those are both myths. Don't forget that your video card needs DVI output too; older cards won't have it, but you can upgrade pretty cheaply. 'Nuff said. [Contrast] ""Contrast ratio" is measured by comparing the intensity of the brightest white and the darkest black" and is often an important part of LCD reviews, because it is a value that can be optimized without actually improving overall picture quality. In fact, "the most important element is neither contrast ratio nor brightness, but color accuracy". Take a look at the two pictures below; the second one actually has a higher contrast ratio (difference between black and white) than the first ... it just sucks at all of the colors in between. [image] [image] You can provoke the same bad effects by messing with the contrast slider in any graphics program. At some point, the transitions are so stark that details are washed out. So, if color is more important than constrast (obvious when you think about it), how do you measure it? The picture below "is a patch of 24 scientifically selected colored squares in a wide range of colors that represent natural objects such as human skin, foliage, and blue skies and have stood up to the test of time. Doing well with these 24 colors is predictive for doing well with all 16.7M colors." The screenshot of the graphic on a given monitor against the reference graphic indicates whether it tends to blue, green or red. "[T]he absolute color isn't what's important", so don't worry if your monitor has a tinge as well - that tinge is applied equally to both graphics and you'll still see the relative difference applied by the monitor in question. [image] One last thing to note is that a color profile can be applied by the operating system to correct inherent tinging. This applies to everything that appears on screen, including games, but not including video overlays as used in DVDs. If you're going to watch a lot of films and absolute color is important, make sure to get a quality LCD out of the box. Also, make sure to calibrate your monitor, as manufacturers tend to ship at higher color temperatures that look brighter, but are false. See "Color Temperature" for more information. How do top-end CRTs fare? A "4-year-old Iiyama i90A CRT ... was an order of magnitude superior to any other LCD" in pixel refresh and lack of smearing. "[A] black level of 0.01 cd/m2 and a peak brightness of 94.15 cd/m2 for a staggering contrast ratio of almost 9415:1" put the CRT in a league of its own contrast-wise and "the average color accuracy was notably more accurate than even the best LCD. Once calibrated, the Iiyama CRT was nearly flawless." What does that mean? Should you start hording vintage, high-quality CRTs? No. Most people will never need nor notice the additional quality offered by the top-of-the-line CRT. Heck, most people don't even calibrate their color in the first place, regardless of monitor. The better LCDs found in this review (all around $300) are excellent for gaming, watching DVDs and anything else you want to do. If you've already got a good CRT and have the room for it, you can smile smugly to yourself. Just remember, LCDs are the future and will continue to get better. ]]> https://www.earthli.com/news/view_article.php?id=1120 https://www.earthli.com/news/view_article.php?id=1120 Sat, 28 May 2005 01:37:11 +0200 mentions right off the bat that "[a]s OS X improves, it becomes harder to convince OS X users to make the jump." Panther already did its job so well for most people that the goodies in Tiger may not be enough to entice upgrades. That's why Apple is selling their "over 200 new features" so hard. The most interesting big features for users are probably Spotlight and Widgets. [Spotlight Pros & Cons] Spotlight is a way of searching for stuff on your computer that permeates every level of the operating system. The technology is extremely solid and "from a technical point of view, the file system team has done a terrific job." Re-indexing of files is performed on-the-fly as they are modified, the entire system is easily extensible for new file types and the OS now updates instantly everywhere whenever a change is made: regular folders always have current contents and even smart folders (based on a query) update in real-time. The application that provides access to the search functionality leaves something to be desired: * "Some simple searches are now much harder", including simply searching for a filename and no other fields. The workaround is to "use an undocumented feature, and wrap the search term in quotes". Not exactly the user-friendly Apple way of doing things. * The spotlight window itself lives halfway in the finder, without a Dock icon and impedes speedy navigation using the keyboard, in that "[i]f it loses the focus, you need to use another undocumented feature: apple-space-space to return the focus". * Though the underlying engine has a powerful querying interface, "the user interface severely hampers what queries can be made". Apple is still convinced that people can't handle the complexity of an interface that allows "all", "none" or boolean operators other than "and". * Finally, though Spotlight results are nicely organized and stylishly presented, there is no Google-like "context provided by the search results", so it's difficult to distinguish similar results. * "Spotlight" by John Siracusa contains some movies of other UI glitches arising from the introduction of smart folders and spotlight windows into the Finder. There is also a brief introduction to the querying language for the file system. Many of these problems are probably not something that most people will notice (especially the switchers from Windows). Mac users and especially Mac reviewers do, though. Apple tends to be quite responsive to some issues, having already released 10.4.1, which improves overall speed and usability and drastically improves Widget refresh speed. [Big News for Developers] Note the distinction above between the technology and the application. Though Tiger has many shiny geegaws and doodads for the everyday user, it is the underlying subsystems that have really improved in Tiger. This is just as much a release for developers as for users. "Mac OS X 10.4 Tiger" by John Siracusa is a 21 web page (104 page PDF), incredibly detailed investigation of all that is new, good, bad and improved in the latest edition of Apple's operating system. "Kernel Programming Interfaces (KPIs)" Apple has finally cleaned up their kernel, and "there are stable, officially supported kernel programming interfaces (KPIs)". This means that low-level extensions will be more stable between releases and more applications will be willing to take advantage of them for the same performance gains that Apple applications receive. "Fine-grained kernel locking" "Instead of restricting access to huge chunks of the kernel, locks can be placed in front of smaller pieces of functionality." This allows multiple threads to all be executing in the kernel at once, so an application doing file io no longer necessarily blocks network activity. "The end result is less contention, and the ability to scale to a higher number of CPUs" Again, a smart move for the future that brings performance gains today. "launchd" Apple has ditched the standard UNIX way of launching processes in response to events and replaced it with their own single-app solution (that's open source, too). That means that "common events [like] system startup, shutdown, and restart, user login, and incoming or outgoing network connections" are now all configured and launched using the same application under OS X. This drastically lowers the learning curve and improves the scriptability of the system. "Extended file system attributes" Thanks largely to the efforts of former BeOS file system engineer, Dominic Giampolo, "Mac OS X now includes support for arbitrarily extensible file system metadata." This feature is used heavily by Spotlight and its indexing plugins, but is also an API that is available to any application. "Access control lists" provides an in-depth look at one of the powerful uses to which Apple has put this feature. See the bullet list halfway down in "Spotlight analysis and potential" for a vision of what life with Spotlight and extendible attributes could be like. "Uniform Type Identifiers" UTIs are a universal, hierarchical way of classifying file types that is a replacement for mime types, file extensions and creator codes. [image]The diagram to the right shows a sample hierarchy out of the UTI tree Apple has defines - and which vendors can easily extend by following a naming convention (reverse DNS) that guarantees uniqueness without a central registry. It is this typing system that Spotlight uses internally to decide which plugin "is the best fit" for a particular file. It's a massive step in the right direction and all applications will be able to benefit from it. "Quartz 2D Extreme" OS X's 2-D rendering has taken the next logical step and moved all instructions onto the graphic card if possible. The old quickdraw libraries are finally obsolete and many Apple applications have been rewritten to use newer APIs. [image]The diagram to the right shows how an application simply issues drawing commands and OS X maps them to OpenGL and the GPU, if possible (almost always, for most 2D drawing). Naturally, this approach only offers performance improvements if the necessary data is also already in VRAM; if not, there is still the same performance hit as before as memory is swapped in over a smaller pipe. Never fear, though, even applications that still use QuickDraw got major performance boosts in a general cleanup of the rendering APIs. This feature is currently only available for ATI 9600 and above (which explains why the iMacs just got an upgrade, eh?) and is currently disabled for all Macs, pending a service release. "Core Image" Staying on the graphics theme, we have the rendering API applications can use to reap the benefits of the GPU without programming to it directly. Core Image allows applications to chain together rendering plugins, (e.g. Gaussian Blur, Sharpen, etc.) and pass them to the OS to render. Core image builds a small "program" out of the group of plugins and executes it all at once on the given image buffer. That means that the speed of the operation is not necessarily constrained by the number of plugins applied at once. It also means that the OS can seamlessly decide whether the operation can be moved onto the GPU instead of executing in software. "Core Video" This is yet another API offered by Apple that is based, naturally, on the Core Image API. Quicktime 7 has been completely rewritten on top of it and renders videos to OpenGL surfaces, so that transformations of video can also occur on the GPU. The Video iChat application included with OS X demonstrates this as it shows the chatting heads at angles to simulate a room. Other video applications will be able to use these standard APIs for similarly manipulating video in a high-performance, standardized and stable fashion. "Core Data" "It's a framework for object management and persistence. It allows a developer to define object attributes and relationships, then build an application based on this data model without having to write any code to manage the object graph or serialize objects. The currently supported serialization formats are XML, binary (essentially compressed XML), and SQLite. Applications that use Core Data also get niceties like undo/redo for free." This is an extremely good thing, as it means that smaller Mac utilities and applications will be able to focus on their task rather than on saving/restoring data like configuration and other things. It also means that it's much faster to develop applications on a Mac, which lowers the barrier to entry. As you can see, Apple is putting a tremendous amount of effort into making their platform as extendable and usable as possible. Everything from file searching and identification, data persistence, image and video handling to kernel extensions has been made easier and much more powerful. This release may have some usability problems, but inside it's a big step forward for the platform. It's the kind of investment that will pay off in the long run. ]]> https://www.earthli.com/news/view_article.php?id=1075 https://www.earthli.com/news/view_article.php?id=1075 Sun, 27 Feb 2005 22:46:23 +0100 offers an in-depth speed comparison of dozens of popular browsers (in different versions and platforms) in several categories: * Startup time * Table rendering * CSS rendering * JavaScript * Graphics (downloading and displaying multiple graphics) * History (traversing back and forth) The results are hardly surprising for those that have tried and used different browsers: Opera wins in amost every category. On Windows, it's almost twice as fast as any other browser in most of the tests. In fact, the latest version (8.0b1) only loses to older versions of Opera, where rendering speed is slower only in absolute terms (progressive rendering in Opera 7.x/8.x makes it feel like it's loading faster, but it reformats more often, using more time overall). On the Mac, it's the fastest at most categtories (even though it's still in preview release on that platform), losing only at startup speed (which is much better in the latest releases) and CSS rendering, where Safari 2.0 kills it. Even on Linux, it's the clear speed winner, coming in first in most cases. 'nuff said. ]]> https://www.earthli.com/news/view_article.php?id=1065 https://www.earthli.com/news/view_article.php?id=1065 Wed, 02 Feb 2005 23:12:18 +0100 reviews the product of the same name (their attention to graphic detail does not extend to their "home page" , which is likely to make you go blind). John Siracusa's loving review spends a considerable amount of time trying to tease out why this "glorified list of books, movies, music, and games" still has the Mac mystique. Its base purpose isn't earth-shattering, so why does it still make you want to download it? There are several reasons, but they all boil down to its seamless integration into the Mac OS and clever positioning. Even the name, "Delicious Library", is just odd enough to be intriguing. "It's not "MacLibrary X" or anything similarly predictable". Apple has "Human Interface Guidelines" for OS X. If you look at the guidelines for "icons" , you'll see that the icon to the right fits them perfectly. "If the primary function of your application is creating or handling media, its icon should display the media the application creates or views. If appropriate, the icon should also contain a tool that communicates the type of task the application allows the user to accomplish." The icon has a few books with barcodes on them, on top of which lies a barcode reader. This is not rocket science, but to an OS X user, this icon will "feel" just right. The two developers behind the project are formerly of the "Omni Group" , makers of other extremely carefully constructed Mac OS software (like the "Omniweb Browser" , for example). The pedigree is good, so lets see what Delicious Library gets so right. [Installation] [image]Mac applications are typically downloaded as disk images; there is no installer. You get this disk image, pop it open and see a nice background with a single icon. There's also usually text telling you to drag the icon to your "Applications" folder to install it, if you're a total noob. How the hell do you distiguish yourself here? Well, instead of the standard white disk image icon, you get the image to the left. This may just be a pretty picture; it may just be throwaway fluff if the application doesn't provide any useful functionality. However, compare and constrast to the other two contenders for our desktops. Siracusa asks: "Windows users, think about what your typical download and installation experience is like. How many dialogs are you presented with? What do the file names and icons look like? Linux users, when you look at the carefully laid out disk image contents in the screenshot and links above, think about how far "desktop Linux" has to come before it can even begin to think about details like [this]..." It's this obsessive focus on design that creates easier-to-use products that are a whole lot easier on the eyes on the Macintosh. If something is hard to use or doesn't integrate into the platform, it gets torn apart. I know: I'm in the Mac OS X beta tester group for Opera's web browser. It's a constant battle explaining that you cannot have a successful cross-platform product if that means that the Mac version looks and works the same as the Windows version. Ever Firefox, an open source browser, gets it. They have a special skin which uses the native Mac APIs to render the browser UI. Windows users have been clamoring for it since it came out. [Features] So, what does the product do? It catalogs your media and stuff. Big deal. It's a glorified database. For this kind of product, it would be tempting to throw in a whole bunch of features just to try to make it stand out. "Choosing the right features, and only the right features, is important", but choosing the features to leave out is just as important. Present a simple face to your initial users so they feel that they understand the product. Add more stuff later when your user base tells you what they want. [image]So, what kind of features do you stuff into a media application. Well, think of the kind of obsessive market you're targeting: they want to catalog everything they own in a database. They also want to do this on the Mac, so they want it to look nice. Even realistic. To the right, you see the main (and only) window of the application. Right away, if you're a collector, you think "cool ... I want my stuff to look like that". And it can. The book, game, cd and dvd covers are automatically pulled from Amazon and composited with stock graphics to create realistic looking copies for your shelf. Again, they're just using the amazing compositing capabilities offered by the OS to bring you flair you probably didn't expect in such a mundane application. The end result makes you want to enter more data and make your shelves look better and better. There are naturally other features you might want and the graphics aren't always so well integrated (Amazon doesn't always provide a good cover graphic), but for a first version of the product, it makes a fantastic impression. And I think that's the point I wanted to make. The point is not to get you hooked on the Mac, OS X or the Delicious Library. It's that the Mac quite frequently plays host to applications that make interesting, new impressions. I think it lies in the integration and presentation that is possible on that platform. ]]> https://www.earthli.com/news/view_article.php?id=1053 https://www.earthli.com/news/view_article.php?id=1053 Sun, 16 Jan 2005 20:34:17 +0100 has 450,000 articles, while the "German Wikipedia" has a respectable 188,000 articles. What's more, it's created completely by its users and visitors, constantly evolving and growing with no central guiding authority or plan. "Why encyclopaedic row speaks volumes about the old guard" by John Naughton discusses the reaction of the "old guard" encyclopedia vendors, which can be summed up as being "outraged by the notion that anything produced by hoi polloi could have lasting value." Encyclopedia Brittanica's official stance is a pseudo-scientific one stating that "[t]he premise of Wikipedia is that continuous improvement will lead to perfection...[t]hat premise is completely unproven." It is this type of assertion that will have people nodding in agreement because it sounds so smoothly convincing whereas one could just as easily say that "the premise of Brittanica is that rigorous controls and planning will lead to perfection...that premise is completely unproven". Done poorly, anything is going to suck. Duh. Another EB official compares an encyclopedia to a "public restroom" whose cleanliness only "[lulls one] into a false sense of security" (having gone to the "Bill Gates School of Hyperbolic Metaphor" , perhaps). Well, at least with Wikipedia, you can assume that people from many walks of life and political/social/philosophical positions are contributing; a traditional encyclopedia has only the promise of objectivity, whereas the way that Wikipedia is built ensures at least a modicum of it. The proof, as they say (no idea why, they just say it), is in the pudding. The English version of Wikipedia has grown by about a third in the last year alone and the author suggests that the reader look up tsunami in both "Brittanica" and "Wikipedia" and ask yourself which one you think is more informative. The corporate version which tries to get you to sign up to get more information? Or the open source version that gives you pages of information, including up-to-the-minute information on the recent tsunami in Indonesia? "The Faith-Based Encyclopedia" by Robert McHenry offers a slightly more informed critique of the Wikipedia, delving into the way that content is added and moderated on the site. He's the author of the "public restroom" quote above. He notes that even Wikipedia's mission statement: "Wikipedia's goal is to create a free encyclopedia -- - indeed, the largest encyclopedia in history, both in terms of breadth and depth and also to become a reliable resource." is an editable entry and can only be provably known to represent the "view of the last person to modify it, and those of unknown others who have chosen not to modify it further". That Wikipedia openly admits that it is "possible for biased, out of date or incorrect information to be posted" makes it almost unique in the publishing world. How does a print encyclopedia guarantee any different? It is the reflection of the bias of the entry writer just as much as the Wikipedia entry is. It is simply imbued with a false sense of legitimacy because it comes from a "traditional" source. Just because it's in a book doesn't mean it is without bias and is the truth. Just because it's online doesn't mean it isn't reliable. That's why the Wikipedia actually has a better chance at accuracy, because it's not set in stone. However, to claim that "the overall accuracy of the encyclopedia is improving all the time as it attracts more and more contributors" (as Wikipedia does) is also not true. Simply watching obviously false memes being reinforced in other forms of media (Jesus is coming back, Saddam has WMD, etc.), one can imagine that it is just as easy for the opposite to be true. Remember, repetition is truth, so if enough people believe something, it's true. If those people build an encyclopedia, it doesn't make it the truth. This does not mean that it does not asymptotically approach the truth, simply that whether it does or not is not provable since we have no metric for truth. All we have is gut instinct for it; we can decide whether it jibes with other things we've heard, from other sources. We can see whether it fits in our worldview or not. Hell, just the fact that the Wikipedia is laid out nicely and formatted well makes it seem so official, doesn't it? Very believable. The author of the critique chooses the entry on Alexander Hamilton as a lodestone of accuracy and comes away sorely disappointed. The iterative nature of the Wikipedia means that many of the issues he raises have since been corrected -- in a response that is much quicker than a traditional publishing format could muster. In fact, it might be that the author of the critique himself corrected the entry. In an interesting twist, his examination of that entry shows that the collaberative concept holds up quite well, since one can now examine the "discussion for the Alexander Hamilton entry" to see the reaction to the article. The web eats itself. The answer to the question: "How long does it take for an article to evolve into a "polished, presentable masterpiece," or even just into a usable workaday encyclopedia article?" is not so simple. It doesn't happen overnight and it certainly can't happen for 450,000 entries simultaneously and with the same degree of accuracy. Instead of asking whether the Wikipedia today represents an absolute truth and deeming it a failure because it has not yet achieved it, ask instead whether it is as good a source as others online. I think the Wikipedia is a fascinating experiment and has grown to immense proportions in just three years. If only 10% of it is at all accurate after so short a time, it is still far ahead of other encyclopedias at that age (most of which have been published for decades, if not centuries). Those who are already calling the Wikipedia a failure have an unproven faith in other information sources and/or don't understand what asymptotic means. Give it time; it will come. ]]> https://www.earthli.com/news/view_article.php?id=1052 https://www.earthli.com/news/view_article.php?id=1052 Sun, 16 Jan 2005 18:34:22 +0100 is a longer one (four pages), in which he shows off his unique interviewing style in which a directly-posed question hardly ever gets a directly-stated answer. Simply getting a response that has a passing connection to the question is considered unusually good. Most answers start off with a marketing plug for a Microsoft product that is within the domain of the question's premise. For example, when asked "Do you see yourself becoming, let's say, more of a seller of content?", he answers (Rumsfeld-style), with: "And so is Microsoft a content company? Well, I'd say "Master and Commander" is good -- people have talked about how the story made them cry -- that's content, but it's also software." Am I the only one somewhat thrown by the abrupt shift of topic here? Did Microsoft make "Master and Commander"? Does Gates have a Russell Crowe fetish? Is he saying that Microsoft won't consider itself a content provider because there are other good content providers and Microsoft doesn't do well in markets in which they don't have a monopoly (see the cellular phone market for an example). Hell, if he's going to give such wacky answers, then I'm free to make up my own reasons why. The next question, about blogging, after a year that saw several open-source, automatic publishing systems hit the market, saw portions of journalistic responsibility in the U.S. replaced by bloggers and what is Gates' response to the question of what he thinks about the liberation of publishing for the masses? "Well, actually I think the biggest blogging statistic I know, which really blew me away, is that we've got close to a million people setting up blogs (Web logs) with the Spaces capability that's connected up to Messenger." If you guessed that he would plug a Microsoft product (that's still in beta, I'd like to add), you'd be right. I mean, as a salesperson, he's spot on; as a predictor of technology, he's got nothing. Even the discussion about browsers ends with him saying that "no one invests more in security of their browser than what we do on IE", which, while technically correct (as most good lies are), seems to ignore the fact that Firefox is open source (read: no budget) and that Opera is about 1000 times smaller than Microsoft. It also misses the point that IE is still one of the more vulnerable browsers out there that causes big problems for a lot of their customers. He ends by threatening that "people who underestimated us ... in the past lived to regret[it]". Now he's doing Tony Soprano impressions? I'm not sure if he's drunk with power here, or if he simply doesn't know how to associate issues at a more holistic level, but answering that "[t]here are fewer communists in the world today than there were." when asked about intellectual property rights is just plain bizarre. He goes on to claim (in true-blue American "it's black or it's white" fashion) that you're either for intellectual property or you're communist because "[i]ntellectual property is the incentive system for the products of the future." There is no other way, got it? There are no other incentives that drive people to create. None. Why? Because capitalism says so and capitalism is never wrong. Because money and consumption are the sum of all human desire. "Gates Interview Part Four: Communists and DRM" continues the discussion about intellectual property and its ugly stepchild: DRM. Here, Gates starts off normally enough, noting, quite reasonably, that "...the number of people who ... believe there should be no incentive systems for creative work -- there's actually less of those people." So far, so good. Don't judge an issue by its extremists. Very good advice. I wish more people gave it and followed it. At this point, he does his thing where he merges sentences from four different conversations to make it sound like an answer. Somthing about that whether or not there's "no patent system" or a "somewhat improved patent system" doesn't matter because we need to "draw out the creativity of all the smart people in China". I'd like to see a debate between him and Ross Perot. The interviewer wisely leaves that point where it lays and moves on to meatier IP and DRM issues. Bill drops back to the old "straw man" argument by comparing DRM to "speed bumps", even though one saves lives and the other simply protects IP rights, which have not (yet) been recognized as citizens of the U.S. Now here's the interesting part, when the interviewer responds that "[o]bviously people think that artists, or you know, whoever creates software should be paid", Gates responds with: "No, no, no. That's not true! Many people don't believe that." Now wait a second, Bill. You just astutely pointed out above that the extremists in an issue are few and far between (on exactly this issue actually) and now you turn right around and claim that "[m]any people" think people shouldn't get paid for stuff they create. That's a pretty extreme viewpoint for many people to have, isn't it? Which is it, Bill? Do we have reasoned debate or extremists everywhere? Then, where does Bill go for an example of this extremism? China! In 1950! He goes on to claim that Microsoft is such a strong DRM proponent because the artists want it. Microsoft is actually politically neutral on the topic. Fascinating. Bill proceeds to spill paragraphs of drivel explaining why DivX, one of the most popular formats available is not supported on the Windows Media Center (if you guessed that he actually admitted it's because it's not a DRM format, you'd be wrong). He follows up strong with an argument that Microsoft's gung-ho approach to DRM is simply an overarching desire to serve the customer by making the most "content available to you". The old straw man having worked so well once, Bill trundles it out again to lump all data protection issues together with "is it your position that rights management for medical records is evil?" This is the type of argument that typically ends with "well, then, you must also be for [insert distantly related issue here]". This interviewer, as opposed to the softball interviewing style on CNet, begs off by saying that "that's a different question" to which Bill responds triumphantly responds "It's not different. It's identical technology. It's the same bits!" Oh, well-struck, Bill! Check-freaking-mate, Gizmodo! The interviewer makes one more attempt at reasoned debate with "I think what people are trying to say is that DRM, as sanctioned by the big players, may be holding back culture as a whole." Bill, unfortunately doesn't take the bait and get involved in a philosophical discussion, defends Microsoft's right to "set... up the [DRM] platform" and ends with a petulant "I think we just disagree". So many people respect Mr. Gates for his business and technical acumen and his intelligence. Why then, does he need to resort to the "I do not agree with what you say, therefore I will reject your ideas without bothering to refute them and treat them as your opinions" form of debate when interviewed by a guy from a site called Gizmodo? ]]> https://www.earthli.com/news/view_article.php?id=1046 https://www.earthli.com/news/view_article.php?id=1046 Sat, 15 Jan 2005 21:46:35 +0100 (click 'Play here now' in the desktop picture shown near the top of the page) "is home to a new kind of application called widgets". There are a ton of these widgets, for checking weather, converting units, translating words, looking up definitions, terms or synonyms or even working with small tasks in iCal, iTunes and other iLife applications. Basically, anything that you probably use in a web page now can be rendered as a widget using only "HTML, Javascript and CSS". [image] "Similar to the way Exposé works, the Dashboard is a semi-transparent layer that zooms across your Desktop with a single button click. To put the Dashboard away, simply press the function key again and you're back to where you started without messing with your Desktop or Dock. Use the Dashboard to get instant access to information and application controls you use most frequently." But you've got to watch the animation/video to see them in action. These are like no other "web applet" you've ever seen. "Complex transitions, movement and visual effects" make these look like native OS X applications using "Core Image" . There's more on "developing widgets" , including examples and suggestions. Here are some closeups of the widgets to give you an idea of what they look like: [image]Weather Widget [image]Flight Tracker Widget [image]iTunes Widget [Spotlight] "Spotlight" is another impressive video that shows how searching will work in OS X Tiger. For those that ever saw the BeOS running, it's like that, only in Aqua. In fact, "Spotlight on Spotlight" by John Gruber indicates that it is "Dominic Giampaolo's baby". That's the guy who pretty much single-handedly wrote the BFS in the first place (read "Practical File System Design with the Be File System" (PDF) for an excellent account of building that file system). --------------------- | Integrated search | --------------------- [image] Clicking "Show all" in the menu search shows the view above [image] This is the same search technology integrated directly into the Finder --------------------- [image]Spotlight's functionality is built with the "SearchKit" . The performance of this kit has been improved considerably for Tiger, "3x indexing, 20x incremental search". The faster indexing means that files are imported into the system faster (less time used by the background task when a new set of files, like a hard drive, is made available) and the faster incremental search means that your results are displayed on-the-fly as you type (see the very impressive "demo video" or the screenshot to the right). "Both metadata collection and full-text indexing depend on cooperating per-file-format Importers, either written by Apple or by third parties. Importers are fired on every file the moment it is created, saved, changed, or moved, including when files are made available through a newly mounted drive." The indexing task is idle if you are. There is no massive index operation that runs every once in a while; the index is updated in real-time as you work and "[p]erformance is said to be excellent" (network drives were still a problem at the time of the report in August 2004). Naturally, there will be comparisons to Google Desktop and whatever Microsoft's solution is called, but they aren't the same. Apple has developed an "elegant array of optimized search technologies" which can be used by any application. The plugin concept for metadata analysis allows your Mac to find as much information as possible, with dozens of common formats supported directly by Apple (including Address Book entries, Pictures, Music and other stuff you search a lot). The SearchKit API ensures that other all OS X applications can integrate powerful search technology directly from the operating system. Given this search feature, gone are the days of carefully storing files in a file hierarchy. Content will be automatically indexed anyway and available with a mouse click from the desktop. Let's just hope they don't make the same mistake as Google by attempting to share these results across machines; it's useful enough just finding your own information ... it doesn't have to be a search result sharing mechanism. [Automator] "Automator" is an improvement on an existing feature that probably doesn't get a lot of use right now: Applescript. Sure, the hardcore Mac user will be writing Applescripts and already has everything wonderfully linked from one app to another to automatically do amazing things. Most of us don't. The video shows the Automator application in action: it's basically the graphical UI equivalent of piping between applications using the command line. [image]On the left is a list of AppleScript-enabled applications on your machine. Click an application and it lists the features and functions that it exposes. Drag one of these actions to the workflow pane, fill in it's parameters and build your script. These actions flow data into one another to seamlessly build the applications you've always wished you had. iPhoto doesn't do exporting the way you want? Export the pictures, then use another, more advanced photo manipulator to perform final touches before uploading them to a website using a web page or another application. Even better, you can use the power of Spotlight to find the items you want (on your machine), then pipe those into the workflow to work on them. Imagine writing a script that picks up pictures you've created in the last week, resizes them and sends them to a mailing list out of your address book using your mailer and you'll see that, with Tiger, Apple has created a set of tools that are just what people have been wanting to do, but have always assumed wasn't possible for them. Now, they can do it with a few mouse clicks. Again, making things much easier for people to get more out of their computers. The potential is already there, but it takes an application like Automator to bring it out. ]]> https://www.earthli.com/news/view_article.php?id=1049 https://www.earthli.com/news/view_article.php?id=1049 Sat, 15 Jan 2005 21:46:20 +0100 is an explanation/manifesto explaining why they offer open-source code for scraping the Google search results pages. "If done in the public interest and not for profit, it's legal. What's more, Google can't block you if they can't find you." Their basic point is that Google has built a $50 Billion market cap simply by trawling the Internet for content you've created, attaching ads to it and serving it all up in super-context-sensitive search results. They do a great job. So what's to stop you from doing the same thing to them? Especially if you don't show any ads or make any money from it. They posit that by US law, pages like this "Google backdoor" are legal. They released the source code in order to "escalate the issue", get it into court and establish a legal precedent. "If it can be established that what we're doing is legal -- or at least sufficiently legal so that Google is not eager to challenge us -- then this will begin to restore a public-interest balance to the web that has been declining ever since big money got behind the dot-coms." I think this is fascinating, will have no effect on Google's profits and may just do what they hope it will. I wish them luck with it. I may even start searching from here; why not? They're the same results. Except ... it's too bad I sometimes click on the sponsored links on the left because Google is pretty damned good at what it does. Gotcha indeed. ]]> https://www.earthli.com/news/view_article.php?id=994 https://www.earthli.com/news/view_article.php?id=994 Sat, 15 Jan 2005 16:31:31 +0100 I've repeated the interesting (read: debatable) points below, with my responses below. "It's like making a lamp which only works with special 63,5 watt lightbulbs instead of the standard 60W. Whatever advantages you can come up with for that, most of them are likely to be stupid." No, it's like making a lamp that only works with the standard 60W bulb, even though 10% (or 25% for your site) of your customers *also* own 63.5W bulbs. The advantage lies entirely with the site builder and maintainer when using standards if 90% (again, 75% in your case) of the browsers will not display it correctly. If you use standards, you are using the 63,5W light bulb (I do it too, by the way, but I have no illusions about it conferring any degree of genius). "Coding to make your site break for 8% of your visitors is definitely stupid..." If you're coding your site for fun, what incentive do you have to code to standards? If your coding tool, say FrontPage, doesn't code to standards, what chance do you have? Is everyone using FrontPage really stupid? If you come to the conclusion that a good majority of a particular group of people is stupid for doing something, then you've almost certainly missed at least some of the reasons why they do what they do. In addition, since you've already passed judgement, you aren't likely to come any closer to understanding those reasons any better and you're certainly never going to figure out how to address those reasons so they aren't stupid anymore. "And non-standard is definitely synonymous with stupid on the web." If you're going to pass judgement, you should at least define what "not stupid" means. Do you mean "non-standard" stupid, or "not-profitable" stupid or "not-visited" stupid? Go validate SlashDot, arguably one of the more successful sites on the web. They don't validate. Pity they're so stupid. IBM is stupid. Amazon is stupid. If it weren't for Opera's quirks mode, we probably wouldn't see their sites at all. Most of the web would just be invisible to us Opera-browsing geniuses and good riddance. There is a standard for the Web ... it's called IE. It's a crappy, proprietary, untenable standard, but 90% of the market = standard. What Opera, the W3C, Firefox, etc. are trying to do is to change the standard. This is something that I wholeheartedly support, but it's a change from an existing standard nonetheless. XTML is the 63.5W lightbulb, not IEHTML. "So I would break the site for 2500 visits by breaking the site for non IE users!" As long as you can afford to offer support for them, I totally agree that you should do so. The key words there are "afford to do so". Many sites may not even be aware they don't support some browsers. That's not their business. If you've got a car that runs like crap, you're not stupid -- you just chose a bad mechanic. Is the mechanic stupid? Maybe, maybe not. Maybe you don't pay him enough to take care of every last little detail. If a site uses an old browser-detector script that kicks people off of their site for using Opera, then they may be stupid. They may also just not be able to change it, or can't afford it, or whatever. On the other hand, I like to code to standards, but I always have to hack my CSS in order to get it to render in a halfway-decent manner on IE ... because about 90% of the people visiting my site still use it. Am I stupid for adding IE-specific hacks? Or are they stupid for browsing with IE because that's the only thing they know? Should we all just get the hell off of the web until we learn to behave? He said "Yes" and the conversation ended there. No, he didn't. The entire discussion devolved into an online shouting match. No, it didn't. ]]> https://www.earthli.com/news/view_article.php?id=999 https://www.earthli.com/news/view_article.php?id=999 Tue, 24 Aug 2004 22:27:32 +0200 takes you through the by-now familiar drill of security problems with Microsoft's flagship operating system. The part that's less familiar is the conclusion that "20 minutes is not long enough to update your Windows PC before it is too late". That's right. The average user has no chance whatsoever of keeping an XP machine clean because it's mathematically impossible to download all of the necessary patches before the machine is infected. The latest Service Pack (2) from Microsoft "may be as small as 70 megabytes (MB) or as large as 260 MB". No way you're getting that installed inside of 20 minutes ... I don't care how fat your broadband pipe is. That's if you even try. Most people don't know that their machine is going to be hijacked, so they want to, God forbid, actually use their computer, rather than spending hours maintaining it when they just got the damned thing out of the box! Instead, they'll: "...head over to eBay to look up auctions for Precious Moments figurines ... [a]nd soon enough, Grandpa and Grandma's new Windows computer is spewing out email ads for offshore casinos, and SUPERLOW!!! mortgage rates, and \/1@gra and (1@li5, and God knows what else." There is a free document published by the SANS institute, called "Windows XP: Surviving the First Day" . (sounds so encouraging, doesn't it? Makes you so happy you decided that that sleek, cool Macintosh was too expensive, no?) It's pretty good and filled with screenshots to help you stabilize your computer before connecting it to the virus/spam highway formerly known as the Internet. In Microsoft's defense (a phrase you're probably surprised to hear), the latest service pack finally turns on the firewall, by default. But the damage for over 100 million PCs has already been done. Apparently, 25% of the Windows world is still using Windows 98. None of those installations can be saved if they're already connected to the internet. They are likely already infected and filling your inbox at this very moment. To save them, they will have to be decontaminated, a process which very few users are capable of. If you do maintenance for less-well-informed members of your family, who come to you wondering why they can't browse the web (it's so slow) and why their modem lights are always blinking like crazy (it annoys the cat) and why they have little to no resources and/or memory free and where did those toolbars come from and why does it take forever to startup? ... the article has some sound advice. Hijack their machines right back. 1. Set Windows Update to automatically update the computer, without asking questions. 2. Install a personal firewall that blocks almost everything by default. 3. Buy a 2- or 3-year subscription to an anti-virus program and set it up to automatically download all updates. 4. Buy an anti-spyware tool and set it up to automatically update, scan, and remove spyware. 5. Replace Internet Explorer with Mozilla or Mozilla Firefox*, and then hide that blue E so it's not on the desktop. 6. Replace Outlook Express with Mozilla Thunderbird. *For step 4, I heartily recommend Opera, even though it's not free, because it's a better browser as far as I'm concerned. Tell them it's the latest service pack and save them from themselves. ]]> https://www.earthli.com/news/view_article.php?id=976 https://www.earthli.com/news/view_article.php?id=976 Wed, 28 Jul 2004 23:31:46 +0200 is a discussion about Firefox, for the most part. Several times during the discussion, people "praise the Extension Manager" in Firefox. It's not enough. To really take off, this Extension Manager is an excellent base. However, if you visit the site and see the jungle of plugins that await you, you're a fool if you think "most" people are willing to wade through it to configure their browser. Programmers and geeks love it. "Most" people will not. Here's the thing. I think that the plugins are a great idea. It's wonderful that the community can finally get going and create a hotbed of research for browsing tools. This is the kind of place where new ideas for browsing are born. I just don't want to play. Ordinarily, I would. A few years ago, I would have been one of the first there, downloading every last stupid plugin to see which one does what without crashing -- until I had a set that defined my perfect browser. Now, I'm just too damned lazy. No, check that. I'm too damned busy to waste massive amounts of time configuring and customizing my browser. And I think a lot of other people are the same way. They may not be too busy, but they probably won't dare to jump into those types of configuration hassles. No, what Firefox needs is to create standard packages of components. Some people at Opera have already been thinking along these lines, with "Hugin and Munin" , offering downloadable packs that magically converts your Opera into Thunderbird/Firebird lookalikes to allow people to slowly convert from another browser. Firefox has an even bigger advantage, because their extensions allow them to add actual new functionality to the browser, whereas Opera only reconfigures existing components. I use Opera. Show me how Firefox does everything Opera does. For free. Then maybe I'll convert to Firefox. But I'm not going to dig through a site full of extensions trying to find the ones that make Firefox do all the stuff Opera does. This comment at Slashdot maintains exactly that: that "Opera..." functionality is available as extensions. "Every single one of the things you listed is available as an extension for Firefox. ... I like extensions because they are incredibly powerful, but avoid bloat for the average user." I think that, as soon as we're talking about the average user, we can stop talking about people that will install extensions. Imagine if the entire IE market were to start using Firefox. How many of them do you think would use extensions? For the average user, there's a huge advantage to having a product that was designed ... instead of a product that is designed by the customer. The Firefox technology is starting to come together; just because it's open-source doesn't mean it can succeed without at least some consideration of product positioning and listening to market needs. What is Firefox's target market? IE users? Opera users? Figure that out, then build pre-made browser configurations that address those markets exactly. ]]> https://www.earthli.com/news/view_article.php?id=852 https://www.earthli.com/news/view_article.php?id=852 Sun, 18 Apr 2004 21:13:49 +0200 https://www.earthli.com/news/view_article.php?id=856 https://www.earthli.com/news/view_article.php?id=856 Sun, 18 Apr 2004 21:12:20 +0200 (Stupid Microsoft Tricks: Why the Richest Company on Earth Feels it Needs to Cheat) talks about recent happenings in yet another lawsuit for anti-competitive practices that Microsoft is involved in; in this case, they are accused of flat-out stealing another company's technology after prolonged (2 years) discussions with that company about licensing. When asked to provide all emails from that period, the record at Microsoft came up blank for 35 weeks. "The reason for this mass erasure, it was explained, is that Burst technology was unimpressive and not of interest to Microsoft, and the e-mails were simply not worth keeping." Is anyone going to be held liable for this obvious purgery? ]]> https://www.earthli.com/news/view_article.php?id=924 https://www.earthli.com/news/view_article.php?id=924 Sun, 04 Apr 2004 23:09:34 +0200 (Timing is Everything: Look at Anti-Trust Law as a Digital Design and --- Guess What --- Microsoft Wins) strings together some numbers to back it up: because it pays. Crime really pays for Microsoft; there hasn't been a punishment handed out that makes obeying the law more cost-effective. Take the recent fine levied by the EU against Microsoft in a ruling that determined that Microsoft had abused its monopoly position in Europe: "...while the fine looks like a lot of money, to Microsoft it isn't. That $600 million is the amount by which Microsoft increases its cash hoard in TWO WEEKS. Even if the EU had hit Microsoft with its maximum allowable fine of 10 percent of gross global turnover or about $3 billion, it wouldn't have mattered. Paying a $3 billion fine to keep moving a $10 billion annual European cash machine that yields $7 billion in annual profits is a no-brainer." And that's only assuming Microsoft ever pays the fine. As with all their other court decisions, it will, of course, be appealed. It will, of course, linger in court for a long, long time. The punishment is just so small compared to the astronomical profits they rake in for breaking the law. The US anti-trust decision of a few years ago is still in appeal, despite the laughable sentence exacted on Microsoft by a corporation-friendly justice department. They aren't complying with the restrictions laid out in that decision, either. "While it may look like the company agreed to comply, what is really happening is the company agreed to be bound by certain requirements, not necessarily to comply with them." That's an important difference lost on most fans of Microsoft. Just because they accept their sentence doesn't mean they aren't going to do it again (or aren't in the middle of doing it). In a person, that would be pathological. In limited liability capitalism, that's the best way to run a large firm and reward your investors. Morals? Ethics? Can't you see we're running a business? Make your own business and compete. Let the market decide. Don't you believe in a free market? Sink or swim. If you can't stand the heat, get out of the kitchen, baby. It's not cheating if you don't get caught. If you do get caught, use your "Get out of jail free" card and keep on playing! In the EU case: "They will appeal the decision, which will freeze any real enforcement action and effectively authorize continuation for another two to five years of otherwise proscribed behavior while the appeal moves forward. And if its European appeal fails, Microsoft will still be $8-20 billion ahead of where it might be had they actually attempted some version of compliance, which they won't." And no one can stop them because what else can you do? You fine them according to the law. The law does not account for simply this kind of egregious "taking advantage of a legal system". If the US got really harsh on them (bear with me while I spin a small fairy tale), Microsoft could threaten to "pull up stakes and move ..., the very threat of which would stimulate a frenzy of political ass-kissing". Yeah, they're that big; how'd you like to be the politician that made Microsoft contribute less to the economy? Yeah, I thought so. Have a happy retirement, Senator. ]]> https://www.earthli.com/news/view_article.php?id=887 https://www.earthli.com/news/view_article.php?id=887 Sun, 15 Feb 2004 21:58:01 +0100 (Steps that you can take to help identify and to help protect yourself from deceptive (spoofed) Web sites and malicious hyperlinks). In it, you'll find the recommendation that you should "...not click any hyperlinks that you do not trust. Type them in the Address bar yourself." So now, you have to type all URLs by hand because Microsoft can't fix their browser. Isn't it time to consider "Opera" or "Firefox" ? A read on Slashdot put this latest development into persepective: "To go back to an often used analogy, if Microsoft were a car company and their vehicles happened to exhibit a problem with the engines catching on fire (as happens, sometimes, with real car manufacturers) other makers would recall and fix the problem. "Not microsoft! "They're innovative. They'd send a helpful sheet out to owners: " -- -- -- -- -- -- -- -- - Things you can do to protect yourself from an engine fire: "The most effective step you can take to protect yourself from an engine fire caused by the known defect, is pushing your car manually. By pushing your car manually, you can avoid creating the temperatures required to initiate combustion. This will keep your car safe. Also, you can save fuel and contribute to a cleaner environment. " ]]> https://www.earthli.com/news/view_article.php?id=785 https://www.earthli.com/news/view_article.php?id=785 Wed, 19 Feb 2003 21:27:22 +0100 is the technology I want, I just don't know of any cameras that use it (or that are in my price range). The diagram to the left shows the technology behind this successor to the standard CCD: "The layers are positioned to take advantage of the fact that silicon absorbs different wavelengths of light to different depths, so one layer records red, another layer records green and the other layer records blue. This means that for every pixel location on Foveon X3 image sensors, there's actually a stack of three photodetectors, forming the first and only full-color image sensors." There is a full description with more pretty diagrams available at "Why X3 is better" . Mosaic Without Blur Filter [image] Mosaic With Blur Filter [image] Foveon X3 [image] Since Foveon detectors don't have to compromise on which color to detect at which pixel, all three values are represented equally instead of using "50% of pixel locations to capturing green light, with the remaining 50% evenly divided between red and blue" (the human eye is much more sensitive to green than red or blue -- digital movie formats like MPEG take advantage of this fact as well in order to get higher compression). Cameras using Foveon detectors also don't have to do "complex processing ... to interpolate the information mosaic image sensors miss" and hence don't need to apply "blur filters [to] reduce artifacts", which reduces the "resolution and sharpness" of the stored image. The images to the right compare the classic, "mosaic" capture device, both filtered (note the softness added by filtering) and unfiltered (note the artifacts that arise from interpolation) and the Foveon capture device, which is crisp, has no artifacts and is far more faithful to the original color. Since each pixel is the now the same, the Foveon can also support grouping pixels together, which reduces the perceived resolution, but "increases the signal-to-noise ratio, allowing the camera to take full-color pictures in low-light conditions". In this way, resolution (which is often higher than needed for a lot of situations) can be scaled back in order to provide higher signal quality; at the same time, this "allows the image sensor to run at higher frame rates" so it can capture pictures at a much faster rate than large CCDs. This feature makes it possible to capture both images and video with the same detector, "[a]nd since the sizing of pixels can be done in an instant, a Foveon X3 image sensor can capture a high-resolution still photo in the midst of recording video." The Foveon also supports a feature called "windowing", which is probably familiar to photographers, enabling "enabling auto-focus, digital zoom and zone metering." It is possible to "digital zoom into any region of an image" without repositioning the camera or sensor. Where can you get this revolutionary thing? From the "Sigma Corporation" , which has a camera called the "S9" <>, which also uses the RAW file format internally, to provide lossless compression. Missing from their pile of statistics and figure, though, is a price, which I presume is a bad sign. It is a bad sign. I've since found that "Photo.net" is selling it for a mere USD$3000. Looks like we're in for a wait on Foveon Technology. ]]> https://www.earthli.com/news/view_article.php?id=769 https://www.earthli.com/news/view_article.php?id=769 Sun, 16 Feb 2003 22:32:40 +0100 is a systematic investigation of the behavior of the MSN website when approached by different web clients. Recently, "Opera Software" discovered that on the home page for the MSN web-site, "...it looks like Opera7 has a serious flaw so that many lines are partially hidden [and] the page shows less content than users of Microsoft's Internet Explorer (MSIE) see." "[MSN in Opera 7]" They concluded that the MSN web-site is sending back a different style sheet to only Opera browsers. However, when the page (and stylesheets) returned to IE was loaded in Opera 6.x or 7.x, it displayed exactly the same as in IE. There are two possible conclusions here: either the Opera-specific coding is deliberate, but is based on the untested notion that the site has to tailor its content to fit browsers or it's a deliberate hack to make the Opera browser look like it can't handle even simple pages. Think of the purveyor of the web-site and decide for yourself. (Note: the image to the left is of the faulty stylesheet displayed in IE, proving that it's malformed code and not the Opera renderer's error). The first conclusion is less believable because: 1. It costs more to make your web-site coded specifically to different browsers. You don't do it unless you have to. 2. The "typo" in the stylesheet is hardly something that could happen by accident; -30px margin is not a common setting. 3. This is the home page for the site - did no one even do a sanity check on all browsers? 4. It's Microsoft; they understand quite well how to sabotage reputations. For those that think this is no big deal: just remember that a year from now when you hear that Opera isn't doing so well anymore and that Microsoft has miraculously cornered the phone browser market. Remember that when you read articles telling you that "well, Opera just doesn't render the sites correctly...that guy showed us the way it screws up sites...I think even really big, popular sites like MSN don't even work. You'd think they could get THAT to work, at least." It's the seed you plant in people's heads that grows into a large Opera-mistrusting tree. Then wonder again why Microsoft would do this. It's not the blocking of the site itself; It's the mindshare you gain. It's the seed you plant in people's heads that grows into a large Opera-mistrusting tree. Go to the MSN site with the user agent set to Opera. It's complete crap. Don't tell me that Microsoft's not afraid of Opera...not on the desktop, no...but Opera's kicking it's ass in the phone business. There is a good ending here: "After this page had been referenced by Cnet, The Register and Slashdot, MSN changed their setup so that Opera7 no longer receives the distorted style sheet. Opera6, however, still does." However, how many people know that? How many people are going to remember that it wasn't Opera's fault? The damage is done in increments to Opera's reputation and Microsoft has the power to make it happen because they've got a monopoly on the desktop and channel all their sheep users through their web site (it's the number 1 portal in the world). As another followup, Opera has struck back. "Slashdot" reported that "Opera Releases "Bork" Edition" , a special version of their browser that runs all requests to MSN through a filter to make it look like it was written by the Swedish chef from The Muppet Show. It's an eloquent, powerful statement about the power of web standards and the chaos that can ensue when companies hold rivalty in higher importance than their customers: "This is a joke. However, we are trying to make an important point. The MSN site is sending Opera users what appear to be intentionally distorted pages. The Bork edition illustrates how browsers could also distort content, as the Bork edition does. The real point here is that the success of the Web depends on software and Web site developers behaving well and rising above corporate rivalry." Mr. Håkon Wium Lie (CTO - Opera Software AS) said that "they repeatedly have complained to MS about this and other problems over a long time, but nothing happened". The problem was heavily reported to Opera and MSN for two weeks before Opera decided to take the error a little more public. At this point, they have every right to believe it's intentional. As one poster on Slashdot said: "if one of my clients' web page was in worldwide news because of a problem that involves fixing one line of CSS, I'd be sure to fix it the very next day". Of course you would. But then you don't have a monopoly on people's systems, browsers and homepages, do you? Microsoft didn't fix the page until a huge shitstorm was raised; until the harm outweighed the benefits. Ask yourself what the benefits are (and who benefits) if MSN is illegible in Opera browsers and you can decide for yourself whether it was just a 'mistake'. ]]> https://www.earthli.com/news/view_article.php?id=734 https://www.earthli.com/news/view_article.php?id=734 Mon, 09 Dec 2002 00:59:44 +0100 reports in "Another Critical Microsoft Hole" that IE, once again, has a problem with granting ActiveX controls too many rights. This latest security flaw in Windows NT/2000 (not present in XP) is a really good as the best solution Microsoft can recommend is to "...to make sure you have no trusted publishers, including Microsoft." ("Security Bulletin MS02-065" (Microsoft Security Bulletin MS02-065: Buffer Overrun in Microsoft Data Access Components Could Lead to Code Execution (Q329414))). That means you have to remove all the trusted publishers from your list, because the control at issue is actually signed and verified by Microsoft. They hesitate to simply disallow that control entirely, using something called a "Kill Bit" to get IE to ignore it, because so many sites hardcode for this particular control. How bad is the problem? "This vulnerability is rated critical because an attacker could take over an IIS server or an Internet Explorer client and run code," Microsoft warned. "Any IIS server with MDAC and all Internet Explorer clients should apply the patch immediately." However, "it is currently possible to make patched systems vulnerable again". As if you're not having enough fun applying patches yet. Of course, you could always just fork over the cash and upgrade to XP, which doesn't have the problem. To Microsoft's credit, they are being quite aggressive about solving this particular hole. Even to the point of coming up with the embarassing solution of saying that they can't be trusted. So, perhaps they do mean it when they say they are now a security company and start babbling about Palladium and DRM. They just mean they care about telling people about security holes, but don't actually intend to write decent software. Again, to be fair, this is not a problem on XP, and software does get better and more secure with newer versions, but it's hard not to be suspicious of their motives in changing from a company that invokes the DMCA for security flaws to a company that trumpets them. Perhaps the whole Trusted Computing movement needs to find a less ironic torchbearer, no? Perhaps Microsoft already knows who could provide these services. "MS paper touts Unix in Hotmail's Win2k switch" on "The Register" examines a recently unearthed study done by Microsoft's server division when they acquired Hotmail (which ran, and still runs, on OpenBSD). Even if they have a secure operating system, I would still wait until we see some behavior from them that isn't just embarassing. The Register again comes up with the scoop "On the Microsoft FTP server leak" . Apparently, early in November 2002, they had an FTP server open, on which some employees had "'published' files [with] an estimated 11 million customer email addresses and seven million snail mail addresses". Thank goodness I don't buy anything from them. ]]> https://www.earthli.com/news/view_article.php?id=644 https://www.earthli.com/news/view_article.php?id=644 Wed, 13 Nov 2002 17:18:38 +0100 by Bruce Schneier at "Counterpane Internet Security" explains what is known about "Palladium", the code-name for Microsoft's trusted computing intiative. It's abbreviated as Pd, like an element. Isn't that cute. This is a natural outgrowth of Hollywood's (in the form of the MPAA and the RIAA) jihad against its customer base and our acceptance of the blame. It aims to use hardware to prevent people from doing anything that Hollywood doesn't want them to with technology they buy. "The idea is that different users on the system have limitations on their abilities, and are walled off from each other. This is impossible to achieve using only software; and Pd is a combination hardware/software system. In fact, Pd affects the CPU, the chip set on the motherboard, the input devices (keyboard, mouse, etc.), and the video output devices (graphics processor, etc.). Additionally, a new chip is required: a tamper-resistant secure processor." The machine itself won't be foolproof, in fact, "Microsoft readily acknowledges that Pd will not be secure against hardware attacks". However, they do try to make it secure and promise that "[i]t is their intention to design the system so that hardware attacks do not result in class breaks: that breaking one machine doesn't help you break any others". That goal will prevent pirates from simply issuing keys that can compromise an entire set of systems; there will be no money in breaking these systems. At least that's the plan. The more probable reason for Microsoft's laser-like focus on trusted computing is not that they want people to crash less or get fewer viruses or get less junk mail. This doesn't really affect their bottom line really (as increasing sales over the years have shown). What affect their bottom line is pesky end users that think they own Microsoft products when they plunk down their $249.99 for them. "Like books and furniture and clothing, the person who currently buys new software can resell it when he's done with it. People have a right to do this -- it's called the "First Sale Doctrine" in the United States -- but the software industry has long claimed that software is not sold, but licensed, and cannot be transferred." These machines will use several partitions of data with different DRM rights attached to manage your content for you. Even though it's your machine, if you want to view certain content, then "MPAA, Disney, Microsoft, your boss" can "put... stuff there that you can't get at". If this kind of security can be delivered, the way we access art content will change significantly. You can't borrow that CD from your friend anymore. No more trying out a program before you buy unless they want you to. No watching that DVD or snipping a piece out of it. How about those handhelds, on which you'll listen to tunes and watch movies and read the news? "Will you need a Pd-enabled device -- the system is meant for both general-purpose computers and specialized media devices -- in order to view copyrighted content? More likely. Will Microsoft enforce its Pd patents as strongly as it can? Almost certainly." He ends his Palladium introduction with a few strong points. One of them is "When you think about a secure computer, the first question you should ask is: "Secure for whom?"" Once again, it's those with the money or power who will have the full use of their computers. Everyday users will have to give up some of their trust if they want to watch movies or listen to music or maybe even browse some sites (maybe that NY Times login won't stay free forever). In short, "Microsoft really doesn't care about what you think; they care about what the RIAA and the MPAA think." They want those companies to start to deliver their high-bandwidth content on Microsoft systems and those organizations will never approve delivery in a world occupied by too open an Internet like we have today. Take heart though; first of all, there will always be a black market (or gray market) for goods and services that people really want, but have gotten too inconvenient to get legally. If done in enough volume, these markets become impossible to close and/or prosecute and become the norm. That will happen again. Hopefully the public gets more educated and balks when told to buy devices that hem them in. Second of all, "[l]ike everything else Microsoft produces, Pd will have security holes large enough to drive a truck through." Finally, he warns that you should be very aware of who is interested in getting Pd made into a reality. The MPAA. The RIAA. Microsoft. "Pay attention to the antitrust angle. I guarantee you that Microsoft believes Pd is a way to extend its market share, not to increase competition." If this comes to pass, Microsoft will only become more ubiquitous unless people get more careful. Your use of technology will only get more controlled and that's a bad thing. The content and news you have access to now is already filtered and adjusted and molded to create the reality you need in order to be a good little patriotic consumer. What will it be like when your tools are hardwired to curtail rebellion? Schneider concludes: "My fear is that Pd will lead us down a road where our computers are no longer our computers, but are instead owned by a variety of factions and companies all looking for a piece of our wallet. To the extent that Pd facilitates that reality, it's bad for society. I don't mind companies selling, renting, or licensing things to me, but the loss of the power, reach, and flexibility of the computer is too great a price to pay." Bob Cringely, of the eponymous "I, Cringely" (I, Cringely &emdash; the Pulpit) adds in the article, "I Told You So" (I Told You So: Alas, a Couple of Bob's Dire Predictions Have Come True): "Under Palladium as I understand it, the Internet goes from being ours to being theirs. The very data on your hard drive ceases to be yours because it could self-destruct at any time. We'll end up paying rent to use our own data!" That's a very real possibility. "How long until only code signed by Microsoft will be allowed to run on the platform?" Another good question. Software developers will have to pay Microsoft a license in order to run on Pd-systems. More secure, trusted-transaction computing is a necessity. It's a job that has to be done before more mundane tasks can be automated and used as appliances rather than as "guru" tasks. "I just don't think we have the right people on the job." The "Schneier newsletter" (August 15, 2002 - Cryptogram Newsletter) has a lot of links to more information on Palladium if you're interested. ]]> https://www.earthli.com/news/view_article.php?id=727 https://www.earthli.com/news/view_article.php?id=727 Mon, 11 Nov 2002 20:07:58 +0100 in "Business World India" and this article, "Bill Gates pledges $100 million to fight AIDS in India" (Bill Gates pledges $100 million to fight AIDS in India, meets patients) on "Canada.com" on the same day and wonder whether the two are connected? I mean, Gates himself said that "...[h]e worried that India's enormous progress in information technology - the country has the only Microsoft software development centre outside the United States - would be thwarted by AIDS." At this point, I don't expect (and view with suspicion) any supposed altruism on behalf of probably the most rapacious businessman in America. In "The Times of India" , "Gates gives India more than Africa for AIDS" quotes Gates as saying further that "[t]here is so much promise from the great talent in this country that AIDS should not limit it." Again, noble-sounding, but considering that "last year, India purchased packaged software worth $409 million - of which 80% were Microsoft products", how altruistic is it? Is it really possible that he's investing US$100 Million in the population of India in order to keep it alive long enough to buy more Microsoft products? No, even I don't believe that. :-) Is it possible that it's just a happy coincidence that he can help humanity and increase his personal wealth at the same time? Yeah, that's possible. Especially when, as seen in the title of the article, Africa, which has far worse of an AIDS problem, doesn't rate as much as India, whose "number of HIV carriers has stabilized to 3.5 million to four million - 0.7 per cent of its adult population - - over the last three years". It might explain why Gates is quoting a disputed "recent U.S. National Intelligence Council report that predicts the number of HIV-infected people in India will rise to 20-25 million by 2010". India's Health Minister regards the report as "completely inaccurate". However, the inflated number suits Gates purposes since he can more easily rationalize giving money to a country that also tends to buy a lot more software (and Microsoft software, specifically) than Africa does. "Estimates put the present size of India's developer population at anywhere between 450,000 and 600,000. That's about 10% of the world's developer population. By end-2002, India will probably have more developers than any country in the world. This is why it is important to gain control of this population." With the recent loss of government agencies in India and China (see "Linux Gains Ground Abroad" ), it seems Microsoft should be very interested in shoring up support in one of the largest countries in the world. Perhaps it's just a happy coincidence that Gates's Foundation is giving money to a country that is die-hard Microsoft, but in which recently "Linux has made inroads into the Indian landscape". The other question to ask is in what form this charity is given. If it's in the form of Microsoft licenses "donated" to hospitals or whether it's actual cash which the hospitals, agencies or government is allowed to spend on the services it needs to combat AIDS. Perhaps I'm just being too suspicious again (although it would be reminiscent of those generous aid packages given by the US, in which the receiving country is required by contract to use a large percentage of the grant on specific US companies, usually weapons manufacturers). Perhaps also it would be too cynical to ask just how much charity you need to give in order to make a dent in the taxes levied on a fortune "which stood at $43 billion in September [2002]". However, if it's truly unabashed, unreserved cynical reporting you want, it's one-stop shopping at "The Register" in "Billg tosses coins to India's poor, touts MS" in which they say: "... he's gone off to India for a bit of philanthropic pandering to women and children, and selling of MS products to developers. The actual selling will be handled by legions of MS flacks, not Gates, to help establish the illusion that this trip is purely humanitarian in nature. ... [T]here is something profoundly tasteless in donating money to avert human suffering as part of a commercial publicity campaign, and touting it so publicly." As for the wealth of coverage the "New York Times" is offering on Bill's trip, The Register is reasonably "certain it has nothing to do with the NYT's whopping share of the MSN-8 advertising budget". ]]> https://www.earthli.com/news/view_article.php?id=719 https://www.earthli.com/news/view_article.php?id=719 Sun, 03 Nov 2002 17:15:27 +0100 reports in "Europe's Microsoft Alternative" that a region of Spain, "a western region of Spain called Extremadura, a mostly rural expanse of olive trees and tiny towns with 1.1 million inhabitants", is planning "to convert all the area's computer systems, in government offices, businesses and homes, from the Windows operating system to Linux". This is a trend that started in Asia, with first China, then India, declaring that they would be standardizing on Linux or other open-source software for their operating software and applications software. Venezuela also recently decided to use only open-source software for all government functions -- covered in "Venezuela's Government Shifts to Open Source Software" on "Linux Today" . The reasoning is quite logical, that Venezuela "indicated that they wish to implement this new policy so that now Venezulan programmers will be handling most of the government's software needs, though keeping a large amount of government funds within the nation itself." As "The Register" points out in "Venezuela eliminates govt. software piracy" : "Piracy is of course a major concern of Microsoft, which for years turned a blind eye to the pestilence so long as world + dog was getting itself nicely addicted to their wares. Now, with nearly every government and business hopelessly dependent on their products, the company feels it's safe to tighten the screws..., leaving behind huge bills for licensing oversights. ... But as Venezuela has just come to realize, the best way to appease Microsoft -- indeed, to assist them in this noble crusade -- is to replace their products with free ones." Early this year, Peru had an open debate about whether to use only open-source alternatives (in which Microsoft played a very vocal interested party, full of gloom and doom). The original open letter written by Peruvian Congressman, Dr. Edgar David Villanueva Nunez, is available in "GNU.org.pe: Peruvian Congressman's Open Letter to Microsoft" , also on "Linux Today" . The arguments there are quite well thought out and makes the Microsoft sales flack's repudiations look pathetic. With OpenOffice and StarOffice both offering free variants and Mozilla providing a free browser and mail client, most government functions no longer really need to use Windows anymore, with their increasingly expensive licenses. This switch in Spain is also not just a tiny test-bed, "more than 10,000 desktop machines have been switched, with 100,000 more scheduled for conversion in the next year". The region paid a developer $180,000 to put together a custom install disc to set up a completely open-source operating system and applications environment. The disc has already been more widely distributed in Spain. As for the rest of Europe, countries "as far away as New Zealand and Peru have inquired about duplicating the region's efforts". In fact, "There are now nearly 70 laws or policy proposals pending in two dozen countries that would force or at least encourage governments to use open-source software. This year Germany said it signed a contract to use Linux in many of its government systems; other significant economic powers such as the United Kingdom, China, Italy and Brazil are studying the matter." Microsoft's response to this? The expected response: "Consider that there's a lot more to the total cost and value of a product than the initial offering somebody might give you," Smith said." Yes, and what exactly is that added value? The opportunity to buy more Microsoft products to get it to actually do what you needed it to do in the first place? Perhaps, it's the fabulous support: " For instance, it is often expensive to find support services for free software, whereas such help comes bundled with the purchase of Windows." Keep in mind that this is the Microsoft rep speaking. My experience is that one can usually easily find free support for free products. Microsoft's "support" plans are usurious. And finally, "companies like Microsoft have a vested interest in updating their products; that's not necessarily so with free software." Again, my experience shows that free software, or software provided by more focussed vendors, is updated far more frequently than Microsoft's. When was the last time your IE browser was updated with new features? Of course, Office and Windows get updated and those upgrades are usually much better for Microsoft than for you. "Namibia wisely spurns M$ 'gift' in favor of Linux" on "The Register" is another tale of Microsoft's efforts to spread farther. They offered to "help" Namibia switch from a Linux-based software offering to Windows. However, their help was to only offer "free licensing for Office Pro, valued at $2,000", which would entail a resulting outlay of "an extra $9,000 for OS licensing in order to exploit the privilege of using the office software". The switch to Microsoft networking and and connectivity products (presumed MSN) would "cost the organization something like $22,000..., in addition to the $9,000 [required] to accept Redmond's incredibly generous $2,000 offer...". The Register sums up nicely what can be construed from this example, that Microsoft " intends to use non-profit organizations in desperately poor countries to subsidize its promotional ambitions and its sales strategy". No wonder countries are switching to Linux in droves. How else do you live with yourself? Note: article authored entirely on and iMac ;-) ]]> https://www.earthli.com/news/view_article.php?id=646 https://www.earthli.com/news/view_article.php?id=646 Fri, 30 Aug 2002 01:02:36 +0200 3.998GHz! Now that's an overclocked chip. This was spotted at "Slashdot" in an article called "P4 2.80GHz Overclocked to 3.917GHz" . In their English language abstract, they mention that they actually got it to run at 3.998GHz after all. Yeah, those numbers are correct. These crazy Finnish guys place the entire chip assembly into a bath of liquid nitrogen inside a styrofoam cup (see picture). In a couple of pictures, you can see the Fluke thermometer registering -193°C! The whole site's in Finnish, but you should check out "Intel Northwood 2,8GHz" on "MuroPaketti.com" if you're interested in seeing what some people will do with a $500 chip. ]]> https://www.earthli.com/news/view_article.php?id=574 https://www.earthli.com/news/view_article.php?id=574 Thu, 22 Aug 2002 22:23:42 +0200 has a rundown on the latest Apple/Mac conference, MacWorld New York, in "MWNY Keynote: Time to line the RDF with asbestos?" , which announced a lot of new products, both hardware and software. Most of the hardware changes are incremental updates, with the IMac upgrading to a 17" wide screen, which is very cool. The IPod now has "[u]p to 20 GB of storage, official support for calendar and contacts, and Windows support via MusicMatch." The most interesting updates are on the software side, in particular changes made to the operating system in the new version, code-named "Jaguar" . It has finally gotten "spring-loaded folders" back and introduces multi-threading into many more places in the Finder. It also includes literally dozens of new application, utilities and tools, including all new version of several programs (like iTunes, Mail, Sherlock and the Address Book). The new rendering layer is confirmed in OS X 10.2, with all display output funneled through "QuartzExtreme" , which "delivers crisp graphics, anti-aliased fonts, and blends 2D, 3D and QuickTime content together with transparency and drop shadows". If you have a 3D video card made in the last couple of years, QuartzExtreme takes advantage of hardware-accelerated OpenGL to boost display speed by up to 3-4 times. Even without hardware support, you still enjoy a 50% to 100% speed increase, as seen in the diagram below. [QuartzExtreme Performance Chart] In Apple's own words: "Here’s how it works. Quartz uses the integrated OpenGL technology to convert each window into a texture, then sends it to the graphics card to render on screen. The graphics processor focuses on what it does best — graphics — freeing the Power PC chip to do more operations in the same amount of time. Everything is zippier." This is the same rendering layer that communicates solely in PDF instructions so any screen or document can be saved as a PDF file. If you're a programmer, "The Register" reports in "Apple unveils shader language, QE APIs" , which gives some scant detail of API support for QuartzExtreme functionality for other programs (though all programs will benefit immediately from improvements to 2D functionality and compositing, few programs take advantage of the 3D support in the interface). The new 3D functionality in the interface library "features ... programmable shaders and a new instruction set for creating OpenGL shaders..." and the "Quartz Compositor features a per-pixel alpha channel, and per-window warp and transform". The Register notes that this means that "true 3D icons and 3D windows become possible" with full hardware support. Early reviews of Jaguar are in, and they are extremely positive, noting many other subtle changes to the interface to improve usability and feel. "MacWorld" 's review, "Should You Jump to Jaguar?" (Should You Jump to Jaguar? Read Our Review.) noticed many small changes, like a "pop-up menu in the General preference pane [that] lists four antialiasing algorithms" for text in the interface so you can choose one that suits your monitor and eyes, and other subtle overall changes like: "Apple's interface designers have toned down the pulsating blue default button in dialog boxes, making its effect subtler. All the Aqua buttons have a flatter appearance, and drop shadows are lighter -- a small but noticeable improvement." As for the vaunted QuartzExtreme, they say that "[t]he result is a system that feels more responsive, especially when it's busy with other tasks." It's also got a faster Classic environment ("roughly 70 percent faster"), far better interoperability with Windows, and an Address Book application that brings in a system-wide database of contact information, which sounds a lot like what the BeOS folk made years ago. This will allow all of your Mac OS X programs, once they've been modified to use the shared database, to use only one set of contact information. The iChat and Mail programs already use it, and the "database itself has the potential to eliminate redundant and out-of-date information across your Mac". If you're still running OS 9, should you upgrade? "If you haven't yet switched to OS X, there's never been a better time -- OS X 10.2 addresses most of the complaints OS 9 users have about OS X. We recommend that you run it on a Mac with a G4 processor, and you'll want as much RAM as your system can take, but OS X 10.2 is refined and powerful -- and it's worth the move." ]]> https://www.earthli.com/news/view_article.php?id=633 https://www.earthli.com/news/view_article.php?id=633 Thu, 22 Aug 2002 21:39:04 +0200 on "CNet's News.com" provides basically a press release about Opera's new 7.0 browser, dubbed Presto. Latest information on the 7.0 release is available on "Opera software" 's "7.0 page" (Opera 7.0 News Page). "Dubbed Project Presto, after the musical tempo-character marking indicating speed and lightness, the rewritten browser was designed to make Opera both faster and more compatible with the Document Object Model (DOM), an emerging standard technology that lets scripts, like JavaScript, act on individual elements of a Web page." DOM-support is the only place where Opera is really lacking. Their CSS and other standards support is outstanding and the browser and rendering engine are already cross-platform, extremely fast, and relatively bug-free, not to mention almost entirely crash-free. It has a small hard-drive and memory footprint and tons of usability features. Why rewrite it? After all, as "Opera Software co-founder and CEO Jon S. von Tetzchner" has said, "Our old engine wasn't that bad". "Opera Software employs about 60 engineers. When Project Presto began 18 months ago, two of them were working on it; now a majority have left the legacy Opera code behind." Since it's apparent Opera has spent so much time on the new version, which "has been rewritten from the ground up", it's no surprise now that several shortcomings in the current browser haven't been addressed. Why update Javascript and DOM functionality in the old engine when the new one is almost ready and already does everything better and faster? This should be very reassuring to Opera users; desktop platform users haven't been abandoned for the device market (as most recent advances in Opera have been made in platform support, interface usability and localization support). "The Register" writes too that "Opera poised for beta of version 7 heavy duty rewrite" . They say that "...Opera Software intends to go to first beta of its new version, Opera 7, soon, with soon probably meaning weeks rather than days or months." This is a very exciting development, as the Opera browser is now a stable, fast, small, full standard implementation with lots of usability that trumps both Mozilla and IE. (For example, bring up a long article in Opera, hit F11 to go full-screen, then hit keypad+ until the zoom level is good for you.) With full DOM support, there will truly no longer be a reason to keep the other browsers around. ]]> https://www.earthli.com/news/view_article.php?id=598 https://www.earthli.com/news/view_article.php?id=598 Thu, 22 Aug 2002 21:17:23 +0200 project finally released a 1.0 version of its browser. "Mozilla Milestone 1.0: the Review" on "Ars Technica" gives a good overview and review of the final product. Those who've downloaded builds of Mozilla over the years have doubtless found that Mozilla seems to suffer from an identity crisis. Sometimes it seems like a browser, sometimes it seems like a standards-compliant rendering engine, sometimes it feels like a development environment cum operating system. It includes support for a slew of technologies, like HTML, CSS, DOM and ECMAScript. It also supports XML, XHTML and its own interface specification language, XUL. "The core of Mozilla is its rendering engine, dubbed "Gecko." Gecko is responsible for taking the markup sent from the server (typically HTML) and turning it into the end product displayed in the browser." It also has full support for PNGs, including alpha channel support. To see a page that looks quite nice, it simple to code and illustrates the power of combining all of these technologies, check out the "Complex Spiral Demo" . Another great demo is the "Eagle Shadow Demo" <>, which demonstrates the power of alpha-PNGs combined with proper DOM and ECMAScript support. The great thing about this project is that the Gecko engine was designed as a separate component, separate from the browser, mail application, JavaScript debugger, etc. that makes the program. The basic rendering engine can be inserted into any application that wants it since it's under an open-source license. "Overall, Gecko is an excellent rendering engine that does a great job implementing the W3C standards while simultaneously handling the less "compliant" content on the web. Several companies already recognize the excellence of Gecko, using it as the core for browsers such as Netscape 6/7 and Chimera (for the Macintosh)." Note that the entire application is completely platform-independent and has been built for Windows, Mac OS 9, Mac OS X and varieties of Linux. This makes the renderer even more attractive. In fact, it seems that AOL will be using the Gecko core for their 8.0 version on Windows and the next version on Mac OS X (since AOL owns Netscape, which developed the lion's share of the Mozilla code). In the end, Ars Technica rates the Mozilla browser a 7 out of 10. The gecko engine they give a 9 out of 10, but the Navigator to which it's attached (the browser itself) is a bit balky and just feels slow. The standards support is better than Opera, but the rendering and interface are just much slower (perceptually and in testing). They recommend that "[i]f you currently use IE, you won't lose too much apart from the professional polish by switching over to Mozilla." I'm not sure which professional polish they're alluding to in the Microsoft product, the security holes or the crashing (which, admittedly isn't as bad as it used to be). On any platform, I would still recommend Opera as a primary browser. It's the fastest and supports the standards extremely well. Mozilla supports the DOM model much better, but feels sluggish after getting used to Opera. Opera feels like a browser application more than a technology demo and shares a cross-platform renderer across all supported platforms (which includes all the platforms Mozilla supports and the QNX and Symbian operating systems as well). ]]> https://www.earthli.com/news/view_article.php?id=612 https://www.earthli.com/news/view_article.php?id=612 Thu, 22 Aug 2002 15:25:04 +0200 (State of Decay: The New Adventures of Verity Stob) on "DDJ" documents a new classification system for a phenomenon everyone in the computing world has experienced: cruft. Cruft is defined thusly: "When you spot a class interface that is no longer used by any client, but that nobody dare delete, that's cruft. It is also the word "seperate," added to a spellchecker's private dictionary in a moment of careless haste, and now waiting for a suitably important document. Cruft is the cruel corruption and confusion inevitably wrought by time upon all petty efforts of humankind." This happens to any machine, regardless of operating system, but the classification system is based on examples from the Windows world (surprise, surprise). It's now possible to refer to your machine as being in a particular stage of system entropy, rather than just a vague "It runs real crappy". The list that follows is extremely funny, most especially, of course, if any of the symptoms have happened to you. Note: against all notions of fair use, I've reproduced the whole list here in case the document dissappears, as they have a habit of doing on "DDJ" .

Cruft Force 0

Virgin. Description: The "Connect to the Internet" shortcut is still on the desktop, and the "How to use Windows" dialog appears at logon. Menu animations and the various event-based sound effects — even the dreaded Microsoft Sound — seem cheerful and amusing. Likewise, a clandestine installation of the Blue Screen Of Death screensaver (complete with simulated reboot, natch) from the Sysinternals web site is hilarious. Compilers run crisply, and report only sensible, easily resolved errors. There are just nine directories off C:\. Filled with the enthusiasm that goes with having a brand new machine, the user resolves to stick to the new-fangled security-conscious temp directory buried deep somewhere below Documents and Settings.

Cruft Force 1

New. Description: User has taken time to rename cutesy desktop icons incorporating the first person singular possessive pronoun. Twice, the mouse cursor has done that poltergeist trick where, with the actual mouse stationary, it drifts three inches due east and then stops. For no reason at all. Works fine afterwards though. Brrrrrrr.

Cruft Force 2

Comfortable. Description: User has now got around to resetting Explorer so that "web content in folders" is suppressed. Something has made a C:\TEMP directory in the proper place unasked, for which mercy the user guiltily feels grateful. A strange entry is found in the System event log: MRxSmb: The redirector was unable to initialise security context or query context attributes. Assiduous googling of the key phrases, up web site and down newsgroup, establishes that, although many have wondered, nobody knows what this means.

Cruft Force 3

Lived-in. Description: One time in seven when the user starts Word or other Office 2000 app, instead of running, it pretends it is installing itself for the first time and starts a setup program. Directory count in C:\ up to 17, and something has pooed a Paradox lock control file there, too.

Cruft Force 4

Middle-aged. Description: Amount of time from screen showing "real" Windows background to the logon box appearing is >30 seconds. Sometimes cannot "browse" other machines on LAN. Get first real BSOD. Uninstall jokey screen saver, replace with SETI. An extra disk of huge capacity has been installed. CD-ROM moves from drive F: to drive [:

Cruft Force 5

Worn out. Description: Some time after bootup, always get a dialog "A service has failed to start - BLT300." What is BLT300? Nobody knows. Although one can manually remove/disable this service, it always reappears two or three reboots later. If one double-clicks a document icon, Word takes 4 minutes 30 seconds to start up. But it still works fine if started as a program. Somebody opines that this is due to misconfigured DDE. Or the Mars-Jupiter cusp.

Cruft Force 6

Limping. Description: [Delphi|Visual Basic|Java] suddenly remembers a trial shareware component — deleted six months ago because it was rubbish — and refuses to compile anything until it is reinstated. "Web content in folders" Explorer setting switches itself back on unbidden. "Setup" programs start crashing while unpacking their own decompression DLLs.

Cruft Force 7

Wounded. Description: No longer able to logon using original account as the system freezes, so must logon as "Verity2" or similar. There are now nine items in BOOT.INI: the original W2K starter, a brace of two-entries-each NT4s (one Turkish), a Windows 98, and three assorted Linuxen. Left to start up by itself, the machine chooses a broken installation of SUSE and halts with a kernel panic.

Cruft Force 8

Decrepit. Description: A virus checker is installed at the insistence of IT. This actually improves performance, apparently violating Newton's laws. Blue Screens Of Death are served daily. The SETI screen saver, like ET himself, encounters difficulty calling home and despairing during an overnight run creates 312 copies of its icon in an (impressively expanded) system tray that fills half the screen. Successful connections to the LAN are very rare.

Cruft Force 9

Putrefaction. Description: Can only see the 32-GB D:\ partition — the one which has all the source code on it — at every third boot. Directory count in C:\ up to 93, partly because some [one/thing] has put a complete (but non-working) installation of the Eudora e-mail client in the root. Starting Control Panel shows rolling torch animation. The applet icons never appear.

Cruft Force 10

Expiry. Description: Machine only runs in Safe mode at 16-color 800×600, and even then for about a minute and a half before BSODing. Attempts to start an app are rewarded with a dialog "No font list found." Ordinary dodges, such as reformatting the hard disk(s) and starting again, are ineffective. Cruft has soaked into the very fabric of the machine, and it should be disposed of safely at a government-approved facility. There it will be encased in cruft-resistant glass and buried in a residential district.

]]> https://www.earthli.com/news/view_article.php?id=584 https://www.earthli.com/news/view_article.php?id=584 Thu, 08 Aug 2002 23:58:05 +0200 point out in "Microsoft begins to clean out Hotmail" "[a]s part of a series of new storage policies aimed at driving more people toward its paid services". So, in addition to Microsoft changing their privacy policy every couple of weeks by adding some extra vendor-sharing checkboxes to their preferences, then selecting them as 'on' by default, now they reserve the right to delete email from your mailbox as well. Amazingly, this is being done as a service for customers, as "MSN product manager Parul Shah" says: "... the deletion of old sent messages is part of Microsoft's plan to help people manage their e-mail, adding the company figured "if it's 30 days or older, it's probably safe to go ahead and delete that." But then, he/she goes on to say that "Shah said the easiest way to ensure that messages are saved is to create special folders and move the messages out of the sent file." So, the same users that need 'help' deleting their email are the same ones who know or are able to figure out how to create new folders and move email around. Unfortunately for many people, they just don't get it and continue to think they can get something for nothing. If you're using the Yahoo service, that appears to be true. If you're still using hotmail (and millions are), you get what you pay for. They have the most bugs, viruses, junk mail and server outages...and now they even delete mail for you even if you're not over the storage limit. Basically, they're making their free service horrible in order to drive you to their paid service. It's a strange way of attracting business in a world with free services that function just as well as their paid services, but the amazing thing is that it works. ]]> https://www.earthli.com/news/view_article.php?id=564 https://www.earthli.com/news/view_article.php?id=564 Fri, 26 Jul 2002 16:34:07 +0200 "GM's Billion-Dollar Bet" on "Wired.com" is about GM's bold plans for a fuel-cell vehicle by 2010, long before other major rivals expect to be forced by oil shortages to change their fleet. In short, GM sees opportunity in fuel-cells because it allows them to design a car that requires far less tooling, less design and fewer moving parts than the internal combustion dinosaurs we think are advanced now. The car itself will be quite different from cars today simply because the move to fuel cells frees up a lot of space and removes limitations imposed by designing around a parts required by an internal combustion engine. "It dispenses with just about everything that makes a car a car, such as the engine, transmission, steering wheel, and gas tank." The smaller number of moving parts means it will last a lot longer and may be able to absorb customer reluctance at higher initial prices (though high prices don't seem to slow the SUV market much at all, but that's for buying land-crushing gas-guzzling statement of American pride, not a water-spitting, electric, quiet, environmentally friendly concession to the tree huggers). "[fuel-cell chassis]" GM's design "looks like a giant skateboard, with motors in the wheels and the power supply and controls built into the 6-inch-thick chassis". With the engine gone from the front, the floor flattened into a layer of cells, with no transaxle or transmission and the gas tank removed as well, the GM design forms a platform for a complete divergence from conventional automotive design. "Seats don't have to lie in rows. The trunk can run the length of the car. The driver can choose where to sit." This is all acheived with a radical rethinking of automotive design, tooling and assemby lines. GM plans to "replac[e] most of the hardware in today's cars with wires and circuits that will be standard across multiple models". That move alone will "streamline its production system and drastically cut costs" to make fuel-cell vehicles more competitive on price and bring them closer to reality within "eight years instead of 30". On top of the new choices for design, it's clean. "Rather than spitting out carbon monoxide and other smog-causing gases, it emits nothing but water because it runs on hydrogen." It's quiet, dead silent because "[e]lectric motors, located in each wheel, propel the vehicle." It'll last longer because "[w]ith few moving parts, it will last for decades." It will also make driving easier than before, because it has independently controlled motors in the wheels, which will make it much more maneuverable and agile than cars today. "The AUTOnomy will accelerate like an F-111 because its electric motors will deliver instant torque to the wheels. It will be silent. The wheels will be controlled independently, allowing the car to swivel and move sideways, doing away with the cumbersome three-point turn." On top of all of that, "[i]t will generate more electricity than it uses and be equipped to apply the surplus to power the owner's house." What's not to love? It's an uphill battle best expressed in the U.S. car-industry tenet, "The Amount of Sacrifice Americans Will Be Willing to Make to Drive a Nonpolluting Car Is Exactly Zero", is it possible to sell such a radically changed car to the U.S. public? Probably not. This sounds far more like a car that will be enthusiastically embraced by Europe first. It's quite obvious what Americans want, or what they have been effectively brain-washed to want. Automakers, with the full complicity of the public: "...have been using their muscle to keep federal fuel-efficiency standards exactly where they were when enacted in 1975. Freed of stringent regulation, the Big Three have reaped billions selling high-profit, gas-guzzling SUVs. Look at the window stickers on GM's current crop, arrayed in the Renaissance Center lobby - Chevrolet Avalanche: 13 city, 17 highway. GMC Denali: 12, 15. Cadillac Escalade: 12, 15. My Pontiac GTO got better mileage than this 33 years ago. Individual engines have become more efficient, but because "light trucks" (SUVs, pickups, and minivans) constitute half of all vehicle sales (54 percent for GM last year), national average fuel economy is at its lowest since 1980: 20.4 mpg." There's a commercial right now showing the new Ford Excursion (Expedition? I can't tell, what's the difference?) with 4 or 5 people staring into the back of it as it folds its own seats down in the back. Wow. Now you can free up those precious seconds of seat-folding for more important things, like calling someone on your cell-phone or cramming more cheese doodles into your face while swigging a mountain dew and wondering if Dad's going to notice the ding in the fender. Plus, there's all the saved effort: bending over and pulling a handle can be so tedious. That appears to be the entire point of the commercial, and, perhaps, that's a good example of just how stupid they (corporations, marketers, the auto industry, etc.) think the customer is. Whereas the commercial should be insulting and offensive, no doubt it more often inspires people to think "I wonder if Bob's truck does that? I bet it doesn't. He's going to be soooo jealous!" "Consumers aren't in any way motivated to buy anything but the vehicle they want," Wagoner says, "and if you don't sell them what they want, they'll buy somebody else's." I think that statement flys in the face of reality and vastly underestimates the power of advertising. People buy what they're told to buy. People buy because they're told to buy. Do you think someone wants to pay 20% of their monthly income on a car payment for a car that does nothing more special than one that would cost 10%? No. They're putting their money into a car because it has been drilled into them that having the most expensive car possible is the highest priority. A lot of people are accepting lease arrangements so big, they could work one day less per week or take more vacations if they just got a less expensive car that does the same thing. But having a fancy car is a higher priority than working less. If you ever mentioned that they express that opinion through their actions, most people would deny it vehemently. They'd say: 'no way, I hate working...I'd love to have more time off'. Then why did you buy that expensive car that you don't need? Because you're trained to want it, trained to want to buy as much stuff as you can because that neoliberal economy needs growth to survive. I think the statement above should be modified to 'Customers will buy the car they're told to buy, or the one their friends or boss bought'. The trick is to convince them that this is the car they want to buy. For some, it's not a fact that it "must be able to go at least 300 miles between fuelings and take no longer than five minutes at the pump." Those would be nice, but for some of us, it's more important that our vehicles don't simply make us mobile hypocrites, eschewing all principles of conservation and ecology simply for convenience. It's just that very few of us live in the States. So, if not in America, where the fuel-cell car is doomed to failure (at least in the short term), regardless of how exciting this all sounds, where could these cars be sold? America is the largest established market, but "Just 12 percent of the world's population can afford to own a car or truck". That's a pretty large untapped market of people without personal vehicles. GM says you "couldn't do it with the internal combustion engine [because of] emissions and affordability." The fuel-cell car, though, with a smaller assembly process and no emissions problems, may be perfectly suited to this niche, once initial prices come down. "AUTOnomy's greatest untapped market might be in China, where there isn't already an entrenched gasoline network. In GM's dreams, the AUTOnomy becomes ready to debut at about the time China's billion-plus people are economically ready for car ownership. China builds a system to deliver hydrogen without ever having one in place for gasoline, the way some African countries are leapfrogging telephone cables and moving straight to cellular. Chinese farmers are given the chance to use a single chassis for both tractor and market truck, and, if they hook up to their houses at night, they make wiring rural China for electricity unnecessary." That would be pretty cool. A leap over the oil economy and over pollution. One billion people using personal vehicles that spit out water and electricity. It's so cool, you just want to help make it happen, don't you? If you're interested in how a fuel cell works, there's a decent article on "How Stuff Works" called, predictably, "How Fuel Cells Work" . (There are a lot of articles on How Stuff Works, just search on 'fuel cells'.) "Page 3" covers the chemistry behind the reaction of a "Proton Exchange Membrane", the simplest type of fuel cell, and the one used by GM. "H₂ is forced through the catalyst by ... pressure. When an H₂ molecule comes in contact with the platinum on the catalyst, it splits into two H+ ions and two electrons (e-). The electrons are conducted through the anode, where they make their way through the external circuit (doing useful work such as turning a motor) and return to the cathode side of the fuel cell. ... on the cathode side..., oxygen gas (O₂) is being forced through the catalyst, where it forms two oxygen atoms. Each of these atoms has a strong negative charge. This negative charge attracts the two H+ ions through the membrane, where they combine with an oxygen atom and two of the electrons from the external circuit to form a water molecule (H₂O)." ]]> https://www.earthli.com/news/view_article.php?id=549 https://www.earthli.com/news/view_article.php?id=549 Wed, 24 Jul 2002 14:52:16 +0200 has a "Satellite Radio Review" . It discusses availability, content, and pricing. There are currently two providers in the market, "XM Radio" and "Sirius" . The technology behind it is quite involved, with XM Radio supporting a "100,000 Sq. Ft. broadcasting facility in Washington DC". The whole enterprise is enormously expensive: "Sirius radio operates three birds all at Geo-Sync orbit as well. When you add up the cost for digital audio storage, encoders, multiplexers, modems, satellite transmitters, and the "bird" you can easily see the enormous cost of deploying such a system." The difference with broadcast anaolog radio is that the signal is only converted to analog for the final step, after reception, before putting it to the analog speakers. Therefore, digital radio can transmit at a lower quality ("128kb/s, 44.1Khz stream") than a corresponding analog signal. Even the new antennas are marvels that make all of this technology possible now, with "new antenna technology has shrunk the satellite antenna down to a small flat size that can receive the satellite signal while in motion." The biggest drawback is, of course, interference from large buildings, bridges, etc. However, the service interruptions were usually limited to "around 5% of the time, but it is enough for me to mention it." In order to address this problem, both companies will have to install ground-based hardware to work around obstructions. "Fortunately, both XM and Sirius are going to install some 1,000 repeaters throughout the country. ... The antenna will pick up this signal as well, and as noted above, the signal will go down the Terrestrial line into the receiver, for supposed un-interrupted reception." How is the quality of the signal? What about the content? How many commercials are played? Are there any non-commercial channels? The answers to all of these questions are pretty good. There aren't nearly as many commercials; some channels have none - others have at most 6 minutes per hour. It is a pay service after all. "Well, to put it simply, fantastic. Depending upon the receiver one chooses, you will notice clear highs, deep, resounding bass, and a clear mid-channel. To put it in terms we would understand, I'd say the audio sounds at least as good as a 128kb/s MP3, but is not quite CD quality." What kind of music is available? This guy says pretty much everything you could dream of is available. There are 100 channels of radio, way more than the handful of stations you probably consider acceptable in analog format. Many of them are dedicated format stations, all compiled and created by XM itself, with their own DJs and announcers, who seem to know what they're doing. "... a full 74 of them are direct XM formats. Only 26 of them of them are either re-broadcasts of large metro FM stations (with commercials and all), audio feeds from CNN, Fox News, CNBC, C-Span, and the Weather Channel, audio versions of MTV and VH1, or mostly talk content from major providers like Clear Channel (eg. Art Bell, Bruce Williams, Phil Hendrie, and Glen Beck). So a full 74% of XM Radio is unique content..." The article gives an extemely complete rundown of the content available on "page 4" . For all of this, at around "$10/month, XM is a bargain". So, it seems if you spend a fair amount of time listening ot radio in the car, or even at home, or you're just sick of maintaining your MP3 collection ("...burning, categorizing, and ensuring that all your MP3s are in excellent condition is a lot of work"), the capital investment of $300 for the receiver and antenna should be well worth it. ]]> https://www.earthli.com/news/view_article.php?id=555 https://www.earthli.com/news/view_article.php?id=555 Wed, 17 Jul 2002 19:00:49 +0200 has the article "A Wireless End Run Around ISPs" discussing how this trend started, some symbols to recognize and possible future usage or problems. Advocates of a free internet have been creating their own antennas and 802.11b or WiFi networks for a little while now. "Enthusiasts can buy an antenna for as little as $50 ... [m]ore creative techies have turned a Pringles can or a piece of tinfoil into a working antenna." But, how do you tell whether there is a connection in the area? "... Create a set of international road signs to the Internet. Two half-moons chalked on a pavement or a wall indicate that a connection is available. A full circle informs would-be surfers that the node is closed." The term warchalking has a suitably geeky pedigree: it's "a play on "wardriving" or "warwalking," which refers to people who toot (sic) around cities with special software designed to sniff out open wireless nodes. (And the term "wardriving" derives from "wardialing," a word coined in the classic 1983 sci-fi thriller WarGames starring Matthew Broderick.)" Of course, one easy-to-spot problem is that ISPs are going to want to shut down these private mini-ISPs as quickly as possible, regardless of the fact that the bandwidth they're sharing has already been paid for. If you let other people use a bit of your bandwidth for free, in corporate capitalist terms, that's people who aren't paying for their own access. That's not fair, of course...and you'd be a fool and a communist to think that it might be. "On June 25, Time Warner Cable sent a dozen "cease and desist" letters to customers it says were publicly instructing others about how to share broadband connections on the NYC Wireless site." The corporations are, of course, addicted to the "one-wire, one-customer philosophy", which makes sense only for the corporation. A cable connection can easily service the web browsing of a dozen or more people. Naturally, that adds us to a loss of 11 customers in the eyes of corporations, but the service being provided is perfect. That's exactly the connection most people need and it's cheap, and will soon be ubiquitous. It'll be like tuning in to a radio station for free. You can just hop from connection to connection as you move around, jumping in and out of broadband networks. Now, that's cool. For more information about Warchalking, check out "Black Belt Jones" . ]]> https://www.earthli.com/news/view_article.php?id=554 https://www.earthli.com/news/view_article.php?id=554 Tue, 16 Jul 2002 16:02:14 +0200 (A Guide To Metric Time Or Decimalized Time) seen on "Slashdot" in "Isn't it Time for Metric Time?" discusses a proposed system for converting to base-ten time. As if the U.S. doesn't have enough problems converting to metric measurement, except curiously for soda containers, here comes a new proposal sure not to be adopted. "Metric Time (MT) is an attempt to create a decimalized time system for our modern base-10 using world. This is a neglected part of the Metric System (or SI) which has created a whole measuring system based on 10 for mass, distance, volume, etc., but no official decimalized time units for normal day-to-day use. Since any system for measuring time is arbitrary, we should be using one that is most practical for us. I think that system is Metric Time." Actually, reading through it gives one a creepy feeling, as of something not quite right. If the human race ever gets into space, this is likely a system that may be used, as it's not dependent on any planetary system. The full discussion is quite in-depth and well thought out, with conversions to and from "Anglo-Babylonian Time (ABT)" time (our Base-60 system). ]]>