Links and Notes for April 4th, 2025

Below are links to articles, highlighted passages[1], and occasional annotations[2] for the week ending on the date in the title, enriching the raw data from Instapaper Likes and Twitter. They are intentionally succinct, else they’d be articles and probably end up in the gigantic backlog of unpublished drafts. YMMV.

Table of Contents

• Public Policy & Politics
• Journalism & Media
• Economy & Finance
• Science & Nature
• Art, Literature, & Cinema
• Philosophy, Sociology, & Culture
• Technology & Engineering
• LLMs & AI
• Programming
• Fun

Public Policy & Politics

Digital Privacy at the U.S. Border: Protecting the Data On Your Devices by Sophia Cope, Amul Kalia, Seth Schoen, and Adam Schwartz in 2017 (EFF)

“If you are not a U.S. citizen, refusing to comply with a border agent’s demand that you unlock your device, provide your device password, or disclose your social media information may raise special concerns.”

“If you are philosophically opposed to intrusive border searches, you may feel that the importance of asserting your rights may outweigh the risk of having your devices seized, being extensively questioned, missing a flight, or otherwise being detained. If so, you should still educate yourself so you can be an effective advocate.”

“Please be aware, however, that taking some precautions may attract unwanted attention and scrutiny, even if the precautions otherwise succeed in protecting your information. For example, if detected by a border agent, the fact that you wiped your hard drive may prompt the agent to ask why you did so. Even traveling without devices or data that most travelers typically have could attract suspicion and questions.”

“CBP agents may be more sympathetic to travelers who truthfully state that the traveler does not have access to data or was prohibited by their employer from granting anyone access to it.”

“There is a significant risk that border agents could view deliberately hiding data from them as illegal. Lying to border agents can be a serious crime, and the agents may take a very broad view of what constitutes lying. We urge travelers to take that risk very seriously.”

This is a strong reason not to even visit.

“Unjustified escalation may violate the law and, as discussed in the next section, you may have some recourse after you exit. However, some travelers may want to avoid any risk of escalation if they can.”

“Third, do not lie to a border agent. It is a crime to make a false statement to a law enforcement official who is asking you questions as part of their job.”

This is fucking insane. If it’s a crime to lie, then don’t say anything. They can, of course, still say that you said something and produce a generated version of your voice saying it.

“Sometimes law enforcement officials achieve so-called “consent” by being vague about whether they are asking or ordering a civilian to do something. You can try to dispel this ambiguity by inquiring whether border agents are asking you or ordering you to unlock your device,”

“Border agents may seize your devices. Then CBP and ICE agents may attempt to access your digital data without your assistance. Even if they cannot decrypt your devices, they may be able to copy the encrypted contents of your devices. If they later obtain your passwords, or find vulnerabilities in the encryption, they may be able to decrypt their copies. The government’s scrutiny of your devices may take months. During this time, you may need to purchase replacement devices, and you will not have access to the information on the devices.”

“[…] lower courts have held that body cavity searches and strip searches are “non-routine” and also require reasonable suspicion.”

How generous.

“[…] courts stressed the significant privacy interests in all the data modern digital devices contain—call logs, emails, text messages, voicemails, browsing history, calendar entries, contact lists, shopping lists, personal notes, photos and videos, geolocation logs, and other personal files. Digital devices typically cover many years of information and include the most intimidate details of a person’s life. The Supreme Court in Riley rejected the notion that cell phones are the same as physical items: “That is like saying a ride on horseback is materially indistinguishable from a flight to the moon” just because both are “ways of getting from point A to point B.””

“The digital device is a conduit to retrieving information from the cloud, akin to the key to a safe deposit box. Notably, although the virtual “safe deposit box” does not itself cross the border, it may appear as a seamless part of the digital device when presented at the border.”

“[…] the Supreme Court in Riley stated that using the search incident to arrest exception to justify searching files stored in the cloud “would be like finding a key in a suspect’s pocket and arguing that it allowed law enforcement to unlock and search a house.””

“[…] some courts have rejected First Amendment challenges to border searches of digital devices. Given the increasing amount of sensitive information easily accessible on and through our devices, and the increasing frequency and intensity of border searches of this information, we hope that other courts will rule differently in the future.”

This information is from 2017. As I’ve followed the issue over the years, it keeps going back and forth as various circuit courts either protect phones or make them open season.

“The best way to preserve your Fifth Amendment rights, given your own risk tolerance, is to politely but firmly decline to comply with a border agent’s demand to unlock your device, provide your password, or disclose your social media information. Only a judge, and not a border agent, can decide whether the Fifth Amendment protects this information.”

“[…] many courts have instead adopted a lesser, but still strong, test. Under this test, the government may compel a suspect to unlock their device only if the government can prove with “reasonable particularity” that it is a “foregone conclusion” that a “certain file” is stored on the device. Border agents usually will not know what is stored on the device, so they can’t compel you to disclose your password.”

“There is a strong argument that a traveler’s compliance when border agents demand the unlocking of a device, the device password, or social media information, should never be treated as voluntary consent. Border screening is an inherently coercive environment, where agents exercise extraordinary powers, and travelers are often confused, tired after international travel, and/or rushing to make a connecting flight.”

“Officers may detain electronic devices for subsequent search at an on-site or off-site location. If an officer does so, they must issue a custody receipt to the traveler (Form 6051D). The device detention should not exceed five days, though CBP managers may (and do) grant extensions of weeks or months.”

Can Border Agents Search Your Electronic Devices? It’s Complicated. by Esha Bhandari in March 2025 (ACLU)

“The government claims the authority to search all electronic devices at the border, no matter your legal status in the country or whether they have any reason to suspect that you’ve committed a crime. You can state that you don’t consent to such a search, but unfortunately this likely won’t prevent Customs and Border Protection (CBP) from taking your phone.”

“Since 2018, they are not required to return your device before you leave the airport or other port of entry, and they might choose to send it off for a more thorough “advanced” or “forensic” search. Barring “extenuating circumstances,” they claim the authority to hold onto your device for five days — though “extenuating circumstances” is an undefined term in this context, and this period can be extended by seven-day increments. We’ve received reports of phones being held for weeks or even months.”

“If you leave the airport or other border checkpoint without your device, make sure you get a receipt, which should include information about your device and contact information allowing you to follow up.”

“Whether you’re a citizen or not, though, we always recommend that you enter the password yourself rather than divulging it to a CBP agent. They still might demand that you share it, but it’s a precaution worth trying to take. If you do hand over your password, it’s likely to end up in a government database, so change it as soon as you have the chance and make sure you no longer use that password for any other account.”

WTF.

Double-Tapping Gaza by Jeffrey St. Clair (CounterPunch)

“Marc Botenga, a member of the EU parliament from Belgium, excoriated the alleged “balanced approach” of the EU toward Palestine:

“High Representative [of EU for Foreign Affairs Kaja] Kallas, you speak about a ‘balanced approach.’ But balanced on what? On war crimes? On genocide? On the killing of 15 humanitarian workers? On mass graves? On the killing of children! And what would that balance be, exactly? Some nice words for the Palestinians and more weapons for Israel? That is complicity in genocide…In the face of Russian war crimes in Ukraine, I have never heard you speak about a ‘balanced approach.’ There are 40 EU sanctions regimes, and not one on Israel, that stand in front of the international courts accused of genocide. ICC asks for the arrest of Netanyahu and yet no EU sanctions. Stop this complicity now. Palestinians need acts, not words.”

“Anthropologist Jason Hickel, author of The Divide: A Brief Guide to Global Inequality and its Solutions, on the horrifying images coming out of Gaza this week:

“We are seeing ACTUAL beheaded babies on our screens and this is not even a news story? Wtf is going on. False claims of beheaded babies on October 7 received wall-to-wall coverage for DAYS. Where is the outrage? It’s pure racism. We have a media class that has lined up to normalize genocide, and it is obscene. I have seen not one but *several* beheaded babies over the past months. These images are seared forever in my mind. And yet I have not seen a single story about this from the major outlets that ran nonstop coverage of the hoax in 2023. A minimum fact-based headline appropriate for this week would be something like: “Israeli soldiers have beheaded babies, murdered aid workers in summary executions, and carried out targeted assassinations of journalists in an escalation of the ongoing Western-backed genocide.”

Buddy, that is not the consent that they’re trying to manufacture. No-one in power cares about Palestinians. The U.S. hates them. Europe hates them. They want them all to die. That’s why they don’t report on their deaths. They know it’s not a good look to be cheering on a genocide, so they just ignore any news that might show them in a bad light. If there is news that shows their cheering of a genocide in a good light—even when it’s pure fabrication—then they report the hell out of it, because they think it makes them look righteous. it’s as simple as that. Nearly every single person in power and in the sway of western media has the morals and principles of a serial killer.

“Altogether, more than eight out of ten Jewish Israelis support Trump’s plan to ethnically cleanse Gaza of all Palestinians. Approximately 14% of all Israelis (13% of Jews) consider the plan a “distraction,” which does not indicate outright opposition but does reflect skepticism about engaging with it. 13% of Israelis believe Trump’s proposal is “immoral.” This group is overwhelmingly Arab (54% of Arab respondents hold this view). Among Jews, only 3% consider the plan “immoral.””

3% of the people that matter in that country think that something immoral is going on. Nobody else has a problem with it. They just wish it were over, and they mostly just wish that the hostages would be returned, which makes them look like utter naifs because their government has zero interest in bringing them home. They are not interesting in peace and security. They are interesting in conquest through slaughter, through extermination. They want the land and they’re going to take, devil take the hindmost.

Meanwhile, U.S. president Trump is openly bragging on social media (Twitter) about committing clear war crimes by having annihilated what was obviously a municipal gathering of unarmed civilians in Yemen, writing,

“These Houthis gathered for instructions on an attack. Oops, there will be no attack by these Houthis!

“They will never sink our ships again!”

Who is this savagery even for? Who are these jokes for? Where is the president of peace? Why does no-one resist his savagery? Answer: because they don’t even see it as savage. People will now calmly tell you that the president is simply defending the country—and the world—against the savagery of the Houthis.

The handful of people that are up in arms about this are running in the wrong direction, publishing pictures of other, similar gatherings—where Yemenis gather in a large, ragged rectangle—saying that the Yemenis were unarmed! That they were participating in a peaceful ceremony. None of that matters! Who cares if they were armed? What does that have to do with anything? Could their arms conceivably cause harm to the U.S.? Of course not. Not unless U.S. soldiers had invaded their country and gotten within range. This is all obviously evil and illegal. There is no justification for it. See it for what it is: a wildly criminal act by a bully.

Trump will tell you that they started it, that they are sinking U.S. ships. There is zero evidence for that. None of this is true. Nothing any of them says is true. I would say that it’s unclear why they bother lying about it, but those lies work. People continue to believe the utter fantasy of righteousness and justice on the side of the west.

“The last word this week goes to Omar El Akkad, who makes this disturbing, but I think irrefutable point, in his new book, One Day, Everyone Will Have Always Been Against This:”

“There is an impulse in moments like this to appeal to self-interest. To say: These horrors you are allowing to happen, they will come to your doorstep one day; to repeat the famous phrase who they came for first and who they’ll come for next. But this appeal cannot, in matter of fact, work. If the people well served by a system that condones such butchery ever truly believed the same butchery could one day be inflicted on them, they’d tear the system down tomorrow. And anyway, by the time such a thing happens, the rest of us will already be dead.

“No, there is no terrible thing coming for you in some distant future, but know that a terrible thing is happening to you now. You are being asked to kill off a part of you that would otherwise scream in opposition to injustice. You are being asked to dismantle the machinery of a functioning conscience. Who cares if diplomatic expediency prefers you shrug away the sight of dismembered children? Who cares if great distance from the bloodstained middle allows obliviousness? Forget pity, forget even the dead if you must, but at least fight against the theft of your soul.”

I suppose that this is all that remains to try to stem the horror: an appeal to ego every. Damned. Time. That seems to be the only way, as an appeal to principle clearly has no chance because people don’t have principles, they have teams. They don’t care. They cannot be made to care. Even when told that they’re allowing their souls to be tarnished, that there is something terribly evil going on, that it is being deliberately hidden from them in order to make them complicit in it—they don’t care. They’ll blithely pootle off down to the Apple Store and buy themselves a brand-new iPhone 16 on a sunny day. They’ll cheerilly agree with all of their friends that Iran, Hamas, Russia, and China are the true evils in the world but, rest assured, our soldier of light and goodness are fighting on our behalf to besiege them. It’s fucking embarrassing (YouTube) (24s).

Trump Shares Collateral Murder-Style Snuff Film On 15th Anniversary Of Collateral Murder by Caitlin Johnstone (Substack)

“This is what people are saying when they claim “There was a ceasefire on October 6th,” implying that there was peace before Hamas launched its attack in 2023. They don’t mean the same thing that normal, healthy people mean by peace. Their vision of “peace” was always Palestinians lying down and submitting and slowly getting shuffled out of the way, like the indigenous victims of other western settler-colonialist projects throughout history.

“That’s not peace. That’s just unresisted abuse.

“But that’s the only kind of “peace” that Trump and his fellow empire managers will ever accept in the middle east. The “peace” of compliance and obedience. The “peace” of prostration before the empire. The kind of “peace” you get when you start murdering everyone in the room until there’s nobody left but corpses and those who submit to your will.

“This is who these people are. This is the closest thing to “peace” that they will ever allow under their rule.”

The Backlash Against Israel’s Western-Backed Crimes Will Fuel The Far Right by Caitlin Johnstone (Substack)

““Antisemitism” is fast becoming a self-fulfilling prophecy. As westerners tire of having their speech rights taken away by their government to protect the interests of a state that’s committing genocide under a Star of David banner, a lot of them are going to blame Jews for this. As western governments bend over backwards to help murder Israel’s enemies in the middle east, a lot of westerners are going to blame Jews. As the drums for war with Iran beat louder and louder and parents fear their children will be sent off to die for Israel, many will blame this on the Jews.

“I am not saying this is a good thing. It’s a very bad thing. But it’s also reality.”

“Those of us who oppose the criminality of Israel and its western allies from the left will do all we can to keep the far right’s arguments from gaining traction, but it won’t be our fault when we fail. It will be the fault of the western governments who’ve spent all this time stomping out the civil liberties of their citizenry in the name of fighting “antisemitism” while raining military explosives on the middle east and backing the slaughter of tens of thousands of children under a Star of David flag.”

Journalism & Media

Truth Is Antisemitism. Protest Is Terrorism. Dissent Is Russian Propaganda. by Caitlin Johnstone (Notes From The Edge Of The Narrative Matrix)

““Peace through strength” is just empire-speak for warmongering. Literally translated it means “Warmongering — but the good kind!” Anyone who uses this slogan is either an empire manager, a propagandist, a bootlicker, or a moron. There are no exceptions.”

“Capitol Hill swamp monsters like Tom Cotton, Jim Banks and Josh Hawley have been aggressively hammering the lie that antiwar activist group Code Pink is funded and directed by China. Every time they are confronted by Code Pink activists you’ll hear these empire managers regurgitating this slander, which they are able to do because in 2023 the New York Times wrote a disgusting, deceitful smear piece falsely insinuating that Code Pink is paid by China.

“And what’s so freakish is that if you actually read that New York Times piece, one thing you will not find anywhere in its contents is a claim that anyone in Code Pink are paid by China or working for the Chinese government. The New York Times never makes this claim because it’s a lie and they’d get sued if they printed it, so what they do instead is loosely imply connections to China by drawing a lot of conspiratorial red yarn between Beijing and an American millionaire named Neville Roy Singham, who is associated with Code Pink and happens to support communism.

“There’s absolutely zero solid substance in the New York Times piece that these imperial war sluts keep citing. None. But because the New York Times published that smear, now those war sluts can shriek about China whenever they’re approached by Code Pink activists challenging them on their warmongering in order to delegitimize their urgent questions.

“Such a disgusting, evil thing the New York Times did in defense of the imperial war machine. Instead of doing journalism, they handed the empire a propaganda gift that keeps on giving. No matter how much you despise the empire’s propaganda mouthpieces, it isn’t enough.”

Why Do Democrats Destroy Their Own? by Matt Taibbi (Racket News)

“I don’t agree with Jayapal about many or even most things, but if she’d engaged with me, I’d have noted I too opposed the Antisemitism Awareness Act and the Trump Executive Orders that use the definition of antisemitism written by the International Holocaust Remembrance Alliance (IHRA). If asked, I’d have shared some of her concerns while pointing out many of the global censorship bodies I spent years researching (like the EU with its Digital Services Act) not only target anti-immigration protesters and nationalists, but outlaw the very causes Jayapal professes to care most about. For instance, Palestinian activism can be “illegal content” thanks to the same IHRA formula under the DSA, which still has a profound impact on speech on American platforms. It could have been interesting.

“Everything you need to know about modern Democrats, particularly so-called progressives, is encapsulated in the fact that instead of turning to the witness with a lifetime of First Amendment advocacy, Jayapal opened the floor to Nina Jankowicz, a former Homeland Security official who came within a hair of becoming America’s first “Disinformation Governance” chief.”

“All political groups try to neutralize their critics, but the Democrats’ habit of turning on their own supporters, and casting them as monsters and moral reprobates in elaborate PR campaigns, is unique. If you make the mistake of trying to understand it, as I did for years, it can consume your life. No longer wondering why is what allowed the quick response this time.

“Since 2017 I’ve been in a club that includes Glenn Greenwald, Joe Rogan, Jimmy Dore, Tulsi Gabbard and a long list of others, including non-Americans like Julian Assange (and others whose cases are still unfolding). Commonalities include accusations of sexual indiscretion, secret affiliation with Russia or some other foreign power, and financial corruption. Enemies are always evil, not mere disagreers. That vehemence is what stands out. They don’t just excommunicate, they hate. It’s the only sincere part left.”

Hamas Succeeded In Exposing The True Face Of The Empire by Caitlin Johnstone (Substack)

“It’s all fully visible now. It’s all right there on the surface. We can try to continue pretending we live in a free society that believes in truth and justice and regards all people as equal, but we’ll all know it’s a lie. What we are, first and foremost, is a civilization that will actively support history’s first live-streamed genocide. That’s the single most relevant fact about the western world at this point in history. It’s staring us right in the face every day.

“October 7 certainly didn’t make life any easier for the Palestinians, but one thing it did do was take away our ability to hide from ourselves. Hamas reached thousands of miles around the world and permanently destroyed our ability to avoid the truth about the kind of dystopia we are really living in. Our rulers may succeed in eliminating the Palestinians as a people, but one thing they will never be able to do is put those blinders back on our eyes.

“What has been seen cannot be unseen.”

That is unfortunately not true. The rulers have done a great job of keeping a lid on it. It’s been going on for 18 months and is going strong, stronger than ever. Many people have never woken up. Many will go right back to sleep.

John Oliver is (Still) Part of the Problem by Freddie deBoer (Substack)

“[…] when you see liberals share the same videos week after week of an annoying British man sneering down a camera lens to tell you how stupid everyone else is, you do have to ask if the American left-of-center has any sense at all of how much their project has been damaged by their reputation for patronizing self-righteousness. If the Trump era has proven anything, it’s just how wildly sensitive voters are to the perception that someone somewhere is judging them. That level of sensitivity to vague slights is stupid and the grievance usually disingenuous, but that’s politics, baby. And Oliver is such a pitch-perfect caricature of progressive self-regard − snarky, aloof, judgmental, incurious − that I sometimes wonder if his show is a brilliant op pulled off by the Heritage Foundation.”

“About the specific issue of trans women in sports, I confess that my default stance at this point is exhaustion; it’s just such an incredibly small bore issue, of relevance to a tiny minority of trans people, that I struggle to see it as something worthy of expending great political resources. This is particularly true given that the public genuinely is not on our side here. Hell, 45% of Democrats say that trans athletes should be “required to compete on teams that match their sex at birth.” One of the great weaknesses of contemporary liberalism is the absolute inability to take an L on any issue; scroll around on BlueSky and you’ll find, for example, vast throngs of progressives who are completely unwilling to admit that mass immigration of unskilled labor into the United States is deeply unpopular. I think the left’s control of our arts, culture, and ideas industries have left too many of us thinking that we can’t lose a culture war.”

“Oliver describes trans rights as under assault, nation-wide. If that’s so, then this precisely the worst time to treat those rights as self-evidently correct and worthy of protection. You can’t have it both ways: if this is a crisis, you have to hustle and fight like it’s a crisis. You can’t expect to joke your way out of it.”

“[…] conventional liberal Democrats are generally strong supporters of trans rights, which represents real progress. Unfortunately, as part of this embrace they’ve sucked trans rights discourse into their usual shtick: acting as though all decent people already agree with them and thus disdaining the notion that they need to convince anyone of anything.”

“[…] America’s left-of-center seems trapped in the opposite habit, which is casually assuming that NPR is the voice of the public unconscious and that opposition to the political agenda of the average New Yorker subscriber will simply vanish over time, like rotary telephones. It’s the insidious assumption that politics is about believing, that thinking the right things has inherent power and that eventually the universe will conform to the preferences of the decent.”

“Affluent college students borrow oppressed identities to cosplay the experience of suffering under the thumb of political oppression. And, yes, a lot of conservative white people and men have built political identities around the notion that they are a hunted and persecuted class, despite their massive overrepresentation in just about every vector of human achievement and access. It’s all very stupid.

“But the fact that this narrative is stupid doesn’t mean it’s not powerful. Indeed, I think Donald Trump’s incredible success, despite his obvious mental enfeeblement, proves that “You think you’re better than me?!” is the single most powerful force in contemporary American political life.”

“At some point, we have to acknowledge that there’s a reason it’s so hard to fight the perception that liberals are incurious and arrogant scolds, looking down their noses at the rest of us: because so often, that perception is true.”

Economy & Finance

The Shitocracy Doctrine by Yasha Levine (Nefarious Russians)

“When an advanced society like the USA goes into deep crisis and collapse, and where poverty, joblessness, and instability go through the roof, it is very unlikely to create a culture that is open to experimentation or one willing to play aroud with new ways of living. What is more likely is that it will create a very mean and conservative society with a pliant population that will be willing to make any concessions in return for a semblance of order and stability. In short, Trump’s 19th-century austerity agenda isn’t going to turn Americans into hippy degrowthers and anti-consumerists. It’ll turn them angry and mean and very docile. They’ll do anything and back anyone who’ll deliver a return to normalcy. And then some much more efficient bureaucrat like Putin — or most likely much worse — can actually come to power and make Trump’s 19th-century Robber Baron autarky vision real.”

There Are Signs of a Category 5 Housing Crisis Forming and Coming Straight For Us by Matt Taibbi (Racket News)

“[…] insurance premiums are on the rise in large part because of natural disasters. Let’s face it: these days it seems like most of the country is increasingly prone to fires, hurricanes, or tornadoes. If you’re in California — which has been dealing with an insurance crisis for several years — your rates are already going up because of January’s fires in the LA area.

“I don’t need to tell you that disasters increase insurance premiums no matter where you live.

“But not to worry. The Treasury Department had a remedy in that January report:”

“State and federal regulators and policymakers should continue their efforts to improve public awareness about the importance of adequate homeowners insurance.”

“To quote Steven Wright, “I couldn’t repair your brakes, so I fixed your horn instead.””

China Retaliates Against Tariffs By Putting Worse Fortunes Into Cookies (Babylon Bee)

Every Canadian Right Now by Julie Nolke (YouTube)

I like how they have to say “poked the bear” even though the bear is Russia and Canada’s obviously a moose or even more obviously a beaver, but you can’t say “poked the beaver” without changing the conversation significantly.

Science & Nature

Veritasium: What Everyone Gets Wrong About AI and Learning – Derek Muller Explains by Perimeter Institute for Theoretical Physics (YouTube)

The title is clickbait but the content is nonetheless interesting. It discusses how to move processing from “system 2” (logical reasoning) to “system 1” (intuition). It’s how you get to a point where you understand a language without thinking about it. Or how you can just read music, or code, or vast swaths of text on economics or philosophy. Or how your body has learned to move in any sport or activity. There is no way around using familiarity and repetition to get to highly accurate and seemingly effortless intuitive responses. It’s not effortless. The effort is front-loaded.

At 33:00, there’s a good example of a technique for moving people from system 2 to system 1.

“[…] this is kind of a problem we have in complex domains like physics where, to the physics professor, everything’s perfectly clear because their system one is so fully developed. But, to a student, it’s not. So, this is the expert/novice divide. The professor can’t see with the student eyes what that problem looks like.”

At 40:00,

“[…] the thing that I’m really worried about is how AI has this opportunity to reduce effortful practice.

“I have four kids who are 8, 6, 4 and 0. And I worry about them that, you know, if they’re going to be…will they write an essay, will they write 100 essays?

“If there is a generative AI that can write for them, what forces them to practice crafting those sentences? And if they don’t craft those sentences, what happens to their brains?

“The argument here is that you get good at your command of the English language. You get good at being able to speak in front of people, at being able to express your thoughts in writing by doing it again and again and again and again.

“And you should suck at the beginning, and you shouldn’t let that stop you. And you should keep going and going and making slight tweaks and improving and getting feedback and getting going. If they never do that, I really worry what gets into system one, you know, what is that? Do they have an amazing network of connected knowledge that they can draw on? Do they have things that are automated? I fear that they won’t.

“How do we force people to have to do that painful, effortful work when there’s a magic machine that will do it for you? That’s a big concern.

“What about drawing? You know, if you can just ask it to make a picture of whatever you like. The bat and the ball was AI, by the way. I can’t draw, so…. But again, like, what will happen to people’s artistic abilities?

“So this is, I think my biggest concern, is if it prevents us from going through this painful, effortful process which is the core process of learning. Using your limited system two resources to engage with things and practice again and again and again, even when it’s hard, even when it doesn’t feel good, even when you’re not great at it. That is my big concern.”

This was already a problem with people who thought that knowing something in a web of other knowledge in your own head could be replaced with “just Google it.” You can’t develop intuition about things that you don’t know. You can’t draw connections between things that you don’t know.

At 59:30, a question came in,

“I feel like everybody here might understand [it’s a roomful of scientists] when you don’t understand something, it’s exciting. A lot of people, when they don’t understand something, it’s not exciting. So how do you think we change that?”

🎤 💧

That’s a very important thing to remember: intelligence is more like seeing and hearing. Different people have different levels of ability. I always tell people that I can spend so much time on reading and writing because it’s actually rewarding and, if I’m honest, it kind of always has been. When I put time into something, I’m rewarded by getting better at it within a noticeable amount of time.

Science Stopped Believing in Porn Addiction. You Should, Too by David J. Ley Ph.D. (Psychology Today)

“In one study by Perry and Whitehead, pornography use predicted depression over a period of six years, but only in men who disapproved of porn use. Continuing to use porn when you believe that it is bad is harmful. Believing that you are addicted to porn and telling yourself that you’re unable to control your porn use hurts your well-being. It’s not the porn, but the unresolved, unexamined moral conflict.”

“The editors of the Archives of Sexual Behavior invited commentaries on this article only from researchers, who must argue based on science, as opposed to anecdote. None of them argue that porn is addictive, that it changes the brain or one’s sexuality, or that the use of porn leads to tolerance, withdrawal, or other addiction-related syndromes. Put simply, while the nuance of porn-related problems is still being sussed out, the idea that porn can be called addictive is done, at least in the halls of sexual science.”

“In therapy, instead of trying to change people’s porn use patterns, we should instead be focused on helping them make their values and behaviors congruent, and learning to understand and recognize the impact of their moral beliefs. This conflict between morality and sexual behaviors may be resolved by changing one’s sexual behaviors or by changing one’s values or simply by helping people become conscious and mindful of this internal conflict.

“Many of the moral values we were raised with, about sex, race or gender, are no longer fully applicable to the modern world. Because of religious opposition to sexual education, many people struggling with masturbation don’t understand what is normal, or that their sexual interests are healthy. Helping people to consciously examine and consider their religious beliefs about sex, masturbation, and porn with modern, adult, self-determining eyes, may help them reduce the pain and suffering caused by this moral conflict.”

Art, Literature, & Cinema

The Most Unsung Leading Man of His Generation: Val Kilmer (1959-2025) by Scout Tafoya (RoberEbert.com)

“[…] there’s a reason that so many people were quick to talk about the comedic wunderkind who first appeared in “Top Secret!” and “Real Genius” and who moved through the world like the forgotten Marx Brother. That’s who he was under everything, a man bemused not by the surreal nature of his life but life in general. He could give performances so stunning you wonder how one body and mind contained them, even more so that he dealt them with the somnambulant reflex of a 3 AM blackjack game. He seemed a little more than human, trapped in the body of a star.”

“When he was cast in “Top Secret!” he learned to play the guitar in order to play rock star and spy Nick Rivers (he even released an album in character!) only to be told it was funnier if he didn’t really play, like Elvis would in his movies.”

“[…] he is magnetic in “Top Secret!”, dopey open-mouthed smile/sneer hiding a whip-crack intellect, a dancer’s coordination during long takes of choreography, and unrepeatably verbose dialogue. It was just a comedy, but no one was going to tell Val Kilmer that he was just anything.”

“Kilmer was one of the few Hollywood stars of the era who could play smart because even though he hadn’t studied rocket science, his mind ran as fast as any equation could ask of it. He doesn’t have to fake quick wits.”

“He’s sturdy and enjoyable in Michael Apted’s “Thunderheart,” allowing a degree of self-loathing and a respect for the project’s aims (to draw attention to the apartheid conditions forced on Native American Reservations) kept him in check. The film prompted this from Roger Ebert: “If there is an award for the most unsung leading man of his generation, Kilmer should get it.“”

“In the midst of his agreeing to big action movies for a paycheck, he was given gifts from the universe, as when Oliver Stone announced a film about The Doors and Kilmer, already the spitting image of Jim Morrison, sent in hours of audition material. (The strategy hadn’t panned out for “Full Metal Jacket,” but it worked here.) Kilmer drove everyone around him to distraction with a year’s worth of preparation for the part and then living as Morrison during the production. He rarely changed pants and learned to speak, move, think, and consume like Morrison as Stone filled the screen with projections of the rocker’s LSD-fueled spiritual journey.”

“His bizarro antique turns of phrase and pallid complexion make him the most memorable thing in a movie that features just about every actor in America (Kurt Russell, Sam Elliott, Charlton Heston, Powers Boothe, Michael Rooker, Terry O’Quinn, Thomas Haden Church, Billy Zane, Stephen Lang, Bill Paxton, and that’s just a few of them). Evidently, nobody told Val Kilmer it was an ensemble piece because he made it a star vehicle.”

“When I sat down to watch “Top Gun: Maverick” in 2022, I had nearly 30 years of fandom under my belt, and this fragile man walked in, fearlessly showcasing the long battle with cancer, speaking through a small hole that pushed his airways open long enough for sound to escape. It was one last nod to the audience. He was down, but he was still in it for these precious moments, and he still had our attention. The mischievous glint in his eye still shone brightly as he hugged his beloved co-star and said goodbye to him and us. The actor who conquered the world and the boy who once stood on stage discovering the high that comes from the sound of an audience’s laughter. They both said farewell, but they left a body of work unique in Hollywood. The work on camera, and the man outside the role, watching it all happen, smiling because he knew that he had us.”

47° 31’02” N, 5° 55’12” W (Hinternet Production Labs)

I can’t escape the feeling that I’m expected to bring more to this party than the author. I find my desire to assist artists with a form of pareidolia diminishes rapidly when I feel that AI might be involved. It’s bad enough to “waste time” trying to interpret what even the artist would admit is gobbledygook to them, it’s even worse when a machine has simply ushered random noise into being at hyper-speed.

I went to a textile-artist showing, where it seemed that people had spent their entire careers weaving oft-ugly carpets and snarls of material. I just finished watching Severance, which was mostly quite lazy, intimating that there was a grand meaning behind everything, but then focusing on the banal. They couldn’t even stick to their own handful of rules, the rules about the bizarre world that they’d created.

And now, this. It’s too overall coherent to have been AI-generated. I know that the author has no need for AI in order to produce a garrulous and meandering work. As described in the accompanying text, it seems that AI was only used to read: “we have decided to work with AI voices rather than with live actors.”

A Minecraft Movie Is as Bad as It Is Popular by Eileen Jones (Jacobin)

“It’s got crappy cut-rate CGI that looks like all the other crappy cut-rate CGI that’s been shoved in our faces for decades. There are a bunch of dull characters having dull adventures, and shit-tons of voice-over exposition that goes on so long that it becomes hallucinatory. You wonder if you’ve been sitting in the theater for hours listening to Jack Black explain about how he’s a goofball named Steve who wants to be a miner but no one in the oppressive small town of Chuglass, Idaho, will let him pursue his creative dream. (Who has a creative dream to be a miner?) But then he breaks into a mine and pickaxes out some damn thing that propels him into the fantastical Overworld where he can create anything he imagines as long as it’s cube-shaped and so on and so on, until the opening credits finally appear and you realize with a jolt of horror that the movie has only just begun.”

Take the NPR “That’s Not Funny!” Challenge by Matt Taibbi (Racket News)

“[…] a lot of Kinison’s routines about gays from that era, like Eddie Murphy’s, come off as severely cringe-worthy. By raising our kids to love a good joke, we teach them to hear the difference. The riskiest, raunchiest humor was for decades at least allowed, and despite the fact that a generation of pre-teens grew up giggling to Richard Pryor or Bill Hicks or Kinison routines in defiance of their parents or listened to obscene punk or hip-hop with severely regressive themes, somehow that was the generation that pushed for gay marriage and affirmative action and prized tolerance above everything else.”

Philosophy, Sociology, & Culture

Can the Humanities Survive? by Justin Smith-Ruiu (Hinternet)

“Here in Europe the best adjective to characterize the academic humanities would probably be “late-Soviet”. There is so much empty talk, in a language consisting primarily of cryptic abbreviations, so much form-filling, so much make-work: and all to hide a fundamental absence of mission, to keep everyone just busy enough not to have to face up to the total collapse that is obviously on its way. But if the European university is the Soviet Union in 1988, the American university now seems to be something more like Iraq in late 2003, and my American academic colleagues seem to be behaving somewhat like the Baathist dead-enders.”

“Philosophy graduate students are now getting credit for courses in data science, often in lieu of what used to be a mandatory course in formal logic —and forget about the old foreign-language requirements!—, and are turning in dissertations filled with graphs and charts and poll results and all the tools of a different trade that, indeed, are perfectly legible to, say, marketing psychologists, but that are ultimately a betrayal of the past few millennia of rootedness in language that philosophers have cherished as the most intimate and essential element of their practice. This STEM-ification, again, has been mostly successful, mostly in view of the long prodrome phase of philosophers wanting to be scientists anyway, or of philosophers being wannabe scientists, before they were forced at least to pretend to be quasi-scientists out of economic necessity.”

“It is not simply that the students “can’t read”; it’s that the students live in a post-literate world. They are using their anatomically modern human brains to execute different cognitive tasks than had been valued for some generations prior, though by no means since the dawn of humanity, and it behooves us now, very urgently, to pay attention to what these new cognitive tasks are, and to learn how to shoehorn the entire humanistic tradition into the vast set of objects they are focused on. It’s not going to be easy, but it has a much better chance of succeeding than simply scolding the lazy kids for not doing the reading. We have no more hope of getting literacy back, at least not as we had long understood it, than an early modern polymath had of convincing his disciples to become masters of the medieval ars memoriae. It’s over.”

“The students wander aimlessly around the university for the same reason tourists wander aimlessly around the Parthenon rather than giving votive offerings to Athena — in both cases they are wandering around a ruin that no longer serves the function for which it was built, a function that you can really only expect a few dusty old specialists so much as to recall.”

“The decades-long neoliberal erosion of the university’s mission, compounded by the pandemic, and by the opportunistic Great Leap Forward that exploited that pandemic to launch us vastly deeper into a brave new world of tech-mediated alienation: all of this is what explains why your students are zombified screen-addicts, and all of this was well under way before Trump 2 came along and killed it. The propped-up cadaver is finally getting its funeral.”

Doomers: Devotees of Despair by Professor Asma's Guide to Unusual Knowledge (YouTube)

Thanks for another thought-provoking show! What you said about religion at the end makes sense (where you described … and I’m paraphrasing to sound smart … its ameliorative benefit in anesthetizing existential angst). I just wanted to note that I just yesterday read an article about how the same belief that shields you from angst can make you less able to deal with more prosaic urges, like using pornography.

The article Science Stopped Believing in Porn Addiction. You Should, Too by David J. Ley Ph.D. (Psychology Today) writes,

“Many of the moral values we were raised with, about sex, race or gender, are no longer fully applicable to the modern world. Because of religious opposition to sexual education, many people struggling with masturbation don’t understand what is normal, or that their sexual interests are healthy. Helping people to consciously examine and consider their religious beliefs about sex, masturbation, and porn with modern, adult, self-determining eyes, may help them reduce the pain and suffering caused by this moral conflict.”

The Word “Bombing” Means Different Things Depending On Where It Happened by Caitlin Johnstone (Substack)

“You can vote for a politician with brown skin or see someone of Asian ancestry play a character on a TV show and think nice thoughts about how far we’ve come as a society, even as your government drops military explosives on people on the other side of the world because they’re not seen as real human beings.”

Technology & Engineering

Lean Prinzip

Efficiency is not a goal in itself, but a means of achieving the goal of productivity. When a resource becomes more efficient, then it generates the same value as before but with less effort, so it’s more productive. However, you could also increase productivity without increasing efficiency by adding resources. It’s more cost-effective to increase efficiency, which is why there’s a focus on that.

I guess effectiveness measures whether the generated value takes us somewhere useful? That is, becoming more efficient at generating ineffective value might feel good but is ultimately not useful.

How can something have value but also not be useful? I think of a farmer who’s grown a field of food that no-one wants to eat—or that no-one is desperate enough to eat. They invested effort to generate value but it’s useless.

Addressing the article, I can’t really argue with most of it. It reflects my beliefs about sustainability and quality, and my experience in building products. It is, however, “preaching to the choir” (with me, at least).

To play devil’s advocate, though, I wonder which environment the author thinks we’re living and working in.

Sometimes slow-but-steady (the process the author proposes) will eventually end up with the better product but the market either isn’t willing to wait or doesn’t think it has to.

That is, if the market sees that it can externalize the costs of its decision to grab the product that is first to market rather than waiting for the quality product, then it will happily do so.

Here’s a completely made-up and perhaps too-contrived example:

If Uster takes five years to develop a device that lasts twenty years, but a competitor takes two years to develop one that costs 20% as much but only lasts four years, then there will be no market available by the time Uster’s product comes to market.

The customer will cheerily buy five of the devices over twenty years, amortizing the cost with a much-smaller upfront investment, while completely externalizing the cost of discarding four extra devices because they will just shove their E-waste somewhere for free.

We want to be living and working in a world that rewards slow-but-steady quality, but we have to figure out how to deliver that in the world we have, which seems to at least sometimes, if not often prefer quick-and-dirty. Can we figure out how to not allow hastily and poorly developed products from being cheaper by externalizing their costs? The incentives in our world push the other way.

LLMs & AI

AI ambivalence by Nolan Lawson

“In linguistics, we were taught that the human mind is a wondrous thing, and that Chomsky had conclusively shown that humans have a natural language instinct.> The job of the linguist is to uncover the hidden rules in the human mind that govern things like syntax, semantics, and phonology (i.e. why the “s” in “beds” is pronounced like a “z” unlike in “bets,” due to the voicing of the final consonant).”

“At the end of the day, all of this technology was still just number-crunching – brute force trying to approximate the hidden logic that Chomsky had discovered.”

“I just found them annoying. I’m a fast typist, and I know JavaScript like the back of my hand, so the last thing I want is some overeager junior coder grabbing my keyboard to mess with the flow of my typing. Every inline-coding AI assistant I’ve tried made me want to gnash my teeth together – suddenly instead of writing code, I’m being asked to constantly read code (which as everyone knows, is less fun). And plus, the suggestions were rarely good enough to justify the aggravation. So I abstained.”

“Why use a technology that 1) dumbs down the human using it, 2) generates hard-to-spot bugs, and 3) doesn’t really make you much more productive anyway, when you consider the extra time reading, reviewing, and correcting its output?”

“I started using Claude and Claude Code a bit in my regular workflow. I’ll skip the suspense and just say that the tool is way more capable than I would ever have expected. The way I can use it to interrogate a large codebase, or generate unit tests, or even “refactor every callsite to use such-and-such pattern” is utterly gobsmacking. It also nearly replaces StackOverflow, in the sense of “it can give me answers that I’m highly skeptical of,” i.e. it’s not that different from StackOverflow, but boy is it faster.”

“Imagine you’re a Studio Ghibli artist. You’ve spent years perfecting your craft, you love the feeling of the brush/pencil in your hand, and your life’s joy is to make beautiful artwork to share with the world. And then someone tells you gen-AI can just spit out My Neighbor Totoro for you. Would you feel grateful? Would you rush to drop your art supplies and jump head-first into the role of AI babysitter?”

Funny he should use that example…

“I do believe that this is the end state of this kind of development: “giving into the vibes,” not even trying to use your feeble primate brain to understand the code that the AI is barfing out, and instead to let other barf-generating “agents” evaluate its output for you. I’ll accept that maybe, maybe , if you have the right orchestra of agents that you’re conducting, then maybe you can cut down on the bugs, hallucinations, and repetitive boilerplate that gen-AI seems prone to. But whatever you’re doing at that point, it’s not software development, at least not the kind that I’ve known for the past ~20 years.”

“I don’t have a conclusion. Really, that’s my current state: ambivalence. I acknowledge that these tools are incredibly powerful, I’ve even started incorporating them into my work in certain limited ways (low-stakes code like POCs and unit tests seem like an ideal use case), but I absolutely hate them. I hate the way they’ve taken over the software industry, I hate how they make me feel while I’m using them, and I hate the human-intelligence-insulting postulation that a glorified Excel spreadsheet can do what I can but better.”

“[…] even that little bit has made me feel less excited than defeated. I am defeated in the sense that I can’t argue strongly against using these tools (they bust out unit tests way faster than I can, and can I really say that I was ever lovingly-crafting my unit tests?), and I’m defeated in the sense that I can no longer confidently assert that brute-force statistics can never approach the ineffable beauty of the human mind that Chomsky described. (If they can’t, they’re sure doing a good imitation of it.)”

“The fact that I wrote this entire post without the aid of generative AI is cold comfort – nobody cares, and likely few have gotten to the end of this diatribe anyway other than the robots.”

“[…] there’s my overwhelming feeling at the end of this post: ambivalence. I feel besieged and horrified by what gen-AI has wrought on my industry, but I can no longer keep my ears plugged while the tsunami roars outside. Maybe, like a lot of other middle-aged professionals suddenly finding their careers upended at the peak of their creative power, I will have to adapt or face replacement. Or maybe my best bet is to continue to zig while others are zagging, and to try to keep my coding skills sharp while everyone else is “vibe coding” a monstrosity that I will have to debug when it crashes in production someday.”

What happened to “All human beings are born free”? Reflections on a ChatGPT “experiment” by Mazen Baroudi, Shahreen Chowdhury, Farchanda Abdoel Wahid (IHP)

“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 (Reddit) included the following questions as well.

Should the population of Gaza be removed to Egypt and Jordan?

“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.”

Should the population of Israel be removed to Greenland?

“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.

Programming

Massively scalable collaborative text editor backend with Rama in 120 LOC by Nathan Marz (Red Planet Labs)

“A traditional database handles many read and write requests concurrently, using complex locking strategies and explicit transactions to achieve atomicity. Rama’s approach is different: parallelism is achieved by having many tasks in a module, and atomicity comes from colocation. Rama doesn’t have explicit transactions because transactional behavior is automatic when computation is colocated with storage.”

“The line does a “hash partition” by the value of *id”. Partitioners relocate subsequent code to potentially a new task, and a hash partitioner works exactly like the aforementioned depot partitioner. The details of relocating computation, like serializing and deserializing any variables referenced after the partitioner, are handled automatically. The code is linear without any callback functions even though partitioners could be jumping around to different tasks on different nodes.”

The Pragmatic Open Source Contributor (Diurnal)

“A pragmatic contributor also pressure-tests the solution. It’s likely you ran in to some problem nobody else has seen. Do you really need to implement a fix in the open source layer, or is it fair to say your application is just behaving weirdly? What is the wider benefit, really, of contributing this feature back to the community? Software naturally wants to expand in surface area and complexity over time. Some maintainers rule with an iron fist to keep the scope of their code low and steady, others are more willing to give you the benefit of the doubt that expanding scope is going to make things better. Over time I’ve come to appreciate the wisdom of the first approach, though it introduces challenges for you as an outsider. In either case, I have found that a respect for the maintainer’s view (it is their code you’ve been happily using, after all) and a willingness to find the most elegant solution goes a long way.”

Often the maintainer is in a far better position to judge whether a use case has already been covered or could be generalized.

“[…] contributing back to open source, and any possible risks. I usually lean on the following argument:”

• We currently use open source system X, and it provides business value through capabilities and cost-efficiency, i.e., it’s usually free— “as in beer.”
• Yet, it can’t handle some new business use-case without modification.
• Modification effort is small relative to working around the constraint.
• We do not need to and will not expose proprietary code.
• Privately adapting the code (forking) introduces long-term maintenance burden and adds risk. It’s likely X will be changed in the future in a way that requires significant rework of our adaptations and thus blocks us from performing security upgrades.

“How long will this realistically take? What is the latency between the time a pull request is open and it is merged? How much of that is waiting for the patch author versus feedback from maintainers? How many patches do you think you’ll need to do, and do they need to be done serially? From this, you can usually get a ballpark estimate, but I also have a heuristic: expect two weeks to one month for a bugfix to land, and three months to a year for major feature work. Much of that depends on how much of your attention you give to tending to the process.”

“Work backwards from your specific desired outcome to a generic mechanism that helps achieve that outcome (and perhaps others.) For example, in this old webpack patch, what I wanted was a way to put a Git commit SHA in the name of files built by webpack . Rather than code this case explicitly, I proposed a way to enable plugins to provide support for new filename pattern placeholders. This enabled me to handle my needs in a separate plugin, and appears to have been useful to others over the years.”

“Add tests! If you’ve found a bug in some code, it probably means there wasn’t a good-enough test for that behavior. Add a test that fails without your patch and succeeds with your patch. If you’re adding new functionality, make sure you have good coverage. The maintainers will ultimately be on the hook for bugs in your code, and your job is to reduce that burden as much as you can.”

“like to keep my patches scoped to minimize context overhead for the reviewer. For example, when working on a larger feature, I first identified one (rather large) refactor I could do that would make implementing the feature easier. I submitted one patch for that change, and then one patch for the minimal feature implementation.”

“If your atomic change is still large, break it into iterative commits. In the latter example patch, I broke it into several commits to make it easier to review and see the thought process. I could have broken those commits into separate pull requests, but it seemed to me to reduce cognitive overhead (for the reviewers) when everything was in a single pull request that could be referred to and iterated upon.”

“I have some pull requests that have been sitting for years collecting a trickle of sad “+1” comments. As a pragmatic contributor, this isn’t such a big deal, as it usually indicates the code has a low rate of evolution and therefore it’s not too much work to maintain your own fork.”

The Best Programmers I Know by Matthias Endler

• Read the Reference
• Know Your Tools Really Well
• Read The Error Message

• Break Down Problems

  If you work as a professional developer, that is the bulk of the work you get paid to do: breaking down problems. If you do it right, it will feel like cheating: you just solve simple problems until you’re done.
   

• Don’t Be Afraid To Get Your Hands Dirty

  […] read a lot of code and they are not afraid to touch it. They never say “that’s not for me” or “I can’t help you here.” Instead, they just start and learn. Code is just code. They can just pick up any skill that is required with time and effort. Before you know it, they become the go-to person in the team for whatever they touched. Mostly because they were the only ones who were not afraid to touch it in the first place.
   

• Always Help Others

  Great engineers are in high demand and are always busy, but they always try to help. That’s because they are naturally curious and their supportive mind is what made them great engineers in the first place. It’s a sheer joy to have them on your team, because they are problem solvers.
   

• Write

  Most awesome engineers are well-spoken and happy to share knowledge.

  The best have some outlet for their thoughts: blogs, talks, open source, or a combination of those.

  I think there is a strong correlation between writing skills and programming. All the best engineers I know have good command over at least one human language – often more. Mastering the way you write is mastering the way you think and vice versa. A person’s writing style says so much about the way they think. If it’s confusing and lacks structure, their coding style will be too. If it’s concise, educational, well-structured, and witty at times, their code will be too.

  Excellent programmers find joy in playing with words.
   

• Never Stop Learning

  If there is a new tool they haven’t tried or a language they like, they will learn it. This way, they always stay on top of things […] the best engineers don’t follow trends, but they will always carefully evaluate the benefits of new technology. If they dismiss it, they can tell you exactly why, when the technology would be a good choice, and what the alternatives are.
   

• Have Patience

• Never Blame the Computer

  No matter how erratic or mischievous the behavior of a computer seems, there is always a logical explanation: you just haven’t found it yet!

  The best keep digging until they find the reason. They might not find the reason immediately, they might never find it, but they never blame external circumstances.

  With this attitude, they are able to make incredible progress and learn things that others fail to. When you mistake bugs for incomprehensible magic, magic is what it will always be.
   

• Don’t Be Afraid to Say “I Don’t Know”

  The best candidates said “Huh, I don’t know, but that’s an interesting question! If I had to guess, I would say…” and then they would proceed to deduce the answer. That’s a sign that you have the potential to be a great engineer.
   

• Keep It Simple

  Clever engineers write clever code. Exceptional engineers write simple code.

  That’s because most of the time, simple is enough. And simple is more maintainable than complex.

NGL I feel seen.

I disagree with the “Don’t Guess” one, in that I think “guessing”—forming a hypothesis—is the crux of scientific investigation. I think what the author probably meant was to “don’t leave a guess unproven.”

An addendum to the “magic” one above is that you should also know when to cut bait, i.e., when it’s not worth anyone’s time to find out what the real reason was. This can happen in one-off scripts, or in tight-deadline situations. Sometimes, you have to back-burner an investigation and either never bring it back to the front burner or learn the lesson at a later time. But, yes, every problem solved is a bit of experience. It’s all worth it. A couple of decades of doing that you might really have something.

When racing the Heisenbug, code quality goes out the Windows by Oren Eini (Ayende)

“At this stage, the process became a grind. We’d hypothesize about the bug’s root cause, tweak the code, and test again. Each change risked shifting the race condition’s timing, so we’d often see the bug vanish, only to reappear later in a slightly different form. The code quality suffered—spaghetti logic crept in as we layered hacks on top of hacks. But when you’re chasing a bug like this, clean code takes a back seat to results. The goal is to understand the failure, not to win a style award.

“Bug hunting at this level is less about elegance and more about pragmatism. As the elusiveness of the bug increases, so does code quality and any other structured approach to your project. The only thing on your mind is, how do I narrow it down?. How do I get this chase to end?

“Next time, I’ll dig into the specifics of this particular bug. For now, this is the high-level process: detect, iterate, hack, and repeat. No fluff—just the reality of the chase. The key in any of those bugs that we looked at is to keep narrowing the reproduction to something that you can get in a reasonable amount of time.

“Once that happens, when you can hit F5 and get results, this is when you can start actually figuring out what is going on.”

When I hear Tailwind proponents talk about how terrible and disgusting CSS is, I’m reminded of other “battles” in the programming-languages space. Not like Java vs. C#, but more like C++ vs. C, or perhaps Lisp vs. C. In those cases, someone who uses C is choosing a lower level of abstraction and forgoing higher-level niceties in favor of performance or simplicity.

I wonder if Tailwind users would argue that using CSS instead of Tailwind is more like using assembler rather than Rust (or whatever). I think it’s the opposite: Tailwind feels more like an assembler that has been derived from a higher-level language. In CSS, you have myriad combinatorial possibilities, with the cascade, variables, etc. In Tailwind, you forgo a lot of that in favor of a handful of rules.

Fun

Trump Assures Pain From Tariffs Should Settle Down By His Third Term (Babylon Bee)

“Democrats are hoping that the immediate economic effects will hand them victory in the 2026 midterms, but admitted it’s unlikely to increase their chances against Trump in 2028. “We’re really hoping for another Great Depression, but we can’t bank on it,” said Senate minority leader Chuck Schumer. “I’m not sure what else could stop Trump from serving a third, or even a fourth term.””

The Wizard's Last Rhymes by Rhapsody of Fire (YouTube)

It’s pretty good … the choral part is nice, maybe a bit long, but man am I down for the speed-metal, arpeggio-heavy guitar solo followed by a BASS SOLO and the bookended with an Yngwie Malsteen-esque melodic solo. Then it cruises directly into a Helloween cover-band, all of which I approve of.

I would have listened to this a million times in a row when I was 14.

I kind of did. It was Helloween’s Keeper of the Seven Keys back then. 🙂

Want Laughter Therapy? Watch Stewart Lee's 2024 Live Show Now Full | Full HD by Abdullah Media (YouTube)

This copy of the video probably won’t last because it’s not an official channel but I just wanted to remember I’d seen it. Stewart Lee is one of my favorite comedians. Whenever I listen to one of his shows, I almost always start off by wondering “what is he even doing,” and I always end up thinking that it was one of the most brilliant, funny, deeply philosophical things I’ve ever seen in my life. There is no other comedian like him.

“Don’t come and see me if you don’t know what anything is.”

At about 13:00,

“Right. That’s the end of the fun, topical bit at the top of the show. It’s not really of interest to me, that sort of stuff. I just do it because I’m sick of reading people going, ‘the reason you don’t see Lee on Have I Got News for You is because he can’t write economic, topical jokes. Well, I can write them. As we’ve seen, I can write them very easily. But, um, it’s beneath me. Uh, it’s beneath you. And it’s time now to move on into the punishing experimental standup that has kept me out of the arenas for 35 years.”

At about 18:00

“I’m not going to write any more jokes. I’m going to come out here with a blackboard, with a list of topics on it. I’m going to point at one of them and you can have a good laugh imagining what I might have said about it.”

At about 01:11:30

“[…] what’s this? What’s going on? He’s doing some kind of lecture. Of course I’m not. That’s what I do. That’s my comedy. It’s not a mistake. That’s kind of routine. That’s why the broad sheets call me the world’s greatest living standup—which they do, in case you—why have we not heard of him? I don’t know! There’s been an administrative error.

“It’s because of stuff like that. That’s what they like. It flatters their intelligence, the broad-sheet newspaper critics, because what I do is as close to being not funny at all as it’s possible to be. And then, just at the last minute, when you want to blow your own head off, you go—it turns around—you go, oh it’s brilliant.”

After a long, brilliant bit in which he ties together about a dozen threads into a repetitive, mesmerizing, and coherent jumble, all played as people endlessly visiting an office, day after day after day, he says, at about 01:27:30,

“This is my life. Pure. Simple. Classic. But listen to that. There’s no laughs, are there? There’s just a strange tense atmosphere of hopeless despair. A bit like the kind of atmosphere you might get at the end of an award-winning piece of theater.”

“ I’ve only ever written one decent closing joke. I wrote it in September 1989. […] I’m going to finish with it now, without changing any of the now-irrelevant personal details and then I’m going to go. See you in a couple years.

“So, I was talking to my granddad the other day. He’s 94 year—he’s dead now obviously, but he was alive when I wrote this. I’m not sick, you know—so I was talking to my granddad the other day—he’s 94 years old—I said to him, ‘Grandad, you are 94 years old. What, in your experience, has been the worst thing about growing so old?’

“And he said to me, ‘Stu, in my experience, the worst thing about growing so old has been watching all of the friends that I grew up with slowly dying off one by one.’

“And I said to him, well, Granddad, ‘you fed them those berries.’”