This page shows the source for this entry, with WebCore formatting language tags and attributes highlighted.

Title

Links and Notes for May 22nd, 2026

Description

<n>Below are links to articles, highlighted passages<fn>, and occasional annotations<fn> for the week ending on the date in the title, <a href="{app}/view_article.php?id=4085">enriching the raw data</a> from <a href="http://www.instapaper.com/starred/rss/1890855/5c1g08eoy9skhOr3tCGqTQbZes">Instapaper Likes</a> and <a href="https://twitter.com/mvonballmo">Twitter</a>. They are intentionally succinct, else they'd be articles and probably end up in the gigantic backlog of unpublished drafts. YMMV.</n> <ft>Emphases are added, unless otherwise noted.</ft> <ft>Annotations are only lightly edited and are largely contemporaneous.</ft> <h>Table of Contents</h> <ul> <a href="#politics">Public Policy & Politics</a> <a href="#labor">Labor</a> <a href="#economy">Economy & Finance</a> <a href="#climate">Environment & Climate Change</a> <a href="#medicine">Medicine & Disease</a> <a href="#art">Art, Literature, Music, & Cinema</a> <a href="#philosophy">Philosophy, Sociology, & Culture</a> <a href="#technology">Technology & Engineering</a> <a href="#llms">LLMs & AI</a> <a href="#programming">Programming</a> <a href="#design">Design</a> <a href="#sports">Sports</a> <a href="#fun">Fun</a> </ul> <h id="politics">Public Policy & Politics</h> <a href="https://pascallottaz.substack.com/p/russia-and-china-issue-declaration" source="Neutrality Studies" author="Pascal Lottaz">Russia & China issue Declaration on Multipolarity</a> <bq>[...] the global situation is becoming more complex. On the rise are negative, neo-colonial tendencies, such as the practice of unilateral forceful approaches, hegemonism, and bloc confrontation. Fundamental, universally-recognized norms of international law and international relations are regularly violated, and it is becoming more difficult for states to coordinate their actions and resolve conflicts within global governance institutions, many of which are losing their effectiveness.</bq> <bq>There is no universal path of development, and no “first-class” countries or peoples exist. Differences between states — natural in such a diverse and complex world — should not be an obstacle to the development of equal, respectful, and mutually beneficial relations. It is necessary to respect the chosen development model of each sovereign state.</bq> Yeah, sure, within reason. Extractive, oligarchic dictatorships should be pressured to behave better, to give their people breathing room. Should we respect how Israel treats its people? It destroys its occupied population while brainwashing the rest into thinking that this is a good thing. Should they be allowed to continue doing this? Yes, if by "allowed" we mean that we will not intervene militarily to stop it. Are we obligated to respect their choices, to pretend that it's OK, to trade with them? No. You don't have to have diplomatic relations with any country you don't want to deal with. Right now, the U.S. dictates that list of countries for most of its sphere of influence. Swiss companies haven't been able to do business with Iran for 50 years, for example. They can't do business with Russia. It's a complicated statement that is clearly born from the idea that the U.S. should stop telling other countries what to do. What they want to say is that the basis of relations should be mutual diplomacy with pressure to change but without punishing measures that make it difficult to change or grow in a positive direction. The heretofore exclusively punitive measures that impose austerity on populations, that impose debt peonage are all designed to produce vassal states, not flourishing, sovereign nations. But they can't come out and say that. <bq>The formation of a more cohesive international community amid growing common risks and challenges for humanity means that the security of one state cannot be ensured at the expense of another. All sovereign states have an equal right to security. It is necessary to pay due attention to the rational security concerns of all countries, focus on cooperation on security issues, reject bloc confrontation and zero-sum game strategies, oppose the expansion of military alliances, hybrid wars, and proxy wars, and promote the creation of a renewed, balanced, effective, and sustainable global and regional security architecture.</bq> This is definitely Russia's bit, of course. It's the drum they've been banging for almost four decades. <bq>It is unacceptable to coerce sovereign states into abandoning their neutrality.</bq> Agree 100%. <bq>All states and their associations are free to choose their foreign partners and models of international interaction. Global hegemony is unacceptable and must be prohibited. No single state or group of states should control international affairs, dictate the fate of other countries, or monopolise development opportunities.</bq> <bq>The UN Charter is the fundamental norm of international relations, and its principles must be observed in their entirety and interrelationship. Rules developed by a narrow circle of states should not replace generally recognized international law. Large states must assume a special responsibility and mission, place additional demands on themselves, and not abuse their advantages.</bq> <bq>It is necessary to resolutely oppose the use of human rights as a pretext for interference in the internal affairs of other states, as well as the politicisation and instrumentalisation of human rights issues. Religion is an important conduit for human culture, playing a special role in building ties between peoples, and all states should create favourable conditions for interreligious dialogue and exchange.</bq> This paragraph seems to be an amalgam of China at the beginning, and Russia at the end. <hr> <a href="https://www.caitlinjohnst.one/p/its-not-okay-to-join-the-military" author="Caitlin Johnstone" source="Substack">It's Not Okay To Join The Military</a> <bq>It is not okay to be a stormtrooper for the western empire. It is not honorable. It is not worthy of respect. If you are a westerner who is considering joining the military, you should choose a different career path instead. Don’t thank soldiers for their “service”. Don’t play along with the lie that your nation’s soldiers fight for your rights or your freedom. It only encourages more people to join the military when you do that. It’s irresponsible and unethical. If you live in the west and you join the military, at no point will you ever be acting in defense of your country; you will be murdering people who are trying to defend their country. You will be murdering them in order to make rich men richer, to make powerful men more powerful, and to help bend the world to the rule of tyrants [...]</bq> <bq>These are grown adults engaging in behavior that would incur the harshest legal penalties in the books if they were inflicted upon westerners in their own country without the blessing of the powerful. It is only because they’re being inflicted on foreigners in the global south with the go-ahead from the relevant authority figures that participating in mass murder can be framed as acceptable.</bq> <hr> <a href="https://www.infosperber.ch/frau-mann/grossmaechte-demonstrieren-patriarchale-macht/" author="Barbara Marti" source="Info Sperber">Grossmächte demonstrieren patriarchale Macht</a> <bq>Kürzlich war Donald Trump zu Besuch bei Xi Jinping. Frauen durften bei den Verhandlungen der Grossmächte nicht mitreden. Das Foto eines ausschliesslich männlich besetzten Gipfeltreffens sorgte in den USA für Unmut. Kritikerinnen sehen darin ein Signal dafür, wer in der Politik der Grossmächte mitreden darf und wer nicht.</bq> This seemingly appropriate critique collapses under scrutiny because, is the problem that there are no women? Or is the problem that there are no people from the non-elite? There are no people representing the overwhelming class interest of the working class. There are no people who will speak for anyone but the the rich. That's the problem. Would it have helped to have Analena Baerbock, Kaja Callas, and Ursula van der Leyen at the table, warmongers all, and all worshipers at the altar of capital? That would have stilled the critical voices in this article because they love being in the elite and they love having their interests represented to the detriment of the overwhelming majority, and they don't even notice that this is exactly what's happening. The Bush administration was and the Trump is filled to the brim with people of color and women, and these are two of the most rapacious, unflinchingly brutal administrations the empire has ever seen. Adding women doesn't help. I 100% think that half of the people at that table should be female. But if they all think just like an elite man would, then all you've changed is the optics to make yourself feel better. And, if you feel better because of those optics, and you don't see any further problems, ... then you are part of the problem. <hr> <a href="https://www.wsws.org/en/articles/2026/05/29/sgxg-m29.html" author="Andre Damon" source="WSWS">Under cover of US-Iran negotiations, Israel steps up effort to annex Gaza</a> <bq>Israeli Prime Minister Benjamin Netanyahu announced Thursday that he had ordered the Israeli army to seize control of 70 percent of the Gaza Strip—well beyond the 53 percent Israel was allowed to hold under the cease-fire that took effect in October. “We now control 60% of the territory in the strip. You know, we were at 50, we moved to 60. My directive is to move to … 70%,” Netanyahu told a conference in an occupied West Bank settlement. The directive would confine the strip’s 2.1 million Palestinians to less than a third of the territory. Israeli Defense Minister Israel Katz on Wednesday reiterated his calls for the ethnic cleansing of Gaza. “We committed that Hamas will not rule Gaza civilly or militarily, and so it shall be, and also the voluntary emigration plan from Gaza will be implemented,” Katz wrote on X.</bq> "Voluntary." <bq>The Israeli army Wednesday ordered the entire city of Tyre to evacuate, declaring all areas south of the Zahrani River—about 15 percent of Lebanese territory—to be a combat zone. Israel is systematically breaking the ceasefires it agreed to. A Gaza “ceasefire” took effect October 10, 2025. The Gaza Health Ministry says Israeli attacks have killed more than 900 Palestinians since the ceasefire took effect. In Lebanon, a US-brokered ceasefire that took effect November 27, 2024, required Israel to withdraw from the south within 60 days; Israel never withdrew and continued bombing throughout. A further ceasefire that took effect April 16 is being broken by Israeli air strikes on a near-daily basis.</bq> It's ludicrous to even discuss a ceasefire with Israel. They always assume it means that the other side stops fighting while they continue their plans unchanged. They give every indication of not stopping for honor or their word, making it clear to all involved that only physical force will stop them. They think that it makes them invincible but it's hard to see how it ends well for them, now that Iran has been activated and is actively defending Lebanon's interests. The U.S. does the same thing, cheerfully bombing whatever it feels like bombing and all the while chirping "ceasefire" whenever it suits their purposes. It's like fighting someone who always calls time-out right after they've lambasted you, then lambastes you again during the timeout, then calls timeout again. If their dad is the mayor of the town or the chief of police, you're going to put up with that for a while, but only only until you come up with a plan to drown him in a river on a moonless night. <hr> <a href="https://responsiblestatecraft.org/israel-west-bank-annexation/" author="Congresswoman Rosa DeLauro Congressman & Sean Casten" source="Responsible Statecraft">Congresswoman Rosa DeLauro Congressman Sean Casten</a> <bq>In February, we led a week-long congressional delegation to visit Israel and the West Bank, the latest of several trips we have taken in recent years to better understand the region and the needs of the people who live there. What we saw on the ground is clear: annexation of the West Bank is happening before our very eyes. We were planning to visit the village of Ras ‘Ein al-’Auja in the northern West Bank. But three weeks before the trip, all 700 residents of the village fled due to violence from nearby settlers. When we drove through the ruined remains of the village, we saw groups of Israeli settlers having a picnic. We were able to visit the village Fasa’il al-Wusta in the Jordan Valley. When we visited, six out of eight families had fled. Two weeks later, the Israel Defense Forces (IDF) demolished the home of the family we visited. Now only one of those families is left.</bq> <hr> I've seen people arguing about the degree to which Israel actually controls U.S. foreign policy. How much this matters depends on what you're trying to do. Are you trying to stop the U.S. from doing what it's doing? Or are you trying to predict what the U.S. will do? If you're trying to stop or change what the U.S. is doing, then it's important to figure out why the U.S. does what it does. In this case, it's more important to determine whether Israel is controlling the U.S. or whether the U.S. is following its own plans, but making it look like Israel controls them as some sort of twisted moral cover. However, if you're just trying to predict what the U.S. will actually do, then you will be well-served these days by paying attention to what Israel wants in the short term. The U.S. has its own reasons for doing what it does, but using the "Israel says to do this" as a proxy has been quite accurate, of late. For example, Israel absolutely does not want a ceasefire in Gaza, Lebanon, or Iran. It wants Hamas, Hezbollah, and Iran to stop shooting at it, but it is utterly uninterested in stopping its own attacks. It is still focused laser-like on acquiring as much of Southern Lebanon as possible, on ethnically cleaning Gaza and then the West Bank, and in shattering Iran into a quasi-state like Libya. These are its stated goals and it pursues them ruthlessly and relentlessly, never acknowledging that there could be any real hindrance to its achieving them. That means that there will be no ceasefire or peace agreement with Iran. It means that the U.S. and Israel will continue to fire at will while claiming that Iran is still bound by the ceasefire and agreements to open the Strait of Hormuz. The U.S. is acting exactly in accordance with the predictions that follow from these facts. It is not really germane whether the U.S. is interested in the same aims in pursuit of a greater strategy of crippling China and Russia. To predict whether the Strait of Hormuz will open, you only need to know that Iran will not open it until it is no longer being attacked in either its own territory or Lebanon (I haven't heard it mention Gaza in a while) and also that Israel is absolutely not going to stop bombing, attacking, and annexing Lebanon. Just because it's a good predictive tool, though, doesn't mean that it's the only---or even the main---reason. It doesn't mean that Israel actually is in control. It just means it happens to be a good proxy for prediction right now. <h id="labor">Labor</h> <media href="https://www.youtube.com/watch?v=DviCUygm3eM" src="https://www.youtube.com/v/DviCUygm3eM" source="YouTube" width="560px" author="Haymarket Books" caption="Fred Hampton on the importance of revolutionary education"> <bq>Papa Doc in Haiti, he hated everything white. He moved all the white people out and he took over as the oppressor---'cause of no education. It the people woulda been educated, they'd have said, we don't hate the motherf@&ker white people; we hate the oppressor, whether he be white, black, brown, or yellow. [...] With no education, you have neocolonialism instead of colonialism. It's so important to us that a person has to go through six weeks of our political education before he considers himself a member of the party. Why? Because, if they don't have an education, they're nowhere---they don't even know why they're doing what they're doing. If they're not educated, they'll want more and, before you know it, they'll be capitalistic, and, before you know it, they'll have negro imperialists.</bq> <h id="economy">Economy & Finance</h> <img src="{att_link}how_did_it_never_occur_to_anyone_that_this_would_be_a_dead-man_switch.webp" align="none" caption="How did it never occur to anyone that this would be a dead-man switch?"> <hr> <a href="https://www.counterpunch.org/2026/05/20/the-2026-world-financial-crisis/" source="CounterPunch" author="Michael Hudson">The 2026 World Financial Crisis</a> <bq>By the 19th century, creditors sought some excuse to justify their interest charges by depicting these as compensation for the risk that they might have to suffer a loss through loan defaults or by a loss of their purchasing power over goods and services as prices rose – and more to the point, over the labor that produced these products.</bq> <bq>Having to pay interest, thus was depicted as the price of “impatience.” It was as if wage earners (“consumers”) had a choice to abstain from running into debt, lacking prudence.</bq> <bq>[...] keeping prices for collateral held by banks and other creditors from falling in price, and thus causing a loss of financialized asset-price gains, requires the economy to take on more and more debt.</bq> <bq>Iran has responded by saying that if other nations do not act to stop Trump’s attack, Iran will destroy Arab oil production and the whole world will pay the price of being pushed into a prolonged economic depression. And the world has stood by, as if believing that the United States can conquer Iran as it did Venezuela and somehow restore normal relations under U.S. control and avoid world depression.</bq> <bq>Many loans for commercial real estate and also private equity are soon coming due to be rolled over. How can these debts be refinanced at the rates that are looming? And new construction and property sales will be constrained by the inability of new borrowers to pay the higher carrying charges for homes or other properties.</bq> <hr> <a href="https://insideclimatenews.org/news/18052026/nextera-dominion-utility-mega-merger/" source="Inside Climate News" author="Dan Gearino, Amy Green, and Charles Paullin">Electrical utility megamerger is all about the data centers</a> <bq>“Mergers are not about consumers; they’re about shareholders,” said Ari Peskoe, director of the Electricity Law Initiative at Harvard Law School. “For the Dominion shareholders, they are selling their shares at a premium. The executives are getting massive payouts for facilitating this, assuming it all goes through, and obviously NextEra believes the transaction is going to add value to the company. Ratepayers are all an afterthought.”</bq> These companies' primary purpose is to increase the fortunes of a handful of people, not to provide the service that they have on the tin. If they could make money without providing the service, they absolutely would. The don't care about providing services. It annoys them that they have to do so, and it annoys them that they have to pretend to care. <bq>“I continue to be sort of flabbergasted by the tone deafness,” she said. “I’m not sure that any of us could point to a major utility merger acquisition that’s happened in the past decade… where that merger acquisition has definitively provided the synergies that they told their commissions were going to come out.”</bq> Because lying to get money is 99% of the economy. The richer you already are, the more you do it. It's much more lucrative than providing value and there's no downside risk because you can also brainwash people into forgetting that you ever lied to them by using some of your ill-gotten gains to bribe or buy a pliant media. <bq>NextEra said the merger creates a pipeline of 130 gigawatts’ worth of demand from data centers, which critics say are speculative, and a chance to more than double generation capacity to 225 gigawatts by 2032.</bq> These are completely fabricated numbers. <hr> <a href="https://aeon.co/essays/to-fund-human-rights-we-need-a-global-fair-tax-convention" source="Aeon" author="Attiya Waris">To fund human rights we need a global fair tax convention</a> <bq>The system is not broken. It has been arranged to serve the people who own the vans, not the millions who board them. Fares rise, routes are fought over, and the daily commute becomes a tax paid to vested interests that go unchallenged.</bq> <bq>There is an Ethiopian proverb: you think of water when the well is empty. This essay is about who is draining the well, and what it would take to fill it back up.</bq> <bq>You cannot protect the right to healthcare without funding hospitals. You cannot guarantee the right to education without paying teachers. You cannot deliver justice without funding courts. And you cannot ensure the right to movement and economic participation without building the infrastructure and regulating the service providers to make it possible. The people of Nairobi know this with their bodies every single morning.</bq> <bq>African countries paid approximately $74 billion in debt service in 2024, more than four times what they paid in 2010. More than 30 African countries now spend more on servicing debt than on public health. In more than half of African countries, debt service now exceeds public spending on health.</bq> <bq>The SACCO does not want a rationalised public transit system because such a system would make its bus routes less valuable. Multinational corporations do not want a reformed global tax architecture because it would mean paying more. The structural logic is identical; only the scale differs. This is not, in either case, a conspiracy. It is rational behaviour within a system constructed to reward it. Changing the behaviour requires changing the system.</bq> <bq>What these examples share is simple: a political decision that public transport is a public good and that the state is responsible for financing it. Not because the market cannot fill the gap – the SACCOs are proof that markets are extraordinarily creative – but because market logic, operating alone, cannot guarantee the equitable, reliable, dignified movement through a city that ought to be every citizen’s right.</bq> <bq>The matatu on the Limuru Road is not a symbol of African ingenuity making do, though it is that. It is evidence of a global financial system that has, for 60 years, made it systematically easier to remove wealth from African cities than to invest in them. The informal settlement dweller who wakes at dawn to catch the first matatu before fares rise, the child who misses school because the family cannot afford the fare that week, the market trader who cannot expand her business because she cannot reliably move her goods: these are not the consequences of poverty. They are among its causes. And their cause has a cause.</bq> <bq>There is a proverb from Cameroon and Congo: rain does not fall on one roof alone. The financing of African development is a global responsibility. It is a responsibility that wealthy states and the international institutions they have historically dominated have consistently declined to accept, not through malice, but through a system of incentives that has made it rational to accept the benefits of a rigged architecture while deploring its outcomes.</bq> They only pretend to deplore the outcomes because it costs them nothing to do so; quite to the contrary, it gains them prestige in their elite circles. They don't care enough, though, to renounce a single dollar of personal profit, a shockingly unjust and greedy attitude that they justify with blithe and largely unacknowledged racism. <bq>The $88.6 billion that Africa loses annually in illicit financial flows is more than double what it receives in official development assistance. Aid has never come close to closing the gap that the system itself creates – and has often arrived with conditionalities that restrict the policy choices of the very governments it claims to be supporting.</bq> <hr> <a href="https://www.wsws.org/en/articles/2026/05/25/iclk-m25.html" author="Nick Beams" source="WSWS">AI-fuelled Wall Street frenzy raises concerns</a> <bq>The IPO for SpaceX, founded in 2002 for space exploration but which has now extended into broadband, mobile satellite service and data centres for AI, was filed with the Securities and Exchange Commission last Wednesday. It is said to be the largest in history. Very few of the company’s shares will be available to public investors; most will initially be in the hands of Musk. But under new rules recently introduced by the NASDAQ exchange, it will be included in indexes which are tracked by Exchange Traded Funds, meaning that billions of dollars will flood into the market to buy its shares. According to estimates by JP Morgan, if 50 percent of the company’s shares are eventually floated, the market valuation will reach $2 trillion.</bq> <bq>[...] much of this boom is not based on profits made by the AI firms today but the expectation that the investments, amounting to hundreds of billions even trillions of dollars, will bring massive returns in the future. The three major firms at the centre of the new round of frenzied activity are all making losses.</bq> No, no, no. They don't expect to make any money in the future. None of them give a shit about the future. They expect to make money now. Look at the citation above: SpaceX is going public not because it's seeking investment: it's going public because it wants to convert its reputation to cash and it sees an opportunity to force people who would otherwise not invest in SpaceX to do so by leveraging investment requirements for indexes. This has all been set up for this payoff. Elon Musk and co. will have their money immediately; pension-fund holders will be sitting there with their assholes clenched, hoping again hope that there's a $2T there there, which there most certainly is not. <bq>Anthropic has said it expects to turn a profit in the second quarter of this year. OpenAI has said it expects to burn through $600 billion cash before becoming profitable in 2030. SpaceX, whose operations are “something of a financial mystery” in the words of the New York Times, boosted its revenue by 33 percent in 2025 to $18.7 billion. But it lost $4.9 billion in 2025 and in the first quarter of this year recorded a $4.3 billion loss.</bq> These are all fairy tales that you tell to your marks. You don't care what you have to say, as long as they buy your snake oil. In the case of IPOs and indexes, it's even easier: they're forced to buy your product whether they even know about it or not. <hr> <a href="https://www.wsws.org/en/articles/2026/05/28/mtrj-m28.html" author="Nick Beams" source="WSWS">The SpaceX IPO: Speculation on steroids</a> <bq>A comment in the FT by Sujeet Indap, headlined, “SpaceX to drive a cyber truck through corporate governance norms,” cited a statement by three major public pension funds, which play an increasingly important role in financial markets. They characterized the Space governance structure as “the most management-favorable governance structure ever brought to the US public markets at this scale.” Under its rules, Musk will be able to appoint a majority of the SpaceX board and will not be able to be removed as chief executive without his consent. It will also be very difficult for ordinary shareholders to pursue litigation. In other words, while listed as a public company on NASDAQ, enabling its shares to be bought by major investors and Exchange Traded Funds, it will be public in name only and will operate as the private fiefdom of Musk. If the SpaceX IPO goes ahead as planned, it will likely be followed by OpenAI and Anthropic and could well see other firms “going public.” This has brought warnings that the flow of capital into these ventures could drain the market, leading to a downturn in other areas. FT columnist Tej Parikh has noted that “history suggests that the issuance buzz may in fact mark the beginning of the end of the rally.”</bq> That has already happened. There is no money for anything else right now. <hr> <a href="https://www.wsws.org/en/articles/2026/05/29/gvjw-m29.html" author="Nick Beams" source="WSWS">War on Iran could trigger a financial crisis, European Central Bank warns</a> <bq>The FSR report of the ECB is along the same lines as other analysis in the recent period. It reveals a financial system in which the potential for a crash, even more significant than that of 2008, not least because of the growth of debt and complex financial mechanisms since then, hangs over the global financial structure. And moreover, that financial authorities have very incomplete information on what is taking place and certainly no measures to deal with it.</bq> <hr> <a href="https://www.wsws.org/en/articles/2026/05/30/lmle-m30.html" author="Andre Damon" source="WSWS">Labor share of income hits record low as corporate profits soar</a> <bq>The profits are concentrated among the largest corporations. Earnings at the 500 biggest US firms rose 28 percent in the first quarter from a year earlier, the fastest pace since 2021, and their profit margins reached 14.8 percent. The seven technology giants known as the “Magnificent 7”—Apple, Microsoft, Nvidia, Alphabet, Amazon, Meta and Tesla—grew their profits 63 percent. Nvidia, which makes the graphics processing units used to train large artificial-intelligence models, became the first company in history to reach a $5 trillion valuation. Micron, a memory-chip maker, crossed $1 trillion on Tuesday on a gross profit margin of about 75 percent. These same companies are carrying out mass layoffs at disproportionately high rates. US employers announced 300,749 job cuts in the first four months of 2026, with the technology sector leading every other.</bq> <h id="climate">Environment & Climate Change</h> <a href="https://www.desmog.com/2026/02/12/the-oil-industrys-latest-disaster-trillions-of-gallons-of-buried-toxic-wastewater/" source="Desmog" author="Justin Nobel">The Oil Industry’s Latest Disaster: Trillions of Gallons of Buried Toxic Wastewater</a> <bq>By the mid-20th century, the industry realized that injecting wastewater could be useful in another way: for pushing hard-to-reach oil lingering in some rock formations up to the surface. This technique, called waterflooding or enhanced oil recovery, generated a significant fraction of the oil produced in the U.S. from the 1950s through the early 1990s.</bq> <bq>Vincent McKelvey, a USGS research director and the symposium’s keynote speaker, said he believed the subterranean earth represented “an underutilized resource with a great potential for contribution to national needs.”</bq> The alternative was to.pay the cost of proper disposal, killing profit margins, which is unacceptable. So, you choose not to live where you shit, pay off a few politicians, and be on your merry way, letting everyone else deal with the mess you made. This is extractive capitalism: never pay for anything you aren't forced to pay for. Live without principles. Sleep like a baby. <bq>“It is clear,” said Theodore Cook of the American Association of Petroleum Geologists, in his forward to a roundup of the symposium’s presentations in 1972, “that this method is not the final answer to society’s waste problems.”</bq> It's not society's answer but it's a minimally palatable answer that will distract long enough to extract short- and medium-term gain, while delaying detrimental effects long enough to avoid blame and consequences. <bq>Immediately the EPA faced multiple lawsuits by industries, including oil and gas, mining, and steel, which complained underground waste injection regulations would cost them billions.</bq> How dare anyone make private companies pay full price for what they do? Doesn't the government know that business is supposed to make profits while the government cleans up behind it, wiping its ass with the poor? <bq>This made it “difficult to predict exactly the action or fate of wastes after their injection,” if not “nearly impossible.”</bq> Who knows, right? It's so unpredictable, maybe birthday cakes and rainbows come out. No-one really knows. So unpredictable. The alternative was to.pay the cost of proper disposal, killing profit margins, which is unacceptable. So, you choose not to live where you shit, pay off a few politicians, and be on your merry way, while your orphan-crushing machine hums along. <bq>“You look at the Permian Basin and you think it’s a huge oil play, but it produces three to four times as much produced water as oil,” says Knewitz. “So the Permian is really a produced water play that on the side produces some oil and gas.”</bq> <bq>Advocacy groups that have spent decades tracking the EPA’s oil and gas waste rules point out that the business model of the U.S. fracking industry depends on operators being able to get rid of waste cheaply.</bq> No shit. It's more convenient for them to put their garbage in the neighbor's garage. <h id="medicine">Medicine & Disease</h> <a href="https://www.wsws.org/en/articles/2026/05/26/ddda-m26.html" author="Benjamin Mateus" source="WSWS">Ebola outbreak in DRC and Uganda passes 1,000 cases, as Italy reports 2 suspected cases</a> <bq>The DRC’s population is remarkably young, with nearly 46 percent of its roughly 115 million people under the age of 15. This large population of youth confront a society ravaged by war and a near-total absence of formal employment. The social crisis is compounded by staggering displacement: an estimated 7.8 million people are internally displaced, one of the highest figures in the world, with Ituri Province alone hosting more than 920,000 and recent fighting around Goma uprooting another 700,000. These populations are concentrated in makeshift camps lacking water, sanitation, and hygiene infrastructure. In parts of North Kivu, people survive on just 6.3 liters of water per day and share a single latrine among 138, ideal conditions for the explosive spread of Ebola and cholera. Entwined with displacement is an escalating hunger crisis. An estimated 25.6 million people nationwide face crisis and emergency levels of food insecurity, including 6.2 million in Ituri and North Kivu, while chronic stunting affects 42 percent of children under five. Recent surveys in South Kivu found acute malnutrition rates of 18 percent, far above emergency thresholds. Such starvation weakens immune systems and sharply raises mortality from infections like Ebola and measles.</bq> <bq>The socioeconomic baseline of the region exposes the structural inequality of global capitalism. Life expectancy is 62.5 years, well below the African average and decades below that of the United States. An estimated 72.3 percent of the population survives on less than $2.15 a day. Maternal and child mortality are staggering: 76 under-five deaths per 1,000 live births and 846 maternal deaths per 100,000. Set against the trillions in mineral wealth extracted from the region by multinational corporations, these figures expose the WHO’s “low” global risk assessment as both shortsighted and false. Recurrent Ebola outbreaks and the emergence of other deadly pathogens will threaten millions, regionally and globally, as long as these conditions persist. The demographic and social collapse in the eastern DRC is no natural phenomenon but the deliberate product of imperialism and capitalist exploitation—what Friedrich Engels called social murder.</bq> <hr> <a href="https://yourlocalepidemiologist.substack.com/p/ebola-chemical-plants-and-health" author="Katelyn Jetelina" source="Your Local Epidemiologist">Ebola, chemical plants and health, hantavirus, common colds, heat and more</a> <bq>The combined confirmed and suspected Ebola cases in DRC are now more than 1,000. All signs are pointing to a very long and catastrophic outbreak in Central Africa: This is a vast undercount. We know this because the test positivity rate is hovering around 50%, only 20% of contacts are being traced (and in some areas, no contacts at all), and more cases keep popping up with no known connection. This all points to widespread and undetected community transmission. This is in only a week of detection. Compared to previous outbreaks, the growth is very fast, as the huge West Africa outbreak in 2016 was first detected at 49 cases and rose to 208 cases a month later. It took four months for that outbreak to reach the size of the current one in the DR Congo. The cases are spread out across 16 health zones. There are now multiple epicenters, making containment very difficult.</bq> <hr> <a href="https://www.wsws.org/en/articles/2026/05/30/htqy-m30.html" author="Cesar Uco" source="WSWS">Peru declares state of emergency as measles epidemic exposes crisis of capitalist-run public health</a> <bq>Measles is not a mild childhood inconvenience. It is a highly contagious viral disease whose complications include pneumonia, encephalitis and permanent loss of vision or hearing. It can kill. It strikes with particular ferocity among unvaccinated children and immunocompromised individuals. Its hallmark symptoms—high fever, skin rash, cough, and conjunctivitis—precede a period during which the virus can spread to others before the infected person even knows they are ill. And yet, measles is entirely preventable. Two doses of the measles-mumps-rubella (MMR) vaccine, administered in childhood, confer lifelong immunity in 97 percent of recipients. This is not a disease for which humanity lacks the tools. It is a disease that spreads because the social and political order refuses to deploy those tools equitably and consistently. Every measles case in 2026 is, in the most literal sense, a political failure.</bq> <bq>A new dimension of danger now looms with the 2026 FIFA World Cup, to be co-hosted by the United States, Canada, and Mexico. Of the 104 scheduled matches, 78 will be played on US soil. Hundreds of thousands of fans from across Latin America—including from countries with collapsing vaccination rates—will travel to host cities and return home, traversing airports, stadiums and public transport in nations where measles is already circulating at elevated levels. The conditions for a significant international transmission event are already present.</bq> <bq>As with Peru’s COVID-19 death toll, the measles epidemic is not a natural disaster, but a concentrated expression of a social crisis decades in the making: a chronically starved healthcare system, soaring inequality and a Peruvian bourgeoisie that faithfully follows the lead of its patrons in Washington in placing profits above human life. Peru is a country of enormous inequality. Millions of households lack reliable access to clean water. Much of the workforce is absorbed by an informal economy in which workers have no access to healthcare, sick leave or occupational protections of any kind. The shantytowns encircling Lima and the Indigenous communities of the Andes and the Amazon operate at a level of material deprivation incompatible with the functioning of any serious public health system. These are not the accidental residues of underdevelopment—they are the structural products of capitalist property relations and the international division of labor imposed by imperialism. Twenty years ago, measles was on the verge of global eradication. As the WSWS has explained in its analysis of its global measles, the two-dose measles vaccination program, before it began to be eroded, had saved an estimated 93.7 million lives—the greatest life-saving achievement of any vaccine intervention in history. The unraveling of that achievement through austerity, defunding and anti-scientific disinformation represents one of the most profound social crimes of the capitalist era.</bq> <h id="art">Art, Literature, Music, & Cinema</h> <a href="https://www.the-hinternet.com/p/divertimento-on-a-footnote-to-gruzinski" source="The Hinternet" author="Justin Smith-Ruiu">Divertimento on a Footnote to Gruzinski</a> <bq>And don’t tell me that it’s precisely because we stopped caring so much about things like Latin that we were able to move on and start doing things like building word-processors instead. If you do tell me that, I will tell you it has not been worth it.</bq> <h id="philosophy">Philosophy, Sociology, & Culture</h> <a href="https://deadsimpletech.com/blog/whats-left-to-say" source="deadSimpleTech" author="Iris Meredith">What's left to say</a> <bq>I'm exhausted at the world and the people leading us, I'm exhausted at the way in which all of our social interactions seem to reduce to a kind of bleak superficiality (hence the networking article of a week-and-a-half ago, which was needlessly mean-spirited and for which I apologise). I'm exhausted by the fact that even people who should and claim to know better fall into that mode of interaction, and I'm exhausted by the fact that there increasingly seems to be no space in the world for those of us who have values beyond the dollar, the click, the like or the engagement statistics.</bq> <bq>[...] we were in the business of consuming and producing slop for a very long time. We loved the stuff: business reports that nobody read, infographics that looked pretty (or even ones that didn't look very pretty and had downright sloppy design), youtube video essays that were just a person reading out a wikipedia article, SEO-calibrated business blogs that are completely vacuous and an endless supply of social media content.</bq> <bq>Marketing copy, after all, is meant first and foremost to elicit an emotional reaction that gets people to do the thing that you want them to do, and SEO doesn't even do that: it aims to trick one kind of machine or another into surfacing your work so that humans can read your marketing copy. Even at its best-crafted, this is slop: it has an effect, not by quality, but by sheer volume of stuff.</bq> <bq>The end result is as we see it; a deep sickness of the soul where, whenever we're given the option, we choose ease, to have our existing beliefs confirmed, to be made angry in a way that feels good, to feel as though we're already all that we need to be rather than making the effort to grow.</bq> <hr> <a href="https://old.reddit.com/r/WorkReform/comments/1tkkh7e/thems_fighting_words/" author="" source="Reddit">Them's fighting words</a> <img src="{att_link}just_be_kind_to_each_other_are_five_fighting_words.webp" href="{att_link}just_be_kind_to_each_other_are_five_fighting_words.webp" align="none" caption="Just be kind to each other are five fighting words" scale="75%"> <bq>Prompt: Things to say that will always start a fight. Answer: Everybody deserves food and shelter before anybody deserves rental properties or yachts.</bq> <h id="technology">Technology & Engineering</h> <a href="https://davidoks.blog/p/why-japanese-companies-do-so-many" source="" author="David Oks">Why Japanese companies do so many different things</a> <bq>What’s striking about Japanese companies is not that they do lots of different things but rather that they do them very well. There are all sorts of high-precision inputs—the e-chuck being just one example—that are produced virtually only by Japanese firms.</bq> <bq>The form of the corporation that we know and love in the United States—specialized, market-oriented, governed by shareholders—is just one form that the corporation can take; but it’s not the only way to coordinate capital and labor in a successful and profitable way. The protean corporations of Japan are best understood as a different species of thing altogether: better at some things, worse at others, but still highly adapted to their particular environment. And the things that they’re very good at turn out to be extraordinarily helpful for all sorts of things in which American companies tend to struggle.</bq> <bq>Even in times of acute distress, a Japanese firm will go to great lengths to find its employees positions at smaller affiliates rather than releasing them onto the labor market. And individual performance isn’t really a huge criterion in someone’s career. Promotions are based largely on seniority; pay differentials between ranks are modest; and bonuses are tied to the performance of the firm.</bq> <bq>Japanese companies strive to avoid financial pressure from outsiders. Relationships with suppliers are longstanding and entrenched: many Japanese companies have been working with the same suppliers for 50 years or longer.</bq> <bq>Japanese companies don’t really try too hard to return profits to shareholders. Earnings are mostly reinvested, and investor dividends are kept low.</bq> <bq>The andon method is really the J-mode in miniature. Information flows laterally, authority to act is widely distributed, and the people closest to the problems are the ones who fix it. And one result of the Toyota-style approach is that Japanese automakers have produced fewer defective cars than their American competitors for a very long time.</bq> <bq>[...] horizontal coordination requires that workers know each other’s jobs, since a worker who spots a problem in one area of the line can only act on it if he understands what that area is supposed to be doing. But in order to understand each other’s jobs, workers cannot be specialized: they have to rotate across different workplace functions to the point where they’re familiar with much of the plant’s operations.</bq> <bq>And you also have to give them an ironclad commitment not to fire them if economic conditions worsen: if they can get laid off at any moment, why would they invest years of effort in learning all the idiosyncratic things that your firm does?</bq> <bq>The H-firm exists to make money, or rather to return money to shareholders; but the J-firm, run by its employees and largely indifferent to the interests of shareholders, exists simply to continue existing.</bq> It exists to provide value. <bq>If you’ve made a commitment to keep people employed for life, then you need to create jobs for them if their current jobs stop making sense: indeed, you might need to keep them employed even if you can’t find anything for them to do. If you’re not very worried about profitability, and have lots of well-trained generalist employees, then it makes perfect sense to reinvest your company’s earnings by expanding into new industries:</bq> <bq>They could throw enormous amounts of patient capital at a problem, spend years refining a process without any imminent expectation of profit, and keep hundreds of broadly trained workers iterating on the shop floor until the quality of the output was world-class.</bq> <bq>They could throw enormous amounts of patient capital at a problem, spend years refining a process without any imminent expectation of profit, and keep hundreds of broadly trained workers iterating on the shop floor until the quality of the output was world-class. And since profitability was never the primary objective, there was no pressure to abandon a difficult market for an easier one.</bq> <h id="llms">LLMs & AI</h> <a href="https://www.seangoedecke.com/the-o3-geoguessr-prompt-did-not-work/" source="" author="Sean Goedecke">The famous o3 "GeoGuessr" prompt did not work</a> <bq>[...] this shows how easy it is to fool yourself about the quality of prompting. When the model is already pretty good at a task, you can give it a very elaborate prompt without impacting performance. It’ll still be pretty good, except this time it’s good because of what you did. This is particularly true if you’re iterating with the model and asking it “what should I add to the prompt” for each mistake. Models will happily make up stories for you about their own reasoning processes, and will almost always say “yes, that helped a lot!” when you ask them if a particular prompt tweak made things better. The only way to actually know is by constructing some kind of benchmark.</bq> <bq>[...] let’s use the benchmark to answer a question I’ve had for a while: do gpt-5.4 and gpt-5.5 have o3’s geolocation abilities? The answer, apparently, is no. [...] Whatever o3 had that made it good at this task hasn’t transferred to newer models.</bq> <hr> <a href="https://nooneshappy.com/article/the-scale-the-plan-and-the-people/" source="No One's Happy" author="">The Scale, The Plan, and The People</a> <bq>Goldman Sachs’ chief economist Jan Hatzius, surveying the same terrain, concluded that AI had contributed “basically zero” to U.S. economic growth in 2025 and observed that “FOMO, not ROI, is driving hyperscaler capex.” This shows simply that the technology is real, its uses are real, and at the scale of the spend, the productivity it returns is not what the spend requires.</bq> <bq>[...] a meaningful share of the current consumption that looks like demand is waste, friction, and architectural limitation — and cost deflation applied to waste is still waste. DeepSeek’s January 2025 release demonstrated a fundamental architectural update to models that can dramatically reduce GPU requirements while maintaining competitive capability, which suggests the buildout is being sized against a hardware curve that research, not spending, may be the faster approach.</bq> <bq>ChatGPT, Claude, Gemini — are not simply LLM calls. They are complex engineering systems that use the model’s output to select and orchestrate non-LLM tooling: search engines, code interpreters, calculators, file systems, external APIs. The LLM produces text; the application routes that text through tools that do the actual work. If the architecture genuinely understood the world — if it could plan, verify, and reason about consequences — the scaffolding would not be necessary. The engineering effort required to make the product useful is itself a measure of what the model cannot do alone.</bq> <bq>The practical consequence is that users compensate for these limitations with tokens. They write longer prompts to constrain outputs that drift. They make multiple attempts at the same task because the model cannot reliably plan across steps. They build elaborate scaffolding — retrieval systems, verification loops, chain-of-thought prompting — to approximate capabilities the architecture does not natively possess. Each workaround consumes tokens. Each token is counted as demand. This means a portion of the consumption curve is not demand for the product — it is demand for the product to be something it is not yet.</bq> And even writing longer prompts and increasing context is basically witchcraft right now that no-one can begin to call engineering with a straight face. The tools fall apart if the wind changes direction. <bq>Pre-AI, my teams regularly developed and reused systems with similar functionalities across projects; it is not as though every engagement required building from scratch. The tool has replaced reuse with regeneration, and the token cost of regeneration is counted as productivity, and soon I think there will be a regression to well tested manually built solutions due to the quality decrease.</bq> That is a wonderful point. <bq>[...] handful of companies and the executives who run them. The same three hyperscalers underwriting the bulk of the capital expenditure are the largest equity investors in the AI companies the capacity is being built for, [...]</bq> <bq>A layer of debt-financed companies has emerged whose entire business is to buy GPUs with borrowed money and rent the compute back to the companies that funded them.</bq> Yes. This is an extremely expensive and public scam. <bq>If Microsoft reduces its OpenAI commitment, it loses one of Azure’s largest customers, the AI revenue line that justifies $192 billion in capex, and the earnings growth that holds its stock price — all at once. The same logic binds Alphabet and Amazon to Anthropic: the equity position and the cloud contract are not separate bets, they are the same bet, and unwinding one unwinds both.</bq> <bq>Fiber-optic cable, once laid, has a shelf life measured in decades. When demand eventually caught up — and it did — the dark fiber lit up and became the backbone of the modern internet. The investors who overpaid were not made whole, but the physical asset retained value. Semiconductors will not. GPUs depreciate on a cycle of roughly six years, driven not by wear but by architectural obsolescence; each new generation renders the prior one uneconomical to operate. The data centers being built today will house hardware that is outdated before the demand the buildout assumes has had time to materialize.</bq> And not only is it showing no sign of materializing but it will almost certainly shrink once those pushing the demand stop heavily subsidizing it. People are going to let their Apple TV subscription keep running at $10 per month even though they don't use it that much. They would absolutely not keep it if the price jumped to $200, $500, or $2,000 per month. <bq>In Q1 2026, more than half of Amazon’s quarterly profit came from marking up the value of its Anthropic stake — not from selling products or cloud services but from updating the estimated value of an investment. Alphabet reported $28.7 billion of its $62.6 billion quarterly profit from the same source. Each revaluation inflates earnings, lifts the company’s index weight, and reweights the 401(k) that buys more of the inflated stock.</bq> <bq>The companies and people distributing it are personally enriched at every step — equity in the labs they fund, stock in the companies they run, fees on the debt they structure, carry on the funds they manage. The buildout does not need to succeed for the people building it to profit. It needs only to continue. There is an implicit guarantee that none of the people who made the bet will be the ones who pay for it.</bq> <hr> <a href="https://www.seangoedecke.com/how-i-use-llms-in-2026/" source="" author="Sean Goedecke">How I use LLMs as a staff engineer in 2026</a> <bq>[...] now I start every single change by asking an agent to solve the problem, and usually push the PR after a single editing pass.</bq> I don't know what problems you're solving but this sounds like a joke. I run aground immediately. <bq>This reflects a shift from having to line-edit the agent basically as it went to only doing an editing pass right at the end. Early agents would go wrong a lot and not be able to recover, so it was valuable to keep an eye on their thought processes and step in to pause them and set them right. In my experience, current agents move too fast to do this, and recover their own mistakes most of the time anyway.</bq> You sound like a shill. <bq>For difficult tasks, I’ll often reject five or six (or more!) agent attempts before accepting one as good enough to work with, or giving up and making the change by hand.</bq> I guess I only have difficult tasks. Hey, wait! This part completely contradicts the first part. Huh. Wild that he believes the two things simultaneously: he never edits or reviews but he magically catches all the errors when it's wrong. Like Karpathy, he doesn't think he misses anything because he stopped looking. If enough people who don't know what they're talking about tell you something, you should believe it. <bq>Just last week I had a tricky bug that took about fourteen agent sessions before one finally figured it out.</bq> Enjoy the cheap tokens while they last. <bq>Writing the PR description by hand also signals to reviewers that I’ve reviewed the change myself, and I’m not asking them to be the first human to read the diff.</bq> Even though they absolutely will be the first one to be reading the diff. You didn't look at the diffs but you write the message to cover up that fact. So, you're lying. <bq>OpenAI models used to be terrible at this and have only very recently gotten acceptable with GPT-5.5.</bq> So, like ... Four weeks ago. Do you realize how stupid you sound? <hr> <media href="https://www.youtube.com/watch?v=VucjurQUHO8" src="https://www.youtube.com/v/VucjurQUHO8" source="YouTube" width="560px" author="Mo Bitar" caption="I'm done. I'm f***ing done."> <bq>The mid-level engineer on your team who's been working in your codebase for 10 years writes a lot better code than a PhD level engineer who you just hired who isn't familiar with your code. It's about carrying the whole thing in your head for many, many years. It's about specializing in that specific code base.</bq> <bq>LLMs are a trick. They are not AI. They trick us to believing they are intelligent. The mechanism matters.</bq> Not for the first time, this reminds me of how 3D-rendering engines work: they lie. They take shortcuts to render plausible reality at a rate that we deem realistic and acceptable. The many, many techniques for rendering shadows or for determining LOD are a testament to the power of lying. Everything lies. It's different if we're being lied to to entertain us, or if we start to believe the lies about important things. <bq>You can polish a lie forever and it never becomes the truth. You can put a billion more parameters on the lie and it's a bigger lie now. Like, congratulations. LLMs are an elaborate trick. There is no theory in there. It's brute-forcing statistics to trick people for long durations, long enough for you to be tricked into forcing your entire company to think this is intelligent and that they have to use this tool to maximize productivity. The real Turing test is whether the human on the other end is f@&king stupid enough to replace their entire labor pool with this statistical-ass tool that builds in inside the distribution demo and thinks it could build anything. The bot doesn't have to be intelligent. It just has to be more convincing than the median CEO is skeptical.</bq> <hr> I asked Copilot the following question: <bq>Which app or update installed the following file?<code>c:\program files\microsoft visual studio\18\community\common7\ide\commonextensions\microsoft\ssas\localserver\mdataengine\odbc drivers\simba spark odbc driver\libcurl64.dlla\openssl64.dlla\libcrypto-1_1-x64.dll</code></bq> This is the first answer: <bq quote-style="none">Those DLLs are not random system files—they belong to a Simba Spark ODBC driver packaged with SQL Server Analysis Services (SSAS) components inside Visual Studio. <h level="3">What installed them</h> The path tells the story: <code> ...\Microsoft Visual Studio\18\Community\Common7\IDE\CommonExtensions\Microsoft\SSAS\... </code> This indicates they were installed by: 👉 Microsoft Visual Studio 2022 (v18 folder) 👉 Specifically the SQL Server Analysis Services / Data Tools components (often installed via the Data storage and processing workload) <hr> <h level="3">Why those specific DLLs exist</h> The subpath: <code> Simba Spark ODBC Driver\ </code> means Visual Studio includes a bundled Simba Apache Spark ODBC driver used for: <ul> Connecting to Spark / big data sources Powering SSAS tabular models Supporting data import / query features in Visual Studio </ul> The files you listed: <ul> <c>libcurl64.dll</c> → HTTP/network communication <c>openssl64.dll</c> + <c>libcrypto-1_1-x64.dll</c> → SSL/TLS encryption Located under Simba driver → standard dependencies for secure data connectivity </ul> These are third-party runtime libraries shipped with Simba drivers, not independently installed apps. <hr> <h level="3">How it got on your system</h> Most likely one of these actions installed it: <ul> Installing Visual Studio 2022 Community Adding workloads such as:<ul> Data storage and processing Azure data tools SQL Server Data Tools (SSDT)</ul> Installing extensions related to:<ul> Analysis Services projects Data modeling / BI tooling</ul> </ul> <hr> <h level="3">How to verify</h> You can confirm it yourself: <ol> Open Visual Studio Installer Click Modify on your VS installation Check installed workloads:<ul> Look for anything related to Data, SQL, or Analysis Services</ul> </ol> <hr> <h level="3">Important note</h> ✅ These files are legitimate and safe ✅ They are expected dependencies, not malware ✅ They don’t run on their own—they’re used by Visual Studio components <hr> <h level="3">Quick summary</h> <pre> | Item | Explanation | | --------- | ----------------------------------------------------- | | Installer | Visual Studio 2022 (Community) | | Feature | SQL Server Analysis Services / Data Tools | | Component | Simba Spark ODBC Driver | | Purpose | Secure connectivity to data sources (Spark, big data) | </pre> <hr> If you want, I can also help you trace exact install date or which update added it, using Windows logs or VS installer logs.</bq> Jesus Christ. Write a little more why don't you. My next question was, <bq>What's the version number for Visual Studio 2022?</bq> The answer was: <bq quote-style="none">Visual Studio 2022 uses the major version number 17. <h level="3">Version format</h> Visual Studio 2022 versions follow this pattern: <code> 17.x.y </code> <ul> 17 → Major version (VS 2022) x → Minor updates (e.g., 17.8, 17.9, 17.10, etc.) y → Patch/build number </ul> <h level="3">Examples</h> <ul> 17.0 → Initial release (Nov 2021) 17.8 → Late 2023 release 17.10 → 2024 update (Current installs continue incrementing within 17.x) </ul> <hr> <h level="3">Important clarification for your path</h> You saw: <code> C:\Program Files\Microsoft Visual Studio\18\... </code> It’s an internal installation directory version and doesn’t reflect the official VS version. 👉 Visual Studio 2022 = Version 17.x, regardless of that <c>18</c> folder. <hr> <h level="3">How to check your exact installed version</h> In Visual Studio: <ol> Open Visual Studio Go to Help → About Microsoft Visual Studio You’ll see something like: <c>Version 17.9.6</c> </ol> <hr> If you want, I can map your installed components to the exact VS update that introduced that Simba driver.</bq> Oh my God, another wall of text to write the number "17." Next question: <bq>What's the version number for Visual Studio 2026?</bq> And the answer: <bq quote-style="none">There is no official “Visual Studio 2026” release (as of now). Microsoft names Visual Studio versions by release year, but the version numbers follow a sequential major version, not the year: <pre> | Product name | Major version | | ---------------------------------------------- | ------------- | | Visual Studio 2019 | 16.x | | Visual Studio 2022 | 17.x | | Next major release (expected \~2025 timeframe) | 18.x | </pre> <hr> <h level="3">So what about “Visual Studio 2026”?</h> <ul> Microsoft has not announced a Visual Studio version named 2026 If you’re seeing references to “18” (like your folder path):<ul> That corresponds to the next major engine version (18.x) It may appear internally or in preview builds before official branding</ul> </ul> <hr> <h level="3">Key takeaway</h> <ul> Visual Studio 2022 → version 17.x Next generation Visual Studio (likely branded 2025) → version 18.x There is no separate “2026 version number” </ul> <hr> <h level="3">Why your path shows <c>18</c></h> <code> C:\Program Files\Microsoft Visual Studio\18\... </code> This likely means: <ul> You have a preview / newer internal build Or Microsoft has already started using the v18 platform internally </ul> <hr> ✅ Bottom line: If you're seeing “18”, that corresponds to the next major Visual Studio generation (v18), not a product officially named “Visual Studio 2026”. <hr> If you want, I can identify exactly which VS build you have from your system files or installer logs.</bq> I don't know how people can stand using these tools. I don't understand how you "get sucked in." This is boring. And wrong. To sum things up from those pages of text: <ol> I asked which tool installed a file at a path that contains <c>microsoft visual studio\18</c> and <c>simba spark odbc driver</c>. I was pretty sure already what the answer would be. Copilot helpfully told me that it was Visual Studio 2022 that had installed the DLL as part of the <iq>SQL Server Analysis Services / Data Tools components</iq>. I guess that's kind of helpful but ... I'm pretty sure it wasn't Visual Studio 2022 that installed it. So, I asked which version Copilot thinks Visual Studio 2022 has. It answered in its typically long-winded way that it definitely has version 17. So why would it think that the path containing an 18 could come from Visual Studio 2022 and not Visual Studio 2026? <div>The answer became clear when I asked which version Copilot thinks Visual Studio 2026 has and it effusively assured me that the tool that's been installed on my Windows machine for the last six months simply does not exist. The "18" in the path became irrelevant because it didn't match anything in the training data, so it couldn't affect the responses. Visual Studio 2022 was the most likely match, so Copilot built an entire answer around that and doubled and tripled down on its error. If I hadn't already known the answer, I'd have cheerfully believed the information from the first response and caused my colleague in IT to spend hours uninstalling components from the wrong version of Visual Studio in order to fix the Windows Defender error they were seeing. It's becoming increasingly clear to me that the potential for productivity gains through LLMs are easily outweighed by the potential for productivity losses through wild goose chases inspired by absurdly incorrect but exceedingly confident responses from LLMs.</div> </ol> To repeat, I honestly don't know how people are gaining value from these tools because they are just so fucking wrong all the time. People must spend all day fooling themselves into believing that they're making progress toward a goal they've chosen, when the LLM coding-harness that they're using is constantly tacking against the wind of their prompts to steer toward its training data instead. What a pain in the ass. <h id="programming">Programming</h> <a href="https://cekrem.github.io/posts/the-tacit-dimension/" source="" author="Christian Ekrem">The Tacit Dimension: Why Your Best Engineers Can't Tell You What They Know</a> <bq>This is the part of programming knowledge that AI is structurally locked out of. Not because the models are too small, or the training corpora too narrow, or the architectures too primitive. Because the knowledge isn’t there to be trained on, and by Polanyi’s definition cannot be put there.</bq> <bq>We can know more than we can tell.</bq> Well, those of us who know anything worth knowing do. I think some people might not have much more to impart than their surface. But that's not fair. Everyone has something that they can contribute, even if it's just being good company for someone. <bq>That’s tacit knowledge at work. Your eyes have been over ten thousand PRs. You’re picking up on a constellation of features — naming choices, indentation patterns, where exceptions get caught, the implicit contract a function seems to expect, the way the author tends to handle nulls. You can recognise a constellation in milliseconds. You can articulate one in maybe ten minutes, and even then incompletely.</bq> <bq>(My favourite version of this is the senior dev who looks at a new design and says “I don’t like it, but I can’t tell you why yet. Give me an hour.” That hour is their doing the slow, painful work of making the tacit explicit.</bq> <bq>[...] the part of knowing that cannot in principle be made fully explicit. Naur called it “theory.” MacIntyre would call it “practice.” Aristotle called it phronesis. Polanyi called it the tacit dimension. They are all pointing at the same thing: the kind of knowing you only get from doing, the kind that cannot be transmitted by writing it down.</bq> <bq>Re-elevate apprenticeship. Working at the shoulder of someone who has the tacit knowledge is the only known transmission mechanism. Pair programming, code review where the senior explains in voice (or admits they can’t), walking through bugs together — these aren’t quaint. They’re the only mechanism we have. Burn them and you burn the wire.</bq> <bq>Pay seniors to teach, not just to ship. A senior who spends two hours pairing with a junior is doing the most important work on the team that week. If your incentive structure doesn’t reflect that, your incentive structure is bankrupting your tacit capital, one sprint at a time.</bq> <hr> <media source="YouTube" width="560px" href="https://www.youtube.com/watch?v=BvJMm8QIa6M" src="https://www.youtube.com/v/BvJMm8QIa6M" caption="'Fine-grained everything' (Englisch)(programmier.con 2025)" author="Rich Harris"> The fine-grained approach to server-side coding is relatively nicely designed, though he's as usual too optimistic about how intuitive the Svelte APIs are. I think they're elegant but I don't think they're very easy to discover or analyze. I see how they're necessary in order to provide the desired functionality---and I can't at all claim that I could have designed a better API---but they're not intuitive. A lot of the optimizations are analogous to Quake's predictive networking code that applies the expected behavior locally, then updates the situation when the network confirms or denies that assumption. The automatic error-handling here for failing APIs was quite nice. <h id="design">Design</h> <img src="{att_link}image_2026-05-29_080222657.png" align="none" caption="'New' Outlook notifications don't show up when battery-saver is enabled"> The new Outlook doesn't show calendar notifications if you have battery saver enabled. In fact, it seems that no notifications are shown when your battery is low. That is kind of ridiculous. Oh, hey, sorry I missed the meeting. Battery on my laptop was low. Oh, I should have charged the laptop? I did! It had just drained its battery within 40 minutes and had switched on battery saver. Yeah, I know, but what can you do? There's literally nothing that could have been done better. <hr> Last night, a friend asked how we were using AI tools at work. I said that we'd found a way to integrate them into our process in a sane, pragmatic way that helps us where it can help us, and we mostly avoid wasting time with the long-form, so-called agentic style of work that you hear a lot about. We do the work ourselves where it's faster to avoid the whole rigamarole. They then wondered how a junior who doesn't yet know how to do much on their own can figure out how to work. That's really the problem, isn't it? Anytime you don't know much of anything about something, you are quickly satisfied with the results. You think it's right because it passed your shitty verification. You are relatively easily convinced that nothing more can be done, so you don't even think to ask the machine to fix it (setting aside whether it could). You're stuck at whatever level the machine is capable of offering you. This is not unlike most automation, though, like, say, a dump truck and steam shovel working together. A dump truck and steam shovel do such an incredibly more efficient job of moving dirt and rocks than people with shovels (or hands!) would, that it's not even a question whether you'd want to use them. The benefits are immediate and obvious given that you can afford a dump truck and a steam shovel and their fuel. If the steam shovel and dump truck break down, though---or you can no longer afford their fuel or maintenance---then we just don't even bother trying to move tons of material. It takes too much time and energy. We wait for them to be repaired or we accept smaller goals; we dig smaller holes. This is where juniors are now at with AIs. They can't write much of anything themselves, either code or text. So they're stuck with whatever the tools offer. And they're stuck paying whatever the tools cost. But the thing that these tools do is something that people very easily used to do without them, and pretty much at the same speed, if we control for quality. The speed boost promised by AIs isn't orders of magnitude---not the serious claims---but a few dozen percent, at most. And even those are based on careful curation of the type of work and the way that people work. And, usually, quite a bit of cheating by not actually verifying the quality of the output. So, now we're training people who have no fallback for when the tools fail them. They have no mechanism for even knowing when a tool has failed them. The shadows they see on Plato's cave is telling them that everything is fine, that no-one could have done it better. Even if they suspect that the shadows lie, they can't do anything about it. They are, in a sense, handicapped. The AIs we have now are more like a parlor trick. They're like the dog or robot that's been trained to go to the refrigerator in the kitchen and bring its owner a beer back in the living room. If it works, great! If it doesn't, its owner can get up at any time to get the beer himself (let's face it, it's gonna be a him) in about the same time or faster. Juniors either won't know how to get up or won't be able to. If the robot can't do it, then it won't get done. So that's the answer, I guess. We are hurtling headlong into a world where there is an ever-decreasing supply of people who will be capable of judging these tools' output, to say nothing of improving on that output, building things without these tools, or working on the tools themselves. Who is going to build the infrastructure on which all of this relies? The LLMs are only able to build React web sites because a team of programmers, architects, and designers worked diligently for years to build React. It can build a .NET back-end because thousands of people built .NET. What happens when everyone's just building mediocre shit on the existing infrastructure and, not only is no one building infrastructure anymore, but everyone who knew how to build and improve infrastructure has either been squeezed out of their jobs, has retired, has otherwise moved on, or has died? I'm probably biased though, as I view the world through a lens of being able to do pretty much anything that an LLM offers me. Sometimes more quickly, sometimes initially more slowly but almost always more thoroughly and better, for all the metrics that matter to me or to those using what I produce. If we're honest, a lot of people have already been sitting in that metaphorical living room, waiting for a machine to do what they want, and going without when it fails. They've been watching mediocre shadow plays that they don't notice are mediocre for most of their lives. Their society has trained them not to notice. They are perfectly primed for a world built on a stagnating infrastructure by juniors with machines that no-one understands. It is the best they that they can imagine. The best customer is the one who doesn't even notice that you're ripping them off. <h id="sports">Sports</h> The Swiss men's ice-hockey team soared into the final match tomorrow on the strength of a 6--0 semifinal win over Norway, after having defeated 8 other teams with an overwhelming goal differential, including the U.S., Sweden, and Finland. They play Finland in the finals tomorrow, after Finland defeated Canada 4--2 in its own semifinal, coming back from being down 2--1. Hopp Schwiiz! <h id="fun">Fun</h> <img src="{att_link}is_it_humid_today_-_it_feels_humid_to_me.jpg" align="none" caption="Is it humid today? it feels humid to me."> <hr> <a href="https://theonion.com/trump-makes-figurines-of-himself-ivanka-kiss-in-miniature-ballroom-model/" author="" source="The Onion">Trump Makes Figurines Of Himself, Ivanka Kiss In Miniature Ballroom Model</a> <bq>Mashing their faces together as he produced loud smooching sounds, President Donald Trump made figurines of himself and his daughter Ivanka Trump kiss in a model of his under-construction White House ballroom, reports confirmed Thursday. According to sources, Trump raised the pitch of his voice and said, “Such a splendid ballroom, Daddy! Let us dance!” as he pressed the figurines into each other at the waist and whirled them around the checkered marble floor.</bq>