Links and Notes for May 15th, 2026

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 They are intentionally succinct, else they’d be articles and probably end up in the gigantic backlog of unpublished drafts.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
• Economy & Finance
• Environment & Climate Change
• Medicine & Disease
• Art, Literature, Music, & Cinema
• Philosophy, Sociology, & Culture
• Technology & Engineering
• LLMs & AI
• Programming
• Sports
• Fun

Public Policy & Politics

Trump’s Iranian Nightmare by Chris Hedges (Substack)

“America’s newest quagmire in the Middle East is like its old quagmires in the Middle East. It is based, as were the wars in Afghanistan and Iraq, on a gross misreading of our adversaries, a catastrophic failure to understand the limits of imperial power and no discernible strategy. It swells the profits of the war industry, wasting billions of public funds, alienates our allies and erodes the global power and prestige of the United States.”

“Iran is the clear winner of Operation Epic Fury. Trump is the clear loser. The dilemma is that Trump’s penchant for inventing his own reality means he is unlikely to acknowledge his blunder and negotiate a way out of the debacle he created.”

“Fuel shortages and supply disruptions are crippling countries in Asia, with Thailand facing panic buying and rationing at some petrol stations. Vietnam and South Korea are scrambling to secure alternative crude and fuel supplies. Japan, which relies on the Persian Gulf for roughly 95 percent of its crude oil imports, has had to dip twice into its strategic reserves since the war started in February.”

“The rise in price of liquefied petroleum means cooking fuel prices have increased by about seven percent for domestic use in India, but have skyrocketed by around 76 percent in the commercial sector. This has resulted in production cuts and job losses in the garment and textile sector in India, as well as in Bangladesh and Cambodia.”

“Before leaving for China, Trump claimed: “We have Iran very much under control… We’re either going to make a deal or they’re going to be decimated. One way or the other, we win.” The rants are pathetic and unhinged. But they are also ominous.”

“The management of the conflict is far beyond the capabilities of the buffoons within the Trump administration. They prefer global misery and carnage to defeat. By the time they face the inevitable, they will have left mounds of corpses in their wake. The tragedy is not that the empire is dying. The tragedy is that the empire is bringing so many innocents down with it.”

The Self-Indulgent, Dead-End Politics of AOC’s Partisan Liberalism by Glenn Greenwald (Substack)

“[…] in stark contrast to the aforementioned animal activists, who maintain a genuine devotion to achieving their stated goals and thus creating a positive impact, AOC Liberals are extremely picky, selective, and deeply judgmental of those with whom they would be willing to work to create majoritarian, issue-by-issue coalitions that would succeed. Their own political branding and sense of moral superiority are infinitely more important than stopping policies that they insist so deeply offend their elevated sense of right and wrong.”

“[…] she would never deign to work with someone like Greene because, under AOC’s verdict, she’s “a bigot and an antisemite.””

Her answer could have been better, saying that it is difficult to trust that someone like that wouldn’t try to subvert the process, leading to a net loss of effort, to wasting energy on vigilance. That’s a concern, but you still need their vote. As long as the thing you end up getting has the shape of the thing you’d carefully considered wanting, then you should at least consider it, rather than burn bridges (especially if you’re blatantly doing so to build your brand).

“Behold the noble principles that define AOC and her supporters: they would rather let Americans be forced to pay for Israel’s military and wars, and let Palestinians be bombed, and have Iran destroyed, if the alternative is to talk to or build majorities with gauche and morally inferior “bigots.” What matters — truly matters — is getting to prance around at events filled solely with like-minded, already converted people and be cheered for your elevated tastes and feel good about how untarnished you are, all while calling everyone a racist and a misogynist and a bigot and an antisemite so you signal to the world that you are not any of those things. That, for them, is the real goal of politics.”

“The left-wing flank of the Democratic Party has spent almost three years now insisting that the worst moral crime is the U.S.-funded Israeli genocide in Gaza. Yet, when a Republican who wants to cut off all funding to Israel is seated next to a Democrat who wants to force Americans to pay for Israeli weapons (like AOC), these liberal frauds somehow side with the one who wants to fund Israel. (That AOC finally changed her mind just last month and now fully embraces MTG’s position only serves to further highlight the absurdity of all this.)”

“AOC made a point of announcing that she would never work with MTG on issues relating to Israel and war, despite the fact (or, more so, because of it) that MTG has displayed more courage and principle on that issue than AOC ever would. AOC lied to protect her party’s leaders as they financed Israel’s war, whereas MTG loudly denounced her party’s leaders as they continue to do so, being forced out of Congress as a result (the same risk taken by Rep. Thomas Massie (R-KY)).”

It’s a little unclear why she left Congress, to be honest. You can be a staunch opponent of Israel’s murder machine and still be a grifter who retires a week after the lifelong government pension for former Congresspeople kicks in.

“Sure, working with them might increase both the number and type of people willing to work for the causes to which they claim to be so devoted. But it would also dilute their specialness, their brand of virtuousness and personal superiority, their addiction to denouncing everyone as racist and bigoted, so that they can feel that they are not those things.”

Kind of a broadside against certain people at the WSWS, as well.

Why the US is at War with Iran and Why the War Might Pause but Won’t End by Brian Berletic (Land Destroyer)

“A similar war of aggression by the US against Russia through Ukraine is also quickly expanding into a war directly against Russian energy production, storage, and export infrastructure through the use of drones that − while attributed to Ukraine − the New York Times has revealed is actually overseen by the US Central Intelligence Agency (CIA) and the US military.”

“From the late-February start of hostilities to the recent ceasefire agreement, energy exports from the entire region to China dropped from approximately 52% of China’s total imported needs to around 30%, according to Reuters.”

“Just as the US had previously done to Europe through its instigation of war with Russia in Ukraine, the destruction of the Nord Stream pipelines, and the implementation of sanctions on all other energy imports from Russia − and now including the striking of Russian energy production, storage, export facilities and actual tankers carrying Russian energy exports − all of this forcing Europe into energy dependence on US exports − the US is now pursuing a similar policy targeting China and the rest of Asia by deliberately disrupting access to Middle East energy exports.”

“By the early 2030s, the US is expected to double its LNG export capacity, making it capable of meeting the demands of key Asian proxies including South Korea and Japan as well as the island province of Taiwan − but again − only if cheaper and more reliable alternatives remain off the market.”

“[…] a recent US Senate hearing has made it clear nations like Japan, South Korea, and the Philippines will be shaped into military industrial outposts of US power in the region, helping minimize the “tyranny of distance” the US is faced with when provoking war with China on the other side of the planet from where the US is actually located.”

“The purpose of maintaining a global network of proxies from Europe to the Middle East to the Asia-Pacific is specifically to have other nations pay all the costs for US foreign policy, allowing the US to assume any and all benefits solely for itself.”

“[…] the prospects of accessing affordable and reliable energy from the Middle East for China and the rest of Asia are steadily fading.”

Gaza then and now

This picture appeared in several of my feeds this week (“went viral” I guess) but it is manipulated. The upper photo was color-enhanced and the lower photo was generated. There is no need to do this, though, as the reality is just as harrowing. Using AI-generated “photos” undermines the intent because it encourages those of bad faith to deny the actual reality that they depict.

The article Fact Check: FAKE ‘After Image’ Does NOT Match Actual Destruction For “Gaza in 2023 and 2026” Comparison by Sarah Thompson (Lead Stories) seems quite credible—the purpose of the site seems to be to non-ideologically check the veracity of evidence in claims in diverse media—and provides additional images, shown below.

The upper image is accurate. The following screen capture from a video at the time portrays the same subject.

Aman Palestin video on YouTube

The next image depicts the same neighborhood but vertically, from above.

Airbus imagery on Google Earth

As you can see, it’s gone. It’s all gone. Only dust and rubble remains. The generated image above is not real but it depicts reality. It’s more like a painting than a photograph.

If the top-down view isn’t as impactful, then the following capture from a video shows the view from the ground.

Sheikh Ajlin neighbourhood in western Gaza City in the northern

The following interview describes the bleak situation in Gaza and is well worth your time.

The History of National Resistance in Palestine (w/ Ramzy Baroud) by The Chris Hedges Report (YouTube)

Gaza has been under siege for decades. Even in the pictures above, where things were “going well,” Gazans were nearly completely dependent on food and supplies allowed in by their Israeli occupiers. Their harbor has been blocked for decades. Their water supplies have been pathetically small for decades—even before October 3, 97% of the water in Gaza was not safe to drink. Now, everything has been flattened. There are no buildings, not shelter other than ragged tents.

Palestinians live atop the rubble, scraping together a meager existence. They refuse to leave because they refuse to submit to occupation and genocide. They are not stupid; they have shared a sense of justice that cannot be extinguished by killing individuals.

What you can do is to erase them from people’s minds. Delegitimize their claim to humanity. Declaim them and anyone who recognizes their humanity as antisemites, as inhuman monsters who deserve their own genocide, who bring genocide on themselves with their intransigent dedication to mindless violence.

I visited the Swiss national museum this weekend to see two new exhibits: one on Swiss press photos and one on war. In the first exhibit, there were two photos with the word Palestine in them.

The captions for a photo of pro-Palestine protestors being sprayed with high-pressure hoses

The caption reads, in English,

“On October 11, an unauthorized demonstration against the Gaza war in Bern with around 8,000 participants escalates. Street clashes with police erupt, shop windows are smashed, and a restaurant catches fire. There are injuries on both sides, and the material damages run into the millions. The pro-Palestinian unrest is also fertile ground for antisemitic sentiments.”

This is the only thing that the western media cares about. This is the only thing that western societies officially care about. This is how the decades-long occupation and now nearly three-year-long genocidal intensification of that occupation is depicted. The protestors “escalate”, “smash”, and “clash”. They engender “injuries” and “damages”. They are “antisemitic.”

Were there any press photos depicting the destruction that these people were protesting? Of course not. Even in the “war” exhibit, Palestine was mentioned only twice: I heard a snippet that had been included in a loop of news segments in a giant video display. It played for about ten seconds in a five-minute loop.

There was also a lone entry for “Palestine” in the wall of wars, which as at least honestly marked with “1948 –”. It was called the “Middle East conflict” and described as “War-related violence.”[3]

'War-related violence' in Palestine

There was another press photo of the GHF (Gaza Humanitarian Foundation), which is not in any way humanitarian, which is run by Israel and the U.S., and whose members were slaughtering Palestinians at utterly inadequate food-drops a year ago.

A Swiss press photo whose caption lends credence t…dea that the Gaza Humanitarian Foundation was real

It was captioned,

“On October 10, a ceasefire between Israel and Hamas comes into effect in the Gaza Strip. A team of journalists is granted exclusive access to one of the food distribution centers run by the Gaza Humanitarian Foundation. The private foundation is controversial because it operates with little transparency, its aid supplies fall far short of meeting the need, and people have been shot at in the vicinity of the centers.”

Note the use of the passive voice in “people have been shot” when what they meant was “the U.S. and Israeli mercenaries employed by GHF to distribute food shot hundreds of starving people who’d approached to get the food supplies that they were ostensibly distributing.”

Note that the caption says that the GHF “operates with little transparency,” when the organizers of the exhibit know very well that it is very transparently run by the U.S. and Israel but what they meant to write was “the GHF is a sham but we all pretend that it is not because it serves our purposes.”

Note that it writes that “its aid supplies fall far short of meeting the need” as if that were not the entire point of it: they are starving people and the GHF is a fig leaf on that deliberate starvation, behind which the entire western media cheerfully hides itself as that would provide them actual moral cover.

It does not. It only provides them moral cover in the eyes of their unprincipled, unethical, and immoral peers, or in the eyes of the populations of their countries, well-trained by the propaganda spewed by the mainstream media, which, with one voice, wholly approves of the Palestinian genocide and considers even a slight word against it to be antisemitism.

And hence the mealy-mouthed formulations in the captions.

This is how you get the job done.

All Riot On The Northern Front by Indrajit Samarajiva (Indica)

“Elmer says Hezbollah immediately jumped to fiber-optic drones (which evolved out of radar-jamming in Ukraine slowly). These things, as you can see, have a big ‘fishing-line’ spool of fiber-optic line that literally flies the drone by wire. Hezbollah has then strapped their standard anti-tank shell (what looks like a 93mm PG-7VL) which is comically large ordnance for a drone, I dunno how these things even fly, but they do.”

“Since the Rocket-Propelled Grenade (RPG) shells Hezb uses are not, in fact, rocket-propelled, all ‘Israeli’ defensive mechanisms are like what the hell? For example, you can sometimes see the defensive Trophy system on Merkava tanks turn around, but it doesn’t fire. If it fired at FPV drones it would also be firing at every flipping bird, which would be absurd. FPV Drones are too slow-moving for the air defenses ‘Israel’ has evolved. It’s like the ‘slow blade’ in Dune, where the advent of personal shields took them back to sword-fighting because anything fast-moving would be stopped.

“The only way to reliably intercept FPV drones is with dumb fishing wire net, which limits your freedom of movement and still has an entrance somewhere, or with smart, situation-aware soldiers using shotguns, which does not describe IOF home invaders and panty raiders. IOF soldiers still park their tanks with the hatches open, still do not cover their tanks with infantry, and hang out on the hood. And now I have seen them blown up in all three circumstances. They have learned nothing from Gaza, let alone from Ukraine.”

“[…] the materiel you see getting blown can get replaced—the ‘Israeli’ conscript colony has received more than 115,600 tons of military equipment in 403 airlifts and 10 sealifts since this Iran War alone—but the conscripts and contractors operating it can break permanently. Many of them have already been deployed for years and in addition to Hezbollah fighters—described as ghosts—they now have drone fears. ‘Israel’s’ will to fight has been broken in Lebanon before, and inshallah will be again.”

Anybody who has to cheat to win is a sucker by Gary Chambers Jr. (YouTube)

“When black men with courage, conviction, and righteousness show up, it triggers something in you. And you feel a way about it. So you try to limit us. You try to steal from us and you think that we don’t understand it. Every one of the black men we put up before you stand head and shoulders above every one of you on this committee and you know it. And it does something in you that makes you feel inferior. So then you come with these white-supremacist tactics because you have the numbers, but you don’t have the courage.

“Because if you were really visionary leaders, you’d run against these black men with fair maps and you get your asses whooped. Louisiana is 33% black. 33% black. We deserve, we have earned, we are due to congressional seats. Now, if you take them from us, just know there will be a day in this state when we organize and mobilize to take something from you. It’s coming.

“And when you lose your House seat because you decided to be Jeff’s boy, come on. When you lose your Senate seat because you decided to be Trump’s minion, remember today. Remember the people that came from your state that you looked in their faces, that you act like what they said didn’t matter to you, because something somebody said thousands of miles away—who don’t really care about any of you on this committee. Be honest, nobody in that conservative party in DC cares about any of you on this city committee other than the fact that you have the ability to take something away from black people. And if you were anything like what America should be, you would find some courage.”

Trump appears poised to restart the Iran war by Trita Parsi (Responsible Statecraft)

“Iranian officials increasingly describe the next war as an opportunity to inflict maximum strategic damage on the United Arab Emirates, citing Abu Dhabi’s active role in the previous conflict, its deepening and increasingly overt partnership with Israel, and its role in urging Trump to resume hostilities.

“Tehran is likely to target American data centers in the UAE, a move that serves multiple purposes. Iranian officials argue that these American technology firms have already become participants in the conflict through their support for the Pentagon. At the same time, Tehran sees an opportunity to cripple the UAE’s ambitions to become a global artificial intelligence hub — and, in doing so, potentially undermine Washington’s AI competition with China.

“This points to a second defining feature of Iran’s strategy in a future war. Tehran believes Trump and his family hold financial stakes in many of these same technology ventures. Targeting Trump’s personal business interests is a lever Iran conspicuously avoided pulling during the first conflict but now appears increasingly willing to use. The logic is straightforward: Trump may tolerate damage to American strategic interests, but he is acutely sensitive to threats against his own financial empire. Raise the personal cost to Trump himself, the reasoning goes, and he may prove more willing to adopt a realistic negotiating position.

“Third, Tehran is likely to show far less restraint if evidence emerges that other Gulf Cooperation Council states permit the United States or Israel to use their territory or airspace in a renewed conflict. The result would be broader and far more perilous horizontal escalation, with potentially catastrophic consequences for the global economy should critical energy infrastructure come under attack.

“Fourth, the Red Sea is now in play. That would dramatically widen the geographic scope of the conflict while placing even greater upward pressure on already volatile oil prices.”

The Bust-Out Of ‘America’ by Indrajit Samarajiva (Indica)

“If you analyze ‘America’ politically, you’re making an error, unwittingly. ‘America’ is not a polity, people’s opinions have nothing to do with policy, it’s a business, pathologically. The war business is booming when bombs are flying and the healthcare business is making a killing when people are dying and the media business is talking money when they’re lying.

“Understanding ‘America’ through its politics is like trying to understand Coca-Cola through its advertising. Coke isn’t trying to make ‘moments’ or ‘memories’ or ‘open happiness’ or anything so humane, they’re a corporation, do I need to explain? In the same way, ‘America’ isn’t trying to deliver ‘human rights’ or ‘democracy’ or ‘freedom’, are you insane? They’re all just lying in order to sell you something. Like Michael Corleone said, it’s not political, it’s strictly business.”

“If you understand colonialism as a business you can understand that it never ended, it just rebranded. The banner of White Empire went from Lisbon to Amsterdam to London to Washington, changing marketing terms from monarchy to democracy, but never changing the underlying business model. Why change when you’re making bank?”

“[…] the White mafia has ‘busted-out’ entire continents. They corrupt local compradors, debt trap entire nations, strip the resources, and then ‘light a match.’ They have done this to every country on Earth and now there’s nothing left to bust-out, so they’re cannibalizing the imperial periphery (Europe, the UAE) before descending on their own corpse.

“This is how you understand what’s happening today, with war everywhere, prices rising even in the imperial core, and yet the stock markets going gangbusters. Of course, stock markets are just the place where genteel gangs do their dirt in public. The seeming illogic of modern politics is simply an age-old mafia bust-out.”

“In genteel gangland, however, this isn’t called a bust-out. It’s called a leveraged buyout (LBO). It’s the same thing with more lawyers. In an LBO, private equity guys (White word for oligarchs) borrow against a company (which they don’t own yet) to buy the company. If this sounds like a con, it’s because it is, but it’s legal because the bank’s in on it. ‘America’ has legalized corruption.”

“When ‘Republicans’ said (in the 1980s) that they wanted to run government like a business, this is the business model. They have been busting out the world and their own country since then, stripping assets, bilking labor, and goosing the stock market to get paid now. Now, especially since Citizens United gave corporations ‘speech’ rights, they have completed a leveraged buyout of the US government, making the two-party system as redundant as Coke and Pepsi. And making analyzing their political positions as relevant as comparing marketing.”

“This seems cruel if you take it personally and insane if you take it politically, but remember. It’s nothing personal. It’s strictly business.”

“It’s really not that complicated if you stop believing the marketing and follow the money. If you ignore the politics and look at what colonialism always was. A business, built on bones.”

“We are now at the stage in Goodfellas where they light a match to the restaurant and drive away. We are witnessing a last orgy of insider trading and profiting on controlled volatility while the strategic reserve of oil is emptied and even the home economy is hollowed out [from] within. The peripheries of Empire are getting busted-out first but make no mistake, the whole thing is going bust. This is, inshallah, the end of it all. There’s no more out to bust, and no more leverage to be bought.

“People may be like ‘this is bad for America!’ or ‘this is bad for Americans’ but this misses the point entirely. What do y’all have to do anything? You’re like the customers or workers of a company being bust-out by the Mafia, irrelevant.”

In the Wake of Iran War, African Nations Struggle to Cope with Rising Fuel Costs (Drop Site News)

“Some countries are implementing emergency measures: Madagascar declared a national state of energy emergency across the entire country on April 7 to address the country’s supply crisis. Despite being an oil producer, on March 25 South Sudan implemented power rationing in the capital, because it lacks refining capacity. A few days later Egypt ordered restaurants, cafes, and stores closed by 9 p.m. to cut electricity use.”

“Rising prices have doubled aid transport costs in Somalia and delayed shipments of nutrition supplies and medicines. Before the war petrol was at $0.65 per liter but by the end of March had more than doubled to $1.50. “The rise in price of fuel has led to the price of food to also rise tremendously. The fishing fleets in Mogadishu are docked, unable to afford the diesel, causing a secondary protein crisis.” said Mogadishu councilor Abubaker Ali.”

Iran demands Big Tech pay fees for undersea Internet cables in Strait of Hormuz by Jeremy Hsu (Ars Technica)

“[…] the greatest threat to subsea cable infrastructure in the Strait of Hormuz may simply come from delays in any necessary cable repairs in the region. Such jobs require specialized ships to find the damaged area and lower grappling hooks to lift up the cable for inspection and repair, according to BBC News. That repair process can require days or sometimes weeks, which would leave the ship vulnerable to Iranian missiles, drones, or fast boats that have continued to attack commercial shipping in and around the strait.

““Operators face a choice: pay protection fees and accept Iranian licensing over Middle East Gulf seabed activity, or accept that future faults may go unrepaired indefinitely,” said Windward, a maritime intelligence company, in a blog post. “A single transoceanic cable system costs between $300 million and $1 billion to deploy. The expected value of an Iranian protection fee, from Tehran’s perspective, is structured to sit well below that.””

Roaming Charges: Peanuts From Heaven by Jeffrey St. Clair (CounterPunch)

“Graham Platner, who actually fought in two post-911 wars, has a somewhat different take on Trump’s Iran War:”

“I want to shame the hell out of these people. I fought in these stupid wars. I spent the bulk of my 20s and early 30s in the infantry, fighting in Iraq and Afghanistan. And I’m not JD Vance. I didn’t go sit in an air-conditioned and fucking typing copy all day. I was a machine-gunner in the Marine Corps. I was a long-range surveillance team leader and squad leader in the United States Army. I’ve seen it. I’ve touched it. I know what it looks like when American high explosives interact with fucking children. And it’s the most awful thing you’ll ever see. I want to be in the Senate to make sure that when even people in my party think that sending America’s sons and daughters off to fight for stupid reasons, when they think that’s a good idea, I want to be able to go up to them and tell them that they are fucking assholes. By the time this thing goes to air, it is quite possible that we are going to start to realize that war isn’t a fucking game and that the United States military has gotten itself embroiled in a conflict that it’s not in control of, that might be escalating in ways that we can’t really comprehend. I am terrified. And it’s not the people who started this war who will be the one’s that pay the price.”

I can’t disagree with any of this.

“Thomas Massie, during his concession speech to the Trump-approved, AIPAC-sponsored former Navy SEAL Ed Gallrein: “I would have come out sooner, but I had to call my opponent to concede and it took a while to find him in Tel Aviv.””

Can’t disagree with that either.

“Mayor Zohran Mamdani:”

“Ronald Reagan famously said, “The 9 most terrifying words in the English language are ‘I’m from the government, and I’m here to help.‘” I disagree. Nine more terrifying words are actually, “I worked all day, and can’t feed my family.””

Still agreeing over here.

“According to an investigation by Yahoo Finance, Donald Trump made 3,642 securities trades during the first quarter of 2026, averaging nearly 58 transactions for every U.S. trading day or about nine trades every hour in the day or around one trade every seven minutes while the markets were open. Trump made 94 different trades of “Magnificent Seven” stocks (64 buy orders and 30 stock sales) in the first quarter, valued at between $50 million and $70 million.

“[…]

“Aaron Fritschner: “Trump traded up to ~$700 million in stock in Q1 of 2026. The 535 Members of Congress made ~$635 million in trades in 2025. Trump bought and sold more stock in 3 months than all of Congress put together did in a year.””

Nothing to see here. He’s the people’s president. He gets the working class. That’s why they love him.

Economy & Finance

Who Is “Out of Touch?” by Hamilton Nolan (How Things Work)

• Have you taken a flight recently? The majority of Americans did not take one flight in the past year.
• Did you read more than two books last year? You’re in the minority.
• Have a college degree? Also a minority.
• Do you eat out? The most common place that Americans eat out is McDonald’s, and the most popular sit-down restaurant brand is Olive Garden. Is that where you go? Or do you go somewhere fancy, like, you know, TGI Friday’s? What—fancier than that? Wow.
• Are you a white male? Seven in ten Americans are not.

“Etcetera. I can barely imagine what qualities Marc Andreesen believes that he has that qualify him for being In Touch, but I guarantee that they are all very stupid.”

“I submit to you that the one characteristic that unites the lives of all Normal People is this: They are at the mercy of forces greater than themselves. They have to work for money in order to pay bills in order to survive. They are at all times subject to the cruel depredations of fate. Even if they have savings, the stability of their lives could be snatched away by a single disaster. If they rest for too long, they will lose their ability to support themselves and their families. They are all, to varying degrees, in the position of having to do things that they would not choose to do, because those things are necessary in order to earn money and live and navigate their position in society.”

“If you do not have to work to live then, yes, you are out of touch with the organizing principle of the average person’s life. You may feel sympathy for them, or spiritual and political affinity, but your life is of a fundamentally different type than theirs. Congratulations! You’re out of touch. Enjoy it. If you don’t like it, give all of your money away. Otherwise, shut the fuck up.”

Making sense of Trump’s unscheduled sudden midair disassembly of the American empire by Cory Doctorow (Pluralistic)

“Financial economies “suck the air out of the rest of the economy and make it less competitive.” Keeping billionaires in megayachts comes at the expense of “research, education, infrastructure, and healthcare.” Countries that financialize lag behind countries where the economy is based on making things, not extracting or financing things.

“Generations of both imperial looting and domestic investment made America the richest country on earth. That wealth cushioned America’s transition to oligarchy: for a while, the country could both “finance and billionaire parasites sucking its blood” and continue to invest in itself. But while you can double the wealth of a billionaire at the expense of a town or two, doubling the wealth of a centibillionaire requires the destruction of whole regions.

“As America looted itself into irrelevance, China – a very different kind of autocracy – invested in domestic capacity and domestic consumption.”

There follows of standard equivocation on China that seems to be required whenever a westerner talks about China.

“China’s hardly a well-run place: like any autocracy, it functions according to the whims of extremely fallible officials, which produces real-estate bubbles and other crises of production (to say nothing of the demographic crisis of the One Child policy) and necessitates steadily increasing oppression, from online surveillance to concentration camps in Xinjiang.”

Yeesh. Look, some of that might be kind of halfway accurate but it feels more like we’re increasingly incapable of acknowledging what China is today.

Like, how is “having real-estate bubbles” a distinguishing factor to note? Do you know how China got rid of its real-estate bubble? It’s still working on it, but it declared officially that “housing is not an asset” and started dismantling the speculative infrastructure that had benefitted oligarchs over people seeking housing. I have no idea whether that’s going to work, or how long it’s going to take, but it certainly seems preferable to letting the bubble burst and letting the oligarchs keep all of their money, as the west did.

What does Doctorow even mean when he calls the “One Child policy” a demographic crisis. The policy left deep scars on China’s psyche, sure, but demographically it was a success, no? How do you feed a nation that has an ever-increasing number of people when no-one will help you get to the point that you can feed them because you’re communist and refuse to submit to capitalism?

And from someone who complains about online surveillance all the time, it’s odd that he would mention China’s doing it in a way that allows readers to think that that country has a version uniquely worse than the western flavor.

And, finally, of course, we must unquestioningly mention the “concentration camps in Xinjiang” as night follows day, almost as rote as a land acknowledgement before a valedictory address at a liberal-arts university.

“[…] bad news for a software industry that “shifted its entire value proposition from ‘we make tools that help you make or save money’ to using political clout and the dollar hegemony to capture, control, and loot entire sectors of the various economies of the world. That strategy only works when you’re in charge.””

Trump’s Failed China Trip Shows His Trade War Backfired, And US Corporations Are Desperate by Ben Norton (Scheer Post)

“Reuters concluded, “U.S. President Donald Trump left China on [15 May] with no major breakthroughs on trade or tangible help from Beijing to end the Iran war”.

“It was easy to predict this outcome. The US government has spent nearly a decade now waging a trade and tech war, aiming to prevent China from developing, seeking to isolate the country.

“Why Trump thought he could suddenly play nice, and get China to make concessions to benefit the US at its expense, is a mystery.

“Moreover, the US started a war of aggression against Iran, which has disrupted the global economy and caused the largest oil crisis in history, but Trump now expects China to bail him out. It is clearly absurd.

“In other words, after years of punching China in the face, Trump hopes Beijing will help to save the US economy. It is obvious why China was not interested.”

The Bust-Out Of ‘America’ by Indrajit Samarajiva (Indica)

“If you analyze ‘America’ politically, you’re making an error, unwittingly. ‘America’ is not a polity, people’s opinions have nothing to do with policy, it’s a business, pathologically. The war business is booming when bombs are flying and the healthcare business is making a killing when people are dying and the media business is talking money when they’re lying.

“Understanding ‘America’ through its politics is like trying to understand Coca-Cola through its advertising. Coke isn’t trying to make ‘moments’ or ‘memories’ or ‘open happiness’ or anything so humane, they’re a corporation, do I need to explain? In the same way, ‘America’ isn’t trying to deliver ‘human rights’ or ‘democracy’ or ‘freedom’, are you insane? They’re all just lying in order to sell you something. Like Michael Corleone said, it’s not political, it’s strictly business.”

“If you understand colonialism as a business you can understand that it never ended, it just rebranded. The banner of White Empire went from Lisbon to Amsterdam to London to Washington, changing marketing terms from monarchy to democracy, but never changing the underlying business model. Why change when you’re making bank?”

“[…] the White mafia has ‘busted-out’ entire continents. They corrupt local compradors, debt trap entire nations, strip the resources, and then ‘light a match.’ They have done this to every country on Earth and now there’s nothing left to bust-out, so they’re cannibalizing the imperial periphery (Europe, the UAE) before descending on their own corpse.

“This is how you understand what’s happening today, with war everywhere, prices rising even in the imperial core, and yet the stock markets going gangbusters. Of course, stock markets are just the place where genteel gangs do their dirt in public. The seeming illogic of modern politics is simply an age-old mafia bust-out.”

“In genteel gangland, however, this isn’t called a bust-out. It’s called a leveraged buyout (LBO). It’s the same thing with more lawyers. In an LBO, private equity guys (White word for oligarchs) borrow against a company (which they don’t own yet) to buy the company. If this sounds like a con, it’s because it is, but it’s legal because the bank’s in on it. ‘America’ has legalized corruption.”

“When ‘Republicans’ said (in the 1980s) that they wanted to run government like a business, this is the business model. They have been busting out the world and their own country since then, stripping assets, bilking labor, and goosing the stock market to get paid now. Now, especially since Citizens United gave corporations ‘speech’ rights, they have completed a leveraged buyout of the US government, making the two-party system as redundant as Coke and Pepsi. And making analyzing their political positions as relevant as comparing marketing.”

“This seems cruel if you take it personally and insane if you take it politically, but remember. It’s nothing personal. It’s strictly business.”

“It’s really not that complicated if you stop believing the marketing and follow the money. If you ignore the politics and look at what colonialism always was. A business, built on bones.”

“We are now at the stage in Goodfellas where they light a match to the restaurant and drive away. We are witnessing a last orgy of insider trading and profiting on controlled volatility while the strategic reserve of oil is emptied and even the home economy is hollowed out [from] within. The peripheries of Empire are getting busted-out first but make no mistake, the whole thing is going bust. This is, inshallah, the end of it all. There’s no more out to bust, and no more leverage to be bought.

“People may be like ‘this is bad for America!’ or ‘this is bad for Americans’ but this misses the point entirely. What do y’all have to do anything? You’re like the customers or workers of a company being bust-out by the Mafia, irrelevant.”

S13 E12: Trump’s Ballroom & Structured Settlements: 5/17/26 by Last Week Tonight with John Oliver (YouTube)

The U.S.A. is a criminal enterprise where the worst people flourish by fraud.

Anthropic’s “Profitability” Swindle by Ed Zitron (Where's Your Ed At?)

“Let me speak directly and with more empathy than usual: if you want Anthropic to win, you should be just as skeptical of these numbers as I am. You should want to smash my face in the tarmac with the most crystal-clear, impossible-to-argue with numbers, bereft of asterisks or discounts from suppliers or obfuscated accounting metrics.

“You should want better from your heroes. If you truly think this company is amazing, unstoppable, and leading the tech industry to a glorious era of innovation, there shouldn’t be this many questions, and the metrics shouldn’t be this murky.

“Every other time when a company has played this level of silly, weird bullshit has led to disaster — for example, WeWork claimed to be profitable since the second month of its operations, and repeated claims of profitability throughout its existence, and it turned out that it was only “profitable” if you removed things like “some of the costs of doing business.”

“I get why you’re so defensive, and I get why you want this to work. A lot of you are very excited about generative AI, and being excited about it has given you a tremendous community of equally-excited people. I get that you like these tools.

“And I need you to know these companies are laughing at you.

“Anthropic timed this leak to focus on a specific quarter where it artificially suppressed costs, and gave you the flimsiest proof imaginable, specifically-crafted for you to share it as a triumph and spread the idea that “AI labs are actually profitable,” when their core economics haven’t changed. Costs increase linearly with revenue, and will continue to do so in perpetuity.

“I genuinely can’t wait for both OpenAI and Anthropic to file their S-1s.”

Environment & Climate Change

Why Walking to the World Cup Final Is Illegal by Evan Edinger (YouTube)

“Across the entire Super Fund program, legal fees and cleanup fees are roughly equal. Meaning that for every dollar that’s actually spent cleaning up the polluted waterway, another dollar is spent between lawyers arguing about who should have to pay for it. And if you want to better understand how America operates as a country, I do not think you can find a better example. Why put any time and money into improving everyone’s quality of life when you can just spend 50 years arguing about who should pay for it instead?

“But now New Jersey’s in a bit of a pickle. How’s New Jersey supposed to support the huge surge of people coming for the World Cup if it hasn’t actually done anything to support the huge surge of people coming for the World Cup? Not just in terms of basic safety, but oh my god, financially. It’s going to cost the state a lot of money to run all those extra train and bus services they had 8 years to prepare for. They can’t just make public transport in the city free for the World Cup guests like London did. That would cost too much money. It’s not like this is the most densely populated region of the richest country in the world.

“And a ticket from Penn Station in New York City to MetLife Stadium only costs $12.90 on a normal day. But what if to solve the problem that they themselves created, they simply increase the price of public transport to the World Cup? Nothing crazy, just a casual 12 times increase to $150 for a train ticket and $80 for a bus.

“But don’t worry, according to New Jersey Transit President and CEO Chris Kori, he says this isn’t price gouging. We’re literally trying to recoup costs.

“Okay, so they’re just trying to recoup cost. They can’t build anything that would cost money. They can’t clean the most contaminated waterway in the country. How would they recoup their costs? The plan’s simple. Don’t do anything and then point fingers at others for why nothing was done. I think you’ll find it’s quite genius really.”

“But when you raise a society on the double think that they have the freedom to criticize the government while simultaneously training them that any criticism is unpatriotic, you don’t get democracy. You get a cult unable to perceive its own cognitive dissonance.”

“A society grows great when old men plant trees whose shade they will never sit in. But planting trees is expensive. So, I guess it makes more sense to chop your trees down and charge $150 for your guests to stand in the sun. But don’t worry, you can also charge them for sunscreen.

“I stand corrected. Since filming this, it no longer costs $150 to stand in the sun. New Jersey Transit has reduced the cost of a ticket to $105 now, thanks to sponsors and other sources. Thank God to our corporate overlords for the tiny morsels that we receive.”

Colorado River Basin Users are Cooked by nostoneunturned0479 (Reddit)

“At deadpool for Mead, it means no further water delivery for California, Arizona and Mexico. It means the loss of Hydroelectric power from Lake Mead, Lake Mohave, Lake Havasu, the loss of water to cool the Nuclear Reactors at Palo Verde Nuclear Power Plant near Phoenix. Technically speaking, Palo Verde uses treated wastewater from Phoenix area to cool the reactors, but with water not being assured, Phoenix area customers will have to cut consumption, which will result in less waste water to use.

“Can you imagine the repercussions of the loss of 2,080 megawatts from Hoover Dam, 240 megawatts from Davis Dam (Lake Mohave), 120 megawatts from Parker Dam (Lake Havasu), 4,000 to 4,200 megawatts from Palo Verde Nuclear Power Plant? A cumulative loss of approximately 6500 megawatts, means about 6.5 million households will go without power, in the hottest desert areas of the US, where temperatures regularly are in excess of 100 degrees for 60-90 days of the year.

“A few years ago I came on this sub begging for awareness and action, and had several people question the direness of the situation. The day has finally come.”

Roaming Charges: Peanuts From Heaven by Jeffrey St. Clair (CounterPunch)

“March was a previously unfathomable 9.35 degrees Fahrenheit hotter than the 20th-century average for the month. The last 12 months in the U.S. were the hottest ever recorded. And Super El Niño is still coming…”

“Stormwatch’s Colin McCarthy: “Insane stat of the day: California almonds use roughly 3–5.5 million acre-feet of water per year, depending on methodology. That’s ~4-7x more water than all data centers in North America used combined in 2025.””

“The water level in at least 13 of India’s largest reservoirs has fallen below 50% of capacity. River flows are below normal and are expected to fall further with the developing super El Niño, placing the entire subcontinent’s drinking water, irrigation and hydropower systems at extreme risk.”

Medicine & Disease

What science knows about Andes hantavirus and why governments ignore it by Benjamin Mateus (WSWS)

“The disease then abruptly shifts into the cardiopulmonary phase, characterized by a rapid onset of coughing, severe shortness of breath and profound hypoxia. The pathophysiology behind this collapse is rooted in the viral infection of the endothelial cells lining the blood vessels. This cellular invasion triggers a massive immune system overreaction heavily mediated by infiltrating T lymphocytes. The resulting immunologic assault causes a catastrophic increase in pulmonary capillary permeability. As plasma rapidly leaks from the microvasculature, the alveoli flood with high-protein fluid, leading to massive noncardiogenic pulmonary edema and acute respiratory distress syndrome. Hemodynamically, the patient experiences a severe drop in blood pressure driven initially by distributive fluid loss into the lungs, which is quickly complicated by profound myocardial depression, ultimately culminating in fatal cardiogenic shock.”

“Currently, there are no approved vaccines and no specific antiviral medications available to treat the infection. Treatment remains entirely supportive, relying heavily on lung-protective mechanical ventilation, vasopressors to maintain blood pressure, and extracorporeal membrane oxygenation in cases of refractory shock. Consequently, the case fatality rate for the Andes virus is extraordinarily high, hovering around 38 to 40 percent in published series, with some severe outbreaks recording mortality rates exceeding 50 percent.”

“The researchers concluded that person-to-person transmission of the Andes virus was a reality. The epidemiologic data indicated that close contact during the prodromal phase or early cardiopulmonary phase is likely required for the virus to successfully jump between human hosts. However, the papers also identified critical known unknowns that persist today. The exact route of transmission—whether through respiratory droplets, salivary transfer or other bodily fluids—remains unconfirmed. Furthermore, the minimum infectious dose required to transmit the pathogen and the precise role of an infected patient’s viral load in driving transmission remain dangerously undercharacterized.”

“The Andes virus efficiently sheds from the oral and respiratory surfaces of patients precisely when they appear to be suffering from only a mild illness. In densely packed social environments like a ship dining room or a crowded social gathering, prolonged close contact is not an anomaly but the default condition—transforming enclosed spaces into ideal environments for superspreading events.”

“The median incubation time is approximately 18 days after human-to-human contact, but clinical reports document a range from 7 to 39 days. This extended timeline poses a nightmare for contact tracing […]”

“It is imperative to draw a sharp boundary between established evidence and scientific speculation. There is currently no proof that the virus has mutated to become inherently more contagious. However, the absence of evidence is not evidence of absence. Because capitalist governments have deliberately defunded critical ecological surveillance programs and terminated pandemic prevention research, our understanding of the Andes virus genetic diversity currently circulating within wild rodent reservoirs is dangerously incomplete.”

Art, Literature, Music, & Cinema

“Maitreya Corso“ by Hinternet Editorial Board (The Hinternet)

“Maitreya Corso, I am therefore ready to venture, is a true heteronym, in the Pessoan sense, of Maya Hawke — Maya, namely, insofar as she has become at least dimly aware of her true bodhisattva-being, riding along on the immanent plane, for now, doing the things that other humans do, feeling the things they feel, but now confidently expressing it all in words and sounds that do not, strictly speaking, quite come from here.”

Rhythm and Reason by Justin Smith-Ruiu (The Hinternet)

The article discusses several albums in the genre of what is often unfairly called “Easy Listening” or, perhaps less disparagingly, “Smooth Jazz”. The following album cover stood out because it was pretty risqué for 1958. Actually, it was wildly risqué for 1958.

Sea of Dreams by Nelson Riddle featuring Diane Webber

The album’s Wikipedia page even notes that the lady on the album cover “may have been” the absolutely striking Diane Webber (Wikipedia), who was trained as a ballerina, then became a chorus girl and was even photographed by Russ Meyer for Playboy magazine.

In the 1960a, she apparently chafed against the frowning and iron-fisted megrims of the deeply conservative U.S. culture—thank goodness that’s all changed by now—and was involved in the nudist movement,

“In the mid to late 1960s, as a part of the counter-culture movement in the United States, Webber became involved with nudism and appeared in numerous nudist publications advocating the lifestyle, such as Naked and Together: The Wonderful Webbers (Library Thing) by June Lange (1967). In 1965, she traveled to Sioux City to give evidence at the request of a District Attorney’s Office in a court trial involving the sending of allegedly obscene nudist publications into the State of Iowa. However, when taking the witness stand, instead of proving the prosecution’s case, she gave a spirited defense of the principles of the naked lifestyle.”

Also,

“Her iconic status among Playboy models is referenced in Gay Talese’s non-fiction book Thy Neighbor’s Wife (Wikipedia) (1980). Talese had published an extensive article in the August 1975 issue of Esquire, in which Webber is considered an object of fantasy as well as an actual person. Two nude photos of her appear in the article, and one is on the cover.”

Laurie Anderson: Tiny Desk Concert by NPR Music (YouTube)

My first encounter with Laurie Anderson was on their cover of her 1984 song Excellent Birds on Peter Gabriel’s album So. I didn’t hear much else until her album Heart of a Dog in 2015, which is spoken-word and absolutely amazing. I listen to it only all at once because that’s the only way you can listen to it. Her music is amazing. Avant-garde indeed.

I saw in the comments that someone wrote that they listened all the way through, even though “this isn’t [their] genre,” and that they’re happy for the people who enjoyed it. Do yourself a favor: evolve until this is your genre. The music is beautiful, haunting, inspiring. There’s really nothing else like it.

I can’t imagine what breakfast was like at her house with late husband Lou Reed, with their voices rumbling over coffee.

Philosophy, Sociology, & Culture

In “Mutual Analysis” with Wallace Shawn’s Moth Days by George Prochnik (The Paris Review)

“Characters in Shawn’s later works often spend little or no time speaking to one another, instead directing their remarks to the onlookers. They talk in terms that suggest they are presenting not just their story, but also their case—shifting abruptly between emotional registers: one minute confessional and penitential, the next self-righteous and defiant. Shawn has talked about putting audience members in a position to adjudicate the scenes they’re watching, yet he also frequently implicates them in the unfolding moral dilemma.”

“The Fever, an expansive one-man show from the nineties, whose speaker is overcome by visions of foreign suffering entangled with American interests. This contrapuntal double bill featured Shawn himself performing the latter twice weekly.”

“The drama is effectively a conversion story, from solipsism to Marxism. The narrator discovers Das Kapital and begins to comprehend “commodity fetishism,” along with the invisible labor and bloodshed that went into his bourgeois wrapping. Like Moth Days, as Dizzia put it to me, The Fever concerns a confrontation with what it means to have chosen “to believe you are the life you live in your head, without any sense of responsibility for the life you live in the physical world.” Ultimately, the education that the narrator undergoes destroys his pleasure in the cosmopolitan comforts he had been raised to expect.”

“The Fever, Shawn told me, was an attempt to write something absolutely truthful to what he himself had undergone: a stark confrontation with the fact that his own comforts were inextricable from the suffering of others. The land he owned, as the protagonist reflects, had been allocated not “by chance, not by fate,” but had been “pieced together one by one, by thieves, by killers . . . until the beautiful Christmas morning we woke up, and our proud parents showed us the gorgeous, shining, blood-soaked fields which now were ours.””

“Initially, he performed it at parties in the apartments of friends and acquaintances, sometimes without the guests’ foreknowledge and to occasional outrage. “I don’t think I had the slightest consciousness of the arrogance and presumption involved in asking people to listen to me that way,” Shawn said. “I was just so upset, so concerned with getting people to pay attention.””

““My political opinions fly out across the world and determine the course of political events,” Shawn continues. “What I say to you about my neighbor’s child affects what you feel about the nurse who sits by the side of your friend in the hospital room, and what you say about the nurse affects what your friend’s sister thinks about the government of China.””

Perhaps in the eighties, but no longer. Such minor influences are nowadays quickly drowned in a torrent of counterfactual slop.

“He goes on to describe meeting a young woman at a dinner party who tells him that she sometimes likes to go out with gangsters. “She describes in detail the techniques they use in getting other people to do what they want—bribery, violence. I’m shocked and repelled by the stories she tells. A few months later I run into her again at another party and I hear more stories, and this time I don’t feel shocked. I’m no longer so aware of the sufferings of those whom the gangsters confront. I’m more impressed by the high style and shrewdness of the gangsters themselves.” By their third encounter, he’s become a “connoisseur of gangster techniques” and finds her stories comic. “And so every day,” Shawn writes, we confront the “numberless insidious intellectual ploys by which the principle of immorality makes a plausible case for itself.””

“Shawn acknowledges the paradox of a form of determinism that doesn’t preclude an individual’s responsibility to help cultivate a more just society. “I don’t have the brain that could possibly defend what I believe,” he told me, “which is that other people are determined by the forces working on them, but I still have free will and could make better or worse choices.” And yet there is, throughout his body of work, a strain of hopefulness, however faint, that people might be shaken from their preconditioned paths, and that art, in enacting diverse dialogues of unconsciouses, might play a role in bringing that change about. “Wally’s plays,” Eisenberg told me, “make you aware that you are part of a system, that the way you live is a choice—that at least you should be conscious of this.””

“When I was in college, my mom sent me the script of The Fever. For me, it was my introduction to socialism, to the very personal morality of how we contribute to and benefit from all those structures. I would read it aloud in my dorm. I mean, that’s really the actual story: she sent me the book, and I would read Wally’s words out loud by myself.”

“[…] the truth is that at this moment, to show any sensitivity, delicacy, gentle feeling at all is to take a radical stand against the thugs who are running our country, because their ideology is so opposed to any sort of delicate feeling. Their aesthetic is even opposed to any sort of charm at all.”

“I haven’t resolved that in my own mind. I do say to myself every day, Well, these crimes that have been committed in order for me to have this lovely fruit salad are inexcusable, but shouldn’t I at least enjoy the fruit salad? I mean, if I don’t enjoy it, I’m just going to throw it out. And that won’t erase the crimes that have been committed in order to bring it to me.”

“You could say that people who are brought up in a privileged environment are stupider than people who are brought up in a more desperate environment. There’s an idiocy built into being a privileged person, and when you’re raised in that environment as a child and as a young person, you can’t see around it or through it.”

But you still instinctively know its there, protecting your privilege. Even an ideological attack is threatening, so it doesn’t take much to encourage a defense. Those who attack are jealous.

“When the protagonist says at the end, No one is reading John Donne anymore, that’s not a joke. It’s okay if you find it funny—a lot of Wally’s work invites that specific kind of laughter. But to me, that sentiment is tragic. What Wally’s saying is that if the world were a more just place, and we didn’t insist on poverty, more people might like Beethoven. More people might like John Donne. And what a better world that would be.”

“For a long time I went through a process of thinking, If only I could tell my audience what the world is like and show them their involvement in creating that world and sustaining that world—the world in which the oppressed are crushed in order to create a pleasant environment for the privileged—if I could show my audience how that world works and how they fit into it, they would be shocked and want to change the world. There was a time when it really hadn’t occurred to me that people in my audience might not be shocked. At any rate, I thought that they might be a little bit surprised by what they saw. I didn’t realize that they would accept it. But their conclusion after seeing that they were not nice guys was to accept the fact that they were not nice.”

Because the privilege is worth it. Because the bad thing is never, ever going to happen to them. Because they have no principle and in no way feel its lack.

“Art itself, I think, has become one-dimensional, rather superficial. So work that is actually stripped of artifice and is telling the truth, talking about the way things are, has become quite radical and in a way political.”

A Whole New World by Madeleine Adams (The Baffler)

“Sampling surveys assessing guest behavior was designed to increase revenue and ensure that Disneyland visitors were efficiently and smoothly conveyed through the park, reducing bottlenecks while keeping visitors there for as long as possible. These insights into bottlenecking were gained from the think tank’s studies of mess hall lines in military operations. Studies of television ratings and programming in the 1950s that streamlined the conveyance of a viewer from one show to the next informed the park’s layout.”

“[…] incidents at Disneyland this month involving dropped iPhones and Stanley cups (the huge sippy cups upon which Gen Z nervously suck when no watermelon strawberry cream choco-banana vapes are available) have stopped the rides for hours at a time because of the sensitivity of the park’s track sensors, forcing staff to ban these items from certain rides.”

Snarky but not inaccurate. Having a Stanley Cup send the signal that you’re willing to join cults, that you’ll overspend on whatever you think will gain you acceptance by worthless people that you don’t know.

“In truth, we all live in a Disneyfied world: Our smoking is automated by vape, our gambling is automated by betting apps, and our sex is automated by Tinder. Not even our vices, in the world that Disney made, are truly ours. And our taste is automated by algorithm. Liked Snow White? You’ll love Elsa! AI will embed automation even more deeply into pleasure.”

Well, not for all of us. But it’s becoming increasingly difficult to escape the vortex.

The Rise of the Bullshittery (マリウス)

“The bullshitter is optimising for a different objective, usually appearing competent, appearing confident, or appearing to be the right kind of person to be in the room. And precisely because the bullshitter is indifferent to truth, Frankfurt argued, they are a greater threat to honest discourse than any liar.”

“The unspoken contract behind most professional life used to be as simple as learning how to do something, doing it well and gradually developing a reputation among people who could tell the difference. Over time, that reputation would then translate into work, money, and a degree of stability. It was a slow process, that sometimes was unfair, and that was never as meritocratic as its proponents claimed, but at least the basic shape of it made sense. Doing a good job was, on average, an advantage.”

“The algorithm, howeveer, does not particularly care whether you are good at your job, it only cares whether your message is engaging enough to spread fast and far.”

“The people who optimise for being correct are competing on an unfair playing field against people who optimise for being heard, and the result of this is a slow inversion of incentives.”

“The careful professional, who takes a week to think through a problem, who refuses to claim expertise they do not have, and who writes one in-depth researched post about a specific topic, gets out-competed and buried by the carnival barker who will claim any expertise that fits the trending topic, and who fires off five posts a day, each of them a slightly different rephrasing of the same content-free observation.”

“The algorithm does not know the difference between a thoughtful five-paragraph essay by somebody who has spent a decade in the field, and a five-paragraph essay generated in twenty seconds by an LLM, that’s probably sprinkled with emojis. From the algorithm’s perspective, both are content, and the one that triggers more engagement (usually the cheaper, more emotional, more bombastic one) wins.”

“[…] the marginal cost of producing convincing bullshit has collapsed. Large Language Models have done for grift what the shipping container did for global trade. They did not invent it, but they turned a manual process into an industrial one.”

“[…] anyone with a browser can generate a thousand words of confident, on-topic, syntactically clean text on any subject in under a minute. They can ship a book to Amazon, an article to a content farm, a thread to LinkedIn, and even a video to YouTube, all without ever having to know what they are talking about. The output passes the basic test of sounds about right, and that is, increasingly, the only test the distribution channels (and sadly the readers/viewers) apply.”

“This is the bullshittery in its mature form, which doesn’t consist of individual lies, or individual scams, but a steady-state ecosystem in which a large share of professional output is produced to be seen by other people producing output, and in which the connection to anything resembling a real customer, a real problem, or a real outcome has gone slack.”

“[…] a craftsperson of any kind who treats the work as the whole point of it, you are competing in a market that has been quietly tilted against you. The person next to you, who is willing to fake the demo and declare victory on LinkedIn even before the launch, is going to look more successful than you. They will get the speaking slots, they will get the promotions or, worse, the funding rounds. Heck, they might even end up on Forbes’ 30 under 30. All that you will get is the satisfaction of doing the job properly, which, don’t get me wrong, is a beautiful thing, but sadly it does not pay rent. I think a lot of the cynicism, exhaustion, and quiet bitterness that has crept into professional life over the last years is downstream of this problem. I don’t believe that people no longer want to do good work, but I think that doing good work has stopped paying the way it used to, while doing bad work loudly has started paying significantly better, so people notice and they adjust.”

“The slop-posting middle manager who cannot tell you what their team actually built last quarter is not necessarily a malicious fraud, but they may be a person whose job no longer rewards them for knowing, in a system that has trained them to perform and act instead. While this, if true, does not make the output less hollow, it certainly does change who the actual villain is.”

“[…] the people are mostly responding rationally to a system that pays for performance and ignores substance.”

“Keep doing the work, keep a principled and honest stance, keep saying I don’t know when you don’t, keep being embarrassable. Even though the market is bad at rewarding it right now, it will not continue to be forever. Hopefully.”

💪🏼

Shame them, shun them, ban them, beat them! by Adam Mastroianni (Experimental History)

“Say what you will about the Union of Soviet Socialist Republics, its 1936 constitution was a banger.

“It guaranteed freedom of speech, the press, assembly, and protest. It extended equal rights to all citizens, regardless of race or gender. It shortened the working day to seven hours, affirmed “the right to rest and leisure”, and offered free education and free health care to all, including a “wide network of health resorts for the working people.””

“[…] rules don’t matter unless people act like they matter. Writing down laws does not endow them with physical force or psychic potency. We all know this. We all believe this.

“So why don’t we act like it?”

“You want your partner to realize that your preferences are not silly affectations that can be belittled, ignored, or disputed until they go away, that they are, in fact, load-bearing parts of your personality, and to reject them is to reject you. In return, you have to realize that some of your preferences are more malleable than you thought, that maybe they don’t all have to be foundational to your sense of self, and that some of them can be bent or jettisoned in the interests of coexistence.

“This is the work of love, and it takes a lifetime. You can’t speedrun it by filling out a spreadsheet or signing a contract.”

“Or maybe we misdiagnosed the problem in the first place. We assumed that the justice system was eager to hold bad cops accountable and that all it was missing was the necessary evidence. It turns out the justice system is actually rather ambivalent about holding bad cops accountable, and so it handles additional evidence as halfheartedly as it handled all of the evidence it already had. A camera can allow you to see, but it can’t make you look.”

“At some point, there has to be an Unwatched Watchman, someone who will do the right thing not because they are forced to, but because they want to. Instead of asking, “How we can get people to do the right thing,” we should ask, “How can we get people to want the right thing?””

We could try to have a society that didn’t brainwash people into wanting things that are societally and environmentally detrimental simply because those things happen to be lucrative for the elites.

“As Richard Feynman once put it:”

“But this long history of learning how to not fool ourselves—of having utter scientific integrity—is, I’m sorry to say, something that we haven’t specifically included in any particular course that I know of. We just hope you’ve caught on by osmosis.”

“I think Feynman was right. The most important lessons—in science, or in anything—are not learned. They are absorbed. And if you’re steeping in dirty water, you’ll absorb the wrong lessons, and then it’s almost impossible to get them back out again.”

you don’t know where anything comes from by Adam Aleksic (The Etymology Nerd)

“Sure, you can walk to the local store and pay extra for that “fair trade” label, but you’re only really paying for your own peace of mind. Just like “American legal gold,” the certification probably covers up a litany of worker abuses you’d rather not know about. At the end of the day, you still have no clue where your fair trade alpaca wool cardigan actually came from.”

In fairness it’s also because you live in a nearly uniquely mendacious society.

You Can’t Defend a Policy By Getting Angry at the Suggestion That It’s Benefitted People by Freddie deBoer (Substack)

“The strangest thing about all of this is that the very same people who say that nothing has changed will, given a slightly different prompt twenty minutes later, tell you proudly about the change they helped bring about. You just have to be careful about how you angle the question. Ask “Did your diversity programs accomplish anything?” and you get a catalogue of accomplishments. Ask “Is it conceivable that someone else lost an opportunity because of those accomplishments?” and you get a flat, slightly offended denial that any change occurred at all. And you know in advance how the BlueSky posts go: “You’re saying ‘oh but what about the poor white men???’” Well, no, what I’m actually saying is that increasing the number of group X in a zero-sum system must necessarily decrease the number of group Not-X; that is inherent, inevitable.”

“I spoke at a college a few years ago and I gave the students this little challenge. I asked how many students in the audience supported race-based affirmative action at their school − that is, the program that gave underrepresented racial minorities an admissions boost to help them get into their quite exclusive college. Most raised their hands. I then asked if they agreed with the statement “There are Black students at this school who would not have gotten in without affirmative action,” none of them raised their hand. I asked if they thought that statement was offensive, and several murmured yes. But of course, if an affirmative action program does not get Black students into a school who would not have gotten in without affirmative action, then it does nothing; it can’t really be said to exist.”

Seaton: Grocery Rules by Chris Seaton (Simple Justice)

The person who wrote this is a sociopath raised in a sociopathic society. I did not get the impression that this post was written at all in jest.

“You will consult your list exactly three times while grocery shopping: once before you enter the store, once before checkout, and once when you get to your car. You will not pull out your list and randomly check off items while shopping. That’s moron behavior. You can memorize your list and check off items after you’ve shopped.”

Unless you’re old. Or forgetful. Or both.

“[…] you’re using the self-checkout. We’re not here to make small talk with the help. We’re buying food items and toiletries. That’s it. No need to chat with Gloria in the process.”

God forbid you associate with people in your community. Oh, you don’t have a community. You can’t even conceive of what it would be like to have a community. Or to like people.

“[…] you are permitted to visit the store’s fish monger and meat gentleman to discuss your purchases. They can’t give you what you want unless you ask, after all. Same goes for the deli section. All of these folks are hard workers and don’t want to participate in small talk with you, so put your order in and move on.”

Yeah, who would want any human interaction breaking up their eight-hour shift of hard work?

“Speaking of small talk, the grocery store is not for conversing with your neighbors. They have shit to do just like you and you’ll see them later. Say hello if you must. Definitely acknowledge their presence. Just don’t go into great detail about your life in the aisle where frozen breakfast items are stored. That’s weird.”

You should only interact with people online, as God intended.

Don’t acknowledge otherwise lonely people in public or give them any of your precious time.

The other day, I chatted for nearly an hour with an elderly neighbor who was walking by my garden. Did I have a ton of things lined up to do that day? Of course I did. I always do. Was it worth it? Sure! I learned things about her that I hadn’t know; and she had some company for a while. Win-win.

The author of this article seems like he’s proud to be an abrasive asshole who’s too good for anyone else. Or maybe he just lives in an abysmally shitty society where human interaction has stopped being rewarding in any way. But I doubt it.

“I now officially recommend people stop using the plastic grocery store bags if you can help it. They’ve been recycled so many times they are basically useless for holding anything now. Best to suck it up, invest in a couple of reusable grocery bags and go from there now. Hey, it’s got the added bonus of being environmentally friendly!”

Some people just can’t do something good for environment, except as a reluctantly accepted side-effect for another reason (like that the bags are no-good). It is wild watching someone write something like this: that being sustainable and not wasteful is something that you should only reluctantly accept, once all other options are exhausted.

It is utterly unsurprising that this author would couch this otherwise banal recommendation in these terms: he’s probably spent a dozen years denouncing “pussies” who couldn’t wrap their heads around the glory of plastic bags.

LLMs and the Library Card Fallacy by Freddie deBoer (Substack)

“The Library Card Fallacy is the mistaken notion that the purpose of education is to transfer information from teacher to student, and thus that schools and teachers are subject to disruption when any technology comes around that democratizes access to information. The trouble with this theory is that information has been very broadly available for a hundred years or more; depending on how exactly you want to define things, most Americans have enjoyed public library access since sometime between the 1890s and the 1920s. In the late 1990s, people started saying that Google was an existential threat to colleges and universities − you can just get the knowledge from Google! But most people already had access to an immense amount of knowledge before Google, in the form of their public library. You certainly can give yourself quite a self-education with a library card, but the plain reality is that almost no one actually does. Most people aren’t busy little self-starters who will diligently learn on their own. That’s why schools exist, because people need someone looking over their shoulder to force them to learn the material! And even then it often doesn’t work. Most people resist being educated, and the assumption otherwise is part of why policy discussions about education are so unhelpful.

“That’s why I call it the Library Card Fallacy: if it was true that education was about access to information, then anyone with a library card would become educated. But that’s just not what education is about. Education is about being challenged to learn things you don’t particularly want to and about creating an incentive structure that forces you to do so. The much-ballyhooed prediction that Google would create a nation of busy little autodidacts has clearly not come to pass. Of course it hasn’t! Most people aren’t Googling “explain the factors that led to World War I,” they’re Googling “Sydney Sweeney nude” or “Batman torrent” or “fantasy football rankings.” Some people love to learn; many, many, many more love to waste time with trivial bullshit. This is why, for example, the famous NBER study that distributed PCs randomly to homes showed no sign of educational gains for the kids whose families received one. Those kids weren’t reading Wikipedia entries! They were playing Farmville on those computers! Sometimes I wonder if these big-think types have ever met an actual child. And the same thing goes for our 18-25 year olds − how many of them, honestly, do you think are going to be sitting there having Gemini come up with a lesson plan to learn about something they find boring? That is not how human beings function.”

“[…] even when you filter the sample down to people who said they wanted to finish, almost four in five failed to do so. The technology was there; the lectures were free; access was granted. What was missing the sustained desire to grind through twelve weeks of problem sets when nothing external was forcing the issue.”

“This is what that Khan Academy’s Sal Khan, quoted in the piece excerpted in that image, just cannot seem to wrap his mind around: you can lead a horse to water but you can’t make them drink. The sunny, supposedly egalitarian vision of a world full of people hungry to learn just doesn’t fit the reality. Look around you. How many people are spending their free time learning? And even among the people who are, how many of them are learning things that are genuinely boring and frustrating to learn, instead of what’s fun to learn?”

“The people predicting that ChatGPT will achieve in 2030 what Coursera couldn’t achieve in 2015 are wrong in the exact same way and for the exact same reasons. They’re confused about what education supplies; they think it’s a matter of access to information, which has been ample for some time, when it’s really a matter of institutional accountability, incentives, and personal inspiration. And they’ve ignored the demand side problem, which has always been the binding constraint. An LLM that can patiently walk you through the causes of the Thirty Year War doesn’t matter if almost nobody wants to be walked through the causes of the Thirty Year War. The marginal student who wouldn’t crack open a textbook at school won’t bother to type a smart LLM prompt, either… and in fact will happily type a prompt asking the bot to write the paper for him, which is the use case actually playing out in every classroom in America right now. Indeed, if LLMs prove anything, it’s how widespread the desire to cheat and cut corners really is; that’s not a condition conducive to autodidacticism. Belief in MOOCs presumed a belief in student willingness to work. The LLM era is, if anything, a regression, a technology sold as the engine of unprecedented self-education that in practice serves as a tool for unprecedented evasion of it. Anyone who’s spent five minutes around an actual teenager could have predicted this outcome.”

“[…] supply the external scaffolding that the vast majority of human beings require in order to learn anything they don’t already want to learn: deadlines, grades, embarrassment in front of peers, the looming presence of a teacher who will notice…. That scaffolding is the product and always has been. The lectures are incidental, the textbooks are incidental, and the personalized AI tutor will turn out to be incidental too. What is not incidental is the social and institutional pressure that compels an ordinary late adolescent to sit in a room and slog through the Federalist Papers when every fiber of their being would rather be doing anything else. Maybe we can’t make young people feel that pressure in a meaningful way anymore. Maybe. But that just means that our whole society is doomed anyway, and ChatGPT is not going to be able to fix it.”

“I confess that in the last couple of years I’ve quietly given up, and if LLMs have done one thing for me, it’s to force me to recognize just how little the average person gives a shit and just how willing the great mass of humanity is to slip into apathy and decline. But I do have hope for individuals, the exceptional and talented people who really give a shit. For them, the ones who need it least, the ability to learn is there. The library card has been in our collective wallet for a hundred years. The whole internet has been in our pockets for fifteen. So go learn something.”

The crux is that these tools provide people the ability to appear to provide value that they have either not provided or the verification of that value takes much more effort than its generation. This is a dangerous situation, ripe for scams, as the delay in verification will generally allow the scammer to scamper away with value in exchange and to be long gone before the scammed party notices what happened. The only recourse is for the scammed party to try to find their own victim. LLMs industrialize scams.

Technology & Engineering

How NASA Built Artemis II’s Fault-Tolerant Computer by Logan Kugler (Communications of the ACM)

““Modern Agile and DevOps approaches prioritize iteration, which can challenge architectural discipline,” Riley explained. “As a result, technical debt accumulates, and maintainability and system resiliency suffer.””

“The hardware itself is also reinforced. The system employs triple-modular-redundant memory that self-corrects single-bit errors on every read. Even the network interface cards utilize two lanes of traffic that are constantly compared, ensuring that a bit flip in the communication fabric results in a fail-silent event rather than a corrupted command. The network itself is triple redundant with three separate planes, and all network switches employ self-checking strategies.”

“Orion carries a completely independent Backup Flight Software (BFS) system. This is a prime example of dissimilar redundancy. It is implemented on different hardware, runs a different operating system, and utilizes independently developed, simplified flight software.

““It is intentionally different to ensure that a common mode software failure in the primary flight software isn’t also implemented incorrectly on the backup,” Uitenbroek said. The BFS runs constantly in the background and automatically takes over via source selection if the primary computers fail. If the system finds itself on the BFS, it can complete all dynamic portions of the mission to reach a quiescent phase, at which point the crew can attempt to recover the primary FCMs.”

“High-performance supercomputers are used for large-scale fault injection, emulating entire flight timelines where catastrophic hardware failures are introduced to see if the software can successfully ‘fail silent’ and recover.”

The Worlds Left To Conquer by Nikhil Suresh (Ludicity)

“I’m competing with people that don’t have functional literacy. And it’s not just incompetence at programming, it’s everything. The world has phoned it in, leaving us with no pressure to push for excellence. Last year, I was unable to put clients on both Evidence and Prefect because the former failed to attend a sales meeting booked through their website and the latter failed to book a meeting after the ex-real estate agent they hired failed to actually schedule a meeting following outreach also through their website. Our (excellent) accounting team is Hales Redden, who managed my co-founder Jordan Andersen’s old physiotherapy business… because the people I tried in Melbourne don’t check their sales inbox. Our lawyer is reader Iain McLaren4 because the firms I initially tried also don’t respond to their sales inbox. I cannot state this clearly enough – the bar is so low that it is hard to give people money. There are competent actors on the market, but at least in software, there are simply so few of them that you’re more likely to be allies than enemies.”

“It is unbelievable how much of a competitive advantage “Responds to emails from paying clients within 24 hours” is. The bar is subterranean.”

LLMs & AI

Companies under heavy AI psychosis by Mitchell Hashimoto (Twitter)

“I lived through the great MTBF vs MTTR (mean-time-between-failure vs. mean-time-to-recovery) reckoning of infrastructure during the transition to cloud and cloud automation. All those arguments are rearing their ugly heads again but now its… the whole software development industry (maybe the whole world, really).

“It’s frightening, because the psychosis folks operate under an almost absolute “MTTR is all you need” mentality: “its fine to ship bugs because the agents will fix them so quickly and at a scale humans can’t do!” We learned in infrastructure that MTTR is great but you can’t yeet resilient systems entirely.

“The main issue is I don’t even know how to bring this up to people I know personally, because bringing this topic up leads to immediately dismissals like “no no, it has full test coverage” or “bug reports are going down” or something, which just don’t paint the whole picture.

“We already learned this lesson once in infrastructure: you can automate yourself into a very resilient catastrophe machine. Systems can appear healthy by local metrics while globally becoming incomprehensible. Bug reports can go down while latent risk explodes. Test coverage can rise while semantic understanding falls. Changes happens so fast that nobody notices the underlying architecture decaying.”

I don’t think AI will make your processes go faster by Frederick Van Brabant

“Software development is about translating a problem into a solution that a computer can understand and automatically resolve. Preferably in a secure and scalable way.

“To do something like that, you need a full overview of the problem. Either in feature or scope documents (if you’re going more waterfall), or with constant iteration with the domain experts (more agile).

“This is often the part that slows down software development. Trying to figure out what a vague, title only, feature request actually means.

“What does “send mail to user once sale is completed” mean? Ok, we can send a mail, but what should be in the mail? What if there was an issue in the sales process, do we still send an error mail? When is a sale completed?”

“I also think it’s an unfair comparison. Working like this requires a much deeper involvement of domain and product experts. This involvement would mean writing out every feature and bug fix down to the tiniest detail.

“This exact thing is what software developers have been begging for since the beginning of the profession: Receiving a detailed outline of the problem and what the end result should look like.

“If you were to give human developers the same amount of feature/scope documentation you would also see your productivity skyrocket.”

“One of the big lessons of The Goal is: ”bottlenecks should receive predictable, high-quality inputs”.

“I think that should be the first stop in process automation.”

The just-say-no engineer was a ZIRP phenomenon by Sean Goedecke

“When banks hiked interest rates, almost every tech company immediately laid off 5-20% of their engineers. It was just no longer profitable to keep a bloated engineering staff around to boost the stock price. Instead, companies had to actually make money3. However, that wasn’t a good public explanation for the layoffs, since it sounds weak to admit that you were paying hundreds of engineers to do unprofitable work. Fortunately, the end of ZIRP coincided roughly with the rise of ChatGPT, so tech companies were able to to blame their layoffs on the power of AI. Saying “with this transformative new technology, we’re able to deliver 10x the value with half the engineers” is a much stronger message, even though it doesn’t make much sense (if this is true, why not keep your engineers and deliver 20x the value?)”

OK, I’m with you so far. What else?

“Something like this dynamic has been happening to the just-say-no engineer. Tech companies are now more focused than at any time in the past two decades. They are not doing a bunch of random crap anymore; instead they’re desperately chasing new capabilities and features that can make money (mostly built on AI, for obvious reasons). This new environment is actively inimical to the just-say-no engineer. It’s as if a shark got pulled out of the deep ocean and dropped into a fast-flowing river: what was once a powerful apex predator is now disoriented and flailing.”

What the actual hell are you talking about? They’re not doing random crap anymore? They’re doing it more than ever, no? After having dump nearly $100B into the metaverse, Meta is now planning to sink in almost as much just this year into AI products, which are so vaguely defined that it can’t be interpreted as anything other than hey look at us, we’re doing AI too!

Oracle has pretty much doomed its business based on promises contingent on OpenAI delivery multiple hundreds of billions of revenue over the next couple of years. Also, they can’t get their data centers built that OpenAI would use to generate this wholly fantastical revenue. Microsoft and Google are loading up on expensive debt in order to throw money at AI, for which no real product has been defined—it’s just a technology and tools right now. And those tools are aimed at a very small market of people who are building things.

I just don’t understand how this guy can come to the conclusion that the focus has gotten better.

“This kind of engineer used to enjoy implicit (albeit distant) support from their management. If someone complained, they’d often get told “that engineer knows what they’re doing, if they said no, then I trust them”. Now that support is gone. The just-say-no engineer is now being criticized and actively overruled by their management. They’re being told to be more of a team player, to find a way to say yes, or are simply no longer being consulted (with the company’s blessing) on key decisions.”

Companies still need just-say-no engineers because they avoid complexity. They aren’t just-say-no engineers—they are surface-repercussions-and-medium-and-long-term-costs engineers. They point out dependencies to other systems, sometimes non-technical ones. If you’re not a pure cloud shop with sheep-like customers / users who will put up with anything and everything, when you just change everything in the software.

“LLMs are adding insult to injury for the just-say-no engineer. They’re forced to watch while other engineers merge AI-generated PRs that would previously have been blocked, and are told to use the tools themselves: to become the kind of engineer they’ve spent their entire careers battling against.

“Worse still, the AI tooling mostly works. It’s not (yet) causing any kind of catastrophe6. The code isn’t quite as clean, and it’s a bit less well-understood, but it’s good enough (particularly in a world where companies are trying lots of new things and abandoning the ones that fail).”

This has patently never been true and is almost certainly not true now. Companies have always taken half-baked prototypes to production because it feels cheaper short-term. This will only get worse with plausible-seeming AI-generated products.

If You’re Running Claude Code, PLEASE Run It in a Box by Christian Ekrem

“I want the common denominator for all my LLM usage to be that it frees up more time for me to write code and do engineering, not to outsource those very things.”

This has always been the way to integrate productivity improvements. A calculator frees you from doing long division. Formatting rules free you from fixing spacing. A spellchecker frees you from looking up how words are spelled. Etc. Etc. Etc. Mail-merge frees you from manually matching everything up.

The only difference in AI to past tools is not their power, actually. It’s their much higher variability in unreliability. What they produce cannot yet be trusted so you still have to wrap a verification process around it that becomes so heavyweight that it often feels like you should either skip it (YOLO) or it takes just as long as it took to do it yourself, and doing it yourself was more fun.

“What you need is to simply use Docker’s sbx (brew install docker/tap/sbx):”

sbx run claude

“The sbx docs cover the setup, but TL;DR by default this spawns a safe sandbox that can’t git push or read files outside of your project. What an extreme improvement right from the start that is!

“And get this: inside the sandbox, you can actually just let it run without that stupid halt asking for permission to cat a file or whatever. Claude Code auto-approves everything by default – full kamikaze mode with no confirmation prompts. On my host machine that would be terrifying (I mean, even without the dangerous flags it does crazy stuff!). Inside sbx it’s fine, because it has neither my git credentials or any path to anything outside my working directory. Worst case something goes sideways, I close it and git stash. Containable blast radius: √.

“In other words: Sandboxing makes it faster, not just safer.”

AI Is Technology, Not a Product by John Gruber (Daring Fireball)

“The idea that AI agents “will have already figured out where [we] need to go, and the car will be waiting without the friction of a request” strikes me as pure fever dream high-on-the-hype fantasy. I’m just going to step outside a restaurant when I’m done eating a meal and a ride-share is going to be there, waiting for me, without my having hailed it? Every time? And I’m going to find this pleasing, not creepy? And ride-share drivers are going to respond to all these requests, because the requests will never be wrong? And this is going to happen, somehow, without my carrying a phone with me? And this is going to happen in the next four years? I don’t think I’d want this even if it were plausible, but it doesn’t sound plausible.”

Roaming Charges: Peanuts From Heaven by Jeffrey St. Clair (CounterPunch)

Premium: What If…We’re In An AI Bubble? (Part 2) by Ed Zitron (Where's Your Ed At?)

“[…] if data center construction slows to a crawl (as I’ve discussed is already the case) there’s a cascade of events that will occur:”

• OpenAI and Anthropic can’t expand much further than their current capacity.
• As they both make up 50% of Amazon, Google and Microsoft’s revenue backlogs, hyperscalers will be unable to make the majority of the revenue they’ve promised their shareholders.
• The $178.5 billion in US data center debt from 2025 will go mostly unpaid, as a great deal of it is project financing that’s dependent on revenue from data centers that won’t be built and thus won’t be making any revenue.
• NVIDIA, which claims to have shipped over 3 million Blackwell GPUs in 2025, will have trouble selling its next-generation Vera Rubin GPUs, as nobody will have anywhere to put them.
• Alternatively, we’ll see write offs of billions of Blackwell GPUs that will now be considered obsolete.
• Banks that are already afraid of “choking” on data center debt will stop issuing it, because these investments will not be paying off.
• It will become very difficult for anybody to afford to buy more NVIDIA GPUs, because AI data centers — which cost around $44 million per megawatt — require massive amounts of upfront capital expenditures, making it unlikely-to-impossible that somebody has the money lying around.

“Even in an optimistic scenario, if data centers that started being built in 2024 don’t get finished until 2027 or 2028, that means that NVIDIA’s “latest” GPUs are perennially two or three years in the future.”

“I believe there are at least one million Blackwell GPUs sitting in warehouses waiting to be installed years into the future, which means that projects are going to launch in a year or two with potentially three-year-old GPUs, or said projects are going to have to either replace their orders with Vera Rubin or dump aged capacity onto a market saturated with Blackwell GPUs.”

“The same questionable attention to detail applies to venture capital, which has seen (much like private equity) its investment model slow to a crawl since 2018, with an average TVPI (total value paid in) slow to a horrifying 0.8 to 1.2x since 2018, meaning that for every dollar invested, you’re at best likely to get even money in return.

“These are the very same investors telling you that every AI company is worth perpetually-growing amounts of money, that everything will work out perfectly, that somebody will work out how to make AI profitable, and that AI is both here to stay and doing incredible things, even if they can’t really explain what those things might be.

“In reality, none of these people have any idea how to turn around these rotten economics. Data centers are massive money-losing operations that in the best case scenario take five years to make a single dollar of margin, and their customers are eternally-unprofitable AI startups that rely on a constant flow of venture capital dollars.”

Joe Rogan accidentally exposed AI in four words by Mo Bitar (YouTube)

“They’re producing so much code, they’re being so productive that they can’t sleep anymore because the opportunity cost is too high. If you’re sleeping, your agents are not churning. And Mark is like, people are now working 20-hour days voluntarily. They can’t get enough. And the truth is that people are working 20-hour days because they’re less productive. They’re less efficient than they were before.

“Because there’s this promise that one more prompt, one more prompt and it’ll solve the problem that you’ve been toiling on all day. It’s that slot-machine feeling where you’re one more lever-pull away from cracking it. And it keeps you in this trap. Like, you’re at 88% there and you feel like one more prompt and it’ll get you past the 98% point. But every additional prompt inches you up like 0.1. And it’s like, oh, 88.1, 88.2, 88.3.

“And the only way to win, the only way to play this game is to keep prompting 20 hours a day until you hit something that’s shippable and you hardly ever get there. And the problem right now—the dystopia—is coming from the managerial and executive class who are pressuring employees in the wrong direction. They’re pushing this tool on them and saying, “Use this. It’ll make you more productive.” Productive toward what? They haven’t figured that part out. They’re hoping the low-level engineers will figure out what business objectives to work on by themselves.”

“This message is propagated by the token salesman at the top, Sam and Dario. And it’s not that hard to understand. Follow the money. Who are anthropic and OpenAI selling to? They’re selling to enterprises. And what’s the message enterprises want to hear? They want to hear more productivity, more automation, less need for fickle human beings. That’s why the narrative is the way it is.”

“And you might think, okay, surely now that Sam and Dario are going to see all these people booing AI, that they’re going to change it up. They’re going to clean up their act. But the message is the sales pitch. You don’t change a sales pitch that’s working. Because if you suddenly change the pitch to say that AI is going to augment your employees rather than replace them, then what these companies hear is that you’re offering to double my cost because I was paying for the humans and now I have to pay for the AI, which is not cheap?

“So they stick with the enterprise human-replacement pitch because it’s the most profitable pitch in the history of capitalism. the next industrial revolution, the printing press, the cut engine, AI is going to put your organization at the forefront of innovation and the managers buy that up.

“You’ve been sold on this idea of intelligence when really it’s more of a compelling parody of intelligence. Is it useful? Yes. Is it insanely useful that hasn’t been demonstrated from the output? Your job as a manager is to tell your people what objectives to hit. The objective is not more tokens. The objective is not having your employees sit on the bottom of a token chute and feeding tokens straight into their mouth and having them do something that’s useful. Hopefully, the objective is a business objective that you have to figure out. What your employees use to get the job done hardly matters.

“Now, I personally think that the LLM species has been discovered. It’s like you walked onto this foreign planet and you’ve discovered this alien species and they are what they are. You don’t look at these aliens saying, “hm, if they’re this smart now, imagine how smart they’ll be in five years.” No, you’ve already discovered the species. This is just who they are. You can give them more tools. And that’s what’s happening now. AI isn’t getting smarter. It’s the same base LLM technology.

“Whenever you see Claw Design come out or whatever Anthropic is cooking up next, this is not the base LLM suddenly becoming smarter and rounding out towards general intelligence. This is tool use. It’s the same alien intelligence, same alien species learning to use different tools. And that’s powerful, but it also is what it is and not more than that.

“He says to get to the next breakthrough towards AGI, we have to make a couple more scientific discoveries. But the scientific discoveries you need to make happen on the order of like once a century. He’s like, we’re going to need two more events on the scale of the fire and the wheel. And we got that scheduled for Q3 of this year.

“It’s like, dude, what are you talking about? Like, imagine running any other business this way. Our revenue model assumes we discover a new continent. Two new continents, actually. We’re so close. The boats are so fast now. I think a lot of companies right now are not figuring out how to make more money because making more money is hard. And the layoffs are an acknowledgement of that.

“Jason Freed, the founder of Base Camp, has a pretty good analogy about this. He said bragging about how many tokens you produce is like putting your finger on the shutter button of a camera and bragging about how many pictures you’re taking. Like instead of taking one, two, or three good photos, you’re taking like tens of thousands of photos and you’re like, “Wow, I had a really good day today. I took 10,000 photos.” And now you have to review all those photos. You have to find the ones that meet your business objective.”

Microsoft reports are exposing AI’s real cost problem: Using the tech is more expensive than paying human employees by Jake Angelo (Fortune)

“Microsoft has reportedly begun canceling most of its direct Claude Code licenses, according to The Verge, instead moving engineers toward using GitHub Copilot CLI. That comes just six months after the firm first opened up access to Claude Code, encouraging thousands of its developers, project managers, designers, and other employees to experiment with coding.”

What a shitshow. Seriously, only absolutely over-rich companies like Microsoft can afford this level of stupidity-driven churn. Other companies will commit suicide trying to follow along.

“[…] with a token-based pricing system, the work gets more expensive with more use and better efficiency. Goldman Sachs recently forecasted that agentic AI could drive a 24-fold increase in token consumption by 2030 as consumers and enterprises adopt AI agents, reaching a staggering 120 quadrillion tokens per month. As businesses turn to AI agents to boost productivity, aggregate costs could rise sharply even if the price of each token falls.”

This is what counts as “sophisticated analysis”: scammer companies that have their customers trapped in a cult have figured out how to make more money off of their marks.

“Gartner predicted that cheaper tokens won’t translate to cheaper enterprise AI because agentic models require far more tokens per task than standard models, increased consumption can outpace falling unit costs, and AI providers won’t fully pass through lower costs to consumers. In turn, inference costs are likely to push higher.”

Like NO FUCKING SHIT. Jesus Christ, this is Fortune magazine reporting this utterly obvious tripe as if it were etched in two stone tablets clutched by Moses. FFS this is embarrassing. They’re barely even trying anymore. No-one knows anything and the biggest morons are in charge. And they continue to fail upward because everyone else is just a lemming. The bar is so low that a halfway-intelligent person would trip over it and these people manage to keep shimmying under it anyway.

God forbid they should ever even once mention that frontier models from DeepSeek or any of the other open-source providers are nearly as or just as good as the overpriced crap offered by the golden children of the U.S. stock market. Why would they? They know which side their bread is buttered on, and they will not go down with the ship when it sinks.

At the bottom of the article was this,

“In 2001, Fortune first convened the smartest people we know, bringing together CEOs and founders, builders and investors, thinkers and doers. Since then, Fortune Brainstorm Tech has been the place where bold ideas collide. From June 8–10, we will return to Aspen—where it all began—to mark 25 years of Brainstorm.”

Yeah, I’m sure it will be scintillating. The problem is that that what they’re saying might be true—that they really are “the smartest people we know”—but they are probably all still dumb and blinkered and slavishly devoted to a scam economy that happens to be working for them personally quite well, thank you very much. If they ever had to achieve anything without privilege, they’d be sunk, but that’s not where we are, so they’re not. They soar above the clouds, buoyed by the fumes rising from a giant pile of bullshit. Enjoy it while it lasts.

Programming

Canonicalise, Don’t Remember — Smart Constructors in Kotlin by Christian Ekrem

“The defensive re-merge is gone, because there’s nothing left to defend against: a Cart is, by construction, in canonical form. If you have one, its items are merged. The service doesn’t need to know that SKUs can collide any more than it needs to know how PostgreSQL stores rows.”

“The slogan, if I want one: make the canonical form the only form. (Scott Wlaschin’s framing for this kind of thing: the type is a promise. A shape that also commits to something. When the constructor doesn’t enforce that commitment, every caller ends up co-authoring the invariants with you […]”

“When I look at it through that lens, all the mergeBys and sortBys and trims and lowercase()s and distinct()s I’ve been sprinkling at call sites for years are the same shape of mistake. A list of items on a Cart means the merged list. A trimmed string means the trimmed string. If two values share a type but differ in things I’d happily call equivalences, the type is lying to me.”

“The invariant either lives in the type or it lives in an unwritten promise about your storage layer — and unwritten promises are how we got here in the first place.”

“The bigger move, if I were starting from scratch, is an inline value class:”

@JvmInline
value class MergedItems private constructor(val value: List<LineItem>) {
    companion object {
        operator fun invoke(items: List<LineItem>) =
            MergedItems(items.mergeBySku())
    }
}

“Now Cart accepts a MergedItems, not a List<LineItem>. The invariant lives in the type of the list, not in the type of the thing that happens to hold it. Any future type that wants a merged list gets one for free, and you can’t accidentally pass a raw list where a merged one is expected — the compiler won’t let you.”

That was my first thought.

“If your domain type can be constructed in an invalid state, every function that consumes it is forced to become a domain expert. Call that “reuse” if you like; I’d call it contagion.”

“Once the type carries the promise, the rest of the codebase gets to be stupid, and services stop being domain experts. Stupid services are the goal.”

“Whenever I find myself writing “remember to call X before you pass this around,” I’m sowing foot guns. Reminders don’t scale. Past-me forgets, future-me forgets harder, and the colleague joining three months from now never had a real shot at remembering in the first place. What scales is making the type carry the promise. The only door into a Cart runs the merge, and there is no other door. If a Cart exists in your program, its items are merged. Nobody has to remember anything.”

Learning Software Architecture by Alex Kladow (Matklad)

“[…] you can speedrun the four stages of grief to acceptance. Incentive structure is almost never what you want it to be, but, if you can’t change it, you can adapt to it. This is also true about most industrial software projects — there’s never a time to do a thing properly, you must do the best you can, given constraints.”

Replacing a 3 GB SQLite database with a 10 MB FST (finite state transducer) binary by Andrew Quinn

“The trick that makes FSTs so much more compact than tries on natural-language data is suffix sharing: a trie shares prefixes (so kadun and kaduille share their first three nodes) but stores every distinct suffix path independently, while a minimal acyclic deterministic finite-state automaton merges any two subtrees that are structurally identical. For a corpus where 100,000 words all end in the same dozen inflectional patterns, this is a license to print memory.”

“This is a recurring shape to my notes here that I keep bumping into qua “it’s okay to solve a problem twice”. One could say in the first quarter-century of my life, that while I was always fascinated by programming, I could never overcome the guilt of not really knowing whether the tool I am building right now isn’t already superceded by some much better implementation someone else has already written 30 or 40 years ago; I could write a TSV-aware search and replace, or I could find out about awk and solve that entire class of problems in one fell swoop, for example. My central conceit is that this is a trap. You need to reinvent a couple of wheels to get to the edge of what we know about wheel-making, not a thousand wheels, and not zero; probably four or five is sufficient in most domains, maybe closer to twenty or thirty in the most epistemically rigorous and developed fields like mathematics or computer science. Each wheel you reinvent, and every directed question you ask along the way, will propel you faster to the true frontier than that same amount of time spend in idle study, or even five times that amount. This is at heart a Caplanian view: “If schools teach few job skills, transfer of learning is mostly wishful thinking, and the effect of education on intelligence is largely hollow, how on earth do human beings get good at their jobs? The same way you get to Carnegie Hall: practice.“”

Always Be Blaming by Alex Kladov (Matklad)

“My default approach to reading is “predictive”: I don’t actually read the code line by line. Rather, I try to understand the problem that it wants to solve, then imagine my own solution, and read the “diff” between what I have in my mind and what I see in the editor. Non-empty “diff” signifies either a bug in my understanding, or an opportunity to improve the code.”

“Most real code is Markov — the shape of the code at time T depends not only on the problem statement, but also on the shape of the code at time T − 1. The 3D step is to trace the evolution of code over time […]”

“[…] mind the gap between the problem that’s easy to solve, and the problem in need of solving.”

Every line of code is always documented by Mislav Marohnić

“There are ways I could have written that code itself better: by encapsulating the magic property access in a function with an intention-revealing name such as triggerLayout(), or at least by adding a code comment with a short explanation that this kicks off the animation. For whatever reason, I might have failed that day to make this particular code expressive. Code happens, and it’s not always perfect.

“Even if this code was more expressive or if it had contained lines of code comments, a project’s history will be able to provide even richer information:”

• Who added this code;
• When did they add this code;
• Which was the accompanying test (if any);
• The full commit message can be a whole novel (while code comments should be kept succinct).

“Code quality still matters a lot. But when pondering how you could improve your coding even further, you should consider aiming for better commit messages. You should request this not just from yourself, but from your entire team and all the contributors. The story of a software matters as much as its latest checkout.”

• Always write commit messages as if you are explaining the change to a colleague sitting next to you who has no idea of what’s going on. Per Thoughtbot’s tips for better commit messages:

  “Answer the following questions:”

  • Why is this change necessary?
  • How does it address the issue?
  • What side effects does this change have?
  • Consider including a link [to the discussion.]

• Avoid unrelated changes in a single commit. You might have spotted a typo or did tiny code refactoring in the same file where you made some other changes, but resist the temptation to record them together with the main change unless they’re directly related.
• Always be cleaning up your history before pushing. If the commits haven’t been shared yet, it’s safe to rebase the heck out of them. The following could have been permanent history of the Faraday project, but I squashed it down to only 2 commits and edited their messages to hide the fact I had troubles setting the script up in the first place.

Build next-generation UIs with the HTML-in-Canvas API by Chrome for Developers (YouTube)

This is kind of awesome: leveraging the HTML/CSS layout system to render user interfaces in 2D or 3D with canvas-style transformation and WebGPU rendering. It’s pretty amazing: the rendered surface is just transformed but is still completely manipulable as a normal HTML surface would be:

Starting at 10:00, there are some pretty amazing demos, showing stuff that you’d normally only see in video games, but all rendered in a web browser and using HTML, CSS, and SVG as layout and specification languages instead of some custom UI-integration-library language for Unity or something like that.

• You can select text, trigger context menus, copy text, change form controls, etc.
• Or you can have an animated SVG that is rendered onto a texture in WebGL, like on a billboard.
• Or you can render a half-transparent, refracting 3D model floating over a form and the form controls are refracted through the model. It’s wild.
• They also show a book UI that let’s you choose the rendering font to use in the 3D-rendered book. It’s all just selectable text. You can even have it translate the text on the fly using regular browser tools.
• Or there’s a 3D-WebGL slider control that’s completely 3D-rendered, squishy, and semi-translucent/refractive that you specify with a range control.

No custom programming. You just author your pages as you always did and then use some plumbing to hook it to a canvas. Some libraries already offer experimental support for high-level APIs that do most of that plumbing for you.

You can edit the the declarative source’s properties in the Web Inspector as you could for anything else and the rendering updates automatically and in real-time. This is kind of like how high-end game-engine editors have worked for years but it’s bringing it to a world of standardized input content. This is a wonderful leveraging of all of these standardized technologies to grant developers superpowers without having to do anything different than they have been.

Sports

Extremsportlerin war schneller als alle Männer (Info Sperber)

“Eine Woche zuvor war Rachel Entrekin eine mindestens ebenso beeindruckende Leistung gelungen. Die Extremsportlerin bewältigte den Cocodona-Ultramarathon in Arizona über 400 Kilometer in gut 56 Stunden – und war damit schneller als alle Männer. Zwar war die Strecke kürzer, dafür hatte die 34-Jährige rund 12’000 Höhenmeter zu überwinden, also deutlich mehr als Saatçi.

“Der Cocodona gilt als einer der härtesten Ultramarathons der Welt. In diesem Jahr nahmen laut Veranstalter fast 400 Athletinnen und Athleten teil. Entrekin stellte mit 56 Stunden und 9 Minuten nicht nur einen neuen Streckenrekord auf, sondern unterbot auch ihre eigene Bestzeit aus dem Vorjahr um gut sieben Stunden. Zudem war sie eine Stunde schneller als der schnellste Mann im Feld. 2024 und 2025 hatte Entrekin die Frauenwertung gewonnen – 2026 dominierte sie das gesamte Rennen.”

Australia-shaped long ride in Switzerland

A good friend mapped out a route for Sunday that looks like Australia. I am in awe of the time he invests.

Fun

The other day, I went from almost getting a hole-in-one on the Wordle but then barely getting it in six guesses. I think it looks pretty nice. If I’d guessed “waner” or “waker” instead, it would have been even funnier.

Water, Wager, Wader, Waxer, Wafer, Waver

14 early 90s comic books

My partner’s aunt and uncle used to run the newsroom back in the late 80s/early 90s. She just dumped a pile of early 90s comic books on me a few weeks ago. Out of curiosity, I asked Copilot to “Create a list of the comic books in this image and estimate the current value of each for near mint condition.”

🧾 Comic List + Estimated NM Values

Top row

• Venom: Lethal Protector #1 (1993)
  Key: First Venom solo series
  💰 $8–15

• Venom: Lethal Protector #2 (1993)
  💰 $3–8

• The Amazing Spider-Man #375 (1993)
  Key: Anniversary issue, hologram cover
  💰 $8–20

• Spider-Man #324 (1990)
  (Punisher appearance)
  💰 $3–10

• The Secret Defenders #1 (1993)
  💰 $3–8

Second row

• Darkhawk #25 (1993)
  “Death & Life” storyline
  💰 $3–7

• Iron Man #290 (1993)
  “Return of Tony Stark” era
  💰 $3–6

• Avengers: The Crossing – “Alternate Visions” (1995 variant/embossed cover)
  💰 $5–12

• The Incredible Hulk #403 (1993)
  💰 $2–6

• Spawn #7 (1992)
  Early Spawn issue
  💰 $10–20

Bottom row

• Silver Surfer #78 (1993)
  💰 $3–8

• X-Force #20 (1993)
  💰 $3–8

• Superman: The Man of Steel #21 (1993)
  “Funeral for a Friend” storyline (Death of Superman arc)
  💰 $4–10

• Superman #77 (1993)
  “Funeral for a Friend” – iconic cover with Superman flying away
  💰 $5–15

💵 Quick Value Summary

Most common value range: $3–10 each
Standout issues:

• Venom #1 → up to ~$15
• Spider-Man #375 → up to ~$20
• Spawn #7 → up to ~$20

• 👉 Estimated total bundle value (NM raw):
• ~$60 to $150 depending on condition and buyer demand.

📌 Notes

These are very typical early-1990s printed comics, which had high print runs, so most are not rare.
Condition matters heavily—true NM copies with sharp corners and no spine ticks trend toward the higher end.
Professional grading (CGC 9.8) can significantly increase value for:

• Venom #1
• ASM #375
• Spawn #7

Neat. I don’t know if those numbers are correct, but they’re correct enough for the amount of time I’m willing to spend on it.