The last several years have been the monkey’s paw moment for rationalists, where they keep getting what they want and realizing it’s actually bad. As for why they keep getting what they want, just look at who’s funding them.

(Also featuring a “Chinese curse” that isn’t actually a phrase in Chinese. At least it’s not “may you live in interesting times”.)

I attended a town hall hosted by the department at my university supposedly for general discussion about department affairs. Considering the university had recently made moves such as adding “AI” into the very name of the department, I had suspicions that much of the discussion would be about AI. (I realize I’m doxxing myself but whatever.) I mostly came for the free food, but I was also interested in seeing what people thought about AI.

The event started with a talk by a prominent professor with major administrative power in the department, and indeed the talk was mostly about AI. His views were that he personally didn’t like AI, but he believed that it had changed the world (particularly in programming), and that it was going to stay. One of his justifications for pivoting the department to AI was ensuring universities had some say in AI and not letting all the control go to unaccountable corporations.

The reaction from the audience was a pleasant surprise to me. He asked everyone how much they were excited about AI (hardly anyone) and how much they were worried (most of the audience). By far the most amusing moment was when someone asked, “What if the assumption that AI is inevitable is wrong? What if AI does not live up to its promises?” (Sadly, I don’t remember the exact words that the person said.) The professor’s response was that by this point, there are so many trustworthy, smart, prominent people who definitely wouldn’t fall for scams, and they have adopted AI. He trusts those people, so he trusts that AI is genuine. I don’t know if the audience member accepted this explanation, but I hope not. Our modus operandi is FOMO.

The pizza was only ok, not really worth a 90 minute event.

This really goes to show how much they need to rely on the LLMentalist effect, despite the AI boosters insisting that the AI is totally different now, everything changed in the last few months. They do not care about creating a useful, reliable tool. That concept doesn’t even occur to them, since why do that when AI is magic?

In any case, they are incapable of creating a useful, reliable tool. Deep down, the only thing the AI companies have at their disposal is the ELIZA effect. OpenAI has every incentive not to truly eliminate AI psychosis, because they need engagement. They only want to mitigate the extreme cases where people go insane and cause bad PR for them. But mild AI psychosis is totally fine, it’s great when people are addicted to your product and make the numbers go up!

Somehow this is no worse than his usual fare, such as a thumbnail that is just a bunch of colored lines resembling a line chart but without representing any actual data, with some random marked points labeled “Dark Farms” and “Human Zoo”.

No, I’m not kidding.

Unfortunately, our problem right now is not Donna the below-average Democrat but Donald the fascist. And when it comes to fascists I do not ask if they are above or below average.

The fire code thing really is an excellent example of LessWrong Brain. Fire truck drivers insist on needlessly large trucks (no citation) which makes roads 30% wider than they would otherwise be (no citation) which has “probably” “non-trivially” contributed to larger cars (no citation) leading to enough additional road fatalities to cancel out the lives saved by stricter fire codes (no citation).

The LessWrong Brain argument starts with a deliberately contrarian conclusion and proves it with a Rube Goldberg chain of logical syllogisms. Of course, citations are strictly optional, and they are free to misinterpret them as they see fit. The only real standard of each claim is “looks good to me”, but you are supposed to be impressed that they managed to string a dozen of them together to reveal some shocking, deep truth of the world that nobody else knows about. The AI 2027 nonsense is an infamous example of this.

He uses the word “fermi” which is cult jargon based on Fermi estimation, a.k.a. guessing shit with back-of-the-envelope calculations. Not exactly what you want if you want to convince people to reform fire codes, especially if you have zero citations for anything.

I guess people just aren’t rational enough, and the only reason the fire codes are so irrational is because people are emotional about fire codes. Firefighters are apparently revered as heroes, when it is the LWers who should be the heroes. After all, firefighters merely save people from fires, while LWers buy multimillion dollar mansions to talk about saving quadrillions of hypothetical people from hypothetical basilisks!

It’s fine, spyware is only a risk when it’s bad people’s spyware. It’s totally fine when it’s Anthropic™-approved spyware!

As for Mythos catching things, maybe they should have used Mythos on their very own Claude Code considering that it has hilariously obvious security exploits, such as this one which inserts an arbitrary string into a shell command. Actually, never mind I don’t see anything wrong here, maybe we should burn another $20k in electricity running Mythos on it again to find out.

In basically every case in history where people decided to kill a bad king, there was a period of chaos and violence that followed it. The killing of Charles I happened during the English Civil War, and the killing of Louis XVI happened during the French Revolution. This has happened many times in Chinese history, with the fall of an imperial dynasty leading to several decades of civil war (most recently in the early 1900s). But I guess if you have a big clever brain with big clever thoughts, you don’t need to look at history.

If the only way to get rid of a bad king is to kill him, he will do anything he can to defend his power, including using as much violence as necessary. (People generally do not like being killed.) Even if you successfully get rid of him, good luck establishing a proper government afterwards with all the violence you’ve caused. And who knows if the new king is gonna be better or worse? A better system would instead have a mechanism that replaces officials on a regular basis, say every few years, and ensure that these replacements are peaceful. Oh wait, that’s liberal democracy. If we do something boring like support democracy, how will people ever think of us as special, clever thinkers with bold, contrarian thoughts?

It’s still One Person. A mortal, fleshy person. Their defence is that they’re inoffensive, things are stable, nothing is directly their fault and people are bound by law and oath.

Bro, your system involves giving all the power to one person. You cannot then say they have no responsibility or that they’re “inoffensive” when they abuse it.

I’ve seen this story play out in software engineering: people were very impressed when the AI does unexpectedly well in one out of 50 attempts on an easy task, and so people decided to trust it for everything and turn their codebases into disasters. There was no great wave of new high-quality software. Instead, the only real result was that existing software has become far more buggy and insecure.

Now we have people using AI in science and math because it was impressive in random demonstrations of solving math problems. I now have friends asking me why I’m not using AI, and also saying that AI will be better than all mathematicians in 30 years or whatever. Do you really think I refuse to use AI out of ignorance? No, I know too much about it! I have seen the same story play out in software engineering, and what makes this any different?

This is what happens when your worldview is based on anime.

(A lot of anime has heavy themes, but most people understand that it’s not real life, just like all such art. Unlike Yud, most people’s worldviews on coding and math are based on actual coding and math.)

We can see that one 9 of availability is 90% = 0.9, two 9s is 99% = 0.99, three 9s is 99.9% = 0.999, etc. In general, for positive integers n, n 9s of availability is 1 - (1/10)^n, and we can extrapolate that to non-integer values of n. The value γ needed for 87.5% availability is the solution to 1 - (1/10)^γ = 7/8, or γ = log_10(8) = 0.903089987. γ is transcendental by Gelfond-Schneider (see this for a reference proof).

Right now, Sora is at zero 9s of availability.

By far the dumbest “feature” in the codebase is this thing called “Buddy” (described in a few places such as here). Honestly, I don’t really know what it’s for or what the point is.

BUDDY - A Tamagotchi Inside Your Terminal

I am not making this up.

Claude Code has a full Tamagotchi-style companion pet system called “Buddy.” A deterministic gacha system with species rarity, shiny variants, procedurally generated stats, and a soul description written by Claude on first hatch like OpenClaw.

…

On top of that, there’s a 1% shiny chance completely independent of rarity. So a Shiny Legendary Nebulynx has a 0.01% chance of being rolled. Dang.

Great, so they were planning on a gacha system where you can get an ASCII virtual pet that, uhh, occasionally makes comments? Truly a serious feature for a serious tool for the serious discipline of software engineering. Imagine if IntelliJ decided to pull this bullshit.

But also, Claude Code is leaning hard into gambling addiction — the “Hooked” model. You reward the user with an intermittent, variable reward. This keeps them coming back in the hope of the big win. And it turns them into gambling addicts.

The Onion could not have come up with a better way to illustrate this very point.

Good luck telling the promptfondlers that LLMs are only useful for entertainment and not for any useful work.

I’m sure these English instructions work because they feel like they work. Look, these LLMs feel really great for coding. If they don’t work, that’s because you didn’t pay $200/month for the pro version and you didn’t put enough boldface and all-caps words in the prompt. Also, I really feel like these homeopathic sugar pills cured my cold. I got better after I started taking them!

No joke, I watched a talk once where some people used an LLM to model how certain users would behave in their scenario given their socioeconomic backgrounds. But they had a slight problem, which was that LLMs are nondeterministic and would of course often give different answers when prompted twice. Their solution was to literally use an automated tool that would try a bunch of different prompts until they happened to get one that would give consistent answers (at least on their dataset). I would call this the xkcd green jelly bean effect, but I guess if you call it “finetuning” then suddenly it sounds very proper and serious. (The cherry on top was that they never actually evaluated the output of the LLM, e.g. by seeing how consistent it was with actual user responses. They just had an LLM generate fiction and called it a day.)

AI seems good at purple prose and metaphors that don’t exactly make sense. No, I do not give a fuck about the “triangle of calm” when it comes to, of all things, the narrator taking off her shoes. No, I am not interested in how long the narrator sets the timer on the microwave when she makes literally the blandest meal of all time.

Now I’m sure the techbros truly think this is good “literary” writing. After all, they only care that the writing sounds flowery, because they seem to be very good at missing the actual meaning of everything. I remember Saltman saying that the movie Oppenheimer needed to be more optimistic to inspire more kids to become physicists (while also saying that The Social Network did that for startup founders).

The article’s entire premise is Musk saying some random shit. Remember how Musk said that he would land a man on Mars in 10 years 13 years ago? Honestly, I am incensed that people like Musk and Trump can just say shit and many people will just accept it. I can no longer tolerate it.

Putting aside the very real human ability to screw up such a concept and turn any fair system into an unfair one, …

He says this after mentioning UBI. He really doesn’t want to confront the unfortunate fact that UBI is entirely a political issue. Whatever magical beliefs one may have about how AI can create wealth, the question of how to distribute it is a social arrangement. What exactly stops the wealthy from consolidating all that wealth for themselves? The goodness of their hearts? Or is it political pushback (and violence in the bad old days), as demonstrated in every single example we have in history?

I’d say the problem is even worse now. In previous eras, some wealthy people funded libraries and parks. Nowadays we see them donate to weirdo rationalist nonsense that is completely disconnected from reality.

No getting up early and commuting on public transit. …

This is followed by four whole paragraphs about how the office sucks and wouldn’t it be wonderful if AI got rid of all that. Guess what, we have remote work already! Remember how, during COVID, many software engineering jobs went fully remote, and it turned out that the work was perfectly doable and the workers’ lives improved? But then there were so many puff pieces by managers about the wonderful environment of the office, and back to the office they went. Don’t worry, when the magical AI is here, they’ll change their minds.

Yes, there are “mindless, stupid, inane things” like chores that are unavoidable. There are also other mindless, stupid, inane things that are entirely avoidable but exist anyway because some people base their entire lives around number go up.

I’d say that the great problems that last for decades do not fall purely to random bullshit and require serious advances in new concepts and understanding. But even then, the romanticized warrior culture view is inaccurate. It’s not like some big brain genius says “I’m gonna solve this problem” and comes up with big brain ideas that solve it. Instead, a big problem is solved after people make tons of incremental progress by trying random bullshit and then someone realizes that the tools are now good enough to solve the big problem. A better analogy than the Good Will Hunting genius is picking a fruit: you wait until it is ripe.

But math/CS research is not just about random bullshit go. The truly valuable part is theory and understanding, which comes from critically evaluating the results of whatever random bullshit one tries. Why did idea X work well with Y but not so well with Z, and where else could it work? So random bullshit go is a necessary part of the process, but I’d say research has value (and prestige) because of the theory that comes from people thinking about it critically. Needless to say, LLMs are useless at this. (In the Knuth example, the AI didn’t even prove that its construction worked.)

I think intelligence is overrated for research, and the most important quality for research is giving a shit. Solving big problems is mostly a question of having the right perspective and tools, and raw intelligence is not very useful without them. To do that, one needs to take time to develop opinions and feelings about the strengths and weaknesses of various tools.

Of course, every rule has exceptions, and there have been long standing problems that have been solved only when someone had the chutzpah to apply far more random bullshit than anyone had dared to try before.

The 31st try resulted in them only solving the problem for odd m, but the even m case was still open. So of course this happened:

Filip also told me that he asked Claude to continue on the even case after the odd case had been resolved. “But there after a while it seemed to get stuck. In the end, it was not even able to write and run explore programs correctly anymore, very weird. So I stopped the search.”

Knuth did add a postscript on other friends maybe kinda vibing a possible solution for even m:

On March 3, Stappers wrote me as follows: “The story has a bit of a sequel. I put Claude Opus 4.6 to work on the m = even cases again for about 4 hours yesterday. It made some progress, but not a full solution. The final program . . . sets up a partial fiber construction similar to the odd case, then runs a search to fix it all up. . . . Claude spent the last part of the process mostly on making the search quicker instead of looking for an actual construction. . . . It was running many programs trying to find solutions using simulated annealing or backtrack. After I suggested to use the ORTools CP-SAT [part of Google’s open source toolkit, with the AddCircuit constraint] to find solutions, progress was better, since now solutions could be found within seconds.” This program is [4].

Then on March 4, another friend — Ho Boon Suan in Singapore — wrote as follows: “I have code generated by gpt-5.3-codex that generates a decomposition for even m ≥ 8. . . . I’ve tested it for all even m from 8 to 200 and bunch of random even values between 400 and 2000, and it looks good. Seems far more chaotic to prove correctness by hand here though; the pattern is way more complex.” That program is [5]. (Wow. The graph for m = 2000 has 8 billion vertices!)

I find it slightly funny how Stappers suggested to the AI to use specific external tools that are actually reliable (like ORTools). This also makes me question how much the of the AI’s “insight” was a result of handholding and the rubber duck effect.

For context:

1. This is planned as a hard exercise for a textbook.
2. There are likely so many solutions that finding a general program that works (at least for enough values that you care to check) is like hitting the side of a barn with an arrow. Random bullshit go is an excellent strategy here.
3. The AIs did not provide proofs that their solutions worked. This is kind of a problem if you want to demonstrate that AI has understanding.

I can see them by clicking on the “Reasoned for 6m 34s” box on my desktop browser (I know, great UI design) without needing to log in. This did not work on my phone. In any case, I can copy it here:

The AI people are still infatuated with math. The Epoch AI staff, after being thoroughly embarrassed last year by the FrontierMath scandal, have now decided to make a new FrontierMath Open Problems benchmark, this time with problems that people might give a shit about!

I decided to look at one of the easiest “moderately interesting” problems and noticed that GPT-5.2 Pro managed to solve a warm up version of the problem, i.e. a version that had been previously solved. Wow, these reasoning models sure are capable of math! So I was curious and looked at the reasoning trace and it turns out that … the model just found an obscure website with the right answer and downloaded it. Well, I guess you could say it has some impressive reasoning as it figures out how to download and parse the data, maybe.