Want to wade into the snowy surf of the abyss? Have a sneer percolating in your system but not enough time/energy to make a whole post about it? Go forth and be mid.
Welcome to the Stubsack, your first port of call for learning fresh Awful youāll near-instantly regret.
Any awful.systems sub may be subsneered in this subthread, techtakes or no.
If your sneer seems higher quality than you thought, feel free to cutānāpaste it into its own post ā thereās no quota for posting and the bar really isnāt that high.
The post Xitter web has spawned so many āesotericā right wing freaks, but thereās no appropriate sneer-space for them. Iām talking redscare-ish, reality challenged āculture criticsā who write about everything but understand nothing. Iām talking about reply-guys who make the same 6 tweets about the same 3 subjects. Theyāre inescapable at this point, yet I donāt see them mocked (as much as they should be)
Like, there was one dude a while back who insisted that women couldnāt be surgeons because they didnāt believe in the moon or in stars? I think each and every one of these guys is uniquely fucked up and if I canāt escape them, I would love to sneer at them.
(Credit and/or blame to David Gerard for starting this.)
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 āmoderately interestingā 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 ā¦ 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.
We really need to work harder at poisoning the training data for math problems.
one of the brain geniuses at bluesky
why, the unlucky stiff
howā¦ whatā¦ howā¦ whyā¦ why would you thinkā¦
The HarfBuzz maintainer has drunk the slop-aid - Baldur has commented on it, warning of the potentially catastrophic consequences:
Fonts are a lucrative target. They require a complex parser, usually written in a language that isnāt memory safe, and often directly exposed to outside data (websites, PDFs, etc. that contain fonts). This means a flaw could lead to an attack worst case scenario: arbitrary code execution. HarfBuzz is pretty much the only full-featured library for that takes font files, parses them, and returns glyphs ready to render. It is ubiquitous. A security flaw in HarfBuzz could make a good portion of the worldās user-facing software (i.e. that renders text) unsafe.
luis villa, who as a lawyer really should have known better, being self-reportedly a friend of behdad and a confabulation/war machine promoter decided to come to rescue, calling the above (a) attack, and (b) slander.
in the past 24 hours I was fooled by 3 pieces of fake news in a row:
- that Kurds from Iraq were crossing the border to fight in Iran
- that Windows 12 would be AI-centred or require an AI chip to work (I helped spread this)
- that Spain has capitulated and let the US use its ports for war (erroneously claimed by a WH official).
I know that fake news can be made organically and have been since forever and Iām doing selection bias here but I canāt help but picture the misinformation engines firehosing bullshit constantly until some of it catches and spreads.
If you have to swim in raw sewage, you shouldnāt blame yourself when some poop gets in your mouth.
yeah itās bad
otoh awareness I think is spreading
swedish public broadcasting has regular āspot the fakeā pieces on their website
I think giving a sensationalist bit of news 6 hours to āmatureā is a good idea before amplifying.
I like this. News is a frittata, it needs time to set before consuming.
was doomscrolling and got fucking jumpscared by this fucking article: https://www.science.org/content/article/meet-three-scientists-who-said-no-epstein
scott jumpscare
Iāve been seeing some people (not here, Iāve been taking a break) saying that we shouldnāt be mean to clankers by bringing up Kantās position on being nice to animals. Well. Fuck all that.
animals are like sentient beings yāknow, a clanker is aā¦ matrix or a bunch of matrices or something
Hey, youāre selling them short: there are also ReLU and softmax activation functions thrown around here and there. Clankers arenāt just linear transformations! /j
Recently discovered Donald Knuth got oneshot by Claude recently (indirectly, through fedi) - feeling the itch to write about techās vulnerability to LLMs because of it.
Even in Knuthās account it sounds like the LLM contribution was less in solving the problem and more in throwing out random BS that looked vaguely like different techniques were being applied until it spat out something that Knuth and his collaborator were able to recognize as a promising avenue for actual work.
His bud Filip Stappers rolled in to help solve an open digraph problem Knuth was working on. Stappers fed the decomposition problem to Claude Opus 4.6 cold. Claude ran 31 explorations over about an hour: brute force (too slow), serpentine patterns, fiber decompositions, simulated annealing. At exploration 25 it told itself āSA can find solutions but cannot give a general construction. Need pure math.ā At exploration 30 it noticed a structural pattern in an earlier solution. Exploration 31 produced a working construction.
I am not a mathematician or computer scientist and so will not claim to know exactly what this is describing and how it compares to the normal process for investigating this kind of problem. However, the fact that it produced 4 approaches over 31 attempts seems more consistent with randomly throwing out something that looks like a solution rather than actually thinking through the process of each one. In a creative exploration like this where you expect most approaches to be dead ends rather than produce a working structure maybe the LLM is providing something valuable by generating vaguely work-shaped outputs that can inspire an actual mind to create the actual answer.
Filip had to restart the session after random errors, had to keep reminding Claude to document its progress. The solution only covers one type of solution, when Claude tried to continue another way, it āseemed to get stuckā and eventually couldnāt run its own programs correctly.
The idea that itās ultimately spitting out random answer-shaped nonsense also follows from the amount of babysitting that was required from Filip to keep it actually producing anything useful. I donāt doubt that itās more efficient than I would be at producing random sequences of work-shaped slop and redirecting or retrying in response to a new āplease actually do thisā prompt, but of the two of us only one is demonstrating actual intelligence and moving towards being able to work independently. Compared to an undergrad or myself I donāt doubt that Claude has a faster iteration time for each of those attempts, but thatās not even in the same zip code as actually thinking through the problem, and if anything serves as a strong counterexample to the doomer critihype about the expanding capabilities of these systems. This kind of high-level academic work may be a case where this kind of random slop is actually useful, but thatās an incredibly niche area and does not do nearly as much as Knuth seems to think it does in terms of justifying the incredible cost of these systems. If anything the narrative that āAI solved the problemā is giving Anthropic credit for the work that Knuth and Stapprrs were putting into actually sifting through the stream of slop identifying anything useful. Maybe babysitting the slop sluice is more satisfying or faster than going down every blind alley on your own, but youāre still the one sitting in the river with a pan, and pretending the river is somehow pulling the gold out of itself is just damn foolish.
I am a computer science PhD so I can give some opinion on exactly what is being solved.
First of all, the problem is very contrived. I cannot think of what the motivation or significance of this problem is, and Knuth literally says that it is a planned homework exercise. Itās not a problem that many people have thought about before.
Second, I think this problem is easy (by research standards). The problem is of the form: āWithin this object X of size m, find any example of Y.ā The problem is very limited (the only thing that varies is how large m is), and you only need to find one example of Y for each m, even if there are many such examples. In fact, Filip found that for small values of m, there were tons of examples for Y. In this scenario, my strategy would be ārandom bullshit goā: there are likely so many ways to solve the problem that a good idea is literally just trying stuff and seeing what sticks. Knuth did say the problem was open for several weeks, but:
- Several weeks is a very short time in research.
- Only he and a couple friends knew about the problem. It was not some major problem many people were thinking about.
- Itās very unlikely that Knuth was continuously thinking about the problem during those weeks. He most likely had other things to do.
- Even if he was thinking about it the whole time, he could have gotten stuck in a rut. It happens to everyone, no matter how much red site/orange site users worship him for being ultra-smart.
I guess ārandom bullshit goā is served well by a random bullshit machine, but you still need an expert who actually understands the problem to read the tea leaves and evaluate if you got something useful. Knuthās narrative is not very transparent about how much Filip handheld for the AI as well.
I think the main danger of this (putting aside the severe societal costs of AI) is not that doing this is faster or slower than just thinking through the problem yourself. Itās that relying on AI atrophies your ability to think, and eventually even your ability to guard against the AI bullshitting you. The only way to retain a deep understanding is to constantly be in the weeds thinking things through. Weāve seen this story play out in software before.
My generous statement: Knuth, being a scientist, is used to an āadversaryā that plays fair. As we have known for decades, a scientist can be tricked in situations that a magician will see through. This applies all the more now with the Sycophancy Engines, which make mathematics into a casino vacation. Just one more prompt, bro. Just one more prompt.
My less generous statement: Knuth is almost 90 years old. Sure, age doesnāt imply a person will become a doddering fool, but people do tend to slow down, to have less energy and more need to spend it managing their health. āThinking about a problem for a few weeksā counts for less in a situation like that.
My extremely ungenerous statement: Hey, remember when Michael Atiyah claimed to have proved the Riemann hypothesis in 2018? And the community reaction was a pained, āAtiyah is one of the great mathematiciansā¦ of the 20th century.ā
Thank you for providing some actual domain experience to ground my idle ramblings.
I wonder if part of the reason why so many high profile intellectuals in some of these fields are so prone to getting sniped by the confabulatron is an unwillingness to acknowledge (either publicly or in their own heart) that ārandom bullshit goā is actually a very useful strategy. It reminds me of the way that writers will talk about the value of just getting words on the page because itās easier to replace them with better words than to create perfection ex nihilo, or the rubber duck method of troubleshooting where just stepping through the problem out loud forces you to organize your thoughts in a way that can make the solution more readily apparent. It seems like at least some kinds of research are also this kind of process of analysis and iteration as much as if not more than raw creation and insight.
I have never met Donald Knuth, and donāt mean to impugn his character here, even as Iām basically asking if heās too conceited to properly understand what an LLM is, but I think of how people talk about science and scientists and the way it gets romanticized (see also Iris Meridethās excellent piece on āwarrior cultureā in software development) and it just doesnāt fit a field that can see meaningful progress from throwing shit at the wall to see what sticks. A lot of the discourse around art and artists is more willing to acknowledge this element of the creative process, and that might explain their greater ability and willingness to see the bullshit faucet for what it is. Maybe because science and engineering have a stricter and more objective pass/fail criteria (you can argue about code quality just as much as the quality of a painting, but unlike a painting either the program runs or it doesnāt. Visual art doesnāt generally have to worry about a BSOD) there isnāt the same openness to acknowledge that the affirmative results you get from an LLM are still just random bullshit. I can imagine the argument being: āThe things weāre doing are very prestigious and require great intelligence and other things that offer prestige and cultural capital. If ārandom bullshit goā is often a key part of the process then maybe it doesnāt need as much intelligence and doesnāt deserve as much prestige. Therefore if this new tool can be at all useful in supplementing or replicating part of our process it must be using intelligence and maybe it deserves some of the same prestige that we have.ā
Baldur Bjarnasonās essay remains evergreen.
Consider homeopathy. You might hear a friend talk about āwater memoryā, citing all sorts of scientific-sounding evidence. So, the next time you have a cold you try it.
And you feel better. It even feels like you got better faster, although you canāt prove it because you generally donāt document these things down to the hour.
āMaybe there is something to it.ā
Something seemingly working is not evidence of it working.
-
Were you doing something else at the time which might have helped your body fight the cold?
-
Would your recovery have been any different had you not taken the homeopathic āremedyā?
-
Did your choosing of homeopathy over established medicine expose you to risks you werenāt aware of?
Even when looking at Knuthās account of what happened, you can already tell that the AI is receiving far more credit than what it actually did. There is something about a nondeterministic slot machine that makes it feel far more miraculous when it succeeds, while reliable tools that always do their job are boring and stupid. The downsides of the slot machine never register in comparison to the rewards. Does it feel so miraculous when I get an idea after experimenting in Mathematica?
I feel like math research is particularly susceptible to this, because it is the default that almost all of oneās attempts do not succeed. So what if most of the AIās attempts do not succeed? But if it is to be evaluated as a tool, we have to check if the benefits outweigh the costs. Did it give me more productive ideas, or did it actually waste more of my time leading me down blind alleys? More importantly, is the cognitive decline caused by relying on slot machines going to destroy my progress in the long term? I donāt think anyone is going to do proper experiments for this in math research, but we have already seen this story play out in software. So many people were impressed by superficial performances, and now we are seeing the dumpster fire of bloat, bugs, and security holes. No, I donāt think I want that.
And then there is the narrative of not evaluating AI as an objective tool based on what it can actually do, but instead as a tidal wave of Unending Progress that will one day sweep away those elitists with actual skills. Random lemmas today mean the Millennium Prize problems tomorrow! This is where the AI hype comes from, and why people avoid, say, comparing AI with Mathematica. To them I say good luck. We have dumped hundreds of billions of dollars into this, and there are only so many more hundreds of billions of dollars left. Were these small positive results (and significant negatives) worth hundreds of billions of dollars, or perhaps were there better things that these resources could have been used for?
-
ooh gooods nooo now all the Claude slurpers are going to refer to this forever as definitive proof of how legitimately useful LLMs have got, it āsolvedā a math problem for Donald Knuth! :<
A lobster invokes classic argument from authority
First Terrence Tao and now Donald Knuth.
If youāre still on the fence about AI, you have to take it seriously now.
yeah b/c Iām a professional computer scientist ā¦
I was pissed when my (non-academic) friends saw this and immediately started talking about how mathematicians and computer scientists need to use AI from now on.
If youāre still on the fence about AI, you have to take it seriously now.
Butā¦ why?
Always remember that Nobel disease is a thing.
The one I often think about is the person who invented PCR and then later claimed to have had an encounter with a fluorescent talking raccoon of possibly extraterrestrial origin.
oh hey I remember reading that Donald Knuth paper earlier today, when it got posted by an AI youtube channel as āproofā AI is on the path to AGI
jesus fuck https://urbit.org/blog/olif-and-urbit-ids
with urbit, you can now sniff each otherās farts
Istg this has come up before, i am just too lazy to prove it. Still. Why would anyone want this
It has, but I honestly thought it was fake and/or satire
thought it was satire, genuinely surprised itās an official Urbit-sponsored project
also very much goes against the grain of elevating the mind over the body which is the vibe I get from urbit and environs
Blast from the past: in 2014, Scott Alexander posted a take on marijuana legalization which showed excellent knowledge of medical papers but huge gaps in his knowledge of what brown people or smart policy reformers have to say. David Gerard and Christopher Hallquist in the comments, digression on how pot affects your IQ with gwern chipping in. Alexander came back in 2018 promising that he was right all along with a footnote about how some people in the comments told him that people like smoking weed and he did not know how to process that because his utilitarian calculation said it was bad for society.
Itās curious how, in terms of utilitarianism, the 2014 post has people doing arithmetic to estimate QALYs but the 2018 post is more of a handwave where Scoot repeats the 2014 numbers verbatim. Advocates of decriminalization and legalization have long argued that the QALYs saved by releasing people from prison and no longer sentencing them (easily 20+ QALYs/person) and not arresting people for possession in the first place (0.5 QALYs/person-arrest) are significant to society at large, even if there were quantifiable health risks.
TBH I think that Scoot got a bit of a tough surprise when data actually came in on cannabis usage; itās now accepted cannabis lore that cannabis can cause onset of e.g. schizophrenia, at a rate of something like 1 in 2000 users, but the numbers on causing cancer never materialized. Meanwhile the case studies treating e.g. epilepsy have multiplied to the point where, again, itās now accepted lore that some epileptics find relief by using products made from high-CBD strains.
Choice sneer from the second post, from somebody with an extremely-relevant Moray avatar:
Yeah but you know what would achieve better results? Criminalizing driving.
Edit: grammar and also the extremely-relevant link. Pass the Moray, please~
I didnāt know that Moray in QC was around in 2018! <Crumbles into dust.>
That is a good example because it shows the failure of imagination (can imagine the end of the world, canāt imagine working public transit and public policy to discourage driving) and because hf he thought it through he might get to āhumh, some people like to drive, but its bad for public and social health, how can we discourage it while preserving liberties?ā
I really wonder what he did as a medical student in Cork other than study and read racist Tumblr accounts. Did his friends never drag him to Amsterdam to ride a bike and eat an edible?
Another surprise is that illegal weed still has 30% of the market in Canada. I donāt know how much of that is consumer inertia (āMy buddy Mike always gets me the good stuff ehā) and how much is avoiding taxes.
https://techcrunch.com/2026/03/02/chatgpt-uninstalls-surged-by-295-after-dod-deal/
Some of my faculty have called for a campus wide boycott. Relatedly, the Scott Galloway scoreboard is up to $250m hit to tech market cap: https://www.resistandunsubscribe.com/
while OpenAI deserves every bit of flack they get, itās comical to see people who criticise OpenAI for creating a āwar machineā turn around and praise Anthropic when they were-by their own admission no less!-the first people to start using AI for military purposes
I mean, I can understand the argument that Anthropic at least maintained a fig leaf of ethics, but notably based on Saltmanās statements OpenAI does still feel the obligation to maintain those optics, theyāre just not nearly as credible at doing so.
The good news is the report is false. According to contacts that are familiar with the Windows roadmap, there is no plan to ship a Windows 12 this year. In fact, I understand that the Windows roadmap for 2026 is all about fixing Windows 11 and attempting to improve its reputation by addressing top feedback such as reducing AI bloat across the OS
āWe have heard your complaints about lead in the paint, and our roadmap for Leaded Paint 2026 is all about improving its reputation by making the lead easier to swallowā
The purpose of AI is theft, part infinity: chardet steals LGPL code for profit using Claude
Todayās AI psychosis casualty, brought to you by Gemini.
Blast from the past: I realized that I didnāt have the exact link detailing why nickpsecurity was banned from Lobsters, but now I do. Youāll have to click the little
[+]to see his comments. Heās still active on HN and Reddit; heās gone full MAGA, which is100% predictablea surprising turn for somebody who constantly preaches born-again Christianbigotrypeace and love. I really do wish that Lobsters did the whole turn-you-into-a-tree thing (sure, crucifixion, or maybe Peneus-style or Pequenino-style) for banned users rather than forcing folks to dig through archives.
