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.)
just got a job in mathematical publishing. itās work i think iāll actually enjoy and expect to be very good at, it pays much better than any other job iāve had previously (and they maxed out the positionās pay range, which i wasnāt expecting) and it has about a month of paid leave a year. such a relief
Felicitations!
(āA job,ā Blake thinks. āI need to find one of those.ā)
fuck yeah! congrats!
Hell yeah!
Itās 10 pm on a Sunday. My FIL is texting me business plans from the slop hole as I try to get the last kiddo down to sleep. He wants me to read them to my wife, who already mad at him about it.
Thank you all for being an island of sanity.
āposting from the slop holeā is probably the best description possible for this, brb stealing
one of the brain geniuses at bluesky
howā¦ whatā¦ howā¦ whyā¦ why would you thinkā¦
Thereās only one thing thatās advertised as not-waterproof that Iāll risk using underwater and thatās Casio wristwatches. āWater resistā is a huge understatement for them the things are indestructable.
(This comment sponsored by Casio)
Ned Kelly, but his armor is made of Casio watches.
What a fool. A proper scientist would test for a bigger N. Drop your phone in the pool again Why.
why, the unlucky stiff
Usually, you wake up on a lifeless beach thatās adorned with some sort of abandoned marble temple. Itās supposed to be beautiful, but instead itās really sad. Almost unbearably sad. So much so that you want to get away from it. So you crawl downward into these vents going below the horrible temple, and suddenly itās like youāre moving through the innards of an incomprehensible machine thatās thudding away, thud, thud, thud. And as you get deeper, the metal sidings are carved with scrawled ominous curses and slurs directed toward you, and you hear the voices, louder than before, and you somehow know these people are in pain because of you. It keeps getting colder. Color drains from the world. And you see the crowd through the slats of the vents: pale and emaciated men, women, and children from centuries to come, all of them pressed together for warmth in some sort of unending cavern. What clothes they have are torn and ragged. Before you know it, their dirty hands and dirty fingernails lurch through the grates, and theyāre reaching for you, tearing at your shirt, moaning terrible things about their suffering and how you made it happen, you made it, and you need to stop this now, now, now. And next theyāre ripping you apart, limb from limb, and you are joining them in the gray dimness forever.
Donāt worry, thereās always Effective Altruism if you ever feel guilty about causing the suffering of regular people. Just say youāre going to donate your money at some point eventually in the future. There you go, 40 trillion hypothetical lives saved!
another Onion banger for these trying times
ā Then you wake up in a cold sweat and canāt breathe at all, almost like youāre drowningāI guess from the weight of untold mobs of people leaping on you and ripping you apartā
the real Scam Altman would never feel any kind of remorse or emotion about this
The god Plutonium will save me.
āThey wanted me to build an AI, so I built a shoddy AI casing filled with used pinball machine parts!ā
Sorry, I was referring to a part of the Prince of Darkness movie
Words on computer screen: āYou will not be saved by the holy ghost. You will not be saved by the god Plutonium. In fact, YOU WILL NOT BE SAVED!ā
As that movie has people sending messages back from the future using dreams plot element.
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.
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.
If you have to swim in raw sewage, you shouldnāt blame yourself when some poop gets in your mouth.
Prosperityās Path: OpenAI has shown it cannot be trusted. Canada needs nationalized, public AI https://archive.ph/QLg2D
tldr tech bullshit requires ur tax dollars. what ever you do donāt question the all knowing laurentian technocrats!
yeah, the current situation in Europe is like: āAs EU citizens, we should break free of our dependency on US Big Tech like the Torment Nexus. Thatās why my company is advancing our fully sovereign solution, the Agony Core! Europe-owned, GDPR-compliant, Frontex-approved scalable Torment-as-a-Service, at competitive prices with TN-based deployments!ā
It is amazing in a way, as in .nl our anti piracy org (brein) already went after local AI models for copyright infringement. While people in power still think we should go all in on AI. Sadly people with tech skills are rare in gov (politicians who go after the votes of tech enthousiasts otoh).
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.
Always a good sign when people call normal security concerns that. Hackers love that. /s
I used to think that I could avoid using open source projects which embrace the slop machines, but new it keeps getting more and more adoption, including in good and beloved projectsā¦ at this point I think Iāll just have to accept and ignore it, or otherwise Iād have to play endless whack-a-mole with stuff all over my operating systems :(
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.
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?
-
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.
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
Iād 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. Itās not like some big brain genius says āIām gonna solve this problemā 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 Iād 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 didnāt 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.
Upvoted, but for me the answer is as simple as noting that Knuth is a reverent Lutheran who is deeply involved with their church. Lutherans generally think that technology is part of Godās wonderful creation and that everything is beautiful from the right angle. Knuth thought that algorithms were beautiful and Godly already, and he understands how LLMs work mechanically, so why canāt they be beautiful and Godly too? Also they think that God exists, so theyāre primed to be misled and deluded.
Hypothesis: When he wrote Surreal Numbers, Knuth was a poet and thus unknowingly of the Devilās party.
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
As a layperson skimming the paper, this strikes me as equivalent to a dashed-off letter to the editor coming from someone in Knuthās position. Itās an incomplete, second-hand reporting of somebody elseās results that doesnāt really investigate any of the interesting features of the system at hand. The implicit claim (here and elsewhere) is that we have a runtime for natural-language programming in English, and the main method reported for demonstrating this is the partial prompt:
** After EVERY exploreXX.py run, IMMEDIATELY update this file [plan.md] before doing anything else. ** No exceptions. Do not start the next exploration until the previous one is documented here.
and later on, a slightly longer prompt from a correspondent using GPT-5.2 Pro, that also loads a PDF of Knuthās article into the context window. No discussion of debugging how these systems arrive at their output, or programmatically constraining them for more targeted output in their broader vector space. Just more of the braindead prompting-and-hoping approach, which eventually, unsurprisingly diverges from outputting any viable code whatsoever. This all strikes me as being an exercise similar to
You are a cute little puppy dog. Do not shit on the floor. Do not deposit bodily waste or fecal matter onto hardwood, linoleum, tile, and especially not carpet. Do not defecate indoors. Do not consume your own fecal matter.
The cargo-cult system prompt approach is like banging two rocks together compared to what a computational system should be capable of, and I would be much more impressed and much more interested if someone like Knuth was investigating such capabilities, instead of blogging somebody else pretending to have the Star Trek computer.
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¦
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.
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.
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
Wonder what would have happened if they had not stopped after 31 tries. Sure it gave a goodish answer once, but was that just a luck of the draw? A proper evaluation imho shouldnt stop when you get a good answer once, esp as bad results tend to not get published. (Also, as always somebody might have found the answer already online).
It is also silly in some ways as I wonder how hard it is for people to evaluate the 31 results and not get stuck in pursuing an earlier false lead.
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. āBut 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.ā
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: āThe 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 Googleās open source toolkit, with the AddCircuit constraint] to find solutions, progress was better, since now solutions could be found within seconds.ā This program is [4].
Then on March 4, another friend ā Ho Boon Suan in Singapore ā wrote as follows: āI have code generated by gpt-5.3-codex that generates a decomposition for even m ā„ 8. . . . Iāve 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.ā 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 AIās āinsightā was a result of handholding and the rubber duck effect.
For context:
- This is planned as a hard exercise for a textbook.
- 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.
- 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.
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.
I canāt see the āreasoningā trace in the link. Do you need to be logged in?
I can see them by clicking on the āReasoned for 6m 34sā 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:
Warning: very long slop
Exploring Hadamard matrix construction for order 428
For a Hadamard matrix of order 428, we need to confirm that itās a multiple of 4, which it is (428 = 4 * 107). However, the challenge is that order 107 doesnāt work since itās not a multiple of 4. A possible approach could involve using constructions like Williamson or Goethals-Seidel. Alternatively, I could try a Kronecker product of smaller matrices.
Examining constructions for Hadamard matrix of order 428
Since 107 ā” 3 mod 4, Paley type I gives a Hadamard of order 108, but I need 428, not 432. Thatās a little tricky. I wonder if thereās a known construction for order 4*107 using āHadamard matrix of order 4qā or conference matrices. Could I adapt the generalized Paley approach for this?
Exploring conference matrix construction for Hadamard order 428
For q = 107, Paley construction doesnāt work since q ā” 3 mod 4. But if I can create a conference matrix of order 214 (since 214 ā” 2 mod 4), then a Hadamard matrix of order 428 would follow. Conference matrices require specific conditions, but this seems promising. Letās focus on 214.
Searching for explicit Hadamard matrix of order 428
To generate a Hadamard matrix of order 428, it might be feasible since many such matrices exist up to large orders, but I need one explicitly with Ā±1 entries. A direct construction could involve methods like Goethals-Seidel, which uses circulant matrices to satisfy specific conditions. Iāll need to implement this method.
Exploring construction methods and searching for Hadamard matrix 428
For n=107, there might be a way to use Legendre sequences for Goethals-Seidel difference sets. I know there are constructions for order 4q where q is an odd prime power, but using approaches like Scarpis or Turyn may help too. Iāll search for an explicit Hadamard matrix of order 428 for a possible example or construction.
Exploring accessible sources and construction options for Hadamard matrix
It seems like there may be server timeouts, so Iāll need to try other sources like GitHub, arXiv, or design theory papers. We could construct the Hadamard matrix ourselves using known algorithms, but itās heavy. If accessible, sequences from a Kharaghani paper could help, and SageMath might have relevant functions too.
Identifying base sequences to build Hadamard matrix
To create a Hadamard matrix of order 428, I think I can use base sequences of lengths 71 and 36, which combine to 107. Iāll look for Turyn-type sequences or T-sequences in accessible PDFs, potentially from open sources like arXiv. A useful file might be āH_428,ā so Iāll search for it.
Checking GitHub for Hadamard matrix at 428 order
I found a GitHub project, āanymatrix,ā which claims to have Hadamard matrices up to order 428. It might include the 428 matrix in MATLAB format. Iāll check the repository to see if it has the actual file with the matrix data. Letās open it and explore!
Opening GitHub repository for 428 Hadamard matrix
The page at math.ntua.gr timed out before, but I might try downloading the file directly instead of opening it. Alternatively, I could explore the GitHub āanymatrixā repository, which likely has Hadamard matrices up to order 428. Iāll open the repositoryās root to check its structure and find the matrix file.
Opening Hadamard folder
Iāll go ahead and open the Hadamard folder at link ID 81. Time to check whatās inside and see if the matrix or relevant files are there!
Trying GitHub raw content for Hadamard matrix
It looks like extracting the files might have failed because of JS requirements, so Iām considering an alternative: accessing raw content directly from GitHub. Iāll search the repository for relevant files containing the 428 matrix ā once I find out the exact file names, I can access them with no issue!
Trying direct access to Hadamard file
It seems the math.ntua listing might still be promising, with both text and zip formats for the Hadamard matrix. Iāll try opening the direct file URL instead of the page, hoping itāll avoid the timeout issues. Itās worth retrying, as the timeout could have been temporary. Letās try again!
Trying alternative ways to access Hadamard matrix
Since opening the math.ntua.gr server is
Checking old Hadamard links
The page seems to be from 2001, and it has a link to Neil Sloaneās library list, which might include the H428 matrix. However, the link for item 8 points to āwww.research.att.com ,ā which could have moved. Letās click and see if itās still accessible.
Trying alternative download for Hadamard matrix
The ATT site removed the old page, and Sloaneās library now points to a page that times out. Another option might be using Anymatrix, but GitHub listings arenāt working. Iāll try accessing the IPM website directly to download the matrix ā maybe the fileās URL works better with HTTP instead of HTTPS. Letās give it a try.
Searching for accessible Hadamard matrix
The page redirects to HTTPS and times out, which might indicate blocking. Maybe the matrix is hosted elsewhere, like in a plain text or PDF format. Iāll search for terms like āh428.txtā or āhadamard428.txtā on cs.uleth.ca ā thereās a mention of a PDF that could include it. Letās give that a try.
Opening ADTHM page for possible matrix
Iāve found a listing on cs.uleth, and thereās a link on the ADTHM page that might lead to the matrix in text format. It could be what Iām looking for, so Iāll go ahead and open the ADTHM page to check it out. Letās see if it includes the matrix!
Accessing matrix text through link
Awesome! I found a link labeled āEntries as textā (ID: 26). This could be the matrix in the text format Iām looking for. Iāll go ahead and click the link to download it. Letās see if this works!
Parsing the XPM image to a matrix
The H428.html contains XPM image data, not matrix entries. It seems to represent values with two colors, p and m, which likely stand for +1 and -1. I can map p to 1 and m to -1 (just to simplify things) and validate that the Hadamard property holds by checking H*H^T = 428I. Iāll fetch and parse the full content to confirm.
Downloading H428.html
Alright, Iāll use the container.download method to fetch the H428.html file. I previously opened the URL, so that should meet the requirement. Now, Iāll download the file directly to /mnt/data/H428.html and get the content I need. This should work smoothly and efficiently!
Understanding limitations for container.download
It seems the container.download method restricts us to file types other than text/html ā likely just images or data. Since I canāt use click or fetch via Python, Iāll need to rely on web.run for the content. However, the 200-word limit means we canāt fully retrieve the 428 lines. I may need to process it in parts.
Handling 200-line limits in tool response
Since the tool response gets cut off around 200 words, I canāt present more than that in the final output. However, I can strategically open various line ranges and parse those internal portions to reconstruct the full matrix. This should allow me to gather all the necessary data without breaking the word limits.
Handling file retrieval and parsing
To retrieve the full content, I can call the tool multiple times from different lines, reconstructing the file. However, retrieving 428 lines in total means a heavy operation, spread across several calls. Given the content-type restrictions, I can process the data using Python, but I need to work with a local file.
Figuring out how to retrieve and process data
To get more lines, I can use a tool to fetch a longer response, but thereās still a limit to the toolās output. Since the H428.html file is too large, I could check if thereās a plain text version like āH428.txtā in the directory that can be downloaded. Iāll also look for any relevant comments in the HTML.
Looking for matrix in different format
The file starts with ā/* XPM */,ā indicating itās actually plain text despite being labeled as HTML. I could try adding a download parameter or using a raw link, but the content type restriction remains. Next, Iāll check if thereās a plain text version of the matrix, like āH428.txtā in the directory.
Considering ways to fetch and process the file
Thereās no plain text, but the XPM format might be parseable. I could gradually access the file using the web tool, then reconstruct it with Python. One option is fetching parts with web tool, accumulating in Python, and then processing. I could work around content type restrictions with query parameters for text/plain.
Exploring options to access content
The H428.html doesnāt seem like real HTML. Maybe I can access it through a ?download=1 query or H428.xpm? I might also try the enlarge image link (id 25). If itās a GIF/PNG, I could download it and extract pixel values, though this might involve some image processing. Iāll check it out.
Downloading and inspecting image
The image is a PNG, so I can download it using the container. Iāll pull down H428_big.png and check the imageās pixel structure. Itās likely 856x856, possibly scaled at 2x, though the matrix should be 428x428. Iāll inspect the image further after downloading it.
Opening image for inspection
The file is small, just 5kb, which likely means itās compressed and may be a 428x428 image with a palette. Iāll go ahead and open the image to inspect it using the container, and then I can analyze the pixels to understand how itās structured further.
Processing image for matrix conversion
We have the image, so itās time to use Python to read it and convert the pixel colors into matrix entries. First, I need to check the imageās pixel dimensionsāmore likely it will be 428x428 or a multiple of that. Iāll use Python with PIL to open the image and confirm
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
God this is so funny. Heās so evasive about why exactly it is bad to be associated with Epstein. I just asked mummy and she said no.
āI donāt think doing that would have made me complicit. But, you know, it would have been very embarrassing for me.ā
Aw donāt worry I have no morals. But people would have been mean to me again!
ok ngl I didnāt actually read the article at first (can you blame me) but since you pointed that out, FUCK. Thatās so fucking pathetic. I was imagining a scenario where scott had met epstein IRL but had gotten ājockā vibes from him and decided not to associate based on that.
Followup on the Mass AI Bill, Russel has 180ād on it:
https://russwilcoxdata.substack.com/p/93a-the-three-characters-that-should
Buried in the penalty clause, the part of the bill that nobody reads, is a single reference: violations āshall be punishable in the same manner as provided in Chapter 93A of the General Laws.ā
For those outside Massachusetts: Chapter 93A is the stateās consumer protection statute. It is, by most accounts, the most aggressive consumer protection law in America.
Hereās what 93A unlocks. Anyone can sue, not just the government. Class actions are on the table. If the court finds a violation was willful or knowing, damages get tripled. And the bar for what counts as āunfair or deceptiveā is lower than in almost any other state.
Now bolt 93A onto all of that. What do you get?
You get a bill that doesnāt need a single regulator to lift a finger. You get a bill that funds its own enforcement through plaintiff attorneys who can file class actions, collect treble damages, and recover legal fees. You get the ADA website-accessibility litigation playbook, where lawyers systematically identify technical violations and file suits at scale, applied to every piece of AI-generated content touching Massachusetts.
Private right of action, fuck yeah. Turns grok into a legal fees dispenser.
The bill doesnāt need to be well-drafted to be dangerous. It needs to be vague, broad, and connected to 93A.
lol
Class action lawsuits by employees against employers that mandate AI tools when?
I fucking hope itās soon
Wow, thatās a sobering article.
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
https://www.wired.com/story/openai-fires-employee-insider-trading-polymarket-kalshi/
lol. Between this and the ayatollah clawback, Iām expecting some entertaining litigation.
new episode of odium symposium. itās a tribute to knowledge fight, in which we dissect an episode of nick fuentesās show. i was nervous about how this would turn out but i think itās actually my favorite episode yet.
https://www.patreon.com/posts/11-groyper-151852222 (links to other platforms at www.odiumsymposium.com)
God that was bleak - I thought Nick was bad in his guest spots on Alexās show (seen via Knowledge Fight, of course) but apparently you really do need at least two layers of insulating podcast to avoid suffering critical psychic damage from that level of hatred. I appreciated the acknowledgement that in order to feel at all okay playing clips you needed to sanewash him a little bit. Iām pretty sure that JorDan do the same thing with Alex and donāt acknowledge it nearly often enough.
I also feel like some of Nickās schtick is about trying to position himself and maintain his position in the right wing grifter bigot-industrial complex. Like, the open disdain for his audience and presenting his actually pretty straightforward feelings on the halftime show as somehow brave and iconoclastic is also about differentiating himself and making his audience feel superior to Alex, Tucker, Candace, etc. In that sense the open disdain for the audience serves another purpose in terms of reinforcing heirarchy. Look at how great it feels for me to be better than you. And even you are better than the chuds, who are better than the racialized other.
wrt to the first part, nick consistently outmaneuvers people who bring him onto their platforms. heās honestly brilliant at understanding who the audience is, what frame heās appearing in, and how to signal given those circumstances. i didnāt understand until i started prepping for this episode that nick is actually lazy and incurious in almost the exact same way alex jones is. dan and jordan notice and call out how he effortlessly establishes dominance over alex, but i think thereās a subtler game going on where nick manages to appear competent and informed compared to alex, and you donāt realize thatās just an artifact of conversational skill until you hear nick on his own show.
wrt to the second part, i could not agree more and iām very glad to hear that is a takeaway because it is absolutely something i was hoping to communicate. thatās the freudianness of it all, how these existing patterns of relations to another get played out and reenacted through the audienceās relationship to nick, and vice versa
The great chain of bleating
