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 (like the author) 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.

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:

Warning: very long slop

Exploring Hadamard matrix construction for order 428 For a Hadamard matrix of order 428, we need to confirm that it’s a multiple of 4, which it is (428 = 4 * 107). However, the challenge is that order 107 doesn’t work since it’s 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 ≡ 3 mod 4, Paley type I gives a Hadamard of order 108, but I need 428, not 432. That’s a little tricky. I wonder if there’s a known construction for order 4107 using “Hadamard matrix of order 4q” 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 doesn’t work since q ≡ 3 mod 4. But if I can create a conference matrix of order 214 (since 214 ≡ 2 mod 4), then a Hadamard matrix of order 428 would follow. Conference matrices require specific conditions, but this seems promising. Let’s 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 ±1 entries. A direct construction could involve methods like Goethals-Seidel, which uses circulant matrices to satisfy specific conditions. I’ll 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. I’ll 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 I’ll need to try other sources like GitHub, arXiv, or design theory papers. We could construct the Hadamard matrix ourselves using known algorithms, but it’s 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. I’ll look for Turyn-type sequences or T-sequences in accessible PDFs, potentially from open sources like arXiv. A useful file might be “H_428,” so I’ll search for it. Checking GitHub for Hadamard matrix at 428 order I found a GitHub project, “anymatrix,” which claims to have Hadamard matrices up to order 428. It might include the 428 matrix in MATLAB format. I’ll check the repository to see if it has the actual file with the matrix data. Let’s 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 “anymatrix” repository, which likely has Hadamard matrices up to order 428. I’ll open the repository’s root to check its structure and find the matrix file. Opening Hadamard folder I’ll go ahead and open the Hadamard folder at link ID 81. Time to check what’s 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 I’m considering an alternative: accessing raw content directly from GitHub. I’ll search the repository for relevant files containing the 428 matrix — 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. I’ll try opening the direct file URL instead of the page, hoping it’ll avoid the timeout issues. It’s worth retrying, as the timeout could have been temporary. Let’s 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 Sloane’s library list, which might include the H428 matrix. However, the link for item 8 points to “www.research.att.com ,” which could have moved. Let’s click and see if it’s still accessible. Trying alternative download for Hadamard matrix The ATT site removed the old page, and Sloane’s library now points to a page that times out. Another option might be using Anymatrix, but GitHub listings aren’t working. I’ll try accessing the IPM website directly to download the matrix — maybe the file’s URL works better with HTTP instead of HTTPS. Let’s 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. I’ll search for terms like “h428.txt” or “hadamard428.txt” on cs.uleth.ca — there’s a mention of a PDF that could include it. Let’s give that a try. Opening ADTHM page for possible matrix I’ve found a listing on cs.uleth, and there’s a link on the ADTHM page that might lead to the matrix in text format. It could be what I’m looking for, so I’ll go ahead and open the ADTHM page to check it out. Let’s see if it includes the matrix! Accessing matrix text through link Awesome! I found a link labeled “Entries as text” (ID: 26). This could be the matrix in the text format I’m looking for. I’ll go ahead and click the link to download it. Let’s 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 HH^T = 428I. I’ll fetch and parse the full content to confirm. Downloading H428.html Alright, I’ll use the container.download method to fetch the H428.html file. I previously opened the URL, so that should meet the requirement. Now, I’ll 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 — likely just images or data. Since I can’t use click or fetch via Python, I’ll need to rely on web.run for the content. However, the 200-word limit means we can’t 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 can’t 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 there’s still a limit to the tool’s output. Since the H428.html file is too large, I could check if there’s a plain text version like “H428.txt” in the directory that can be downloaded. I’ll also look for any relevant comments in the HTML. Looking for matrix in different format The file starts with “/* XPM */,” indicating it’s 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, I’ll check if there’s a plain text version of the matrix, like “H428.txt” in the directory. Considering ways to fetch and process the file There’s 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 doesn’t 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 it’s a GIF/PNG, I could download it and extract pixel values, though this might involve some image processing. I’ll check it out. Downloading and inspecting image The image is a PNG, so I can download it using the container. I’ll pull down H428_big.png and check the image’s pixel structure. It’s likely 856x856, possibly scaled at 2x, though the matrix should be 428x428. I’ll inspect the image further after downloading it. Opening image for inspection The file is small, just 5kb, which likely means it’s compressed and may be a 428x428 image with a palette. I’ll go ahead and open the image to inspect it using the container, and then I can analyze the pixels to understand how it’s structured further. Processing image for matrix conversion We have the image, so it’s time to use Python to read it and convert the pixel colors into matrix entries. First, I need to check the image’s pixel dimensions—more likely it will be 428x428 or a multiple of that. I’ll use Python with PIL to open the image and confirm

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 “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.

Hey, you’re selling them short: there are also ReLU and softmax activation functions thrown around here and there. Clankers aren’t just linear transformations!

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. It’s 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: “Within this object X of size m, find any example of Y.” 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 “random bullshit go”: 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.

It’s 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 “random bullshit go” is served well by a random bullshit machine, but you still need an expert who actually understands the problem to evaluate if you got something useful. Knuth’s narrative is not very transparent about how much Filip handheld for the AI as well.

I can understand why so many people in math/CS research are receptive to this stuff right now. Undecided researchers generally try to see the positives in new things, and AI has gotten very good at superficially impressive performances. They also assume good faith, which is easily exploitable by AI boosters who realize that they can just say things and have people believe them. In comparison, I have been paying an unusual amount of attention to this stuff: I’ve seen how deceptive and immoral the AI companies are. I’ve seen the exact same story play out in software engineering where many people were dazzled into accepting AI uncritically, and the result is far more broken, insecure software.

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.

scott jumpscare