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 you’ll 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 cut’n’paste it into its own post — there’s no quota for posting and the bar really isn’t that high.
The post Xitter web has spawned so many “esoteric” right wing freaks, but there’s no appropriate sneer-space for them. I’m talking redscare-ish, reality challenged “culture critics” who write about everything but understand nothing. I’m talking about reply-guys who make the same 6 tweets about the same 3 subjects. They’re inescapable at this point, yet I don’t see them mocked (as much as they should be)
Like, there was one dude a while back who insisted that women couldn’t be surgeons because they didn’t believe in the moon or in stars? I think each and every one of these guys is uniquely fucked up and if I can’t 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 “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.
I can’t see the “reasoning” trace in the link. Do you need to be logged in?
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 4*107 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 H*H^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
We really need to work harder at poisoning the training data for math problems.