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.)


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 ±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