Post #1490325

2026-03-06 05:12 UTC

@behdad @khaled Finally, if this technology is good for Linus, Guido, and Knuth, among others, I'm not gonna ignore it and let my projects and skills become irrelevant and obsolete. Unrelated to the responses you've received so far, I'll just say that appeal to authority isn't really a good thing. Linus and Guido and Knuth will probably make different choices about their tools and workflow than other people and just because they use something, it's not a strong, or even considerable, reason to use it. I remember reading that Linus uses a personal fork of the mg text editor but that fact makes no case for me to try using uemacs, at all. I also read on @lwn that Linus doesn't really write any code these days but does merge around 12,000 commits in a merge window, including resolving any conflicts that arise during the process. Meanwhile, Greg KH seems to be firmly against using LLMs. If I started judging Linus superficially, I wouldn't consider what he would say about writing code. Ultimately, the message matters more than the person writing it.

Replies (1)

@ayushnix@social.ayushnix.com 2026-03-06 06:39

@behdad @khaled In addition, this comment is just as much a reference for myself as it is a reply. I read the Claude's Cycles PDF written by Knuth. Knuth had already solved the exercise he was working on, himself, and was interested in a generalization of the answer he got for other values. His friend, Filip, gave the question to Claude without bothering to solve it himself? Or maybe he did bother and solved 4 ≤ m ≤ 16 himself, it's not really clear from the PDF. After 30 different explorations, Claude came up short. In the 31st exploration, Claude produced results. Knuth still needed proof and it's not clear if he wrote the proof himself but he doesn't mention using Claude for writing the proof that he did. He then goes on to say Filip told me that the explorations reported above, though ultimately successful, weren’t really smooth. He had to do some restarts when Claude stopped on random errors; then some of the previous search results were lost. After every two or three test programs were run, he had to remind Claude again and again that it was supposed to document its progress carefully. So I don't see how that PDF leads to the conclusion that "if it's good enough for Knuth, it's good enough for me". He's impressed with the results, sure, but it seems like he didn't even use Claude himself? His friends did and they had to repeatedly nudge it to steer it in the correct direction. Regardless of what I said in this comment and the results of the exploration from Knuth's friends, appeal to authority leaves a bad impression.

Open ##1490326