https://inv.nadeko.net/j_0lQUIT8yY?__goaway_challenge=js-refresh&__goaway_id=fccb605869aae189cec04e6f5cef4829&__goaway_referer=https%3A%2F%2Finv.nadeko.net%2F&listen=false
I've read a couple of breathless articles about Donald #Knuth's use of #LLM systems, and found (unsurprisingly) that he has a paper about it, if you prefer your news without someone else's hot takes:
https://www-cs-faculty.stanford.edu/~knuth/papers/claude-cycles.pdf
(Sidebar: apparently he's working on *another* volume of #TAOCP? Good lord. I still haven't worked through the exercises in Vol. 1.)
Further human + AI + proof assistant work on Knuth's "Claude Cycles" problem
https://twitter.com/BoWang87/status/2037648937453232504
#HackerNews #Further #human #AI #proof #assistant #Knuth #Claude #Cycles

Three weeks ago I shared that Claude had shocked Prof. Donald Knuth by finding an odd-m construction for his open Hamiltonian decomposition problem in about an hour of guided exploration. Prof. Knuth titled the paper Claude’s Cycles. The story didn't end there. The updated
Knuth's merge-sort in C. Definitely in the style of mathematician programming.
"Shock! Shock! I learned yesterday that an open problem I’d been working on for several weeks had just been solved by #Claude Opus 4.6 [..]
It seems that I’ll have to revise my opinions about “generative #AI” one of these days.",
Donald #Knuth (2026-03-02)
https://www-cs-faculty.stanford.edu/~knuth/papers/claude-cycles.pdf