Top all-time · #6807
Mathieu Acher
Personal blog · blog.mathieuacher.comaiprogramming
Mathieu Acher's personal blog at blog.mathieuacher.com covers ai and programming. Since 2023, 12 different Hacker News readers have linked it 15 times, most often “Confronting GPTs Against Chess Engines to Estimate Elo and Legal Move Abilities”. It is still writing: the last post was on 2026-09-22, and you can follow it by feed.
Too few sampled comments (6) to say how often HN recommends it.?
Why HN links it
HN commenters link this blog as a source for experiments testing LLMs on chess, including GPT-3.5-turbo-instruct's Elo and illegal-move rates, and for Linus Torvalds' views on LLMs. None praise the writing.
Summarised by Claude from a sample of 6 HN comments that link here. Each comment is marked recommending, critical or neutral (citing without judging); how this works.
Professor in Computer Science
Most-linked posts?
- Confronting GPTs Against Chess Engines to Estimate Elo and Legal Move Abilities5 people · 5 mentions · first linked 2023-10-18
- Linus Torvalds on LLMs and other topics3 people · 3 mentions · first linked 2024-01-21
- Coding agents wrote a chess engine in pure TeX2 people · 3 mentions · first linked 2026-02-27
- BFChess: A Chess Engine in Brainfuck2 people · 2 mentions · first linked 2026-03-24
What Hacker News says?
Nice project! Are you aware of the following investigations: https://blog.mathieuacher.com/GPTsChessEloRatingLegalMoves/ Some have been able to achieve greater elo with a different prompt based on the pgn format. gpt-3.5-turbo-instruct was able to reach an elo of ~1750.
Comment linking /GPTsChessEloRatingLegalMoves/
on “GPT-4o”Submitted Linus Torvalds on LLMs and other topics as a story · 52 points
HN discussionBut in that case there shouldn't be any invalid moves, ever. Another tester found gpt-3.5-turbo-instruct to be suggesting at least one illegal move in 16% of the games (source: https://blog.mathieuacher.com/GPTsChessEloRatingLegalMoves/ )
Comment linking /GPTsChessEloRatingLegalMoves/
on “Something weird is happening with LLMs and chess”Submitted BFChess: A Chess Engine in Brainfuck as a story · 2 points
HN discussionI found a related set of experiments that include gpt-3.5-turbo-instruct, gpt-3.5-turbo and gpt-4. Same surprising conclusion: gpt-3.5-turbo-instruct is much better at chess. https://blog.mathieuacher.com/GPTsChessEloRatingLegalMoves/
Comment linking /GPTsChessEloRatingLegalMoves/
on “Something weird is happening with LLMs and chess”Submitted Coding agents wrote a chess engine in pure TeX as a story · 2 points
HN discussionNot really. https://blog.mathieuacher.com/LinusTorvaldsLLM/
Comment linking /LinusTorvaldsLLM/
on “An Overwhelmingly Negative and Demoralizing Force”Submitted Agents Build Chess Engines from Scratch in Rust, C++, Rocq, LaTeX, Brainfuck as a story · 1 points
HN discussionEver since I started doing this exercise, I've been excited about the future, with LLMs helping us. Now I definitely share Linus' sentiment [1] on this topic. It would be incredible to feed an A.I. some code and request a bug tracking from it. [1]: https://blog.mathieuacher.com/LinusTorvaldsLLM/
Comment linking /LinusTorvaldsLLM/
on “DeepSeek Coder: Let the Code Write Itself”Submitted Coding Agents Wrote a Chess Engine in Pure TeX as a story · 1 points
HN discussionTitle edited for length from "Coding Agents Build Chess Engines From Scratch in Rust, C++, COBOL, Rocq, LaTeX, Brainfuck, and More" He also has dedicated entries on two very special case, the engine running within pdflatex https://blog.mathieuacher.com/TeXCCChessEngine/ and the one in Brainfuck https://blog.mathieuacher.com/BFChessChessEngineBrainfuck/ which are seemingly the first of their kind.
Comment linking /BFChessChessEngineBrainfuck/
on “Agents Build Chess Engines from Scratch in Rust, C++, Rocq, LaTeX, Brainfuck”Submitted Coding Agents Wrote a Chess Engine in Pure TeX as a story · 1 points
HN discussionSubmitted Debunking the Chessboard: Confronting GPTs Against Chess Engines as a story · 1 points
HN discussionSubmitted Confronting GPTs Against Chess Engines to Estimate Elo and Legal Move Abilities as a story · 1 points
HN discussion
