Aligning Superhuman AI with Human Behavior: Chess as a Model System · HackerPapers discussions

Aligning Superhuman AI with Human Behavior: Chess as a Model System — mentioned by janalsncm

Tue, 02 Sep 2025 18:52:23 GMT

https://arxiv.org/pdf/2006.01855 If you check figure 4, SF at depth 15 matches about 47% of the time which is lower than their NN. So quantitatively, SF isn’t amazing at move matching, and lower than the best NN at its relevant rating range (1900 -> 54%). Qualitatively, SF is pretty unsatisfying as a model of a pro human because a lot of its moves are counterintuitive.

Paper and discussion history. A mention is not an endorsement.

Aligning Superhuman AI with Human Behavior: Chess as a Model System — HN submission

Thu, 09 Feb 2023 03:34:24 GMT

Aligning Superhuman AI with Human Behavior: Chess as a Model System (2020)

2 points; 0 discussion replies on HN. Paper and source history. A submission is not an endorsement.

Aligning Superhuman AI with Human Behavior: Chess as a Model System — mentioned by lairv

Wed, 23 Nov 2022 15:12:47 GMT

Wow I played a single game but the prediction was very good, it predicted 1636 on lichess while my best elo was ~1600 (though I haven't played for about a year) But what's even more impressive is that the game felt great to play, I didn't get this feeling that the AI would pick on every of my smallest mistakes like you have with Stockfish. I know there has been several research work [0,1] recently to improve the human-ness of chess AIs, but it's even more impressive that you are able to do it "online", in the course of a single game, bravo. I'd be interested in a blog post with details on the…

Paper and discussion history. A mention is not an endorsement.

Aligning Superhuman AI with Human Behavior: Chess as a Model System — HN submission

Fri, 12 Feb 2021 17:42:15 GMT

Aligning Superhuman AI with Human Behavior: Chess as a Model System

1 point; 0 discussion replies on HN. Paper and source history. A submission is not an endorsement.

Aligning Superhuman AI with Human Behavior: Chess as a Model System — mentioned by lrossi

Sun, 17 Jan 2021 15:08:14 GMT

Paper: https://arxiv.org/pdf/2006.01855.pdf

Paper and discussion history. A mention is not an endorsement.

Aligning Superhuman AI with Human Behavior: Chess as a Model System — mentioned by Imnimo

Wed, 23 Dec 2020 20:04:16 GMT

It turns out that taking a superhuman player and making it play like a weak human is surprisingly tricky. It's not so hard to make a weak player - you just take suboptimal moves instead of the best moves. But often these suboptimal moves are bizarre. A weak human chess player will lose their pieces as they fall prey to forks and skewers and so on - tricks that are hard to see coming for new player. But they will rarely actively throw a piece away by moving it into danger. Even a novice human is pretty decent at looking one move ahead. But to a chess engine, or an MuZero agent, a move that…

Paper and discussion history. A mention is not an endorsement.

Aligning Superhuman AI with Human Behavior: Chess as a Model System — mentioned by reidmcy

Tue, 01 Dec 2020 19:12:19 GMT

Hi everyone, We're happy to announce a research project that has been in the works for almost two years! Please meet Maia, a human-like neural network chess engine. Maia is a Leela-style framework that learns from human play instead of self-play, with the goal of making human-like moves instead of optimal moves. Maia predicts the exact moves humans play in real online games over 50% of the time. We intend Maia to power data-driven learning tools and teaching aids, as well as be a fun sparring partner to play against. We trained 9 different versions on 12M Lichess games each, one for each…

Paper and discussion history. A mention is not an endorsement.