Improving Chess Commentaries by Combining Language Models with Symbolic Reasoning Engines — mentioned by robrenaud

Fri, 15 Mar 2024 19:50:43 GMT

Only tangentially related, but I think the mid/late game is a much more interesting/useful/hard avenue for chess tools. Chess.com's opening explorer is pretty good, which it seems like this is kind of trying to compete against. What I struggle with is the post game review, where I make a dubious move but I don't actually understand the reason why it's bad. Sure, the engine shows better moves and the refutation to my move, but I often don't know why. The automatically generated explanation is usually pretty poor. I wish I had even a poor copy of Danya giving me commentary. Perhaps I should…

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

Improving Chess Commentaries by Combining Language Models with Symbolic Reasoning Engines — HN submission

Mon, 19 Dec 2022 21:20:44 GMT

Improving Chess Commentaries by Combining [LLMs] with Symbolic Reasoning Engines

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

Improving Chess Commentaries by Combining Language Models with Symbolic Reasoning Engines · HackerPapers discussions

Improving Chess Commentaries by Combining Language Models with Symbolic Reasoning Engines — mentioned by robrenaud

Improving Chess Commentaries by Combining Language Models with Symbolic Reasoning Engines — HN submission