Hacker Newsnew | past | comments | ask | show | jobs | submitlogin

This ignores the question how hard it is for a human to find the best (or a "good enough") move. It's easy to find games with 10 "only move" 's in a row where even a beginner could easily have played all if them.


Sure, but it's a start on adding nuance to eval beyond minmax


Is it? TBH it sounds like "climbing a tree is a start on getting to the moon beyond just jumping up and down". Yes, it does "more". But whether it will actually get you to the desired end state is highly dubious. Nobody knows if that will make chess bots more human-like, despite decades of research into the topic.


This is about eval nuance, not how bots play

Bots playing like humans is done by training them to play like humans: https://lichess.org/@/lichess/blog/introducing-maia-a-human-...




Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: