[y-curious]

I'm a big chess buff, and will say that the hard part is not making an engine (which is hard!), but making an engine that plays poorly, well. What I mean is: engines are very smart and better than the best human. When you make a "dumb" engine, you are telling a chess god to intentionally make mistakes. The mistakes they make, however, are not the same mistakes a beginner chess player would make. Today, beginners are discouraged from learning by playing against bots because of this; It simply doesn't serve you in human games.

Lichess has a "humanlike" bot[1] but I haven't played with it yet. I think this problem will haunt you, if you get past the whole "create a chess engine" problem :) I have tried and failed to do this in the past.

[1] https://lichess.org/@/maia1

[djfergus]

Check out chessiverse (I’m not affiliated just found from YouTubers). They purport to be a collection of bots that play like humans with human-like mistakes matched to ELO levels. I like it so far - the main value for me (vs lichess/chess.com) is knowing that who’s on the other end isn’t constantly cheating.

[ema]

I always assumed that chess engines are dumbed down by occasionally inserting random moves but now it occurred to me that a way to get more realistic mistakes might be feed them a distorted version of the game state.