8 Comments
User's avatar
Chen's avatar

Great idea. ! is the code open source? is there a way other people can reproduce the same experiement? Thanks

Expand full comment
Chen's avatar

Thanks for generous sharing. and a lot of interesting ideas in the project. Also I like your testing with lichess puzzle to verify your thought. Out of curiosity, how do you prepare puzzleDB = '~/chess/resources/lichess_db_puzzle-10000.csv' ?

Expand full comment
Julian's avatar

These are the puzzles with more than 10,000 plays, I filtered them beforehand in order to have a smaller file to work with

Expand full comment
Anlam Kuyusu's avatar

Could this inspire a new kind of 'evaluation' puzzle?

Take a position with equal material for both sides. The evaluation is clearly better for one side at low and high depths. Ask the human puzzle solver to identify which side is better?

Maybe it'll be too easy? Plus guessing will be a thing.

Expand full comment
Chen's avatar

the puzzle file is not in the GitHub repo. Is it available in the internet ? Or I can download it from somewhere ? Thanks

Expand full comment
Julian's avatar

It's the Lichess puzzle database: https://database.lichess.org/#puzzles

Expand full comment
Nikodem's avatar

Nice idea. I wonder if an algorithm could make up new positions with tactics... efficiently.

Expand full comment