It struggles a little with complex positions, like when there are an even number of moves and it has to round down, but when run against itself it’s capable of finding some novelties. At one point I saw six knights on the board at once; Stockfish rarely exceeds four.
For the curious: lichess.org/editor/r1b1k2r/…/RNBQ1BNR_b_kq_-_0_1?…
feedum_sneedson@lemmy.world 1 year ago
Don’t get it, at all.
zabadoh@ani.social 1 year ago
The writer played multiple games of chess against some conventional chess programs or AIs, and used a simplified algorithm to determine their own moves:
For each move:
This algorithm for choosing chess moves did not result in optimal play, and lost against the standard chess programs/AIs.
The illustrated position has the algorithm generating a blunder or useless move (Ne2) that allows a checkmate victory for Black with the following move (… b4++), i.e. “Black Bishop moves to b4, checkmate”
The writer named their algorithm “AlphaMove” as a take on Google’s famous chess playing AI from 2017 named “AlphaZero”.
Except in the writer’s case, the “Alpha” in their algorithm’s name is short for “alphabetic”, which makes the expanded name “Alphabetic(-sort)Move”.
feedum_sneedson@lemmy.world 1 year ago
Honestly, I understood that much, but I still don’t get it.