There was a fascinating post by Kai Laskos from November of 2012 called "10 years of Computer Chess" in which he took the top engine of the day, Houdini 3, and pitted it against the top engine from 10 years before that, Shredder 7.04. At a time control of 1'1" the score was a stunning 99.5 to 0.5. Even playing 200 more games, this win rate held up. Someone on the original discussion thread (Vinvin) said "I hope the trend will continue for the next 10 years ". I was so intrigued by this comment that I made a note to check again in 10 years. Well ... here we are almost 10 years later! I'm wondering if Kai or others would like to repeat this experiment sometime this year to see how the current top engines stack up.
Original thread (though somewhat damaged by time):
modolief wrote: ↑Mon Feb 07, 2022 12:25 am
if Kai or others would like to repeat this experiment sometime this year to see how the current top engines stack up.
I find this 2012 comment from Kai Laskos quite interesting:
Observing the games, Houdini outplays Shredder in the opening, if not finished, in the middlegame, and if not finished, then surely in the endgame. Tremendous achievement in these less than 10 years.
How to describe today's top engine victories over Houdini 3 in a similar match?
Stockfish was on version 2 or 3 I think 10 years ago. So that was already a respectable engine, but the advances in 10 years are very considerable. The recent improvements due to NNUE alone are probably worth 200 rating points or so, and of course there has been other progress in the past 10 years.
jdart wrote: ↑Tue Feb 08, 2022 6:39 pm
Stockfish was on version 2 or 3 I think 10 years ago. So that was already a respectable engine, but the advances in 10 years are very considerable. The recent improvements due to NNUE alone are probably worth 200 rating points or so, and of course there has been other progress in the past 10 years.
". I was so intrigued by this comment that I made a note to check again in 10 years. Well ... here we are almost 10 years later! I'm wondering if Kai or others would like to repeat this experiment sometime this year to see how the current top engines stack up.