Engine evaluation consistency/stability

Discussion of anything and everything relating to chess playing software and machines.

Moderators: hgm, Rebel, chrisw

User avatar
Laskos
Posts: 10948
Joined: Wed Jul 26, 2006 10:21 pm
Full name: Kai Laskos

Re: Engine evaluation consistency/stability

Post by Laskos »

Ovyron wrote: Thu Oct 10, 2019 4:15 pm
Laskos wrote: Thu Oct 10, 2019 11:26 am Hmmm, no word about Leela?
It is stable in both time (search) and along the PV, if there is not a lot of tactics.
Or one big tactic. But you never know, the analysis will become inconsistent once she sees it, so it's not stable.
A combination of AB for tactics and Leela ca be a robust tool, stable in PV on quiet positions and stable again in sticking to a tactical line.
Jouni
Posts: 3281
Joined: Wed Mar 08, 2006 8:15 pm

Re: Engine evaluation consistency/stability

Post by Jouni »

Is it 2020 already in Israel? We have still 2019 in Europe :) . Maybe we are long from solving chess: 1.g4 is losing opening move. But all engines I tried score it only around -1,5. They should score -100 or better still mate in -XXX.
Jouni
User avatar
Ovyron
Posts: 4556
Joined: Tue Jul 03, 2007 4:30 am

Re: Engine evaluation consistency/stability

Post by Ovyron »

Jouni wrote: Thu Oct 10, 2019 5:28 pm Is it 2020 already in Israel? We have still 2019 in Europe :) . Maybe we are long from solving chess: 1.g4 is losing opening move. But all engines I tried score it only around -1,5. They should score -100 or better still mate in -XXX.
1.g4 is a draw, what's your winning line?
Your beliefs create your reality, so be careful what you wish for.
Uri
Posts: 473
Joined: Thu Dec 27, 2007 9:34 pm

Re: Engine evaluation consistency/stability

Post by Uri »

In my opinion it will take at least another 2000 years until a computer will be playing at FIDE world champion level.