Author: James T. Walker
Date: 14:58:52 12/14/02
Go up one level in this thread
On December 14, 2002 at 15:01:28, Uri Blass wrote: >On December 14, 2002 at 13:33:18, James T. Walker wrote: > >>On December 14, 2002 at 12:15:18, Uri Blass wrote: >> >>>This position is from the ssdf games >>> >>>[D]7R/2r5/1p5K/1p3B2/6P1/1p6/8/2k5 b - - 0 115 >>> >>>Tiger15 played b2 with evaluation of 0.00 in the ssdf games when only material >>>evaluation can tell us that black is losing. >>> >>>other programs that I tried can understand at least that white is better. >>> >>>Uri >> >>It seems silly to me to pick one position and point out that the engines score >>does not seem perfect. There are millions of these positions for every program. > >I think that this information can reveal important details about weakness of the >program. > >I also saw in the past a case when Tiger overevaluated supported passed pawns >in a queen endgame. >I believe that one of tiger's weaknesses is overevaluating passed pawns in the >7th. > >It seems to imagine that they are promoted if there is a threat to promote them >in the next move and it seems wrong. > >Uri Thank you for your explanation Uri. Your point is valid of course. Jim
This page took 0 seconds to execute
Last modified: Thu, 15 Apr 21 08:11:13 -0700
Current Computer Chess Club Forums at Talkchess. This site by Sean Mintz.