Author: Bob Durrett
Date: 12:13:21 12/03/02
Go up one level in this thread
On December 03, 2002 at 13:41:24, Uri Blass wrote: <snip> >positional test suites should not be always positions that are hard for humans >and they may include also positions that are easy for humans but hard for part >of the computers. > > >A possible way to build them may be to analyze a lot of games of computers from >the ssdf games and find the positional mistakes that were done by the programs >and the target can be to avoid the mistakes. I really like this idea!!!!!!!! It is very similar to what I am doing with my games, and that is working out very well for me. After post-mortem analyses, I identify several positions which I failed to solve in the game. They are characterized by a marked change in the position evaluation score before and after my weak move. I print out the games with the positions printed. Later I study those positions carefully and often. Because I am a chess amateur who has not played games in many years, most [but not all] of my mistakes are tactical. You might say I'm "rusty." [Like an old plow which has been sitting out in the rain for several years.] It seems reasonable to assume that all of the programmers analyze their games exhaustively after each tournament. But they perhaps do not publish their findings. To extend what Uri has said, let me suggest that everybody here *continue* to be on the lookout for positions, from computer vs computer tournaments, where post-mortem analysis shows that a chess engine failed to solve the problems of the position. I believe this is already being done, although maybe not specifically to identify positions where engines failed to solve the *positional* problems. Perhaps each engine programmer could submit a "positional" test position to this forum where his/her engine failed to solve the position in a major recent tournament. It should be a position which is difficult for many different chess engines, if possible. Bob D. <snip>> >Uri
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.