Author: José de Jesús García Ruvalcaba
Date: 11:00:29 06/04/99
Go up one level in this thread
On June 03, 1999 at 19:56:00, Rob Shore wrote: >I agree that a true test of actual playing strength and knowledge would be to >eliminate the "book" factor. I suggest that a dozen or so unbalanced but >dynamically equal positions be used as a starting point for a match between >various programs. Each program could play both sides. While this test might not >say much about the true "rating" of the program, it would be another factor. >Might be real useful info for those postal players who "blunder check" their >moves !? I disagree that a test without book, or with a strange book, or from a given set of positions (like the Nunn test) measures playing strength. Those tests are interesting and fun, and can give the programmer useful information to improve the engine. But they do not measure overall playing strength. IMHO, they way to measure playing strength is test games from the initial position and using the opening book provided for the program. José.
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.