Author: Stuart Cracraft
Date: 13:49:56 12/20/05
Go up one level in this thread
On December 19, 2005 at 17:43:36, Stuart Cracraft wrote: >Has anyone taken Ryba on a Pentium 4 or some other well-known-cpu >and run it through any of the computer chess rating test suites? > >Stuart Brian Richardson has a version for Tinker that solved 100% of a popular problem suite but played horribly in regular game play. Brian says never optimize your program for problem suite play. His best versions do not solve 100%. I would enjoy people's comments as to why they think that is so that good game play does not equal good problem results. What possible explanation? Stuart
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.