Author: Jouni Uski
Date: 02:35:26 02/12/99
Go up one level in this thread
On February 11, 1999 at 19:12:04, William H Rogers wrote: >You make a good point there, in fact Larry Kaughman (?) published a set of >problems in his Computer Chess Reports a few years ago. He had about 30 problems >and a formula for calculating a chess programs stregth, based upon the lenght of >time it took to find the solution. >He stated that he had tested the results, and they were very close. >So it can and does work. >Bill With 30 positions? Not possible! After 15 years in computer chess I think it's impossible to measure strength by testpositions. One good example: Phalanx solves testpositions about 10x faster than Crafty, but still loses about every game in actual play!!
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.