Author: Nouveau
Date: 02:00:33 10/21/98
Go up one level in this thread
On October 21, 1998 at 03:16:39, Dann Corbit wrote: >On October 20, 1998 at 11:45:57, blass uri wrote: >[snip] >>>Why do we need hundreds, maybe thousands of games between computers to evaluate >>>relative strength, when few dozens are more than needed for human GMs ? >> >>I do not think that few dozens are more than needed for human GMs >Indeed, to become a GM a huge number of games must be played. Can anyone >demonstrate a player given a GM title with only 'a few dozens' of games? We must separate things : a chess program is born with a level, once you have it on your harddisk, it won't make any progress (beside learning functions), so it has a level that won't move (as Amir said). A human needs experience, learning and work to reach this level, but once he HAS this level he doesn't need a huge number of games to prove it. Jeff
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.