Author: Nouveau
Date: 05:03:03 10/21/98
Go up one level in this thread
On October 21, 1998 at 05:22:07, blass uri wrote: > >On October 21, 1998 at 04:43:02, Nouveau wrote: > >> >>On October 20, 1998 at 11:45:57, blass uri wrote: >> >>> >>>On October 20, 1998 at 10:37:36, Nouveau wrote: >>> >>>> >>>> >>>>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 >> >>Say a 40 games match between GM X and GM Y with the result : >>X-Y = 24-16. >>Is it false to say : X IS stronger then Y ? > >If there were 24 wins and 16 losses then I am not sure if X is stronger than Y >If there were 8 wins and 32 draws then I think we can say X is stronger than Y Between two GMs 24 wins and 16 losses would be suspicious, wouldn't they ? But I think we agree : let's forget a litlle bit about the stats and have a look at the games ! Jeff > >Uri >> >>Jeff >> >>> >>>Uri >>>> >>>>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.