Author: Dann Corbit
Date: 23:26:05 09/23/99
Go up one level in this thread
On September 23, 1999 at 17:04:32, will smtih wrote: [snip] > So basically you are saying that the SSdf list is inflated? What is your >estimation of the extent of the inflation, and could you give the reasons why >you believe so, based on your own personal testing? Do your master friends for >instance beat Fritz5 repeateadly to make you believe it is not really 2500? The programs have these ratings relative to each other and under the conditions of the test. Against humans, we have very little idea because we have very little data. For the stated conditions the ratings are accurate and mathematically sound. If you change the mode of play, or change the opponent pool, all bets are off.
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.