Author: Enrique Irazoqui
Date: 12:26:43 07/28/00
Go up one level in this thread
On July 28, 2000 at 14:38:04, Dann Corbit wrote: >On July 28, 2000 at 07:55:55, Chris Carson wrote: > >>Nice work. I had not done this for a while. >>This seems to fit with what a lot of other people >>have recommended in the past. SSDF is looking into >>this, I think they have done a great job. > >A real solution to the problem would be to pay ten GM's to play ten matches of >ten games each against the top ten programs. One thousand games provided in >this way would be a real way to measure the true strength of chess programs. > >No other way is effective. And this way is not feasible, so it's not effective either. Besides, it would give at best a new global calibration, but wouldn't tell us in the future if ratings based on comp-comp are also valid for human-comp. Are they? The anti-computer games of Frankfurt and Dortmund wouldn't have been helped by a faster search, so decisive in comp-comp; if machines are allowed in human events, players will be less naive than now and play more anti-computer, with an effect on ratings that won't be reflected by comp-comp lists. Think negative! :) Enrique
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.