Author: Dann Corbit
Date: 10:05:03 07/26/00
Go up one level in this thread
On July 26, 2000 at 12:49:31, Walter Koroljow wrote: >It is possible to infer something quantitative from the data that Chris has >accumulated. Based on some plausible assumptions I make the following claim: > >******************************************************* >***Claim: Chris Carsons' data implies that some program has a rating of 2496 or >more with approximately a 95% confidence.*** >******************************************************* Excellent analysis and I think we must accept 2496 as a provisional rating for some program, because of the reasonable degree of certainty. I suspect that GM's might "catch on" and the rating could drop. On the other hand, programmers might find simple solutions to the remaining problems and begin to crush the GM's. But for now, that is probably a very good measure.
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.