Author: Dann Corbit
Date: 12:10:48 06/03/04
Go up one level in this thread
On June 03, 2004 at 15:05:49, Andrei P wrote: >On June 03, 2004 at 14:46:18, Dann Corbit wrote: > >>On June 03, 2004 at 14:36:25, Andrei P wrote: >> >>>on a related note, are there any tactical chess problems that were tested on >>>GMs? I am curious how well the engines will solve them. I keep hearing >>>statements that the top engines are 3000 elo tactically, but have never seen any >>>human calibration data. >> >>Pretty much every tactical suite was invented by GMs and then we use computers >>to try to replicate the results obtained by the humans. Most test suites have a >>few small flaws in them. > >If the positions come from GM games, it does not mean that they are of >GM-difficulty. For example, in a recent Leko-Kramnik game Leko essentially >blundered and gave Kramnik the opportunity to apply tactics. >http://chessbase.com/newsdetail.asp?newsid=1512 > >Does it mean that the position after 32.Rd7?? is of 2700+ difficulty? of course >- not, one needs to test the positions like that on a pool of GMs to determine >its difficulty. The test suites usually come from books. WAC is from "Win At Chess", for instance.
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.