Author: Andrei P
Date: 16:42:48 06/03/04
Go up one level in this thread
I guess I need re-phrase the question. What is the numerical (elo) evidence that the top engines play at 3000 elo tactically. If one makes a test suite of purely tactical problems and demonstrates that a typical GM solves only 50% while an engine solves >90%, then it would be a valid claim. Has this kind of experiment ever been documented? in fact it would cost only 1000-2000$ to have a few GMs solve some combos for a few hours. I wish I had this kind of money sitting around :) >>>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.
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.