Author: GuyHaworth
Date: 14:55:39 08/01/02
Go up one level in this thread
Good information in the answers, illuminating some of the issues. Thanks. First, my focus is on 'rating' chess-engines on the basis of play against solely human opponents under controlled conditions. As VD says, FIDE defines the conditions it requires for the awarding of norms. Other conditions might be attached to the fact that the chess-player is silicon rather than carbon, e.g. the configuration of the engine in all essential parameters must be logged and maybe 'mothballed' for later replication. I was not suggesting that humans should be rated against computers 'with a FIDE rating'. There is still the question of replicating the engine that got the rating, as VD's scenario about powersaving/small_hash_table/etc/etc engines illustrates. It seems that HIARCS missed out by 0.5 points, though the other criteria were arguably met. There have certainly been cases of engines achieving norms (in principle) in the past, e.g. BELLE (UKCF Chess Master?), DEEP THOUGHT, DEEP JUNIOR, <your nomination goes here> g
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.