Author: Ratko V Tomic
Date: 10:46:35 01/12/01
Go up one level in this thread
> They _still_ have a lot of weaknesses. If Van der Wiel (or any GM) were to play 50 or 100 games against the program, these would become quite obvious and program would start losing badly. Even much weaker players, like myself (around 2100 USCF from early 1980s), after playing daily for a few weeks with a program improve score substantially. This is a similar type of novelty spike effect that many new programs show, and then few months later the competing programmers figure out the new tricks and level the playing field again. The strenghts 2400-2450 you mentioned seem to be this asymptotic value (or its upper bounds). That's where the program's performance would converge over a longer time, well after the novelty spike effect wears off.
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.