Author: Aaron Tay
Date: 23:39:32 03/06/01
Go up one level in this thread
On March 06, 2001 at 17:05:25, Thorsten Czub wrote: >classical problem: > >if they really run their basement tournament with ots of games and only ONE version of the program the programmer has a new version and the results generated by the guy ur not helpful anymore. nobody knows if the pattern the guy has outplayed for the old engine is also working for the new one. >this is catch 22 or quantum-problem: in the moment you measure direction of a >particle you change speed, and then you cannot know about speed. >in the moment you measure speed you change direction. >you canot know speed AND direction. >same with programs. >if you test too long, the programmer has a newer version and often cannot >use your "results". <snip> Interesting analogy, but I don't it applies. You can still continue to test with the old version , it doesn't suddenly disappear and get replaced with the new version as you begin to close in on it's "true" strength. But I agree, you could be 100%(or as close to it as possible given the number of games) right, but yet produce no useful [??] information if the engine has a silly bug that causes it to say resign whenever it was winning every game! On the other hand, mixing the two versions again, means that you won't be 100% right, accurate, but will the information be more useful?
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.