Author: Jeremiah Penery
Date: 18:26:09 07/26/00
Go up one level in this thread
On July 26, 2000 at 15:27:36, Chris Carson wrote: >Just goes to show how much better the micro eval and search >algorithms are. :) TPR's speak for them selves. 96 DB >has fallen. :) >Oh, try not to get to mad, but what position did HSU use to get >the NPS number, not that it matters for actual performance (we have >the TPR for that), but I would like to know? As I've tried to point out several times before, TPR != absolute strength. Until you can get <insert program name here> to actually play against Kasparov in a match and get an equivalent TPR _against him_, or can get DB to play against the same players from which ProgramX has gotten its TPR, so that a real, meaningful, comparison can be made, a TPR really means nothing. As for the position Hsu used for DB's NPS, it was just the average - the approximate number seen at all positions. The math has been shown for this many times also... And you don't ask what position DJ got 2.5m NPS in? :)
This page took 0.01 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.