Author: Ratko V Tomic
Date: 19:20:46 05/22/01
Go up one level in this thread
> It has to produce the SSDF list even if you improve > the hardware. And it has to produce the SSDF list even > if you add new programs to the list. The question is > whether a suite can do these two things. As I recall, Larry Kauffman's secret suite used to be fairly accurate and kept up with the improvements of the programs and hardware. (Once it becomes public it loses much of its value due to human nature.) Larry also used to publish quite an insightful analysis of the latest programs.units and their capabilities, based on his test suite and a handful of games against them. He was usually months ahead of SSDF and his estimates stood up over time quite well to (and were more meaningful than) the raw SSDF figures. That was the example (I had in mind when starting this sub-thread) of high efficiency information extraction from what some here would call a meaningless handful of coin tosses.
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.