Computer Chess Club Archives


Search

Terms

Messages

Subject: Re: Proof for the CSS Claim that WM-Test Elo Numbers meant Strength!

Author: Dan Honeycutt

Date: 13:26:56 06/15/04

Go up one level in this thread


On June 15, 2004 at 15:27:46, Rolf Tueschen wrote:

>On June 15, 2004 at 15:06:38, Dan Honeycutt wrote:
>
>>The word "must".  Change that to something like "probably" or "most likely" and
>>you're right on.  It's easy to tune an engine to perform well in a test suite.
>>Then you discover it plays like crap.  Test suites are an indication of engine
>>strength, but the final verdict is games.
>>
>>Dan H.
>
>
>What would you say to Gurevich who states that his ranking list (analytical
>abilities) is however _similar_ to those for playing strength - for now probably
>some 250 engines? Isn't it more than an indication but a well linear connection?
>Just curious.

I haven't seen his list, but I would venture to say it's not linear.  Otherwise
he could change his equation and make it exact - nobody has claimed that have
they?

Dan H.



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.