Computer Chess Club Archives


Search

Terms

Messages

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

Author: Rolf Tueschen

Date: 09:57:34 06/15/04

Go up one level in this thread


On June 15, 2004 at 12:41:33, Steve Glanzfeld wrote:

>On June 15, 2004 at 12:29:24, Rolf Tueschen wrote:
>
>>On June 15, 2004 at 12:11:46, Steve Glanzfeld wrote:
>
>[...]
>
>>>So what?  Testing an engine by playing (a) game(s) shows how it will perform in
>>>that game(s), only. When you doubt testsuites to work as good samples, I can
>>>also doubt any set of test games being good samples (compared to other games,
>>>under other conditions, against other opponents...).
>>
>>
>>Of course. Doubt what you want but you wont change the decisions of the top
>>programmers who do NOT believe in position-test-suites.
>
>Who cares? I decide by arguments, not by famous names who say this or that. And
>I say, a good and large test suite will always be a much better sample than some
>test games, because in a game the opening book may decide, the time consumption
>may influence the outcome, etc. and 97% of the positions won't tell if a 2200 or
>a 2800 program is playing.
>
>But please don't listen, I'm not talking to you. I don't want to see another
>reply from you, because my stomach is already aching so much from the laughing
>:))
>
>Steve


I suspected that you wouldn't care if the top programmers were interested or
not. You have a higher interest into the information if a 2200 or a 2800 program
is actually playing in a game of computerchess. Yes. In such cases I always look
into the scoresheet and there I can read who's playing. Honestly I did never see
Steve Glanzfeld, but I admit I know the scores only for the last two centuries
of the whole history of computerchess. But perhaps you are a Knight of the
Ancient Past. Nice to meet you......



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.