Computer Chess Club Archives


Search

Terms

Messages

Subject: Re: Testresults WAC, LCT II, WM (K)

Author: Uri Blass

Date: 16:29:40 09/29/03

Go up one level in this thread


On September 29, 2003 at 18:50:07, Jeroen van Dorp wrote:

>On September 29, 2003 at 16:22:06, Drexel,Michael wrote:
>
>
>>What are you talking about?
>
>You are writing your question directly under the answer. I repeat it for your
>convenience. You cannot prove that an engine finding the right move for the
>wrong reason is the strongest engine.
>
>You stated yourself that it's quite possible that an engine changes the PV and
>evaluation after a longer time. Anyone with experience with test results knows
>this is not a "statistical" or "hypothetical" question, but a very valid
>situation that often occurs.
>
>That's why you were given the advice to repeat the suite with the full time, and
>see it for yourself.

He already explained his reason not to do it in the following words

"You can not manually test 400 positions for each engine in reasonable time."

I guess that he tried to do the best test in limited time and he gets some good
estimate for the strongest engine in similiar positions.

Uri



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.