Computer Chess Club Archives


Search

Terms

Messages

Subject: Re: Nolot test fun!

Author: Jeremiah Penery

Date: 16:20:21 01/13/00

Go up one level in this thread


On January 13, 2000 at 18:51:43, Tom Kerrigan wrote:

>On January 13, 2000 at 03:37:19, Dann Corbit wrote:
>
>>This is a bone of contention with me as well.  If an eval shows -1000 and the
>>right move is chosen, it means nothing if the eval should be +1000.  I think
>>there should also be a minimal ce value for important tests to know if they
>>really found the move.  It would also remove a loophole used by some programs to
>>"exit early" as soon as they happen to hit the right move (for any reason --
>>without regard to ce).  "LOOK HOW FAST WE SOLVE THE TEST!!"  Sure, but your
>>program thought it was losing on 40% of the answers.
>
>If you use chess programs for analysis, or you are trying to improve your own
>program, then the scores and PVs that it produces probably matter to you.
>
>But if you're just concerned with chess program strength, then the only thing
>that matters is what moves the program plays. It does not matter AT ALL what it
>"thinks."

It does matter, IMO.  Take Nolot #1, for example:
If, say, Fritz plays Nxh6, but doesn't follow up with the combination, it means
nothing.  Nxh6 without the combination isn't going to get you anywhere in this
position - Fritz will still lose the game, and this _does_ matter.
If, however, Fritz _does_ find the rest of the combination, then it will go on
to win the game.



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.