Computer Chess Club Archives


Search

Terms

Messages

Subject: Re: Next Human vs Computer ratings list - I need opinions

Author: Ed Schröder

Date: 12:06:43 05/19/00

Go up one level in this thread


On May 19, 2000 at 13:50:04, Alberto Rezza wrote:

>>>Sure, but if the purpose of this rating list is to give us an idea of the
>>>strength of programs, I would discard games that we know are meaningless, like
>>>the 2 forfeits of Fritz in Holland and this Shredder game. The key word, to me,
>>>is "meaning", and this game has none. The list may be more complicated, but also
>>>more accurate.
>>
>>What about the GM's wife example? The computer won or lost? Or drop the
>>game? You never get a perfect system. Why not stick to the FIDE rule?
>>If you lose on time you have lost whatever happened. 2 hurrays, not 3
>>as 3 is too much.
>
>Suppose computers were allowed to play in tournaments and get ratings, titles,
>etc. Human players would expect a program to enter the tournament with the
>correct rating, since their own rating change would depend on it.
>
>Now imagine I write a program and have it play in some tournaments. It gains a
>rating of, say, 2200. Then I realize that my operator is making far too many
>mistakes, and I decide to operate the program myself in the next event. No more
>operator mistakes, suddenly my program is playing at the 2500 level. Every human
>player starts to protest, and with good reason...
>
>No, operator error should definitely be left out of any program's rating.

Humans can do the same. Both cases do not happen in practice.

Ed


>Alberto



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.