Computer Chess Club Archives


Search

Terms

Messages

Subject: Re: Last SSDF Rating List

Author: Sarah Bird

Date: 16:34:39 03/30/99

Go up one level in this thread


On March 30, 1999 at 18:38:30, Micheal Cummings wrote:

>
>On March 30, 1999 at 14:47:49, Timothy J. Frohlick wrote:
>
>>If you would read SSDFs' own disclaimer at CCC then you would see that there is
>>a 70 to 80 elo point margin of error in the ratings for CM6000 as it stands.
>>SSDF has stated that.
>>
>>In any case CM6000 plays like a moron compared to Yermolinsky and Kasparov.
>>
>>Respectfully,
>>
>>Tim Frohlick
>>
>>PS  I play like a moron compared to the above gentlemen.
>
>Then you are also saying that all other chess programs play like morons in
>regard to those two players. They must CM6K is on top with Fritz, and the rest
>of the moron playing programs are lower than CM6K.

Hi,
I would just like to point out that the statement made by the SSDF says margin
of error 70-80 points. Timothys statement reads like that it is a certainty that
CM6000 is 70-80 points overrated. The statement margin of error means plus or
minus NOT MINUS. It could also mean the rating will stay around the same after
900 games. The exact statement is as follows.

"Compared to the earlier program version, CM5000, which we tested on P90, the
new program seems to be about 110 points stronger! I can not deny that the
result surprised me somewhat. Still, the rating is based on only 100 games with
a margin of error of 70-80 points, so much could change if we succeed in playing
more games."  Thoralf Karlsson, Chairman of the SSDF.
Thx UltraB.




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.