Author: Dann Corbit
Date: 16:01:56 10/11/99
Go up one level in this thread
On October 11, 1999 at 17:12:56, Leon Stancliff wrote: [snip] >It is true, however, that after Rebel 10 has played as many as ten games against >a variety of grandmasters, we have an approximate anchor for estimations. If we >know Rebel 10 can play at 2525 Elo against ten different grandmasters, we can >compare the relative ratings of SSDF and adjust all of them the same amount as >the difference between Rebel's SSDF and its actual performance against humans. >Yes, any one computer program may have a flaw which will allow humans to exploit >that flaw, but I think the time when humans can just summarily dismiss the >rating lists is quickly drawing to a close. > To earn a grandmaster title the human must have three results within a one >year period that are 2550 or above. Rebel 10 may well accomplish that feat. We >are informed that a human who can generally play at 2500 can very likely >qualify. It is my personal opinion that if Rebel can play at or above the 2500 >rating over an extended length of time, it should be recognized as being of >grandmaster strength. Truly the SSDF ratings are inflated. We will now have a >method for determining just how much! I think that (perhaps) this is another area where 'provisional' rating makes sense. Let's take the example of a human who masters one opening really well and takes off to get a high ELO. Now, the GM's catch on that this guy will try to steer everything into his favorite. So they counter by steering into something else or studying up on that line when they are going to face him. His meteoric rise is over. With a program, we can have the same effect. If a weakness of any kind becomes discovered, it will be exploited. And so until a large number of games have been played, we won't be really sure. OTOH, every new game increases the certainty of the quality of play and we have a huge leap over the same time last year. Time will tell.
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.