Author: Dann Corbit
Date: 13:51:17 03/21/05
Go up one level in this thread
On March 21, 2005 at 12:53:56, Roger D Davis wrote: >On March 21, 2005 at 12:06:31, Vincent Lejeune wrote: > >>On March 21, 2005 at 11:52:47, Roger D Davis wrote: >> >>>On March 21, 2005 at 11:32:38, Vincent Lejeune wrote: >>> >>>>http://hydrachess.com/ >>>> >>>>"The developers expect to break the 3000 Elo barrier till the end of this year. >>>>" is quite clear. >>>>A video (19 min duration) with a quick history of computer chess and history of >>>>hydra's games. >>>>hydra games + some pictures + hydra informations >>>> >>>>great ! >>> >>>Since ELOs are meaningful only within some reference group...what is the >>>reference group? The top SSDF programs running on AMD 1200s, I guess...right? >> >>I suppose they mean "an estimated strengh of 3000 human elo" and they will try >>to play more games against humans, but it's only a guess. > >I guess I have to wonder what Hydra's performance rating would be against SSDF >rated programs. There are some Shredder, Gandalf, and Tiger games listed in its >tournament history. It is clear that Hydra is very strong. But there are not enough published games to verify anything meaningful. And there are basically no games by indepenent testers (who do not care about the outcome). The 3000 number is pulled out of a hat to sound impressive. It means nothing. Of course, they can say anything they want: "We think it is 200 Elo stronger than Kasparov" or "We think it is 200 Elo stronger than Deep Blue" And it might or might not be thost things. But without lots of data from independent testers, we will never know the answers. Still, it's fun to guess and there is nothing wrong with that. And I do not blame the Hydra team for hype. Each and every professional chess program has huge volumes of hype connected with them. It's just the nature of how things are sold.
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.