Author: Robert Hyatt
Date: 08:27:30 11/19/00
Go up one level in this thread
On November 19, 2000 at 11:20:20, Ricardo Gibert wrote: >On November 19, 2000 at 11:16:43, Hermano Ecuadoriano wrote: > >>On November 19, 2000 at 11:05:41, Ricardo Gibert wrote: >> >>>On November 19, 2000 at 10:25:21, Hermano Ecuadoriano wrote: >>> >>>>There has been some discussion here about holding some >>>>"exhibition" variations on the Turing test. >>>> >>>>This must be done eventually. >>>>If successful, it would be epoch-making. >>>> >>>>I think the year 2001 is fantastically apropo, >>>>promotionally speaking! >>> >>>I don't think any of the top computer programs can come close to passing a >>>turing test. There is a well known class of positions that are easy for humans, >>>but hard or impossible for computers. >>> >>>The programmers of the top chess programs have invested little effort to change >>>this for the simple reason that such positions are relatively rare and the net >>>effect of trying to deal with such positions would only serve to weaken their >>>programs. >>> >>>I would not be surprised if the CCC membership could easily devise a test >>>consisting of 10 positions, which virtually any strong human would solve 10 of >>>10 and the top programs would solve 0 of 10. >>> >>>BTW, please ignore my other post in this thread. I unintentionally hit submit >>>without writing anything. Sorry. >> >>You are definitely right. >>That's why I said "exhibition variations on the Turing test". >>They were talking about playing whole games, not special test positions. >>And we know that the computers are getting close here. >> >>I'm talking about an "exhibition". > >Okay. Now I understand. I still agree with Ricardo. Computers do things that no human would consider. One game? It _might_ pass. Six games? Not a chance.
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.