Author: Torstein Hall
Date: 14:10:07 09/02/98
Go up one level in this thread
On September 01, 1998 at 20:43:04, Robert Hyatt wrote: >On September 01, 1998 at 17:09:51, Torstein Hall wrote: > >>On September 01, 1998 at 14:35:24, Mark Young wrote: >> >><BIG SNIP> >> >>>I agree we need more data, but because of this crafty bug and how much it did >>>differ in performance against humans and computers has to raise a few alarm >>>bells in our faith of computer Vs computer testing. Who is to say that there >>>could not be a program that could perform wonders playing humans, but could not >>>win a game against computers, without having a bug. The Crafty results makes >>>computer Vs computer testing very suspect in my eyes. If the goal of chess >>>programming is still to beat top human players. >> >>If you keep improving against other computers you are still improving and >>perhaps you can reach the goal ( to beat top humans ) in the end. Even if you >>did not go the shortest route! >> >>Torstein > > >Not necessarily... one idea is to take the top 3-4 programs on SSDF and auto- >play against them day in and day out, and tune for best results. And there's >nothing in doing this that will have any influence on beating humans, unless >they happen to have the same weaknesses you tuned against on the other programs, >which is unlikely... If thats was all they did, it would not give anything but commersial improvments I guess. But I hope there has been some software improvments the last 10 years! If it was all hardware, why not just use CM 2K and wait for the next prosessor? Torstein
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.