Computer Chess Club Archives


Search

Terms

Messages

Subject: Re: Is Deep Blue still considered better than Deep Junior ?

Author: Robert Hyatt

Date: 08:29:47 08/19/02

Go up one level in this thread


On August 19, 2002 at 00:29:06, Mark Schreiber wrote:

>On August 18, 2002 at 21:56:05, Robert Hyatt wrote:
>
>>On August 18, 2002 at 17:57:11, Chris Carson wrote:
>>
>>>On August 18, 2002 at 14:50:19, Gian-Carlo Pascutto wrote:
>>>
>>>>On August 18, 2002 at 12:48:02, Chris Carson wrote:
>>>>
>>>>>3.  There are a lot of tatical/strategic holes in DT games that modern
>>>>>commercial programs do not make.
>>>>
>>>>The commercial programs may have a lot of tactical/strategical holes
>>>>that DT didn't had. But we can't check those.
>>>>
>>>>>4.  Today's programs would crush DT.
>>>>
>>>>How can this possibly be 'an observation'. It's your personal
>>>>opinion, not a verifyable fact.
>>>>
>>>>>5.  The GM's that DJ, DF, CT, Rebel, Hiarcs, The King have played recently
>>>>>would crush DT.
>>>>
>>>>Same remark as last one.
>>>>
>>>>>6.  DT would have no chance in a match with a 2700 GM (today) that had 100
>>>>>games of preparation, Rebel played this GM even for 4 games.
>>>>
>>>>And again
>>>>
>>>>>7.  I am pretty sure I could crush DT today.
>>>>
>>>>And again...sigh.
>>>>
>>>>--
>>>>GCP
>>>
>>>Yes, this is just my opinion, post I was responding to voiced an opinion and I
>>>posted a different one.  However, DT did not score 2650 against GM's, I went
>>>back and checked the PGN's, they were FIDE/USCF rated and many were IM's and
>>>some FM's.
>>>
>>>I can live with differing opinions, but saying it is just my opinion, does not
>>>make it wrong.  :)
>>>
>>>Chris
>>
>>
>>Sorry but you are _wrong_ above.  The Fredkin prize rules are still available
>>on the net.  They _specifically_ required that a program produce a 2550
>>performance rating, over 25 consecutive games, against _only_ GM opponents.
>>No IMs.  No FMs.  _just_ GM players.  This doesn't mean that DT didn't play
>>FM/IM players in tournaments, but those games did _not_ count in the fredkin
>>prize committee analysis.  The rules said that the prize would be awarded
>>when 25 consecutive games at 40/2 were played against GM players and the
>>performance rating was 2550 or greater.  The DB team we free to pick any
>>25 consecutive games they wanted, but they could not omit any except for
>>those before the 25 they chose, or those after.
>>
>>Please don't try to rewrite history.  The result of the Fredkin prize awards
>>is already well-documented...
>
>With hindsight the Fredkin prize turned out to be a fraud. The Fredkin prize was
>awarded to the deep blue team for beating Kasparov after only 6 games. What
>happened to the 25 games? What a disgrace! The $10,000 prize needed 25 games why
>not the $100,000 prize? To prove you are a World Champion should take at least
>as many games as proving you are a Grandmaster. Kasparov was willing to play
>again. IBM knew they could not beat Kasparov again. The $100,000 award should
>have waited till they won 25 games.
>Mark


There was no 25 games for the stage III prize.

Stage 1 was for the first computer to become a chess master.  That was awarded
to Belle.

Stage 2 was for the first computer to become a GM.  This was defined as a 2550+
rating over 25 consecutive games vs GM players, at 40/2hr time controls.  Deep
Thought won this.

Stage 3 was for the first computer to beat the world champion in a match.  It
was originally set at 12 games but the fredkin prize committee at Carnegie-Melon
decided that _any_ match vs the current world champion would suffice so long as
it was more than a couple of games.  Deep Blue 2 won this.



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.