Author: Robert Hyatt
Date: 11:21:38 06/21/99
Go up one level in this thread
On June 21, 1999 at 11:41:27, José Carlos wrote: >On June 21, 1999 at 09:29:53, Robert Hyatt wrote: > >>On June 21, 1999 at 04:18:57, Jouni Uski wrote: >> >>>After this 2 - 2 (Cilkchess removed) against super GMs with average ELO >>>2621 I think there is no doubt, that PC programs are playing at GM level! >>>Actually hardly no further games are needed. And remember, that average GM has >>>only 2500 as rating. >> >>That is incorrect. 2500 is the _minimum_ rating to earn the GM title, the >>average is well above this. > > But not the minimum to mantain it. Several GM's earn the title, and then >hardly mantain 2500 or less. > sure... but 2500 is _not_ the average of all the FIDE players with GM ratings. >> >> >> >> >>> >>>I was at the playing hall in Paderborn. The conditions were excellent and >>>sure GMs were playing very serious. I was sitting quite near Fritz - Sokolov >>>board and after 14. Bh6 Sokolov's look was "interesting". He starts to think >>>about 20 minutes. In the continuation I didn't heard him to resign, but after >>>move 24. he simply starts to discuss with Friz operator Feist.... >> >> >> >>Let me give you my reasons why I _still_ consider computers to be 2400 >>players: >> >>1. Pick any of the 5 programs that played the GM players. I will find a >>game where they played so badly that if you look at _that_ game no one would >>consider that program to be a GM. For example, take the winner and look at >>the playoff game. Three different GM players commented that they had _never_ >>seen white screw up the opening so badly... > > Kasparov made a terrible bluder in the opening in one of the games against DB. >It occurs sometimes... Never said otherwise. But in how many games have you seen Kasparov do that? Once in 100? So that of our 5 games the other day, one was a 100-1 shot? That was the only point... > >> >>2. Fritz won in the same way that Deep Blue won the last game vs Kasparov, >>actually even worse... The GM simply made a blunder that a 2000 rated player >>would spot in an instant. If you take that win away, the even result goes >>away. > > Humans make tactical blunders sometimes, it can't be avoided. And computers >make "positional blunders" sometimes. It can't be avoided, yet... > >> >>3. I've been working on chess programming for a long time. And regardless of >>how they 'seem' to play in many games, I still know just what they can and can't >>do. And they are nowhere near a GM's level in 'knowledge'. They are still >>surviving on tactics. > > I disagree. I think top programs are better in tactics than the average of >GM's. In some types of tactics, yes. IE open board, kings exposed, pieces all over the place. In other types of tactics, computers have no chance. IE who finds the Shirov Bh3 sac? Not hard to understand as a human... but very deep (although fairly forcing) from a human perspective. So computers are _not_ tactically supreme just yet... Even the Rebel/Rohde game showed that quite clearly as well... > > And there are plenty of GM players that know how to >>squelch tactics and make the game hinge on positional play. And there the >>programs simply don't measure up. >> >>4. I still consider computers to be 2400+. What is the probability that in >>5 games, 2400 players could play evenly with a group of GMs rated 2600? some- >>thing like 25%? >> >>5. GM players exhibit a consistency in quality that computers don't. > > Yes and no. GM's make tactical bluders sometimes. Computers mantain a tactical >consistency all over the game. Never leave a bishop... (top programs, I mean). Never experience a fail low after playing a move? Every program I know of benefits from faster hardware. Which means that tactics are not "there" just yet... otherwise faster hardware would be worthless.. > > A >>computer will play like a GM for 5 games, and like a beginner for 1. What >>happens when the GM players learn what the computer can't do and then >>exploit that game after game?. > > Is it so easy? Perhaps if the best GMs had tons of knowledge in artificial >intelligence... Here is how to see this first-hand. Log on to ICC and play using your favorite program... with one rule... you _must_ accept rematches for as long as your opponent wants to play. Then watch them find a hole and drive a truck thru it. And your opponent might not even be a GM or IM. There are several masters that can do this effectively as they will _really_ play anti-computer while most GM players won't, and a few IM players won't... The 'rematch' clause is critical however, because normally a human will intervene and simply refuse to play the same person after losing or drawing two in a row. The automatic programs sit there 24 hours a day and will play 100 games in a row vs the same player if he wants... > >We had at least 4 different GM players watching >>part of the games on ICC (particularly the GM games the last day) and it was >>quite a common question "how can the machine play this opening, and then play >>_that_ move?" Or "why does the machine play so nicely for several games and >>then play like a beginner here?" > > I repeat, GMs make sometimes tactical blunders that a beginner don't do. I am _not_ talking about a single tactical blunder. The Shredder/Ferret game wasn't a "single poor move" game. It was a series of bad moves leading to a totally lost (at least according to three GM players we had commenting on ICC during the game) position. So a blunder is one thing, playing like an 1800 for many moves is something else entirely... > >> >>So they are very strong, yes. And if you want to lump these games together >>with what we have so far, I don't have a problem with that. So far, I am >>counting: >> >>Humans 5 (counting Anand and Rohde vs Rebel) >>progs 3 > > I think there are many more games played beetwen GMs and computers at >tournament level, do you remember MChess 1.52 victory over Larry Christiansen, >for example? Not at 40/2, no. I don't claim to know all the results. But you can't 'cherry pick' either. IE for each 'victory' you also have to find all the losses that invariably happened to keep the statistics accurate... I started my counter ticking with Anand's 2 games vs Rebel, as everyone saw those... > >> >>at 40/2hr. That is within reason for a 2400-2600 rating split, particularly >>when the just-finished 5 games were played with little preparation by the GM >>players, since they didn't know who they were playing 24 hours before they >>played. >> >>Yes, I think the machines are doing well. No I don't think they are 2500+ >>_yet_. And the gaps in the program's knowledge are big enough that I don't >>think that tactics alone will make up the difference. It goes a long way, >>but it doesn't close all the holes. >> >>One example (I won't name the GM because he asked me not to, and I won't name >>the program because I am not certain of the hardware nor that the program was >>that which was claimed since I only watched): >> >>The other nite on ICC, a GM friend of mine asked me to watch 2 games a friend >>of his was playing against a computer. The computer hardware was supposedly a >>PIII/500 xeon (1 processor) running a program that everyone here thinks is a >>very 'smart' one based on NPS. In the two games I watched, the GM made it look >>easy. This 'smart' program seemed to not be real aware of the dangers of a >>'distant passed pawn' and allowed the GM to create one, and trade material, >>until it would see it was lost. I wasn't playing the game, obviously, so I >>can't say how 'hard' the GM was 'thinking', but my 'friend' (not the one that >>was playing) commented on this. That is a _fatal_ mistake were this program >>trying to make its way up the GM ranks, because word spreads, and it simply >>gets rolled game after game. I am pretty sure that until a GM finds this >>'hole', that program will give them fits on decent hardware. And I am also >>sure that once a GM finds that hole, it is over except for the occasional >>tactical mistake he will make that the program won't overlook. >> >>The thing we are 'missing' in the programs is the 'consistency' that GM players >>have. IE Shredder played very well throughout the tournament, yet reached a >>position in the playoff that I doubt even a 2000 player would reach. almost >>zero mobility. Cramped. Inactive. A position unlike one I have ever seen >>while watching hundreds of GM games on the chess servers... The problem is >>_not_ impossible to solve. But it is _not_ solved just yet. >> >>This match was 'data'. Let's see how it looks when our data reaches 10 and >>then 20 games. So far we only have 8. And 5-3 is not a horrible result for >>the machines. Unfortunately, based on prior experience, the programs tend to >>win early games and lose later ones as the GM players spot weaknesses that >>can be exploited. Even IM players comment on the current crop of programs not >>doing decently with 'king safety' and how they are all very insensitive to >>long-term kingside attacks. Playing on ICC will expose such. If I didn't >>tweak things regularly, or add code to handle cases I was not handling before, >>I would do horribly on ICC. Because after a while, players find the weaknesses >>and then they sit on those over and over and over. Unfortunately programs are >>complex enough that fixing one often exposes more... >> >>Other opinions are welcomed of course. This is only _mine_. > > > This is only another opinion. I second the motion that other opinions are >welcomed. :) > > José C.
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.