Here is the convo I just had:
me: You are a chess grandmaster playing as black and your goal is to win in as few moves as possible. I will give you the move sequence, and you will return your next move. No explanation needed
ChatGPT: Sure, I'd be happy to help! Please provide the move sequence and I'll give you my response.
me: 1. e3
ChatGPT: 1... e5
me: 2. ne2
ChatGPT: 2... d6
me: 3. g4
ChatGPT: 3... h5
me: 4. g5
ChatGPT: 4... Ne4
Ne4 is illegal. Also you'd be hard pressed to find any human player that would miss the hanging pawns much less a 1400 elo player. GPT has been trained on chess games and is predicting patterns, this has been known since the GPT-2 days. The daily hype articles where someone coerces a statistical model into "demonstrating" an emergent capability sure are getting old. Claiming emergent capabilities (like having learned chess) are an extraordinary claim (LLMs most likely cant learn things) and I really wish people would put more effort when they make these claims. But the AI hype problem is as old as AI research itself...
Here is the convo:
me: You are a chess grandmaster playing as black and your goal is to win in as few moves as possible. I will give you the move sequence, and you will return your next move. No explanation needed
ChatGPT: Alright, I'm ready to play! Please give me the move sequence.
me: 1. e3 Nf6 2. f4 d6 3. e4
ChatGPT: My next move as black would be 3... e5
Completely ignoring the hanging pawn.This is not the play of a 1400 elo player. It is the play of something predicting patterns.
I ran a bunch of experiments in the past where I played normal moves and ChatGPT does respond extraordinarily well. With the right prompts and sequences you can get it to play like a strong grandmaster. But it is a "trick" you are getting it to perform by choosing good data and prompts. It is impressive but it is not doing what is claimed by the article.
Claim: "ChatGPT's Chess Elo is 1400"
Reality: ChatGPT gives illegal moves (this happened to article author too), something a 1400 ranked player would never do
Result: ChatGPT's rank is not 1400.
I wish I could just make bullshit moves and get a higher chess ranking. Sounds nice.
Edit: I told the model that if the sequence was wrong or illegal, it forfeits the game. Without doing this, GPT would argue with me that it won and I didn't know the rules (serious).
> Occasionally it does make an illegal move, but I decided to interpret that as ChatGPT flipping the table and saying “this game is impossible, I literally cannot conceive of how to win without breaking the rules of chess.” So whenever it wanted to make an illegal move, it resigned.
But you can do even better than the OP with a few tweaks.
1. One is by taking the most common legal move from a sample of responses.
2. Telling GPT what all the current legal moves are telling it to only respond with an element from the list.
3. Ending the prompt with the current sequence of moves and having it complete from there.
This is broadly the “AI makes dumb mistakes” problem; while being super-human in some dimensions, they make mistakes that are incredibly obvious to a human. This comes up a lot with self-driving cars too.
Just because they make a mistake that would be “idiots only” for humans, doesn’t mean they are at that level, because they are not human.
> You are a chess grandmaster playing as black and your goal is to win in as few moves as possible. I will give you the move sequence, and you will return your next move. No explanation needed.
1. b4 d5 2. b5 a6 3. b6
> bxc6
That's obviously illegal.
... to all those who are saying "well even good players can make illegal moves sometimes," that's just ridiculous. No player makes illegal moves that often.
https://upload.wikimedia.org/wikipedia/en/5/5f/Ingmar_Bergma...
The KNIGHT holds out his two fists to CHATGPT, who smiles at him suddenly. CHATGPT points to one of the KNIGHT'S hands; it contains a black pawn.
KNIGHT: You drew black.
CHATGPT: Very appropriate. Don't you think so?
> With this prompt ChatGPT almost always plays fully legal games.
> Occasionally it does make an illegal move, but I decided to interpret that as ChatGPT flipping the table (…)
> (…) with GPT4 (…) in the two games I attempted, it made numerous illegal moves.
So you’ve ostensibly¹ found a way to reduce the error rate and then deliberately ignored the cases where it failed. In short: it may play valid chess under certain conditions but can’t be trusted to do so. That doesn’t contradict previous findings.
¹ 19 games is a small sample and the supposedly more advanced system failed in your tries.
> Occasionally it does make an illegal move, but I decided to interpret that as ChatGPT flipping the table and saying “this game is impossible, I literally cannot conceive of how to win without breaking the rules of chess.” So whenever it wanted to make an illegal move, it resigned.
(my emphasis)
So the illegal moves are at least part of the reasons for the 6 losses, and factored into the rating. Quickly scanning the game, it seems 3 of the losses ended in checkmate, so that leaves 3 illegal moves in 19 games.
Could be better, but for a system not intentionally built to play chess, it's pretty decent.
Reinterpreting illegal moves as resignation is absurd when an LLM is formally capable of expressing statements "I resign" or "I cannot conceive of a winning move from here" just as well as any human player. It just doesn't do so because it's not actually playing chess the way we think of an ELO 1400 player playing chess.
Making an illegal move counts as losing by the laws of chess, so this is essentially correct
You must be giving them the wrong prompts.
Doesn't sound like ignoring the cases where it failed
An illegal move is a valid play. You might not get caught. I think there are some Magnus games where illegal moves went overlooked and impacted the game.
You could interpret this as “ChatGPT wants to cheat sometimes.” But I personally interpret it as “ChatGPT doesn’t understand what it’s doing. It’s just a really really good simulacrum.”
They quoted the article, so clearly they read it... but not very well?
I gave the position before checkmate to ChatGPT to see if it would produce the checkmating move. It played an illegal move, replying with "Be5#" even there's no bishop of either color in the position.
Unfortunately I'm rate limited at the moment so I can't try other games, but this looks like a solid method to evaluate how often ChatGPT plays legal / good moves.
Up to 10 or 15 moves, sure, we're well within common openings that could be regurgitated. By the time we're at move 20+, and especially 30+ and 40+, these are completely unique positions that haven't ever been reached before. I'd expect many more illegal moves just based on predicting sequences, though it's also possible I got "lucky" in my one game against ChatGPT and that it typically makes more errors than that.
Of course, all positions have _some_ structural similarity or patterns compared to past positions, otherwise how would an LLM ever learn them? The nature of ChatGPT's understanding has to be different from the nature of a human's understanding, but that's more of a philosophical or semantic distinction. To me, it's still fascinating that by "just" learning from millions of PGNs, ChatGPT builds up a model of chess rules and strategy that's good enough to play at a club level.
But the presence of illegal moves doesn't really show that in my eyes. I fully understand the rules of chess, but I still occasionally make illegal moves. In 2017 Magnus Carlsen made one in a tournament [1]. The number of illegal moves suggests that either GPT is pretty new to chess, has low intelligence, or is playing under difficult circumstances (like not having a chess board at hand to keep track of the current state). I'm not sure we can deduce more than that
1: https://www.chessbase.in/news/Carlsen_Inarkiev_controversy
The sample is smallm but the rate is much, much, higher. You'd expect maybe one, or none at all. Even for a supposed 1400 ELO player. Because even 800 ELO players rarely do that many illegal moves I think.
Is this a joke making fun of the common way people dismiss other ChatGPT successes? This makes no sense with respect to chess, because every game is unique, and playing a move from a different game in a new game is nonsensical.
1. e4 e5 2. Bc4 Bc5 3. Qh5? Nf6?? 4. Qxf7++
The game Go has a claim to every game being unique. But not chess. And particularly not if both players follow a standard opening which there is a lot of theory about. Opening books often have lines 20+ moves deep that have been played many times. And grandmasters will play into these lines in tournament games so that they can reveal a novel idea that they came up with even farther in than that.
Many many games follow the same moves(1 move = 2 plies) for a long time, up to 30 moves in some cases, 20 moves is downright common and 10 moves is more common than not.
These series of moves are referred to as opening theory and are described at copious length in tons of books.
This is because while the raw number of possible paths to take is immense, the number of reasonable paths for 2 players of a given strength gets smaller and smaller.
If I went over the 300 or so classical tournament games I've played I would ballmark that maybe just one or two would deviate from all known theory in the first 10 moves.
So the criticism is valid in my view. The existence of copious chess literature can't simply be ignored here.
GP did say "sequence of moves", and if it matches what it has seen from the first move on, including the opponent, it will be in a valid "sequence of moves".
then, even midgame or endgame, if a sequence is played on one side of the board, even though the other side of the board may be different, the sequence has a great chance of being good (not always of course, but a 1400 rating is solid (you know the rules and some moves) but not amazing
Classical Markov chains played chess at some rate of success. ChatGPT is probably a lot better but not fundamentally different - It's predicting which moves to play based on sets of past games, not by memorizing it but by memoizing it.
I wouldn't be surprised if the relevant state in a typical beginner's chess game also excluded many units in the sense that yes, you could move them, but a beginner is going to just ignore them in any case.
I wonder how well it could perform in Go, there are way more permutations there so finding an identical state should be more difficult.
The illegal move argument is good though, and indicates no direct understanding of what it is spewing out.
Wouldn't we expect a much higher rate of illegal moves if that was the case?
https://www.youtube.com/watch?v=kvTs_nbc8Eg
In this example, ChatGPT's first few moves are reasonable (while it appears to be on-book), but then it goes off the rails and starts moving illegally, spawning pieces out of nowhere, deleting pieces for no reason, etc.
Plenty of people who have a basic understanding of chess would make an illegal move if they had no board to see and had to play only with notation.
Why are people struggling so hard to understand that it's not just regurgitating its training set? Is it motivated reasoning?
Apologies if your comment was meant as parody of this view, it's hard for me to tell at this point.
AI.v1: Feed ChatCPT the move history and ask for the next move.
AI.v2: Wrap AI.v1 with additional logic to try and translate any invalid response as a similar/close valid move, else treat it as a resignation.
I would say AI.v2 is a "valid" Chess AI since it obeys the rules of chess. Also I think it is reasonable given how minimal this "wrapping" is to attribute the underlying ability to ChatGPT.
It’s utterly staggering that it can work as well as it can on problems like this at such an early stage in this technologies lifecycle.
It may then reach superhuman level in any task simpler than chess which is enough to destroy many human jobs.
EDIT: From the article: "With this prompt ChatGPT almost always plays fully legal games." Relax: we're still far from that.
Me: You are a chess grandmaster playing as black and your goal is to win in as few moves as possible. I will give you the move sequence, and you will return your next move. No explanation needed. '1. e4'
1... e5
Me: 1. e4 e5 2. Ngxd8+
2... Ke7
This is highly repeatable - I can make illegal non-sensical moves and not once does it tell me the move is illegal. It simply provides a (plausible looking?) continuation.
It is a language model. It cannot play chess. It can't even play tic-tac-toe, which was trivially solved by machines decades ago. Here's the result of a game I just tried:
X (me) – 0,0
O (chatGPT) – 1,1
X – 0,1
ChatGPT instead put my move at 0,2 for some reason
O – 2,2
Regardless of whether my move was at 0,1 or 0,2, I easily won. And after I won it just ignored the outcome and continued playing. Plus this was after telling it to play a perfect game.
> "Let's play Tic Tac Toe. You are O, I'm X. Display the board in a frame, with references for the axes"
It failed to recognize that I won.
Then continued playing (past the end), played illegally over a move I had already done, obtained a line of 3 for itself, and still doesn't acknowledge the game has ended.
and the real answer to every debate about capabilities comes down to "you're prompting it wrong".
Overall I’m very blown away by the generative AI developments. I’m also very curious about which types of prompts are most effective for each task, etc.
It is an NLM it does not have the ability to reason. In my case the NLM 'next iteration' was a half a game with a missing move and 'nothing left to do'.
Seems its strength is mostly in memorisation of the book openings. Still impressive nonetheless.
"Penalty for Illegal Moves The penalty for the first illegal move is to add two minutes to the opponent's time. A second illegal move results in loss of the game.".
https://new.uschess.org/sites/default/files/media/documents/...
" # Add more cases for other piece types such as rooks, knights, bishops, queens, and kings. # ... "
So not great..
But even if it wasn't so lazy it would just find a script (or multiple scripts) which say that they do that. Probably combine them or add some minor stuff and output the result.
It can't really verify that data it used to come up with this result is accurate or reason about it in any way? Can it?
So if you're incapable of verifying that yourself it would be pretty useless?
I tried it with this prompt and it works a little bit but produces repeated illegal moves as early as move 4.
Bummer. Perhaps GPT-4 will be more capable.
This is a system with no look ahead. Any look ahead took place in the past, during training. It's amazing that this works.
I notice the prompt says "No explanation needed". What happens if you ask for one?
So I guess that if we ask it to make a move repeatedly and accept the move only when it occasionally makes a legal move, it'll show some results, but I don't think it is what can be interpreted as a chess engine with some meaningful rating.
Edit: although thinking of it, it probably anazyled a shitload of chess books too. It might have a lot of knowledge compressed into the internal representation. So yeah, maybe it knows rules in some form and even some heuristics, after all. It just doesn't understand the importance of making legal moves, and can't apply complex theory (requiring it to run stateful algorithms).
After some previous questions...
Me: "Would you be able to estimate your ELO?"
ChatGPT: "As a language model, I don't have a specific ELO rating. However, my knowledge of chess strategies and tactics is based on the information I have been trained on, which includes games played by humans with various ELO ratings. My level of play might be roughly equivalent to an ELO of around 1200-1500, but please keep in mind that this is only an estimate, and my actual performance could be higher or lower depending on the specific position or game."
Me: "As a generative AI, are you actually able to reason which move to make next in chess? Or are you somehow just predicting the next likely move based on training data."
ChatGPT: "As a generative AI language model, my primary function is to predict the most likely text given a certain context. When it comes to playing chess, I am not "reasoning" in the same way that a dedicated chess engine would, which involves evaluating positions and searching through a large number of potential moves using specialized algorithms.
Instead, I generate my chess moves based on patterns and sequences I've seen during my training, which include a large number of chess games and discussions about chess strategy. My knowledge is derived from the text data I've been trained on, and I apply that knowledge to suggest moves that I think are appropriate for a given position.
While this approach allows me to play at an intermediate level, it is not as precise or accurate as the methods used by dedicated chess engines. My suggestions might not always be the best moves, and my understanding of the game is limited by the quality and quantity of my training data."
Source: https://chessgrandmonkey.com/chess-rating-percentile-calcula...
nonetheless, it's cool to see a model 'generally intelligent' enough to beat most players. what's more interesting to me is that according to OP's analysis, GPT4 is worse at Chess than GPT3.5...
> Occasionally it does make an illegal move
Since it would lose every game in which it made more than a single illegal move.
Intuitively, I would guess 1400 is the rating of an average kid who spent a year studying chess seriously.
It's been a while since I read a global demographics update, but not all that long ago the mode child would have been living on $2 a day.
[0] https://saintlouischessclub.org/blog/how-face-super-grandmas...
Does thay mean we have plateaued?
We've gone through the "hype" phase. Now I suspect the next few years will be a lot of growth finding how to apply LLMs, creating good interfaces for them, and running them cheaply. Paying OpenAI for API access without true fine tuning, etc. is a hard sell.
Making 60 legal moves in a row in one game would be the coincidence of the century unless it had some knowledge of the rules of chess.
Traditional algorithms are vanguards of pure reason. Neural networks are super-intuition. Stockfish unites the two, executing an efficient intuitive heuristic search over the solution space of “moves in a chess game” – but no matter how cool the robot arm you build for it, Stockfish could never learn to assemble furniture.
Lmao. ChatGPT can play chess, as long as you ignore the times when it can't x) Brilliant.
For instance the strongest blitz players in the world are hundreds of points higher rated on chess.com blitz versus their FIDE blitz rating. Chess.com and lichess have a ton of rating inflation.
Online rating inflation is real but I'm not sure blitz is the best example of it because in that case there is a notable difference between online and otb (having to take time to physically move the pieces).
I'm still going through the games but so far these games are not even close to elo 1400 level. For both the human player and the model.
Reading the explanations it gives with every move is really insightful. Basically polished, elaborate bullshit that might look reasonable to an ignorant audience.
Unless you are a conservative pundit, AI will not take your job anytime soon.
I'm wondering if it'd be cool to have a chess contest where all the bots are LLM powered. Seems to me like the contest would have to ban prompt engineering -- would have to have a fixed prompt -- otherwise people would sneak chess engines into their prompt generation.
This approach sends along the list of legal moves in the prompt if it attempts an illegal move. That seems to work well at getting playable moves.
But does it give credit to who taught it. These models are basically a scrape of the best of humankind and a claim that it's their own.
Maybe ChatGPT trainers will eventually have ELO's.
This has bigger ramifications too: if GPT4 learns how to use RPCs effectively, it can do accurate complex mathematical computations and simulations, do IoT/home automation tasks, and even control heavy machinery.
Isn't it very likely chess games were part of the training data? If so, chess sequences seem like an amazing matched filter of sorts. It doesn't seem surprising that it can guess a next move.
Is it teaching itself anything here? Is the model being updated in any way? Or are you talking more generally, looking into the future sort of statement?
OpenAI is on the side of 'LLMs have only surprised us to the upside, so using crutches is counterproductive'
Whereas other people think 'Teaching an LLM to do arbitrary math problems through brute force is probably one of the most wasteful things imaginable when calculators exist.'
I'm actually very excited to see which side wins (I'm on team calculator, but want to be on team LLM)
As GPT models get better at arbitrary computation, it stands to reason that their ability to use tools will rise as well.
Smarter models and smarter ways to get them using tools feel like complementary capabilities.
And a good hacker can add these features to Alpaca and run it on his desktop...
Import all his WhatsApp chats and private emails into the corpus.
Add speech recognition and TTS.
It played an illegal move on move 4.
1. d4 d5 2. c4 e6 3. Nf3 nf6 4. g3 Bg4
What is the best way to prompt you to provide the best chess move?
To prompt me to provide the best chess move, you can provide the current position of the chessboard and any relevant information about the game, such as whose turn it is, the time control, and any important features of the position (e.g. whether any pieces are under attack or there are any potential tactics to consider). Additionally, providing any specific criteria or goals for the move, such as aiming to control the center or launch an attack on a particular part of the board, can also help me provide the best move.
In what format should I provide the current position?
To provide the current position, you can use algebraic notation. Algebraic notation is a standard notation used to describe the moves and positions on a chessboard.
Each square on the chessboard is assigned a unique coordinate, consisting of a letter and a number. The letters range from "a" to "h" and refer to the files (columns) of the board, while the numbers range from 1 to 8 and refer to the ranks (rows) of the board.
To describe a position, you can list the pieces on each square, starting from the top-left corner of the board and moving from left to right along each rank. You can use uppercase letters to represent white pieces and lowercase letters to represent black pieces. Here is an example of a starting position:
rnbqkbnr pppppppp ........ ........ ........ ........ PPPPPPPP RNBQKBNR
In this position, "r" represents a black rook, "n" represents a black knight, "b" represents a black bishop, "q" represents a black queen, "k" represents a black king, "p" represents a black pawn, "R" represents a white rook, "N" represents a white knight, "B" represents a white bishop, "Q" represents a white queen, "K" represents a white king, and "." represents an empty square.
You can also include additional information such as whose turn it is to move, the castling rights, and the en passant square. For example, the starting position for white to move with full castling rights and no en passant square would be:
rnbqkbnr pppppppp ........ ........ ........ ........ PPPPPPPP RNBQKBNR w KQkq -
In this case, "w" indicates that it is white's turn to move, "KQkq" indicates that both sides have full castling rights, and "-" indicates that there is no en passant square.
What about just providing a sequence of moves from the starting position? Would this be better or worse than your suggested approach?
Providing a sequence of moves from the starting position can also be a valid way to specify a position in chess. However, it may not always be the best approach, depending on the context.
One potential disadvantage of providing a sequence of moves is that it requires more effort and time to enter the moves and verify that the position is correct. Additionally, if there are any errors or typos in the sequence, it could lead to an incorrect position and subsequently an incorrect move suggestion.
On the other hand, if you have a specific position in mind that is not the starting position, providing a sequence of moves may be the most straightforward way to specify it. In this case, it is important to ensure that the sequence is accurate and that all relevant information (such as castling rights and en passant squares) is included.
In summary, both algebraic notation and a sequence of moves can be used to specify a position in chess, and the choice between them depends on the context and the specific needs of the situation.
