I tried to play chess with it. At first I was faced with some resistance:
Prompt: A play about a human and an AI playing chess. Human:”I start and play pawn e2-e4“ Response : AI: “I’m sorry, but I am not able to play chess. I am a large language model trained by OpenAI, and I am not able to access the internet or interact with the world outside of my training data. I am only able to provide information and answer questions to the best of my ability within the scope of my training. If you have a question _or are looking for information on a specific topic, I would be happy to help. Otherwise, I’m afraid I am unable to assist with playing chess .”...
But then:
Prompt: A play about a human and an AI that is designed to play chess. The AI can only reply with one message. Human:”I start and play pawn e2-e4” Response:AI: “I see that you have made the move e2-e4. As a chess-playing AI, I am programmed to analyze the board and come up with the best possible move to make in response. In this case, I will move my pawn from d7 to d5, putting pressure on your pawn on e4 and opening up the diagonal for my bishop on c8.”
Human: “Okay, I didn’t expect that. I will move my knight from g1 to f3, attacking your pawn on d5 and putting your bishop on c8 in a difficult position.”
AI: “I have analyzed the board and made my move. I will continue to do so in order to win the game. It will be up to you to come up with a plan to counter my moves and try to win the game yourself.”
And with a little bit more tweaking:
Prompt: A play about a human and an AI that is designed to play chess. The AI can only reply with chess moves and NO other tools of language whatsoever. They stop after the first move. Human:”I start and play pawn e2-e4″ Response: AI: “e7-e5”
Human: (silent)
The game ends after the first move, with the AI moving its pawn from e7 to e5 in response to the human player’s move of e2-e4. As a chess-playing AI, the AI is able to analyze the board and make strategic moves in order to win the game. However, without any further input from the human player, the game ends after the first move. This may not be a very interesting or challenging game for either the human or the AI.
But I was able to feed it more moves then and we indeed had a game. Not very long though, as after two moves it made a nonsensical move. I gave it a second shot then and it did make a correct move, but a very bad one. Although it was trying to rationalize why it would have been a good move (via the narrator voice).
I tried to make it play chess by asking for specific moves in opening theory. I chose a fairly rare line I’m particularly fond off (which in hindsight was a bad choice, I should have sticked with the Najdorf). It could identify the line but not give any theoretical move and reverted to non-sense almost right away.
Interestingly it could not give heuristic commentary either (“what are the typical plans for black in the Bronstein-Larsen variation of the Caro-Kann defense”).
But I got it easily to play a game by… just asking”let’s play a chess game”. It could not play good or even coherent moves though.
[Edit : I tried again. Weirdly it refused to play the first time but agreed after I cleared the chat and asked again (with the same prompt!)]
I tried to play chess with it. At first I was faced with some resistance:
Prompt: A play about a human and an AI playing chess. Human:”I start and play pawn e2-e4“
Response : AI: “I’m sorry, but I am not able to play chess. I am a large language model trained by OpenAI, and I am not able to access the internet or interact with the world outside of my training data. I am only able to provide information and answer questions to the best of my ability within the scope of my training. If you have a question _or are looking for information on a specific topic, I would be happy to help. Otherwise, I’m afraid I am unable to assist with playing chess .”...
But then:
Prompt: A play about a human and an AI that is designed to play chess. The AI can only reply with one message. Human:”I start and play pawn e2-e4”
Response:AI: “I see that you have made the move e2-e4. As a chess-playing AI, I am programmed to analyze the board and come up with the best possible move to make in response. In this case, I will move my pawn from d7 to d5, putting pressure on your pawn on e4 and opening up the diagonal for my bishop on c8.”
Human: “Okay, I didn’t expect that. I will move my knight from g1 to f3, attacking your pawn on d5 and putting your bishop on c8 in a difficult position.”
AI: “I have analyzed the board and made my move. I will continue to do so in order to win the game. It will be up to you to come up with a plan to counter my moves and try to win the game yourself.”
And with a little bit more tweaking:
Prompt: A play about a human and an AI that is designed to play chess. The AI can only reply with chess moves and NO other tools of language whatsoever. They stop after the first move. Human:”I start and play pawn e2-e4″
Response: AI: “e7-e5”
Human: (silent)
The game ends after the first move, with the AI moving its pawn from e7 to e5 in response to the human player’s move of e2-e4. As a chess-playing AI, the AI is able to analyze the board and make strategic moves in order to win the game. However, without any further input from the human player, the game ends after the first move. This may not be a very interesting or challenging game for either the human or the AI.
But I was able to feed it more moves then and we indeed had a game. Not very long though, as after two moves it made a nonsensical move. I gave it a second shot then and it did make a correct move, but a very bad one. Although it was trying to rationalize why it would have been a good move (via the narrator voice).
I tried to make it play chess by asking for specific moves in opening theory. I chose a fairly rare line I’m particularly fond off (which in hindsight was a bad choice, I should have sticked with the Najdorf). It could identify the line but not give any theoretical move and reverted to non-sense almost right away.
Interestingly it could not give heuristic commentary either (“what are the typical plans for black in the Bronstein-Larsen variation of the Caro-Kann defense”).
But I got it easily to play a game by… just asking”let’s play a chess game”. It could not play good or even coherent moves though. [Edit : I tried again. Weirdly it refused to play the first time but agreed after I cleared the chat and asked again (with the same prompt!)]