GPT-4 can follow the rules of tic-tac-toe, but it cannot play optimally. In fact it often passes up opportunities for wins. I’ve spent about an hour trying to get GPT-4 to play optimal tic-tac-toe without any success.
Have you or all the other tic-tac-toe people considered just spending a bit of time finetuning GPT-3 or GPT-4 to check how far away it is from playing optimally?
I would guess that you could train models to perfect play pretty easily, since the optimal tic-tac-toe strategy is very simple (Something like “start by playing in the center, respond by playing on a corner, try to create forks, etc”.) It seems like few-shot prompting isn’t enough to get them there, but I haven’t tried yet. It would be interesting to see if larger sizes of gpt-3 can learn faster than smaller sizes. This would indicate to what extent finetuning adds new capabilities rather than surfacing existing ones.
I still find the fact that gpt-4 cannot play tic-tac-toe despite prompting pretty striking on its own, especially since it’s so good at other tasks.
GPT-4 can follow the rules of tic-tac-toe, but it cannot play optimally. In fact it often passes up opportunities for wins. I’ve spent about an hour trying to get GPT-4 to play optimal tic-tac-toe without any success.
Here’s an example of GPT-4 playing sub-optimally: https://chat.openai.com/share/c14a3280-084f-4155-aa57-72279b3ea241
Here’s an example of GPT-4 suggesting a bad move for me to play: https://chat.openai.com/share/db84abdb-04fa-41ab-a0c0-542bd4ae6fa1
Optimal play requires explaining the game in detail. See here
https://chat.openai.com/share/75758e5e-d228-420f-9138-7bff47f2e12d
Have you or all the other tic-tac-toe people considered just spending a bit of time finetuning GPT-3 or GPT-4 to check how far away it is from playing optimally?
I would guess that you could train models to perfect play pretty easily, since the optimal tic-tac-toe strategy is very simple (Something like “start by playing in the center, respond by playing on a corner, try to create forks, etc”.) It seems like few-shot prompting isn’t enough to get them there, but I haven’t tried yet. It would be interesting to see if larger sizes of gpt-3 can learn faster than smaller sizes. This would indicate to what extent finetuning adds new capabilities rather than surfacing existing ones.
I still find the fact that gpt-4 cannot play tic-tac-toe despite prompting pretty striking on its own, especially since it’s so good at other tasks.
Optimal tic tac toe takes explaining the game in excruciating detail. https://chat.openai.com/share/75758e5e-d228-420f-9138-7bff47f2e12d
Skip over tic-tac-toe and go straight to chess: