Re:I played chess against ChatGPT-4 and lost
by rajnathani on Sunday March 19, 2023 @03:15AM
(#35216764)
Check if you replace the “ValValVal” formatting you mentioned with spaces (such that “XOO” becomes “X O O”). The reason I suggest this is that the NLP tokenizer would set “XOO” to 1 token, which could cause interpretation issues.
[ Parent
| on HN ]
Re:I played chess against ChatGPT-4 and lost
by dwaltrip on Sunday March 19, 2023 @03:50AM
(#35216925)
Very interesting... I tried your suggestion and fixed a few other typos / inconsistencies in my prompt.
Here is the new version: https://pastebin.com/BSUGtxfb
It seems to be performing better! It played 2 games without mistakes, and was able to evaluate diagonals correctly. I just hit my usage limit for GPT-4, I'll do more testing later.
I asked GPT-4 to give me a prompt to use with it in order to set up a game of tic tac toe and it came up with a similar representation and played successfully.
I'm still blown away that this is possible.