Using openai to solve Wordle

I am trying to come up with a prompt to pick a next word in the game of Wordle. I tried a whole bunch of variations of this basic format but it keeps picking words that include letters not in the word like caret or train (in this particular instance).

Play a game to guess a five letter word. After each guess you are told how close your guess is to the word. Your next guess should take into account the information from the previous guesses. Try to guess the word in as few attempts as possible.

Guess: crane
Result: The letters c, r and n are not in the word. The letters a and e are in the corrects places in the word.

Guess:

1 Like

I tried giving it even more information and it is spectacularly bad at this game, lol. I will try giving it a whole example of a complete game and try again.

I’ve tried a few more prompt ideas and engines, but no better results:

1 Like

I would try including a bunch of examples of what you want to do in in the prompt, something like 50 shot learning. Show the guess progression at several different stages with desired completions. Get enough of these and you can find tune a model

1 Like

I think the problem here is that it is fundamentally adversarial. It’s almost like you’d need two separate prompts or models running to do this right… hmmm… there’s an idea

What do you mean by that?

The hurdle here might even be more fundamental than the fact it’s an adversarial game. I tried a few variations of the prompt below and couldn’t reliably get it to generate words with specific letters excluded.

I wonder if it could ‘learn’ the rules given enough examples?

You have an agent with hidden information and a guesser trying to defeat it. It’s basically a two player game, hence according to game theory it’s adversarial

3 Likes

I don’t think it understands word rules. I’ve been trying to get it to write poetry – it knows what a sonnet looks like but it can’t grasp the rules behind a sonnet.

Things like syllables and letters seem to be beyond it, but I’d happy to be proven wrong.

1 Like