Generate multiple responses in polling and select the most popular choice? Particularly for -accurate grid overwrite about self-operating-computer HOT 7 CLOSED

@klxu03 Curious how much this would affect the token count and cost per API call.

from self-operating-computer.

I don't think that much.

Seems like it is input + n * output

If n (the number of completions returned) or best_of (the number of completions generated for consideration) are set to > 1, each request will create multiple outputs. Here, you can consider the number of generated tokens as [ max_tokens * max (n, best_of) ]

https://platform.openai.com/docs/guides/production-best-practices/number-of-completion-tokens

I think most of the API cost will be in embedding the input (tokens, and the image especially)

from self-operating-computer.

@klxu03 This could be an interesting approach.

@Sameeraali835 Feel free to join the Discord to discuss any issues you're having. You can also open an issue here on the repository if it could be affecting other users as well.

from self-operating-computer.

@klxu03 still believes this approach shows promise. Would love to see a PR for it!

from self-operating-computer.

@klxu03 still believes this approach shows promise. Would love to see a PR for it!

ahh yes! was looking into it, looks like you can also just set temperature to like 0 so there's no variability (in the grid choice at least), gpt basically always takes the highest probabilistic token as well

from self-operating-computer.

I was having the hardest time with repetitive mouse clicks originally, so I played around with temperature to try to fix it. I should try reducing it and see if repetition is still a problem

from self-operating-computer.

Closing since it has been some time and we never pursued further

from self-operating-computer.