OpenAI codex can now generate best of N responses
help.openai.comAt first pass this seems 1) incredibly useful for me 2) incredibly expensive for them, but after using it a bit I'm thinking it might be incredibly valuable for them because once I review and approve one of the options, they're essentially getting preference data on which of the approaches I felt was "best".
Thoughts from those who have used it?
I've been using it for problems where the model struggles. Even if it doesn't find an answer, the extra opportunity for it to explore the problem space usually helps in getting me closer to the right answer.