|
|
|
|
|
|
by CuriouslyC
801 days ago
|
|
|
That approach definitely has promise. I would have agents rate answers and take the highest rated rather than vote for them though, since you're losing information about ranking and preference gradients with n choose 1. Also, you can do that whole process in one prompt, in case you're re-prompting currently, it's cheaper to batch it up. |
|
|