Thirty recursive loops of LLMs perform better than one prompt? I should hope so!... | Hacker News

Hacker News new | past | comments | ask | show | jobs | submit

login

fmbb 5 months ago | parent | context | favorite | on: AI agents but they're working in big tech

Thirty recursive loops of LLMs perform better than one prompt? I should hope so!

But how much power does it need?

alsima 5 months ago [–]

A lot...as you might imagine the costs of running the whole organization scale immensely.

Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact