Agent-to-Agent Pair Programming

(axeldelafosse.com)

20 points | by axldelafosse 3 hours ago ago

5 comments

  • bradfox2 21 minutes ago

    Multi turn review of code written by cc reviewed by codex works pretty well. Been one of the only ways to be able to deliver larger scoped features without constant bugs. I've seen them do 10-15 rounds of fix and review until complete.

    Also implemented this as a gh action, works well for sentry to gh to auto triage to fix pr.

  • vessenes an hour ago

    I prefer claude for generation / creativity, codex for bull-headed, accurate complaining and audit. Very rarely claude just doesn't "get it" and it makes sense to have codex direct edit. But generally I think it's happiest and best used complaining.

  • cadamsdotcom 31 minutes ago

    The vibes are great. But there’s a need for more science on this multi agent thing.

  • alienreborn an hour ago

    I have been trying a similar setup since last week using https://rjcorwin.github.io/cook/

  • jedisct1 an hour ago

    I systematically use reviewers agents in Swival: https://swival.dev/pages/reviews.html

    Even with the same model (--self-review), that makes a huge difference, and immediately highlights how bad the first iterations of an LLM output can be.