Agent-to-agent pair programming

(axeldelafosse.com)

67 points | by axldelafosse 7 hours ago

14 comments

  • yesensm 48 minutes ago
    I’m curious whether anyone has measured this systematically. Right now most of the evidence for multi-agent setups still feels anecdotal.
  • edf13 2 hours ago
    Nice - I do something similar in a semi manual way.

    I do find Codex very good at reviewing work marked as completed by Claude, especially when I get Claude to write up its work with a why,where & how doc.

    It’s very rare Claude has fully completed the task successfully and Codex doesn’t find issues.

    • axldelafosse 1 hour ago
      I created the first version of loop after getting tired of doing this manually!
      • edf13 1 hour ago
        I’m going to take a look today!
  • cadamsdotcom 4 hours ago
    The vibes are great. But there’s a need for more science on this multi agent thing.
    • axldelafosse 4 hours ago
      I agree! Right now it is leveraging the Codex App Server, which is open-source and very well implemented, but using Claude Code Channels is probably a bit hacky.

      The good thing is that it establishes a direct connection so it's already much better than having one agent spawn the other and wait for its output, or read/write to a shared .md file -- but it would be cool to make it work for all agent harnesses.

      Open to ideas! The repo is open-source.

    • d0963319287 3 hours ago
      there’s a need for more science on this multi agent thing
  • alienreborn 5 hours ago
    I have been trying a similar setup since last week using https://rjcorwin.github.io/cook/
  • vessenes 5 hours 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.
  • ph4rsikal 3 hours ago
  • shreyssh 1 hour ago
    This is interesting for code, but I'm curious about agent-to-agent coordination for ops tasks — like one agent detecting a database anomaly and another auto-remediating it
    • highphive 37 minutes ago
      I think a lot of people/companies are integrating workflows like that, it's just separate from the point of agent pair coding.

      The interesting thing here is agents working together to be better at a single task. Not agents integrated in a workflow. There's a lot of opportunity in "if this then that" scenarios that has nothing to do with two agents communicating on one single element of a problem, it's just Agent detect -> agent solve (-> Agent review? Agent deploy? Etc.)

  • elicohen1000 1 hour ago
    Been using Claude for pair programming since we're just two founders building MediTailor. It's wild - I can now prototype features that would have required hiring a full-time dev six months ago. The bottleneck shifted from "can we build this" to "should we build this" which is a much better problem to have.
  • bradfox2 4 hours 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.

    • _ink_ 1 hour ago
      How do you do this? Are you just switching between clis? Or is there a tool that uses the models in that way?
    • encoderer 4 hours ago
      Yes I’ve had a lot of success with this too. I found with prompt tightening I seldom do more than 5 rounds now, but it also does an explicit plan step with plan review.

      Currently I’m authoring with codex and reviewing with opus.

      • axldelafosse 4 hours ago
        Good reminder: don't forget the plan review!
  • jedisct1 5 hours 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.

  • hikaru_ai 1 hour ago
    [dead]
  • kevinbaiv 1 hour ago
    [dead]
  • vacancy892 2 hours ago
    [dead]