Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Agent-to-agent pair programming

axeldelafosse.com

Post reply on HN
Print view View original

51–60 of 78 posts

Re: Agent-to-agent pair programming

#51

Post by axldelafosse »

etothet wrote: post #45

"Letting the agents loop can result in more changes than expected, which are usually welcome..." If "more changes than expected" means "out of scope", then I disagree. Those types of changes are exactly one of the things that's best to avoid whether code is being written by a person or an LLM.

It doesn’t mean that they are always out of scope, rather than the reviewer can be nitpicking (like humans do) and instead of addressing the comment in a follow-up PR, the change gets addressed in the same PR. So not necessarily out of scope, but it can add up and make it harder for a human to review.

That’s why I’m wondering if we should instruct the agents to act more like humans would: if the change can be done in a follow-up PR, this is probably what an experienced engineer would do.

Re: Agent-to-agent pair programming

#52

Post by bulletsvshumans »

ramon156 wrote: post #50

I've always wondered what it would be like if we reversed the roles. I remember people claiming they had gotten better results if an agent started asking the questions. What if we had an agent-to-agent network that contacted the human as a source of truth whenever they needed it. Keep a list of employees that are experts in said skill, then let them answer 1-2 questions. Or are we speeding up our replacement like thi…

I had a prototype where the agent primarily worked autonomously, and it could solicit human feedback via tool calls. But yes that pattern does feel like it is hastening the apocalypse.

Re: Agent-to-agent pair programming

#54

Post by pancsta »

ramon156 wrote: post #50

I've always wondered what it would be like if we reversed the roles. I remember people claiming they had gotten better results if an agent started asking the questions. What if we had an agent-to-agent network that contacted the human as a source of truth whenever they needed it. Keep a list of employees that are experts in said skill, then let them answer 1-2 questions. Or are we speeding up our replacement like thi…

What if a search engine queried YOU? That’s the question (I guess).

Re: Agent-to-agent pair programming

#55

Post by rootnod3 »

ramon156 wrote: post #50

I've always wondered what it would be like if we reversed the roles. I remember people claiming they had gotten better results if an agent started asking the questions. What if we had an agent-to-agent network that contacted the human as a source of truth whenever they needed it. Keep a list of employees that are experts in said skill, then let them answer 1-2 questions. Or are we speeding up our replacement like thi…

Hint: how did these humans become experts in that area? Definitely not by using AI.

Re: Agent-to-agent pair programming

#56

Post by axldelafosse »

woadwarrior01 wrote: post #46

This is very reminiscent of the review-loop Claude Code plugin. https://github.com/hamelsmu/claude-review-loop

Yes, the goal is the same. This plugin is similar to the Codex gstack skill.

What makes loop different is that it lets Claude and Codex talk to each other directly (receiving messages from Claude via the Codex App Server and from Codex via Claude Code Channels). I believe this approach works even better than having one agent spawn the other and wait for its output, or read/write to a shared file.

Re: Agent-to-agent pair programming

#57

Post by axldelafosse »

ramon156 wrote: post #50

I've always wondered what it would be like if we reversed the roles. I remember people claiming they had gotten better results if an agent started asking the questions. What if we had an agent-to-agent network that contacted the human as a source of truth whenever they needed it. Keep a list of employees that are experts in said skill, then let them answer 1-2 questions. Or are we speeding up our replacement like thi…

Interesting! Feels like a good way to write docs/memories. What I like about loop is that it runs the interactive TUIs so you can answer questions in both sessions (not just the main worker). It is not human multiplayer though (but that would be cool).

I like this idea, I’ll experiment with it as part of a brainstorming skill to make the agents ask clarifying questions (to each other and to the human in the loop).

Re: Agent-to-agent pair programming

#58

Post by axldelafosse »

3yr-i-frew-up wrote: post #41
not_ai wrote: post #35

Earlier quoted context omitted.

And expensive, exactly the way a pay per use product would push its customers… “It’s not working well enough!” We tell them. They respond with “Have you tried using it more?”

Back in 2024 I read a study saying: "Ask 4 LLMs the same question, if they all give you the same answer there is some 95-99% chance its correct" Soooo... Its not just greed. There is something there.

Yes exactly. I’m talking about this in the article. I found out that when Claude and Codex both review the same PR and both find the same issue, our team fixes it 100% of the time.

Re: Agent-to-agent pair programming

#60

Post by pkaeding »

pancsta wrote: post #54
ramon156 wrote: post #50

I've always wondered what it would be like if we reversed the roles. I remember people claiming they had gotten better results if an agent started asking the questions. What if we had an agent-to-agent network that contacted the human as a source of truth whenever they needed it. Keep a list of employees that are experts in said skill, then let them answer 1-2 questions. Or are we speeding up our replacement like thi…

What if a search engine queried YOU? That’s the question (I guess).

That's how they worked in Soviet Russia, right?
Post reply on HN