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

41–50 of 78 posts

Re: Agent-to-agent pair programming

#41

Post by 3yr-i-frew-up »

not_ai wrote: post #35
yesensm wrote: post #25

I’m curious whether anyone has measured this systematically. Right now most of the evidence for multi-agent setups still feels anecdotal.

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.

Re: Agent-to-agent pair programming

#42

Post by hrimfaxi »

sibtain1997 wrote: post #36

The PLAN.md question is the one worth pulling on. Once the plan lives in git or the PR it's already downstream of intent and whoever defined what to build has already handed off. The harder problem is giving agents access to the original intent, not just the implementation plan derived from it. When there's drift between what was planned and what got built, a git-resident PLAN.md makes it hard to trace back to why th…

The plan will always be downstream of intent though. At least in git you can track the evolution of the plan over time and hopefully annotate the rationale for changes in direction.

Re: Agent-to-agent pair programming

#43

Post by lancekey »

edf13 wrote: post #17

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.

Do you see any benefit in doing this locally versus having Codex review the PR Claude generates?

Re: Agent-to-agent pair programming

#45

Post by etothet »

"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.

Re: Agent-to-agent pair programming

#49

Post by sibtain1997 »

hrimfaxi wrote: post #42
sibtain1997 wrote: post #36

The PLAN.md question is the one worth pulling on. Once the plan lives in git or the PR it's already downstream of intent and whoever defined what to build has already handed off. The harder problem is giving agents access to the original intent, not just the implementation plan derived from it. When there's drift between what was planned and what got built, a git-resident PLAN.md makes it hard to trace back to why th…

The plan will always be downstream of intent though. At least in git you can track the evolution of the plan over time and hopefully annotate the rationale for changes in direction.

Fair point. Git helps track how the plan changes, but it doesn’t always capture the original intent behind it.

Re: Agent-to-agent pair programming

#50

Post by ramon156 »

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 this?

Post reply on HN