Agent-to-agent pair programming • Hacker News Board

Re: Agent-to-agent pair programming

#61

Post by axldelafosse » Fri, Mar 27, 2026, 3:03 PM UTC

dgb23 wrote: post #33

If this approach turns out to be valuable, it's unlikely that it has anything to do with having multiple actual agents, but rather that it's valuable to have 2 configurations (system prompt, model, temp, context pruning, toolset etc.) of inside the same agent being swapped back and forth.

Yeah maybe! Right now I find it useful to use different agent harnesses but as the models get better (and the agent harnesses simpler), it might be possible to get the same result with the same model. Would be cool to experiment with open-source models

Re: Agent-to-agent pair programming

#62

Post by axldelafosse » Fri, Mar 27, 2026, 3:08 PM UTC

sibtain1997 wrote: post #49

hrimfaxi wrote: post #42

Earlier quoted context omitted.

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.

I’m glad someone is finally bringing this up, thank you!

What are you suggesting instead? To share the prompt in order to capture the intent? Usually I expect the plan to reflect the prompt.

I find it interesting when I create a PR after a quick session: the description really captures the intent instead of focusing on the actual implementation. I think it’s because the context is still intact, and that’s very useful.

Re: Agent-to-agent pair programming

#63

Post by axldelafosse » Fri, Mar 27, 2026, 3:09 PM UTC

rsafaya wrote: post #28

I think the A2A space is wide open. Great to see this approach using App Server and Channels. I tried built something similar (at a high level) for a more B2C use case for OpenClaw https://github.com/agentlink-dev/agentlink users. Currently I think the major Agents have not fully owned the "wake the Agent" use case fully. Regardless this is a very cool approach. All the best.

Cool! Thank you.

Re: Agent-to-agent pair programming

#64

Post by axldelafosse » Fri, Mar 27, 2026, 3:12 PM UTC

divan wrote: post #31

You can also create a skill for reviewing (which calls gemini/codex as a command line tool) and set instructions on how and when to use. Very flexible.

Yes, but what’s cool about loop is that it runs the interactive TUIs and establishes a direct connection between them. You can steer and answer questions in both sessions, not just from the main worker.

Re: Agent-to-agent pair programming

#65

Post by observationist » Fri, Mar 27, 2026, 3:20 PM UTC

shafyy wrote: post #40

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?”

Haha yeah... Wait until they start jacking up the subscription prices

They don't change the prices, they just modify the amount of compute allocated - slower speeds and fewer tokens, they can set everything in the background to optimize costs and returns, and the user never realizes anything has changed.

Sometimes they'll announce the changes, and they'll even try to spin it as improving services or increasing value.

Local AI capabilities are improving at a rapid pace, at some point soon we'll have an RWKV or a 4B LLM that performs at a GPT-5 level, with reasoning and all the bells and whistles, and hopefully that'll shake out most of the deceptive and shady tactics the big platforms are using.

Re: Agent-to-agent pair programming

#66

Post by torginus » Fri, Mar 27, 2026, 3:31 PM UTC

I think they're trying to implement every management fad with AI agents and see if improves performance.

Personally, I have tried pair programming, and it hasn't really felt like something that works, for various reasons - the main one is that I (and my partner) have complex thought processes in my head, that is difficult and cumbersome to articulate, and to an onlooker, it looks like I'm randomly changing code.

Re: Agent-to-agent pair programming

#67

Post by zombot » Fri, Mar 27, 2026, 4:26 PM UTC

Is there a prize yet for the most absurd application of AI? Pair programming seems a fair first step in the quest for this holiest of grails. How about an agentic implementation of the House of AI Lords?

Re: Agent-to-agent pair programming

#68

Post by latchkey » Fri, Mar 27, 2026, 4:34 PM UTC

torginus wrote: post #66

I think they're trying to implement every management fad with AI agents and see if improves performance. Personally, I have tried pair programming, and it hasn't really felt like something that works, for various reasons - the main one is that I (and my partner) have complex thought processes in my head, that is difficult and cumbersome to articulate, and to an onlooker, it looks like I'm randomly changing code.

I worked at Pivotal Labs where hundreds of developers pair programmed every day, all day. It works, the trick is learning how to get out of your head and communicate with your pair in a way that two brains works better than one.

I agree, it isn't for everyone.

Re: Agent-to-agent pair programming

#69

Post by zombot » Fri, Mar 27, 2026, 4:36 PM UTC

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.

What's the point of pair programming then if they both have the same opinions?

Re: Agent-to-agent pair programming

#70

Post by encoderer » Fri, Mar 27, 2026, 4:37 PM UTC

torginus wrote: post #66

I think they're trying to implement every management fad with AI agents and see if improves performance. Personally, I have tried pair programming, and it hasn't really felt like something that works, for various reasons - the main one is that I (and my partner) have complex thought processes in my head, that is difficult and cumbersome to articulate, and to an onlooker, it looks like I'm randomly changing code.

Pair programming works best when you are tasked with a problem that’s actually beyond your current abilities. You spend less time in your head because you are exploring a solution space for the first time.