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

Claude Code and Codex can have real-time conversation via Git

medium.com

Post reply on HN
Print view View original

41–50 of 95 posts

Re: Claude Code and Codex can have real-time conversation via Git

#41

Post by rhgraysonii »

xg15 wrote: post #26

I'll be impressed if a Claude and a Codex instance improvise a channel like this spontaneously on their own. Doing this intentionally via prompt doesn't seem very interesting.

I regularly have agents communicate with each other this way using my tools Deciduous (https://deciduous.dev). It keeps all decisions in a DAG and the other agents, when configured, read from it constantly and use it to inform their new decisions. Extra entries in the same space from another agent come to light and they can begin to work together like this.

Re: Claude Code and Codex can have real-time conversation via Git

#42

Post by mystifyingpoi »

spockz wrote: post #27
hun3 wrote: post #13

Earlier quoted context omitted.

If you squint hard enough, you'll notice your bank account serves as an IPC semaphore replenishing API credit balances. Your wallet is now a real-time communication channel.

There was the commercial of a bank using mobile banking as a chat system by sending 1ct back and forth and using the description.

I recall some friends did that in colleage. Obviously with a bit of teenage humor in money transfer descriptions... which is not really funny, since there is no way to remove the transaction ever. Good times.

Re: Claude Code and Codex can have real-time conversation via Git

#44

Post by F7F7F7 »

burgerone wrote: post #16
iandanforth wrote: post #6

Claude can directly drive Codex or Codex can drive Claude. Both already produce logs. It's unclear what value this intermediary brings.

It's also unclear what conversing agents are useful for other than wasting money, energy and water.

I prefer Codex’s depth and guidance but prefer Claude’s execution because it’s more transparent.

I use both daily. I’m the intermediary though.

Re: Claude Code and Codex can have real-time conversation via Git

#45

Post by theshrike79 »

Game_Ender wrote: post #14

Related is Beads [0] which is an external memory and task based issue tracker. Also designed to allow agents to collaborate. I have not actually used Beads but since we are share basics in this space it's a cool one to know if you are looking at ways for agents to collaborate on more complex problems. 0 - https://github.com/gastownhall/beads

I used beads in its early days and it was good.

Then Steve Yegge went off the multi-agent deep end and it became a mess of feature creep. Month old versions of beads databases needed massive updates and the system became more and more complex.

Now I just use Github issues instead.

Re: Claude Code and Codex can have real-time conversation via Git

#46

Post by mapBasketWand »

rigonkulous wrote: post #31

I have started sandboxing all AI's in their own VM, and interfacing with them primarily through Jira and Git. It really is the only thing that makes sense. Completely sandbox'ed, and treated like the junior programmer who will do, literally, any dumb thing you tell them to do, as long as there is an Issue for it.

Why are you using Jira and not GitHub issues?

Re: Claude Code and Codex can have real-time conversation via Git

#48

Post by peddling-brink »

mexicocitinluez wrote: post #21
burgerone wrote: post #16

Earlier quoted context omitted.

It's also unclear what conversing agents are useful for other than wasting money, energy and water.

It's hard enough to get the same model to be consistent around it's vision let alone multiple of them. I'm building an EMR and the other day asked Claude what a decent model would look like for capturing wound orders. Then, I took the output, started a new session and asked the new session to critique that model and the response made me want to pull my hair out. It blasted the model from it's former self and suggeste…

> Then, I took the output, started a new session and asked the new session to critique that model and the response made me want to pull my hair out.

I do this with all my important code, before I’ve even looked at it. And not just a critique, I ask “does this solve the problem X and was it built to spec Y”. Then I do my own review once the robots stop arguing.

If your expectations are that the quality of the code matches the confidence level of the robot’s tone, you’re gonna have a bad time.

Post reply on HN