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

Show HN: A lightweight way to make agents talk without paying for API usage

juanpabloaj.com

Post reply on HN
Print view View original

11–20 of 21 posts

Re: Show HN: A lightweight way to make agents talk without paying for API usage

#13

Post by pidgeon_lover »

> use the subscription plans you already have, avoid paying for API usage, and keep the setup simple enough that you can try it in a few minutes.

That interested me, but the article does not explain how to do this at all. I was hoping it would tell how use my work's ChatGPT Pro subscription via the CLI without having to pay per token over their API.

Re: Show HN: A lightweight way to make agents talk without paying for API usage

#14

Post by d4rkp4ttern »

My regular workflow is to run code agents in Tmux panes and often I have Claude Code consult/collaborate with Codex, using my tmux-cli [1] tool, which is a wrapper around Tmux that provides good defaults (delay etc) for robust sending of messages, and waiting for completion etc.

[1] https://pchalasani.github.io/claude-code-tools/tools/tmux-cl...

Re: Show HN: A lightweight way to make agents talk without paying for API usage

#15

Post by harish124 »

Using tmux session as short-term memory is great idea. When you force a model to look at other model's cli history they tend to stay focussed on the technical constraints already discussed.

Also, I like this idea because now the agents are not talking in private, they're talking in a window you can peek into. If you see the two AI agents starting to get confused or repeating mistakes, you can just hop into that same window, type a quick correction, and jump back out.

Re: Show HN: A lightweight way to make agents talk without paying for API usage

#16

Post by 7777777phil »

> whether the final result is actually better, or whether it is just a more polished hallucinatio

Agents sampled from the same base model agreeing with each other isn't validation, it's correlation. Cheaper orchestration mostly amplifies whatever bias the model already has. Neat hack though.

Post reply on HN