Live data from Hacker News

Claude Code's new hidden feature: Swarms

twitter.com

51–60 of 351 posts

Re: Claude Code's new hidden feature: Swarms

#51
post #29
post #28

Earlier quoted context omitted.

That’s just spawning multiple parallel explore agents instructed to look at different things, and then compiling results That’s a pretty basic functionality in Claude code

Sounds like I should probably switch to claude code cli. Thanks for the info. :)

[dead]

Re: Claude Code's new hidden feature: Swarms

#52

This is just sub agents, built into Claude. You don’t need 300,000 line tmux abstractions written in go. You just tell Claude to do work in parallel with background sub agents. It helps to have a file for handing off the prompt, tracking progress, and reporting back. I also recommend constraining agents to their own worktrees. I am writing down the pattern here https://workforest.space while nearly everyone is buildi…

Yeah, since they introduced (possibly async) subagents, I've had my main claude instance act as a manager overseeing implementation agents, keeping it's context clean, and ensuring everything goes to plan in the highest quality way.

Re: Claude Code's new hidden feature: Swarms

#53
post #52

This is just sub agents, built into Claude. You don’t need 300,000 line tmux abstractions written in go. You just tell Claude to do work in parallel with background sub agents. It helps to have a file for handing off the prompt, tracking progress, and reporting back. I also recommend constraining agents to their own worktrees. I am writing down the pattern here https://workforest.space while nearly everyone is buildi…

Yeah, since they introduced (possibly async) subagents, I've had my main claude instance act as a manager overseeing implementation agents, keeping it's context clean, and ensuring everything goes to plan in the highest quality way.

yep this is exactly how I use the main agent too, I explicitly instruct to only ever use background async subagents. Not enough people understand that the claude code harness is event driven now and will wake up whenever these subagent completion events happen.

Re: Claude Code's new hidden feature: Swarms

#55
post #47
post #37

Earlier quoted context omitted.

Swarm is actually OpenAI's terminology https://github.com/openai/swarm

Swarm is actually bee terminology

Swarm is actually human terminology

I believe bees call it "bzz bzzt *clockwise dance* *wiggle*"

Re: Claude Code's new hidden feature: Swarms

#57
post #45

I'm a fan of AI coding tools but the trend of adding ever more autonomy to agents confuses me. The rate at which a person running these tools can review and comprehend the output properly is basically reached with just a single thread with a human in the loop. Which implies that this is not intended to be used in a setting where people will be reading the code. Does that... Actually work for anyone? My experience so…

Based on Gas Town, the people doing this agree that they are well beyond an amount of code they can review and comprehend. The difference seems to be they have decided on a system that makes it not a terrible idea in their minds.

Re: Claude Code's new hidden feature: Swarms

#58
> You're not talking to an AI coder anymore. You're talking to a team lead. The lead doesn't write code - it plans, delegates, and synthesizes.

Even 90 word tweets are now too long for these people to write without using AI, apparently.

Re: Claude Code's new hidden feature: Swarms

#59
post #58

> You're not talking to an AI coder anymore. You're talking to a team lead. The lead doesn't write code - it plans, delegates, and synthesizes. Even 90 word tweets are now too long for these people to write without using AI, apparently.

You're absolutely right! I apologise — hopefully you can forgive me.

Re: Claude Code's new hidden feature: Swarms

#60
post #58

> You're not talking to an AI coder anymore. You're talking to a team lead. The lead doesn't write code - it plans, delegates, and synthesizes. Even 90 word tweets are now too long for these people to write without using AI, apparently.

I wonder how much 'listening' to an LLM all day affects one's own prose? Mimicry is in the genes…
Post reply on HN