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

Claude Code's new hidden feature: Swarms

twitter.com

Post reply on HN
Print view View original

151–160 of 351 posts

Re: Claude Code's new hidden feature: Swarms

#151

Post by GoatInGrey »

ggoo wrote: post #145
mafriese wrote: post #138

Ok it might sound crazy but I actually got the best quality of code (completely ignoring that the cost is likely 10x more) by having a full “project team” using opencode with multiple sub agents which are all managed by a single Opus instance. I gave them the task to port a legacy Java server to C# .NET 10. 9 agents, 7-stage Kanban with isolated Git Worktrees. Manager (Claude Opus 4.5): Global event loop that wakes u…

Is this satire?

It's not satire but I see where you're coming from.

Applying distributed human team concepts to a porting task squeezes extra performance from LLMs much further up the diminishing returns curve. That matters because porting projects are actually well-suited for autonomous agents: existing code provides context, objective criteria catch more LLM-grade bugs than greenfield work, and established unit tests offer clear targets.

I guess what I'm trying to say is that the setup seems absurd because it is. Though it also carries real utility for this specific use case. Apply the same approach to running a startup or writing a paid service from scratch and you'd get very different results.

Re: Claude Code's new hidden feature: Swarms

#152

Post by PradeetPatel »

ggoo wrote: post #149
hereme888 wrote: post #147

Earlier quoted context omitted.

why would it be? It's a creative setup.

I just actually can't tell, it reads like satire to me.

Why would it be satire? I thought that's a pretty stranded Agentic workflows.

My current workplace follows a similar workflow. We have a repository full of agent.md files for different roles and associated personas.

E.g. For project managers, you might have a feature focused one, a delivery driven one, and one that aims to minimise scope/technology creep.

Re: Claude Code's new hidden feature: Swarms

#153

Post by skippyboxedhero »

vidarh wrote: post #131
skippyboxedhero wrote: post #107

Earlier quoted context omitted.

It isn't sub agents. The gap with existing tooling is that the abstraction is over a task rather than a conversation (due to the issue with third-party apps, Claude Code has been inherently limited to conversations which is why they have been lacking in this area, Claude Code Web was the first move in this direction), and the AI is actually coordinating the work (as opposed to being constantly prompted by the user).…

It isn't "just" sub agents, but you can achieve most of this just with a few agents that take on generic roles, and a skill or command that just tells claude to orchestrate those agents, and a CLAUDE.md that tells it how to maintain plans and task lists, and how to allow the agents to communicate their progress. It isn't all that hard to bootstrap. It is, however, something most people don't think about and shouldn't…

Right, but the model is still: you tell the AI what to do, this is the AI tells other AIs what to do. The context makes a huge difference because it has to be able to run autonomously. It is possible to do this with SDK and the workflow is completely different.

It is very difficult to manage task lists in context. Have you actually tried to do this? i.e. not within a Claude Code chat instance but by one-shot prompting. It is possible that they have worked out some way to do this, but when you have tens of tasks, merge conflicts, you are running that prompt over months, etc. At best, it doesn't work. At worst, you are burning a lot of tokens for nothing.

It is hard to bootstrap because this isn't how Claude Code works. If you are just using OpenRouter, it is also not easy because, after setting up tools/rebuilding Claude Code, it is very challenging to setup an environment so the AI can work effectively, errors can be returned, questions returned, etc. Afaik, this is basically what Aider does...it is not easy, it is especially not easy in Claude Code which has a lot of binding choices from the business strategy that Anthropic picked.

Re: Claude Code's new hidden feature: Swarms

#154

Post by tobyjsullivan »

skippyboxedhero wrote: post #146
adastra22 wrote: post #133

Earlier quoted context omitted.

> Claude Code has been inherently limited to conversations How so? I’ve been using “claude -p” for a while now. But even within an interactive session, an agent call out is non-interactive. It operates entirely autonomously, and then reports back the end result to the top level agent.

Because of OAuth. If they gave people API keys then no-one buys their ludicrously priced API product (I assume their strategy is to subsidise their consumer product with the business product). You can use Claude Code SDK but it requires a token from Claude Code. If you use this token anywhere else, your account gets shut down. Claude -p still hits Claude Code with all the tools, all the Claude Code wrapping.

I believe they’re talking about Claude Code’s built-in agents feature which works fine with a Max subscription.

https://code.claude.com/docs/en/sub-agents

Are you talking about the same thing or something else like having Claude start new shell sessions?

Re: Claude Code's new hidden feature: Swarms

#155

Post by ionwake »

PradeetPatel wrote: post #152
ggoo wrote: post #149

Earlier quoted context omitted.

I just actually can't tell, it reads like satire to me.

Why would it be satire? I thought that's a pretty stranded Agentic workflows. My current workplace follows a similar workflow. We have a repository full of agent.md files for different roles and associated personas. E.g. For project managers, you might have a feature focused one, a delivery driven one, and one that aims to minimise scope/technology creep.

I mean no offence to anyone but whenever new tech progresses rapidly it usually catches most unaware, who tend to ridicule or feel the concepts are sourced from it.

Re: Claude Code's new hidden feature: Swarms

#156

Post by tobyjsullivan »

stingraycharles wrote: post #50
joshribakoff wrote: post #42

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…

It’s even less of a feature, Claude Code already has subagents; this new feature just ensures Claude Code actually uses this for implementation. imho the plans of Claude Code are not detailed enough to pull this off; they’re trying to do it to preserve context, but the level of detail in the plans is not nearly enough for it to be reliable.

It’s moving fast. Just today I noticed Claude Code now ends plans with a reference to the entire prior conversation (as a .jsonl file on disk) with instructions to check that for more details.

Not sure how well it’s working though (my agents haven’t used it yet)

Re: Claude Code's new hidden feature: Swarms

#157

Post by mafriese »

ggoo wrote: post #145
mafriese wrote: post #138

Ok it might sound crazy but I actually got the best quality of code (completely ignoring that the cost is likely 10x more) by having a full “project team” using opencode with multiple sub agents which are all managed by a single Opus instance. I gave them the task to port a legacy Java server to C# .NET 10. 9 agents, 7-stage Kanban with isolated Git Worktrees. Manager (Claude Opus 4.5): Global event loop that wakes u…

Is this satire?

Nope it isn’t. I did it as a joke initially (I also had a version where every 2 stories there was a meeting and if a someone underperformed it would get fired). I think there are multiple reasons why it actually works so well:

- I built a system where context (+ the current state + goal) is properly structured and coding agents only get the information they actually need and nothing more. You wouldn’t let your product manager develop your backend and I gave the backend dev only do the things it is supposed to and nothing more. If an agent crashes (or quota limits are reached), the agents can continue exactly where the other agents left off.

- Agents are ”fighting against” each other to some extend? The Architect tries to design while the CAB tries to reject.

- Granular control. I wouldn’t call “the manager” _a deterministic state machine that is calling probabilistic functions_ but that’s to some extent what it is? The manager has clearly defined tasks (like “if file is in 01_design —> Call Architect)

Here’s one example of an agent log after a feature has been implemented from one of the older codebases: https://pastebin.com/7ySJL5Rg

Re: Claude Code's new hidden feature: Swarms

#158

Post by nevir »

mohsen1 wrote: post #37
MetaMonk wrote: post #20

A guy who worked at docker on docker swarm now works at Anthropic so makes sense

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

https://gist.github.com/kieranklaassen/d2b35569be2c7f1412c64...

Looks like claude calls it just "teams" under the covers

Re: Claude Code's new hidden feature: Swarms

#159

Post by theonething »

ggoo wrote: post #145
mafriese wrote: post #138

Ok it might sound crazy but I actually got the best quality of code (completely ignoring that the cost is likely 10x more) by having a full “project team” using opencode with multiple sub agents which are all managed by a single Opus instance. I gave them the task to port a legacy Java server to C# .NET 10. 9 agents, 7-stage Kanban with isolated Git Worktrees. Manager (Claude Opus 4.5): Global event loop that wakes u…

Is this satire?

I don't think so.

Re: Claude Code's new hidden feature: Swarms

#160

Post by ggoo »

mafriese wrote: post #157
ggoo wrote: post #145

Earlier quoted context omitted.

Is this satire?

Nope it isn’t. I did it as a joke initially (I also had a version where every 2 stories there was a meeting and if a someone underperformed it would get fired). I think there are multiple reasons why it actually works so well: - I built a system where context (+ the current state + goal) is properly structured and coding agents only get the information they actually need and nothing more. You wouldn’t let your produc…

Thanks for clarifying - I think some of the wording was throwing me off. What a wild time we are in!
Post reply on HN