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

231–240 of 351 posts

Re: Claude Code's new hidden feature: Swarms

#231

Post by alphazard »

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…

Every time I read something like this, it strikes me as an attempt to convince people that various people-management memes are still going to be relevant moving forward. Or even that they currently work when used on humans today. The reality is these roles don't even work in human organizations today. Classic "job_description == bottom_of_funnel_competency" fallacy.

If they make the LLMs more productive, it is probably explained by a less complicated phenomenon that has nothing to do with the names of the roles, or their descriptions. Adversarial techniques work well for ensuring quality, parallelism is obviously useful, important decisions should be made by stronger models, and using the weakest model for the job helps keep costs down.

Re: Claude Code's new hidden feature: Swarms

#232

Post by DanOpcode »

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…

Very cool! A couple of questions:

1. Are you using a Claude Code subscription? Or are you using the Claude API? I'm a bit scared to use the subscription in OpenCode due to Anthropic's ToS change.

2. How did you choose what models to use in the different agents? Do you believe or know they are better for certain tasks?

Re: Claude Code's new hidden feature: Swarms

#233

Post by rlayton2 »

alphazard wrote: post #231
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…

Every time I read something like this, it strikes me as an attempt to convince people that various people-management memes are still going to be relevant moving forward. Or even that they currently work when used on humans today. The reality is these roles don't even work in human organizations today. Classic "job_description == bottom_of_funnel_competency" fallacy. If they make the LLMs more productive, it is probab…

My understanding is that the main reason splitting up work is effective is context management.

For instance, if an agent only has to be concerned with one task, its context can be massively reduced. Further, the next agent can just be told the outcome, it also has reduced context load, because it doesn't need to do the inner workings, just know what the result is.

For instance, a security testing agent just needs to review code against a set of security rules, and then list the problems. The next agent then just gets a list of problems to fix, without needing a full history of working it out.

Re: Claude Code's new hidden feature: Swarms

#234

Post by andrekandre »

mrtesthah wrote: post #136
atonse wrote: post #118

Earlier quoted context omitted.

I don’t know what your stack is, but at least with elixir and especially typescript/nextJS projects, and properly documenting all those pieces you mentioned, it goes a long way. You’d be amazed.

I would never use, let alone pay for, a fully vibe-coded app whose implementation no human understands. Whether you’re reading a book or using an app, you’re communicating with the author by way of your shared humanity in how they anticipate what you’re thinking as you explore the work. The author incorporates and plans for those predicted reactions and thoughts where it makes sense. Ultimately the author is conveyin…

  > The second problem is that, the less human touch is there, the less consistent the mental model conveyed to the user is going to be, because a specification and collection of prompts does not constitute a mental model. This can create subconscious confusion and cognitive friction when interacting with the work.
tbf, this is a trend i see more and more across the industry; llm or not so many process get automated that teams just implement x cause pdm y said so and its because they need to meet goal z for the quarter... and everyone is on scrum autopilot they cant see the forest for the trees anymore.

i feel like the massive automation afforded by these coding agents may make this worse

Re: Claude Code's new hidden feature: Swarms

#235

Post by fphhotchips »

rlayton2 wrote: post #233
alphazard wrote: post #231

Earlier quoted context omitted.

Every time I read something like this, it strikes me as an attempt to convince people that various people-management memes are still going to be relevant moving forward. Or even that they currently work when used on humans today. The reality is these roles don't even work in human organizations today. Classic "job_description == bottom_of_funnel_competency" fallacy. If they make the LLMs more productive, it is probab…

My understanding is that the main reason splitting up work is effective is context management. For instance, if an agent only has to be concerned with one task, its context can be massively reduced. Further, the next agent can just be told the outcome, it also has reduced context load, because it doesn't need to do the inner workings, just know what the result is. For instance, a security testing agent just needs to…

Which, ultimately, is not such a big difference to the reason we split up work for humans, either. Human job specialization is just context management over the course of 30 years.

Re: Claude Code's new hidden feature: Swarms

#236

Post by ceroxylon »

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…

What are you building with the code you are generating?

Re: Claude Code's new hidden feature: Swarms

#237

Post by AlexErrant »

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…

For those ignorant, CAB is Change-advisory board

https://en.wikipedia.org/wiki/Change-advisory_board

Re: Claude Code's new hidden feature: Swarms

#238

Post by spondyl »

mtalantikite wrote: post #175
daxfohl wrote: post #124

I want it to generate better code but less of it, and be more proactive about getting human feedback before it starts going off the rails. This sounds like an inexorable push in the opposite direction. I can see this approach being useful once the foundation is more robust, has better common sense, knows when to push back when requirements conflict or are underspecified. But with current models I can only see this ap…

Agreed, I'm constantly coming back to a Claude tmux pane just to see it's decided to do something completely ridiculous. Just the other day I was having it add some test coverage stats to CI runs and when I came back it was basically trying to reinvent Istanbul in a bash script because the nyc tool wasn't installed in CI. I had to interrupt it and say "uh, just install nyc?". I was "Absolutely right!".

> it was basically trying to reinvent Istanbul in a bash script because the nyc tool wasn't installed in CI

For the first part of this comment, I thought "trying to reinvent Istanbul in a bash script" was meant to be a funny way to say "It was generating a lot of code" (as in generating a city's worth of code)

Re: Claude Code's new hidden feature: Swarms

#239

Post by Razengan »

Xmd5a wrote: post #63
Razengan wrote: post #55

Earlier quoted context omitted.

Swarm is actually human terminology I believe bees call it "bzz bzzt *clockwise dance* *wiggle*"

https://ignitionscience.wordpress.com/2022/05/17/quantum-bio...

https://www.youtube.com/watch?v=nq-dchJPXGA (A Bit Of Fry And Laurie)
Post reply on HN