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

301–310 of 351 posts

Re: Claude Code's new hidden feature: Swarms

#301

Post by rafaelmdec »

dist-epoch wrote: post #298
joshuaisaact wrote: post #279

Earlier quoted context omitted.

This has been pretty comprehensively disproven: https://arxiv.org/abs/2311.10054 Key findings: -Tested 162 personas across 6 types of interpersonal relationships and 8 domains of expertise, with 4 LLM families and 2,410 factual questions -Adding personas in system prompts does not improve model performance compared to the control setting where no persona is added -Automatically identifying the best persona is challen…

In a discussion about LLMs you link to a paper from 2023, when not even GPT-4 was available? And then you say: > comprehensively disproven ? I don't think you understand the scientific method

...or even how fast technology is evolving in this field.

Re: Claude Code's new hidden feature: Swarms

#302

Post by kaspermarstal »

mogili1 wrote: post #215
kaspermarstal wrote: post #205

Earlier quoted context omitted.

Can you share technical details please? How is this implemented? Is it pure prompt-based, plugins, or do you have like script that repeatedly calls the agents? Where does the kanban live?

Not the OP, but this is how I manage my coding agent loops: I built a drag and drop UI tool that sets up a sequence of agent steps (Claude code or codex) and have created different workflows based on the task. I'll kick them off and monitor. Here's the tool I built for myself for this: https://github.com/smogili1/circuit

Cool, thanks for sharing!

Re: Claude Code's new hidden feature: Swarms

#303

Post by rafaelmdec »

AlexErrant wrote: post #237
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

Thank you for the link and the compliment.

Re: Claude Code's new hidden feature: Swarms

#304

Post by vercaemert »

sathish316 wrote: post #253
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…

Subagent orchestration without the overhead of frameworks like Gastown is genuinely exciting to see. I’ve recorded several long-running demos of Pied-Piper, which is a Subagents orchestration system for Claude Code and ClaudeCodeRouter+OpenRouter here: https://youtube.com/playlist?list=PLKWJ03cHcPr3OWiSBDghzh62A... I came across a concept called DreamTeam, where someone was manually coordinating GPT 5.2 Max for plann…

Personally, I'm fascinated by the opening for protocol languages to become relevant.

The previous generations of AI (AI in the academic sense) like JASON, when combined with a protocol language like BSPL, seems like the easiest way to organize agent armies in ways that "guarantee" specific outcomes.

The example above is very cool, but I'm not sure how flexible it would be (and there's the obvious cost concern). But, then again, I may be going far down the overengineering route.

Re: Claude Code's new hidden feature: Swarms

#305

Post by lwhi »

XenophileJKO wrote: post #260
rlayton2 wrote: post #233

Earlier quoted context omitted.

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…

So two things.. Yes this helps with context and is a primary reason to break out the sub-agents. However one of the bigger things is by having a focus on a specific task or a role, you force the LLM to "pay attention" to certain aspects. The models have finite attention and if you ask them to pay attention to "all things".. they just ignore some. The act of forcing the model to pay attention can be acoomplished in al…

What do you think context is, if not 'attention'?

Re: Claude Code's new hidden feature: Swarms

#306

Post by JasperBekkers »

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…

This is genuinely cool, the CAB rejecting implementations must be hilarious to watch in action. The Kanban + Git worktree isolation is smart for keeping agents from stepping on each other.

I've been working on something in this space too. I built https://sonars.dev specifically for orchestrating multiple Claude Code agents working in parallel on the same codebase. Each agent gets its own workspace/worktree and there's a shared context layer so they can ask each other questions about what's happening elsewhere (kind of like your Librarian role but real-time).

The "ask the architect" pattern you described is actually built into our MCP tooling: any agent can query a summary of what other agents have done/learned without needing to parse their full context.

Re: Claude Code's new hidden feature: Swarms

#307

Post by joshuaisaact »

dist-epoch wrote: post #298
joshuaisaact wrote: post #279

Earlier quoted context omitted.

This has been pretty comprehensively disproven: https://arxiv.org/abs/2311.10054 Key findings: -Tested 162 personas across 6 types of interpersonal relationships and 8 domains of expertise, with 4 LLM families and 2,410 factual questions -Adding personas in system prompts does not improve model performance compared to the control setting where no persona is added -Automatically identifying the best persona is challen…

In a discussion about LLMs you link to a paper from 2023, when not even GPT-4 was available? And then you say: > comprehensively disproven ? I don't think you understand the scientific method

Fair point on the date - the paper was updated October 2024 with Llama-3 and Qwen2.5 (up to 72B), same findings. The v1 to v3 revision is interesting. They initially found personas helped, then reversed their conclusion after expanding to more models.

"Comprehensively disproven" was too strong - should have said "evidence suggests the effect is largely random." There's also Gupta et al. 2024 (arxiv.org/abs/2408.08631) with similar findings if you want more data points.

Re: Claude Code's new hidden feature: Swarms

#309

Post by joshuaisaact »

ryanjshaw wrote: post #288
joshuaisaact wrote: post #267

This feels like massively overengineering something very simple. Agents are stateless functions with a limited heap (context window) that degrades in quality as it fills. Once you see it that way, the whole swarm paradigm is just function scoping and memory management cosplaying as an org chart: Agent = function Role = scope constraints Context window = local memory Shared state file = global state Orchestration = co…

I don’t follow. You said it’s over engineering and then proposed what appears to be functionally the exact same thing? Isn’t a “role” just a compact way to configure well-known systems of constraints by leveraging LLM training? Is your proposal that everybody independently reinvent the constraints wheel, so to speak?

Fair push back. The distinction I'm drawing is between:

A. Using a role prompt to configure a single function's scope ("you are a code reviewer, focus on X") - totally reasonable, leverages training

B. Building an elaborate multi-agent orchestration layer with hand-offs, coordination protocols, and framework abstractions on top of that

I'm not arguing against A. I'm arguing that B often adds complexity without proportional benefit, especially as models get better at long-context reasoning.

Fairly recent research (arXiv May 2025: "Single-agent or Multi-agent Systems?" - https://arxiv.org/abs/2505.18286) found that MAS benefits over single-agent diminish as LLM capabilities improve. The constraints that motivated swarm architectures are being outpaced by model improvements. I admit the field is moving fast, but the direction of travel appears to be that the better the models get, the simpler your abstractions need to be.

So yes, use roles. But maybe don't reach for a framework to orchestrate a PM handing off to an Engineer handing off to QA when a single context with scoped instructions would do.

Re: Claude Code's new hidden feature: Swarms

#310

Post by amelius »

ComplexSystems wrote: post #291
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…

How much does this setup cost? I don't think a regular Claude Max subscription makes this possible.

Can't you just use time-sharing and let the entire task run over night?
Post reply on HN