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

311–320 of 351 posts

Re: Claude Code's new hidden feature: Swarms

#311

Post by simoncion »

birken wrote: post #75

I'd really like to see a regular poll on HN that keeps track of which AI coding agents are the most popular among this community, like the TIOBE Index for programming languages. Hard to keep up with all the changes and it would be nice to see a high level view of what people are using and how that might be shifting over time.

> ...like the TIOBE Index for programming languages.

Why would you want a list with such godawful methodology? Here's [0] what the TIOBE folks have to say about their data analysis process:

  Since there are many questions about the way the TIOBE index is assembled, a special page is devoted to its definition. Basically the calculation comes down to counting hits for the search query
  
  +" programming"
The only advantage this methodology has is it's extremely cheap for the surveyor to use.

[0] https://www.tiobe.com/tiobe-index/programminglanguages_defin...>

Re: Claude Code's new hidden feature: Swarms

#312

Post by ljm »

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…

It shows me that there doesn’t appear to be an escape from Conway’s Law, even when you replace the people in an organisation with machines. Fundamentally, the problem is still being explored from the perspective of an organisation of people and it follows what we’ve experienced to work well (or as well as we can manage).

Re: Claude Code's new hidden feature: Swarms

#313

Post by ryanjshaw »

uxhacker wrote: post #294
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…

Persona’s is not the same thing as a role. The point of the role is to limit what the work of the agent, and to focus it on one or two behaviors. What the paper is really addressing is does key words like you are a helpful assistant give better results. The paper is not addressing a role such as you are system designer, or you are security engineer which will produce completely different results and focus the results…

Aside from what you said about applicability, the paper actually contradicts their claim!

In the domain alignment section:

> The coefficient for “in-domain” is 0.004(p Although the effect size is small, why would you not take advantage of it.

Re: Claude Code's new hidden feature: Swarms

#314

Post by big-guy23 »

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…

Share your code of the “actual best quality “ or this is just another meaningless and suspicious attempt to get users to put the already expensive AI in a for-loop to make it even more expensive

Re: Claude Code's new hidden feature: Swarms

#315

Post by chickensong »

lwhi wrote: post #305
XenophileJKO wrote: post #260

Earlier quoted context omitted.

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'?

You can create a context that includes info and instructions, but the agent may not pay attention to everything in the context, even if context usage is low.

Re: Claude Code's new hidden feature: Swarms

#316

Post by adastra22 »

mmcclure wrote: post #250
adastra22 wrote: post #214

Earlier quoted context omitted.

That’s not what this subthread is about. They’re talking about the subagent within Claude Code itself. Btw, you can use the Claude Agent SDK (the renamed Claude Code SDK) with a subscription. I can tell you it works out of the box, and AFAIK it is not a ToS violation.

Oh really? I was looking at the Agent SDK for an idea and the docs seemed to imply that wasn't the case. Unless previously approved, we do not allow third party developers to offer Claude.ai login or rate limits for their products, including agents built on the Claude Agent SDK. Please use the API key authentication methods described in this document instead. I didn't dig deeper, but I'd pick it back up for a little…

You can’t resell - that’s the third party language. You can build and use for your own purposes. And yes it just picks up your local sessions out of the box.

Re: Claude Code's new hidden feature: Swarms

#317

Post by Sateeshm »

serial_dev wrote: post #83
czhu12 wrote: post #66

The problem I’ve been having is that when Claude generates copious amounts of code, it makes it way harder to review than small snippets one at a time. Some would argue there’s no point reviewing the code, just test the implementation and if it works, it works. I still am kind of nervous doing this in critical projects. Anyone just YOLO code for projects that’s not meant to be one time, but fully intend to have to be…

In a professional setting where you still have coding standards, and people will review your code, and the code actually reaches hundreds of thousands of real users, handling one agent at a time is plenty for me. The code output is never good enough, and it makes up stuff even for moderately complicated debugging ("Oh I can clearly see the issue now", I heard it ten times before and you were always wrong!) I do use t…

Exactly my experience too.

I also heard "I see the issue now" so many times because it missed or misunderstood something very simple.

Re: Claude Code's new hidden feature: Swarms

#318

Post by mythrwy »

replwoacause wrote: post #230

I've done plenty of vibe coding even though I know how to program but I mostly work with a single agent through its CLI. The progress is really good and more importantly, I can follow it. I can read the output, test it, and understand what changed and why. I don't see much upside in swarms. But I do see the downside which is losing the ability to keep the whole system in my head. The codebase starts growing in direct…

Ya I saw a comment a few weeks ago about "leaving productivity on the table!". I'm generating 3 long files at a prompt now, how much more productivity do I need? Any more and I'll have zero idea what is going on.
Post reply on HN