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

331–340 of 351 posts

Re: Claude Code's new hidden feature: Swarms

#331

Post by XenophileJKO »

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'?

Context is the information you give the model, attention is what parts it focuses on.

And this is finite in capacity and emergent from the architecture.

Re: Claude Code's new hidden feature: Swarms

#333

Post by VivaTechnics »

OPINION:

This will only compound wasted time on Claude.ai, which exploits that time to train its own models.

Why time wasted? Claude’s accuracy for shell, Bash, regex, Perl, text manipulation/scripting/processing, and system-level code is effectively negligible (~5%). Such code is scarce in public repositories. For swarms or agents to function, accuracy must exceed 96%. At 5%, it is unusable.

We do also use Claude.ai and we believe it is useful, but strictly for trivial, typing-level tasks. Anything beyond that, at this current point, is a liability.

Re: Claude Code's new hidden feature: Swarms

#334

Post by Shebanator »

vorticalbox wrote: post #78
AffableSpatula wrote: post #7

Earlier quoted context omitted.

ha! The default system prompt appears to give the main agent appropriate guidance about only using swarm mode when appropriate (same as entering itself into plan mode). You can further prompt it in your own CLAUDE.md to be even more resistant to using the mode if the task at hand isn't significant enough to warrant it.

I like opencode for the fact I can switch between build and plan mode just by pressing tab.

Its shift-tab in Claude Code, fyi

Re: Claude Code's new hidden feature: Swarms

#335

Post by lwhi »

XenophileJKO wrote: post #331
lwhi wrote: post #305

Earlier quoted context omitted.

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

Context is the information you give the model, attention is what parts it focuses on. And this is finite in capacity and emergent from the architecture.

So attention is based on a smaller subset of context?

Re: Claude Code's new hidden feature: Swarms

#336

Post by overfeed »

tripledry wrote: post #293
overfeed wrote: post #176

Earlier quoted context omitted.

> [...]coding agents only get the information they actually need and nothing more Extrapolating from this concept led me to a hot-take I haven't had time to blog about: Agentic AI will revive the popularity of microservices. Mostly due to the deleterious effect of context size on agent performance.

In a fresh project that is well documented and set up it might work better. Many issues that Agents have in my work is that the endpoints are not always documented correctly. Real example that happened to me, Agent forgets to rename an expected parameter in API spec for service 1. Now when working on service 2, there is no other way of finding this mistake for the Agent than to give it access to service 1. And now yo…

> In a fresh project that is well documented and set up it might work better.

I guess this may be dependent on domain, language, codebase, or soke combination of the 3. The biggest issues I've had with agents is when they go down the wrong path and it snowballs from there. Suddenly they are loading more context unrelated to the tasks and getting more confused. Documenting interfaces doesn't help if the source is available to the agent.

My agentic sweet spot is human-designed interfaces. Agents cannot mess up code they don't have access to, e.g. by inadvertently changing the interface contract and the implementation.

> Agent forgets to rename an expected parameter in API spec for service 1

Document and test your interfaces/logic boundaries! I have witnessed this break many times with human teams with field renames, change in optionality, undocumented field dependencies, etc, there are challenging trade-offs with API versioning. Agents can't fix process issues.

Re: Claude Code's new hidden feature: Swarms

#337

Post by asimeqi »

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…

I can barely keep up with one instance of Claude Code. In fact even that one sits iddle half the time as I test its output and try to explain what it did wrong. What are people programming that needs 10 agents?

Re: Claude Code's new hidden feature: Swarms

#338

Post by dexdal »

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

A paper’s date does not invalidate its method. Findings stay useful only when you can re-run the same protocol on newer models and report deltas. Treat conclusions as conditional on the frozen tasks, criteria, and measurement, then update with replication, not rhetoric.

Re: Claude Code's new hidden feature: Swarms

#339

Post by throwup238 »

stingraycharles wrote: post #90
dceddia wrote: post #74

Earlier quoted context omitted.

Interesting about the level of detail. I’ve noticed that myself but I haven’t done much to address it yet. I can imagine some ideas (ask it for more detail, ask it to make a smaller plan and add detail to that) but I’m curious if you have any experience improving those plans.

I’m trying to solve this myself by implementing a whole planner workflow at https://github.com/solatis/claude-config Effectively it tries to resolve all ambiguities by making all decisions explicit — if the source cannot be resolved to documentation or anything, it’s asked to the user. It also tries to capture all “invisible knowledge” by documenting everything, so that all these decisions and business context are ca…

> The downside is that it takes 30min - 60min to write a plan

Oof you weren't kidding. I've got your skills running on a particularly difficult problem and it's been running for over three hours (I keep telling it to increase the number of reviews until its satisfied).

Re: Claude Code's new hidden feature: Swarms

#340

Post by zhenyakovalyov »

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…

i guess, as a human it’s easier to reason about a multi-agent system when the roles are split intuitively, as we all have mental models. but i agree - it’s a bit redundant/unnecessary
Post reply on HN