Claude Code's new hidden feature: Swarms • Hacker News Board

Re: Claude Code's new hidden feature: Swarms

#181

Post by blibble » Sat, Jan 24, 2026, 11:03 PM UTC

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.

can't you just rip the oauth client secret out of the code?

Re: Claude Code's new hidden feature: Swarms

#182

Post by nojs » Sat, Jan 24, 2026, 11:06 PM UTC

daxfohl wrote: post #171

sothatsit wrote: post #142

Earlier quoted context omitted.

They haven’t released this feature, so maybe they know the models aren’t good enough yet. I also think it’s interesting to see Anthropic continue to experiment at the edge of what models are capable of, and having it in the harness will probably let them fine-tune for it. It may not work today, but it might work at the end of 2026.

True, though even then I kind of wonder what's the point. Once they build an AI that's as good as a human coder but 1000x faster, parallelization no longer buys you anything. Writing and deploying the code is no longer the bottleneck, so the extra coordination required for parallelism seems like extra cost and risk with no practical benefit.

It’s more about context management, not speed

Re: Claude Code's new hidden feature: Swarms

#183

Post by sothatsit » Sat, Jan 24, 2026, 11:07 PM UTC

daxfohl wrote: post #171

sothatsit wrote: post #142

Earlier quoted context omitted.

They haven’t released this feature, so maybe they know the models aren’t good enough yet. I also think it’s interesting to see Anthropic continue to experiment at the edge of what models are capable of, and having it in the harness will probably let them fine-tune for it. It may not work today, but it might work at the end of 2026.

True, though even then I kind of wonder what's the point. Once they build an AI that's as good as a human coder but 1000x faster, parallelization no longer buys you anything. Writing and deploying the code is no longer the bottleneck, so the extra coordination required for parallelism seems like extra cost and risk with no practical benefit.

Each agent having their own fresh context window for each task is probably alone a good way to improve quality. And then I can imagine agents reviewing each others work might work to improve quality as well, like how GPT-5 Pro improves upon GPT-5 Thinking.

Re: Claude Code's new hidden feature: Swarms

#184

Post by aschla » Sat, Jan 24, 2026, 11:10 PM UTC

svara wrote: post #45

I'm a fan of AI coding tools but the trend of adding ever more autonomy to agents confuses me. The rate at which a person running these tools can review and comprehend the output properly is basically reached with just a single thread with a human in the loop. Which implies that this is not intended to be used in a setting where people will be reading the code. Does that... Actually work for anyone? My experience so…

It likely is acceptable for business-focused code. Compared to a lot of code written by humans, even if the AI code is less than optimal, it's probably better quality than what many humans will write. I think we can all share some horror stories of what we've seen pushed to production.

Executives/product managers/sales often only really care about getting the product working well enough to sell it.

Re: Claude Code's new hidden feature: Swarms

#185

Post by mafriese » Sat, Jan 24, 2026, 11:11 PM UTC

blibble wrote: post #179

ggoo wrote: post #149

Earlier quoted context omitted.

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

to me, it reads like mental illness

maybe it's a mix of both :)

Re: Claude Code's new hidden feature: Swarms

#186

Post by aschla » Sat, Jan 24, 2026, 11:14 PM UTC

mohsen1 wrote: post #35

bonsai_spool wrote: post #18

Earlier quoted context omitted.

Do you know what patch to apply? The Github link from the OP seems to have a lot of other things included.

https://github.com/numman-ali/cc-mirror/commit/0408f60bd7c75... Way too much code for such a small patch

"Co-Authored-By: Claude Opus 4.5 "

Incredible.

Re: Claude Code's new hidden feature: Swarms

#187

Post by heliumtera » Sat, Jan 24, 2026, 11:16 PM UTC

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…

Congratulations on coming up with the cringiest thing I have ever seen. Nothing will top this, ever.

Corporate has to die

Re: Claude Code's new hidden feature: Swarms

#188

Post by flemhans » Sat, Jan 24, 2026, 11:27 PM UTC

prmoustache wrote: post #140

serial_dev wrote: post #83

Earlier quoted context omitted.

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…

> people will review your code, People will ask LLM to review some slop made by LLM and they will be absolutely right! There is no limit to lazyness.

Soon you'll be seen as irresponsible and wasteful if you don't let the smarter LLM do it.

Re: Claude Code's new hidden feature: Swarms

#189

Post by TeMPOraL » Sat, Jan 24, 2026, 11:31 PM UTC

mrtesthah wrote: post #132

coldtea wrote: post #122

> You're not talking to an AI coder anymore. You're talking to a team lead. The lead doesn't write code - it plans, delegates, and synthesizes. They couldn't even be bothered to write the Tweet themselves...

isn’t it interesting how often this rhetorical construction is overused by AI?

Partly because it's a good construct. Most people's writing is garbage compared to what LLMs output by default.

But the other part of it is, each conversation you have, and each piece of AI output you read online, is written by LLM instance that has no memory of prior conversations, so it doesn't know that, from human perspective, it used this construct 20 times in the last hour. Human writers avoid repeating the same phrases in quick succession, even across different writings (e.g. I might not reuse some phrase in email to person A, because I just used it in email to unrelated person B, and it feels like bad style).

Perhaps that's why reading LLM output feels like reading high school essays. Those essays all look alike because they're all written independently and each is a self-contained piece where the author tries to show off their mastery of language. After reading 20 of them in a row, one too gets tired of seeing the same few constructs being used in nearly every one of them.

Re: Claude Code's new hidden feature: Swarms

#190

Post by vidarh » Sat, Jan 24, 2026, 11:32 PM UTC

GoatInGrey wrote: post #151

ggoo wrote: post #145

Earlier quoted context omitted.

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 t…

I don't know about something this complex, but right this moment I have something similar running in Claude Code in another window, and it is very helpful even with a much simpler setup:

If you have these agents do everything at the "top level" they lose track. The moment you introduce sub-agents, you can have the top level run in a tight loop of "tell agent X to do the next task; tell agent Y to review the work; repeat" or similar (add as many agents as makes sense), and it will take a long time to fill up the context. The agents get fresh context, and you get to manage explicitly what information is allowed to flow between them. It also tends to mean it is a lot easier to introduce quality gates - eg. your testing agent and your code review agent etc. will not decide they can skip testing because they "know" they implemented things correctly, because there is no memory of that in their context.

Sometimes too much knowledge is a bad thing.