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

61–70 of 351 posts

Re: Claude Code's new hidden feature: Swarms

#61

Post by xpe »

AffableSpatula wrote: post #27
storystarling wrote: post #24

Earlier quoted context omitted.

I've found the opposite to be true when building this out with LangGraph. While the subagent contexts are cleaner, the orchestration overhead usually ends up costing more. You burn a surprising amount of tokens just summarizing state and passing it between the supervisor and workers. The coordination tax is real.

Task sizing is important. You can address this by including guidance in the CLAUDE.md around that ie. give it heuristics to use to figure out how to size tasks. Mine includes some heuristics and T shirt sizing methodology. Works great!

Management is dead. Long live management.

Re: Claude Code's new hidden feature: Swarms

#62

Post by IAmGraydon »

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…

No, it doesn't work in practice because they make far too many mistakes.

Re: Claude Code's new hidden feature: Swarms

#64

Post by flkiwi »

jen729w wrote: post #60
bakugo wrote: post #58

> 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. Even 90 word tweets are now too long for these people to write without using AI, apparently.

I wonder how much 'listening' to an LLM all day affects one's own prose? Mimicry is in the genes…

I accidentally gave my wife a prompt the other day. Everything was hellishly busy and I said something along the lines of “I need to ask you a question. Please answer the question. Please don’t answer any other issues just yet.” She looked at me and asked “Did you just PROMPT me?” We laughed. (The question was the sort that might spawn talking about something else and was completely harmless. In the abstract, my intent was fine but my method was hilariously tainted.)

Re: Claude Code's new hidden feature: Swarms

#66

Post by czhu12 »

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 supported for a long time? What are learnings after 3-6 months of supporting in production?

Re: Claude Code's new hidden feature: Swarms

#67

Post by Jweb_Guru »

jen729w wrote: post #60
bakugo wrote: post #58

> 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. Even 90 word tweets are now too long for these people to write without using AI, apparently.

I wonder how much 'listening' to an LLM all day affects one's own prose? Mimicry is in the genes…

It affects it very heavily IME. People need to make sure they are getting a good mix of writing from other sources.

Re: Claude Code's new hidden feature: Swarms

#68

Post by pton_xd »

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…

> 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.

That's what you're missing -- the key point is, you don't review and comprehend the output! Instead, you run the program and then issue prompts like this (example from simonw): "fix in and get it to compile" [0]. And I'm not ragging on this at all, this is the future of software development.

[0] https://gisthost.github.io/?9696da6882cb6596be6a9d5196e8a7a5...

Re: Claude Code's new hidden feature: Swarms

#69

Post by szundi »

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…

[dead]

Re: Claude Code's new hidden feature: Swarms

#70

Post by idontwantthis »

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…

I just can’t get with this. There is so much beyond “works” in software. There are requirements that you didn’t know about and breaking scenarios that you didn’t plan for and if you don’t know how the code works, you’re not going to be able to fix it. Assuming an AI could fix any problem given a good enough prompt, I can’t write that prompt without sufficient knowledge and experience in the codebase. I’m not saying they are useless, but I cannot just prompt, test and ship a multiservice, asynchronous, multidb, zero downtime app.
Post reply on HN