Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Orchestrate teams of Claude Code sessions

code.claude.com

Post reply on HN
Print view View original

121–130 of 238 posts

Re: Orchestrate teams of Claude Code sessions

#121

Post by behnamoh »

mohsen1 wrote: post #98
pronik wrote: post #58

To the folks comparing this to GasTown: keep in mind that Steve Yegge explicitely pitched agent orchestrators to among others Anthropic months ago: > I went to senior folks at companies like Temporal and Anthropic, telling them they should build an agent orchestrator, that Claude Code is just a building block, and it’s going to be all about AI workflows and “Kubernetes for agents”. I went up onstage at multiple event…

It's not like he was the only one who came up with this idea. I built something like that without knowing about GasTown or Beeds. It's just an obvious next step https://github.com/mohsen1/claude-code-orchestrator

Exactly! I built something similar. These are such low hanging fruit ideas that no one company/person should be credited for coming up with them.

Re: Orchestrate teams of Claude Code sessions

#122

Post by resonious »

frde_me wrote: post #119
satellite2 wrote: post #94

Earlier quoted context omitted.

Aren't you just moving the problem a little bit further? If you can't trust it will implement carefully specified features, why would you believe it would properly review those?

It's hard to explain, but I've found LLMs to be significantly better in the "review" stage than the implementation stage. So the LLM will do something and not catch at all that it did it badly. But the same LLM asked to review against the same starting requirement will catch the problem almost always The missing thing in these tools is that automatic feedback loop between the two LLMs: one in review mode, one in impl…

I've noticed this too and am wondering why this hasn't been baked into the popular agents yet. Or maybe it has and it just hasn't panned out?

Re: Orchestrate teams of Claude Code sessions

#123

Post by bashtoni »

resonious wrote: post #122
frde_me wrote: post #119

Earlier quoted context omitted.

It's hard to explain, but I've found LLMs to be significantly better in the "review" stage than the implementation stage. So the LLM will do something and not catch at all that it did it badly. But the same LLM asked to review against the same starting requirement will catch the problem almost always The missing thing in these tools is that automatic feedback loop between the two LLMs: one in review mode, one in impl…

I've noticed this too and am wondering why this hasn't been baked into the popular agents yet. Or maybe it has and it just hasn't panned out?

Anecdotaly I think this is in Claude Code. It's pretty frequent to see it implement something, then declare it "forgot" a requirement and go back and alter or add to the implementation.

Re: Orchestrate teams of Claude Code sessions

#124

Post by gbnwl »

mohsen1 wrote: post #98
pronik wrote: post #58

To the folks comparing this to GasTown: keep in mind that Steve Yegge explicitely pitched agent orchestrators to among others Anthropic months ago: > I went to senior folks at companies like Temporal and Anthropic, telling them they should build an agent orchestrator, that Claude Code is just a building block, and it’s going to be all about AI workflows and “Kubernetes for agents”. I went up onstage at multiple event…

It's not like he was the only one who came up with this idea. I built something like that without knowing about GasTown or Beeds. It's just an obvious next step https://github.com/mohsen1/claude-code-orchestrator

I also share your confusion about him somehow managing to dominate credit in this space, when it doesn't even seem like Gastown ended up being very effective as a tool relative to its insane token usage. Everyone who's used an agentic tool for longer than a day will have had the natural desire for them to communicate and coordinate across context windows effectively. I'm guessing he just wrote the punchiest article about it and left an impression on people who had hitherto been ignoring the space entirely.

Re: Orchestrate teams of Claude Code sessions

#125

Post by d4rkp4ttern »

This sounds very promising. Using multiple CC instances (or mix of CLI-agents) across tmux panes has always been a workflow of mine, where agents can use the tmux-cli [1] skill/tool to delegate/collaborate with others, or review/debug/validate each others work.

This new orchestration feature makes it much more useful since they share a common task list and the main agent coordinates across them.

[1] https://github.com/pchalasani/claude-code-tools?tab=readme-o...

Re: Orchestrate teams of Claude Code sessions

#126

Post by bluerooibos »

This is great and all but, who can actually afford to let these agents run on tasks all day long? Is anyone here actually using this or are these rollouts aimed at large companies?

I'm burning through so many tokens on Cursor that I've had to upgrade to Ultra recently - and i'm convinced they're tweaking the burn rate behind the scenes - usage allowance doesn't seem proportional.

Thank god the open source/local LLM world isn't far behind.

Re: Orchestrate teams of Claude Code sessions

#127

Post by bluerooibos »

mohsen1 wrote: post #100
GoatOfAplomb wrote: post #63

I wonder if my $20/mo subscription will last 10 minutes.

At this point, if you're paying out of pocket you should use Kimi or GLM for it to make sense

These are super slow to run locally, though, unless you've got some great hardware - right?

At least, my M1 Pro seems to struggle and take forever using them via Ollama.

Re: Orchestrate teams of Claude Code sessions

#128

Post by jwpapi »

bluerooibos wrote: post #126

This is great and all but, who can actually afford to let these agents run on tasks all day long? Is anyone here actually using this or are these rollouts aimed at large companies? I'm burning through so many tokens on Cursor that I've had to upgrade to Ultra recently - and i'm convinced they're tweaking the burn rate behind the scenes - usage allowance doesn't seem proportional. Thank god the open source/local LLM w…

I mean what you get for Claude Code Max is insane its 30x on the token price. If you don’t spend that all it’s your own fault. That must be below elecricity cost

Re: Orchestrate teams of Claude Code sessions

#129

Post by emp17344 »

bluerooibos wrote: post #126

This is great and all but, who can actually afford to let these agents run on tasks all day long? Is anyone here actually using this or are these rollouts aimed at large companies? I'm burning through so many tokens on Cursor that I've had to upgrade to Ultra recently - and i'm convinced they're tweaking the burn rate behind the scenes - usage allowance doesn't seem proportional. Thank god the open source/local LLM w…

Especially for what’s basically an experiment. Gas town didn’t really work, so there’s no guarantee this will even produce anything of value.

Re: Orchestrate teams of Claude Code sessions

#130

Post by rahimnathwani »

bluerooibos wrote: post #126

This is great and all but, who can actually afford to let these agents run on tasks all day long? Is anyone here actually using this or are these rollouts aimed at large companies? I'm burning through so many tokens on Cursor that I've had to upgrade to Ultra recently - and i'm convinced they're tweaking the burn rate behind the scenes - usage allowance doesn't seem proportional. Thank god the open source/local LLM w…

Many many companies can afford to hire a junior engineer for $150k/year (plus employer payroll taxes, employee benefits etc.).

Are you spending more than $150k per year on AI?

(Also, you're talking about the cost of your Cursor subscription, when the article is about Claude Code. Maybe try Claude Max instead?)

Post reply on HN