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

131–140 of 238 posts

Re: Orchestrate teams of Claude Code sessions

#131

Post by logicx24 »

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 can't even get through my Claude Max quota, and that's only 200/mo. And I code every day and use it for various other pretty-intensive tasks.

Re: Orchestrate teams of Claude Code sessions

#132

Post by cstejerean »

Ethee wrote: post #65
greenfish6 wrote: post #14

Earlier quoted context omitted.

i would have to imagine the gastown design isn't optimal though? why 8, and why does there need to multiple hops of agent communications before two arbitrary agents communicate with each other as opposed to single shared filespace?

I've been using Gas Town a decent bit since it was released. I'd agree with you that it's design is sub-optimal, but I believe that's more due to the way the actual agents/harnesses have been designed as opposed to optimal software design. The problem you often run into is that agents will sometimes hang thinking they need human input for a problem they are on, or they think they're at a natural stopping point. If yo…

the problem with gastown is it tries to use agents for supervision when it should be possible to use much simpler and deterministic approaches to supervision, and also being a lot more token efficient

Re: Orchestrate teams of Claude Code sessions

#134

Post by freeone3000 »

rahimnathwani wrote: post #130
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?)

If it could do anything that a junior dev could, that’d be a valid point of comparison. But it continually, wildly performs slower and falls short every time I’ve tried.

Re: Orchestrate teams of Claude Code sessions

#135

Post by dangus »

A cynical read of this is that it’s all a ploy to maximize usage.

Why do agents need to speak to each other if they’re just doing the work correctly the first time?

Is it an admission that a single agent is not useful and reliable enough?

Re: Orchestrate teams of Claude Code sessions

#136

Post by dangus »

logicx24 wrote: post #131
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 can't even get through my Claude Max quota, and that's only 200/mo. And I code every day and use it for various other pretty-intensive tasks.

only $200/mo…$200 a month is a used car payment.

I guarantee you that price will double by 2027. Then it’ll be a new car payment!

I’m really not saying this to be snarky, I’m saying this to point out that we’re really already in the enshittification phase before the rapid growth phase has even ended. You’re paying $200 and acting like that’s a cheap SaaS product for an individual.

I pay less for Autocad products!

This whole product release is about maximizing your bill, not maximizing your productivity.

I don’t need agents to talk to each other. I need one agent to do the job right.

Re: Orchestrate teams of Claude Code sessions

#137

Post by troupo »

ttoinou wrote: post #79
bonesss wrote: post #70

Earlier quoted context omitted.

Compare both approaches to mature actor frameworks and they don’t seem to be breaking much ice. These kinds of supervisor trees and hierarchies aren’t new for actor based systems and they’re obvious applications of LLM agents working in concert. The fact that Anthropic and OpenAI have been going on this long without such orchestration, considering the unavoidable issues of context windows and unreliable self-validati…

If it was so obvious and easy, why didn't we have this a year ago ? Models were mature enough back then to make this work

Because they are not good engineers [1]

Also, because they are stuck in a language and an ecosystem that cannot reliably build supervisors, hierarchies of processes etc. You need Erlang/Elixir for that. Or similar implementations like Akka that they mention.

[1] Yes, they claim their AI-written slop in Claude Code is "a tiny game engine" that takes 16ms to output a couple of hundred of characters on screen: https://x.com/trq212/status/2014051501786931427

Re: Orchestrate teams of Claude Code sessions

#138

Post by troupo »

ruined wrote: post #81
bonesss wrote: post #70

Earlier quoted context omitted.

Compare both approaches to mature actor frameworks and they don’t seem to be breaking much ice. These kinds of supervisor trees and hierarchies aren’t new for actor based systems and they’re obvious applications of LLM agents working in concert. The fact that Anthropic and OpenAI have been going on this long without such orchestration, considering the unavoidable issues of context windows and unreliable self-validati…

what mature actor frameworks do you recommend?

Elixir/Erlang. It's table stakes for them.

Re: Orchestrate teams of Claude Code sessions

#139

Post by rahimnathwani »

freeone3000 wrote: post #134
rahimnathwani wrote: post #130

Earlier quoted context omitted.

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?)

If it could do anything that a junior dev could, that’d be a valid point of comparison. But it continually, wildly performs slower and falls short every time I’ve tried.

  But it continually, wildly performs slower and falls short every time I’ve tried.
If it falls short every time you've tried, it's likely that one or more of these is true:

A. You're working on some really deep thing that only world-class expects can do, like optimizing graphics engines for AAA games.

B. You're using a language that isn't in the top ~10 most popular in AI models' training sets.

C. You have an opportunity to improve your ability to use the tools effectively.

How many hours have you spent using Claude Code?

Re: Orchestrate teams of Claude Code sessions

#140

Post by tyre »

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…

Sorry, are you saying that engineers at Anthropic who work on coding models every day hadn’t thought of multiple of them working together until someone else suggested it?

I remember having conversations about this when the first ChatGPT launched and I don’t work at an AI company.

Post reply on HN