[flagged]
When I use Google maps, I learn faster.
And I haven't to solve real hard problems for ages.
Some people will have problems some will not.
Future will tell.
Orchestrate teams of Claude Code sessions
71–80 of 238 posts
Re: Orchestrate teams of Claude Code sessions
#72I absolutely cannot trust Claude code to independently work on large tasks. Maybe other people work on software that's not significantly complex, but for me to maintain code quality I need to guide more of the design process. Teams of agents just sounds like adding a lot more review and refactoring that can just be avoided by going slower and thinking carefully about the problem.
I agree, but I've found that making an "adversarial" model within claude helps with the quality a lot. One agent makes the change, the other picks holes in it, and cycle. In the end, I'm left with less to review.
This sounds more like an automation of that idea than just N-times the work.
Re: Orchestrate teams of Claude Code sessions
#73To 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…
There seems to be a lot of convergent evolution happening in the space. Days before the gas town hype hit, I made a (less baroque, less manic) "agent team" setup: a shell script to kick off a ralph wiggum loop, and CLAUDE-MESSAGE-BUS.md for inter-ralph communication (Thread safety was hacked into this with a .claude.lock file). The main claude instance is instructed to launch as many ralph loops as it wants, in scree…
> Right now I can't write spec (or meta-spec) files quick enough to saturate the agent loops, and I can't QA their output well enough... mostly a me thing, i guess?
Same for me, however, the velocity of the whole field is astonishing and things change as we get used to them. We are not talking that much about hallucinating anymore, just 4-5 months ago you couldn't trust coding agents with extracting functionality to a separate file without typos, now splitting Git commits works almost without a hinch. The more we get used to agents getting certain things right 100% of the time, the more we'll trust them. There are many many things that I know I won't get right, but I'm absolutely sure my agent will. As soon as we start trusting e.g. a QA agent to do his job, our "project management" velocity will increase too.
Interestingly enough, the infamous "bowling score card" text on how XP works, has demonstrated inherently agentic behaviour in more way than one (they just didn't know what "extreme" was back then). You were supposed to implement a failing test and then implement just enough functionality for this test to not fail anymore, even if the intended functionality was broader -- which is exactly what agents reliably do in a loop. Also, you were supposed to be pair-driving a single machine, which has been incomprehensible to me for almost decades -- after all, every person has their own shortcuts, hardware, IDEs, window managers and what not. Turns out, all you need is a centralized server running a "team manager agent" and multiple developers talking to him to craft software fast (see tmux requirement in Gas Town).
Re: Orchestrate teams of Claude Code sessions
#74Earlier quoted context omitted.
Anyone paying attention has known that demand for all type of compute than can run LLMs (i.e. GPUs, TPUs, hell even CPUs) was about to blow up, and will remain extremely large for years to come. It's just HN that's full of "I hate AI" or wrong contrarian types who refuse to acknowledge this. They will fail to reap what they didn't sow and will starve in this brave new world.
[flagged]
[flagged]
Re: Orchestrate teams of Claude Code sessions
#75To 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…
This is nothing new, folks have been doing this for since 2023. Lots of paper on arxiv and lots of code in github with implementation of multiagents.
... the "limit" were agents were not as smart then, context window was much smaller and RLVR wasn't a thing so agents were trained for just function calling, but not agent calling/coordination.
we have been doing it since then, the difference really is that the models have gotten really smart and good to handle it.
Re: Orchestrate teams of Claude Code sessions
#76Seems similar to Gas Town
Where are the polecats, though? What about the mayor's dog?
Re: Orchestrate teams of Claude Code sessions
#77I absolutely cannot trust Claude code to independently work on large tasks. Maybe other people work on software that's not significantly complex, but for me to maintain code quality I need to guide more of the design process. Teams of agents just sounds like adding a lot more review and refactoring that can just be avoided by going slower and thinking carefully about the problem.
Humans can't handle large tasks either, which is why you break them into manageable chunks.
Just ask claude to write a plan and review/edit it yourself. Add success criteria/tests for better results.
Re: Orchestrate teams of Claude Code sessions
#78Re: Orchestrate teams of Claude Code sessions
#79To 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…
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
Re: Orchestrate teams of Claude Code sessions
#80"finish Claude tokens quota in 3 minutes, largely over delegation and result messages instead of code writing"