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

Claude Managed Agents

claude.com

Post reply on HN
Print view View original

81–90 of 109 posts

Re: Claude Managed Agents

#81

Post by spwa4 »

cedws wrote: post #14

I saw this coming. Anthropic wants to shift developers on to their platform where they’re in control. The fight for harness control has been terribly inconvenient for them. To score a big IPO they need to be a platform, not just a token pipeline. Everything they’re doing signals they’re moving in this direction.

Well, that sucks. Replacing the harness with something task-specific has proven very powerful in my usecases.

But you should correct: Claude is very happy to let you use whatever you want for a harness ... as long as you're on a pay-as-you-go plan. So it's not blocked. It's just not allowed on the $20 per month plan.

First, harnesses can give access to company internal tools (like the ticket queue). You could do this with MCP, but it's much harder, slower and it kind of resists doing this (if you want a bot to solve a ticket, why not start with an entire overview of the ticket in the first request to your model? This can't easily be done with MCP)

Second harnesses can direct the whole process. A trivial example is that you can improve performance in a very simple way: ask "are you sure?" showing the model what it intends to do, BEFORE doing it. Improves performance by 10%, right there. Give a model the chance to look at what it's doing and change it's mind before committing. Then ask a human the same question, with a nice yes/no button. Try that with MCP.

Of course you quickly find a million places to change the process and then you can go and meta-change the process. Like asking an AI what steps should be followed first, then do those steps, most of whom are AI invocations with parts of the tickets (say examine the customer database, extract what's relevant to this problem, ...). Limiting context is very powerful, and not just because it gets you cheaper requests. Get an AI to make relevant context for a particular step before actually doing that step ...

Re: Claude Managed Agents

#82

Post by lbreakjai »

intothemild wrote: post #48
mccoyb wrote: post #45

I'm suspicious that this is going to lead to optimal orchestration ... or rather, that open source won't produce a far better alternative in time. The best performance I've gotten is by mixing agents from different companies. Unless there is a "winner take all" agent (I seriously doubt it, based on the dynamics and cost of collecting high quality RL data), I think the best orchestration systems are going to involve m…

Yeah this has been my experience too, mixing agents/models from different companies.. Having Opus write a spec, then send to Gemini to revise, back to Opus to fix, then to me to read and approve.. Send to a local model like Qwen3.5 to build, then off to Opus to review ... This was such an amazing flow, until Anthropic decided to change their minds.

This is still very much doable. This is exactly how I'm working. I'm using opencode with a mixture-of-agents I built (https://github.com/tessellate-digital/notion-agent-hive), where the model behind each agent is configurable.

Re: Claude Managed Agents

#83

Post by Jayakumark »

jawiggins wrote: post #42
rtuin wrote: post #28

Earlier quoted context omitted.

Most definitely. Although I haven’t found an (F)OSS project that lets one easily ship [favorite harness SDK] to self-hosted platform yet. Which projects are standing out in this space right now?

Shameless self promo but, I've been working on Optio specifically for coding, it works by taking any harness you want and tasking it to open Github/lab PRs based on notion/jira/linear tickets, see: https://news.ycombinator.com/item?id=47520220 It works on top of k8s, so you can deploy and run in your own compute cluster. Right now it's focused only on coding tasks but I'm currently working on abstractions so you can…

@jawiggins saw your repo it looks like openAI symphony but better as it works across multiple agents and issue trackers and the feedback loop is great . One feature request though - can you add plan mode ? Your issues are so detailed it becomes plan to implement (but I guess your plan mode is currently happening outside of GitHub issues ) but let’s say issue is “implement support for plan mode” there should be back and forth with agent with issue tags pointing to opus max and/or plan mode - so we can correct agents plan back and forth and once tag is removed it can start implementing or something similar ?

Re: Claude Managed Agents

#85

Post by gck1 »

jameslk wrote: post #27

We're in the early days of agentic frameworks, like the pre-PHP web. CGI scripts and webmasters. Eventually the state-of-the-art will slow down and we'll eventually have something elegant like Rails come out. Until then, every agent framework is completely reinvented every week due to new patterns and new models. evals, ReACT, DSPy, RLM, memory patterns, claws, dynamic context, sandbox strategies. It seems like locki…

I believe framework is simply never, ever going to work for LLM-based agentic workflows.

Framework is simply way too rigid for a non-deterministic technology.

We may see libraries that provide tools for managing agents, but then again, there's nothing that tmux can't do already.

Re: Claude Managed Agents

#86

Post by gck1 »

spwa4 wrote: post #81
cedws wrote: post #14

I saw this coming. Anthropic wants to shift developers on to their platform where they’re in control. The fight for harness control has been terribly inconvenient for them. To score a big IPO they need to be a platform, not just a token pipeline. Everything they’re doing signals they’re moving in this direction.

Well, that sucks. Replacing the harness with something task-specific has proven very powerful in my usecases. But you should correct: Claude is very happy to let you use whatever you want for a harness ... as long as you're on a pay-as-you-go plan. So it's not blocked. It's just not allowed on the $20 per month plan. First, harnesses can give access to company internal tools (like the ticket queue). You could do this…

> A trivial example is that you can improve performance in a very simple way: ask "are you sure?" showing the model what it intends to do, BEFORE doing it. Improves performance by 10%

Put it into the "are you sure" loop and you'll see the model will just keep oscillating for eternity. If you ask the model to question the output, it will take it as an instruction that it must, even if the output is correct.

Re: Claude Managed Agents

#87

Post by gck1 »

mccoyb wrote: post #45

I'm suspicious that this is going to lead to optimal orchestration ... or rather, that open source won't produce a far better alternative in time. The best performance I've gotten is by mixing agents from different companies. Unless there is a "winner take all" agent (I seriously doubt it, based on the dynamics and cost of collecting high quality RL data), I think the best orchestration systems are going to involve m…

I think opus does in fact, find the bugs the same way GPT xhigh (or even high) does. It just discards them before presenting to the user.

Opus is designed to be lazy, corner-cutting model. Reviews are just one place where this shows. In my orchestration loop, opus discards many findings by GPT 5.4 xhigh, justifying this as pragmatism. Opus YAGNIs everything, GPT wants you to consider seismic events in your todo list app. There's sadly, nothing in between.

Re: Claude Managed Agents

#88

Post by gck1 »

intothemild wrote: post #48
mccoyb wrote: post #45

I'm suspicious that this is going to lead to optimal orchestration ... or rather, that open source won't produce a far better alternative in time. The best performance I've gotten is by mixing agents from different companies. Unless there is a "winner take all" agent (I seriously doubt it, based on the dynamics and cost of collecting high quality RL data), I think the best orchestration systems are going to involve m…

Yeah this has been my experience too, mixing agents/models from different companies.. Having Opus write a spec, then send to Gemini to revise, back to Opus to fix, then to me to read and approve.. Send to a local model like Qwen3.5 to build, then off to Opus to review ... This was such an amazing flow, until Anthropic decided to change their minds.

You can still do all of this. With tmux. Nothing anthropic can do about that.

Gemini cli is horrible though.

Re: Claude Managed Agents

#89

Post by harlequinetcie »

gck1 wrote: post #85
jameslk wrote: post #27

We're in the early days of agentic frameworks, like the pre-PHP web. CGI scripts and webmasters. Eventually the state-of-the-art will slow down and we'll eventually have something elegant like Rails come out. Until then, every agent framework is completely reinvented every week due to new patterns and new models. evals, ReACT, DSPy, RLM, memory patterns, claws, dynamic context, sandbox strategies. It seems like locki…

I believe framework is simply never, ever going to work for LLM-based agentic workflows. Framework is simply way too rigid for a non-deterministic technology. We may see libraries that provide tools for managing agents, but then again, there's nothing that tmux can't do already.

I'm a bit at odds with this.

I agree a framework is something that sounds outdated.

I also believe an orchestrator is needed. Something that abstracts you from a specific provider. Like hardware, drivers and operating systems.

Right now, my thoughts are on that line: Who will build that operating system? Who will have it in the cloud?

It needs to be robust to operate for large organizations, open source, and sit on top of any provider.

Right now we are seeing BSD vs GNU/Linux vs DOS kind of battles.

Post reply on HN