> that can do anything
isn't that a tall claim?
Towards a harness that can do anything
91–100 of 121 posts
Re: Towards a harness that can do anything
#92Oh, it’s macOS only. The site didn’t say anything about it, or maybe I’m just blind. I had to look at the repo to see.
Re: Towards a harness that can do anything
#93Earlier quoted context omitted.
The idea of morphing prompts to code and back is revolutionary. You may want to read earlier discussions https://news.ycombinator.com/item?id=48881112 And https://news.ycombinator.com/item?id=48051562 I
I am not sure if this is sarcasm - but just in case - https://github.com/sshwarts/skillscript does not offer a unified namespace for functions and prompts (agents) like https://github.com/zby/llm-do (currently in suspended development). There are now also the 'dynamic workflows' in Claude Code that are pretty interesting approach - they are like a compiled prompt in many aspects.
No sarcasm. In that thread we discussed recursive, interleaved application of code and prompt. No morphing, however.
Thanks for dynamic workflow pointer. I don’t know if I like JavaScript for workflow definitions tho. IMHO sshwarts has the right idea on severely constrained workflow definition language. I plan to look closer into ADK2 workflows as well.
I’m not saying anyone did what you are doing, I’m saying multiple pieces are converging on that, at least in my imagination.
Re: Towards a harness that can do anything
#94This post is chock-full of soft ideas. They make no meaningful steps toward "a harness that can do anything". The suggestion is to replace a small node application with specific tooling, with a vm "to give it more capabilities". This is what Agent sandboxes are, already. Making the sandbox the harness, doesn't achieve a concrete goal.
the current bottlenecks for agents are actually bottlenecks of the LLMs, rather than the agents themselves.
Re: Towards a harness that can do anything
#95I kind of have a different idea of agents. I totally believe in a deterministic scaffold but I really think that an agent should be as deterministic as possible - the more code, the better. Think of a typical loop we may ask of Claude Code today (assume we are not using TDD): run some test suite with fail fast mode, diagnose if the failure is due to recent feature changes (pass reference to backend/frontend, github i…
agreed. i built this for a wide variety of background workflows that have been running seamlessly for many weeks now. it's an overbuilt personal project but i think pretty dialed in and very flexible https://stepwise.run/
Re: Towards a harness that can do anything
#96Earlier quoted context omitted.
I’m definitely on the deterministic code train as well. All of my success for long running tasks has been around wrapping the agentic harness (cc, codex-cli, etc.) in a deterministic workflow with deterministic gates. We need a name for this outer layer. In my mind that is the true harness because it constrains the agents failure mode. I think flow engineering has been proposed. Maybe it’s the agentic exoskeleton?
I believe they call it "loop engineering"
If I hear somebody say “deterministic“ one more time I might lose it lol :)
Re: Towards a harness that can do anything
#97I spent 6 months frantically working fulltime on a harness, and when it was finished, I just stopped using it and went back to Codex CLI. I've also stopped using all the fancy features: subagents, planning mode. I've also stopped worrying about context, since I just let codex hit compaction. Somehow this doesn't seem to hurt much. Weird.
Re: Towards a harness that can do anything
#98[flagged]
Re: Towards a harness that can do anything
#99How much do the labs post-train on the harness inputs & outputs? That's a critical piece to understand if a "generic" harness is at all possible
I've experimented with completely novel tool call syntaxes combined with ordering and structuring the context differenly, and they seem to have a high tolerance for this stuff. But you always risk losing performance, probably highly unlikely to exceed stock performance across the board.
Re: Towards a harness that can do anything
#100I think domain specific harnesses are already surpassing generic harnesses. I also think software development is its own domain. My harness is a Claude Code plugin with its own brainstorming, adr, and planning skills with associated review and interview skills. Behavioral testing related to acceptance criteria is built in. Everything in my harness is gated to prevent ratholes. I recently inflated a docker container t…
I ask it to propose revisions, which I then review and provide detailed feedback on. It then works, and afterwards I review. I always commit beforehand. This works well for me.