Mapping agent concepts to the Unix environment sounds like a great idea in general, but I get off the train at adopting the FHS, which is an ancient relic that has no place in a green-field system. I don't know exactly what shape it should take, but something along the lines of Nix seems more appropriate. Or maybe Plan 9.
Towards a harness that can do anything
51–60 of 121 posts
Re: Towards a harness that can do anything
#52What's with this "harness" word people have been trying to adopt lately? Are we all going rock climbing?
I think a better term would be bridle, but most people don't know it. But they do put harnesses on their kids and pets.
Re: Towards a harness that can do anything
#53Love the Unix philosophy and the buffs mentioned of the Linux FS. Lean, transparent, and auditability-first is exactly the direction harness' should continue in.
Something I am convinced of though, there probably isn't a single `best` harness for all tasks. Different workloads will likely perform better with certain combinations of model + harness, especially when we are talking about token budgeting and cost tracking.
Ambiance feels like a great base “kernel” to build those variants on top of, rather than the one true harness.
Re: Towards a harness that can do anything
#54What's with this "harness" word people have been trying to adopt lately? Are we all going rock climbing?
Buzzword bullshit bingo is a must for anyone who wants to ride the hype.
Re: Towards a harness that can do anything
#55[flagged]
Re: Towards a harness that can do anything
#56This 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.
Re: Towards a harness that can do anything
#57I disagree with the idea that file is a good metaphor for LLM. Files have seek and byte streams, which is just an unneeded abstraction for LLM. The LLM doesn't need to seek or jump to the middle of a file, if you store and organize your data properly.
Why force the LLM to use files over vector database or key-value stores, just because it's a design principal for UNIX (which is designed for human users, not LLMs.)
Re: Towards a harness that can do anything
#58What's with this "harness" word people have been trying to adopt lately? Are we all going rock climbing?
A harness is just a piece of software that exposes APIs for reading files, connecting to the internet, etc.
It parses the LLM output for tool calls, executes the command, and puts the output back into the LLM input. That's all there is to it.
Re: Towards a harness that can do anything
#59Earlier quoted context omitted.
> Awesome work! This is really impressive. I gave a GitHub star. { aislop pitch} > Again, great work. i can bet you didnt actually read the op. i hate these comments so much. selfish and rude.
I did indeed read every word. And read the code. Don't be rude.
You have used too many words. You could not have written that many words yourself, so you must be posting slop. In fact, let's just go ahead and remove your comment which is obviously diminishing the quality of our otherwise impeccable conversations on hn. Sorry, I don't make the rules
(That being said, "the most powerful AI agent file-editing tool in the world" is a bit of a stretch.)
Re: Towards a harness that can do anything
#60I 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…
One of my policies for agentic coding is to spend much effort in developing tests, coded tests not LLM based vibes. My projects have around 1:1 LOC between code and tests. Tests are like skin, when the skin is pricked it hurts, agents need to feel pain too. OP's idea "everything is a text file" is good and I use it too. My plans are saved as task.md files, numbered and named. Work items are checkboxes inside the file…
Thanks for the link. I need to evolve my own system in this direction.