Just one more harness bro, one more harness I swear one more harness and we will have solved AGI bro
Towards a harness that can do anything
41–50 of 121 posts
Re: Towards a harness that can do anything
#42How 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
https://lucumr.pocoo.org/2026/7/4/better-models-worse-tools/ says already too much to use foreign tools.
I think tools have to be flexible enough to accommodate a range of expected inputs. Even assuming models are trained to supply a particular schema, they are stochastic and randomly output variants regularly. My experience has been that it's better to try to auto-normalize the range of anticipated outputs and make tools as forgiving as possible rather than force an overly strict schema that might not match training data on the model.
Re: Towards a harness that can do anything
#43Earlier quoted context omitted.
I did indeed read every word. And read the code. Don't be rude.
you read the whole article and the only thought you had about it is "great work" ? your comment exclusively about your aislop project
The author pointed out that JSON-wrangling and regex issues are a pain in the ass. I found them to be a pain in the ass in my own project, too.
He also argued that his project implemented a kernel pattern that acted as a buffer between the LLM and the outside world. I too implemented a buffer pattern in my own project.
He built an AI harness, I think it's a nice project, and if it extends MCP compatibility, I do think HIC Mouse would be a nice integration with Ambiance.
Yes, I think Ambiance is a great project and I am wishing the author all the best luck and success in the future. Yes, I gave it a GitHub star. Sorry I didn't give fainter praise?
By the way, I wrote every line of my project myself; I wrote every word of my research myself; I wrote every word of the copy on my website, including all legal provisions, docs, and blog posts, myself; I write all my comments on HN myself. I'm proud of my work and stand by my project, which ironically is dedicated to reducing AI slop and boosting accuracy so that AI agents can perform surgical, precise code repairs without ever touching or copying any other part of the code base. Let me know what you're doing to reduce slop, other than accusing people falsely of generating content with AI.
Re: Towards a harness that can do anything
#44Earlier quoted context omitted.
It is not blasphemy if langgraph is trying to do that. As I understand langgraph manages orchestration in custom built agents. I usually stay away from systems which already make it seem as if building agents is a ritual. What I am saying is the opposite - use Claude Code or whatever else - generate actual "programs". Basically scripts. We have tons of ways for "programs" to interact with each other. Then have clearl…
You can drive agents via ACP these days, which I think is the layer you would want for what you’re talking about. The API is basically what you see as a user of Claude Code or Pi or whatever. You can make new sessions, send messages to sessions, configure which MCPs get started, etc. I’ve been poking at something similar to what you’re talking about via that route. My client prompts the agent to do a thing, and then…
I think it all comes down to tight, context efficient, deterministic feedback loops. Pre commit hooks work well for this type of thing. Ideally I think a set of those hooks should run on every file edit, however I haven't gotten around to testing something like that yet.
Re: Towards a harness that can do anything
#45Re: Towards a harness that can do anything
#46I 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…
In the age of agents, I feel like BDD is more important than ever since it describes the behavior, and if it does so well it’ll make it much easier for these tools to pick up correct behavior.
Gherkin style tests also come to mind
Re: Towards a harness that can do anything
#47I 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…
Thank you for framing my laziness as being a daredevil
Re: Towards a harness that can do anything
#48What's with this "harness" word people have been trying to adopt lately? Are we all going rock climbing?
framework is too 90s
Re: Towards a harness that can do anything
#49Earlier quoted context omitted.
you read the whole article and the only thought you had about it is "great work" ? your comment exclusively about your aislop project
The author pointed out that JSON-wrangling and regex issues are a pain in the ass. I found them to be a pain in the ass in my own project, too. He also argued that his project implemented a kernel pattern that acted as a buffer between the LLM and the outside world. I too implemented a buffer pattern in my own project. He built an AI harness, I think it's a nice project, and if it extends MCP compatibility, I do thin…
good job stealth editing your original comment.
Re: Towards a harness that can do anything
#50What's with this "harness" word people have been trying to adopt lately? Are we all going rock climbing?
We're taming a beast.