its best you build your own harness.
What Is a Harness?
171–180 of 200 posts
Re: What Is a Harness?
#172Earlier quoted context omitted.
what have you built other than a harness?
I built a software factory and am now building a stock trader using opencandle extension[0] and a custom extension. For inspiration for how to tweak Pi, check out OMP, Prime Intellect, and Deepseek harnesses. 0. https://github.com/Kahtaf/OpenCandle
arn't those just different types of user-used harnesses?
Re: What Is a Harness?
#173[flagged]
Re: What Is a Harness?
#174A harness is a tool that allows the LLM to focus on the primary objective that the user wants, coding, research, reports, finance anything really but the harness structures the agent interactions with the supporting tools to achieve the narrow scope. Driving the LLM with correct feedback from the domain knowledge provided by the tools. TBH when I was writing my harness this is why i have the Guardrails concept around Any tool, pre and post tool call, pre can make sure the data is formatted correctly lowering incorrect tool calls and post tool calls for validaition of results of output. Harness: https://github.com/zarldev/zarlmono/tree/main/zarlcode Guardrail Design: https://zarldev.github.io/zarlmono/guardrails/ All Docs: https://zarldev.github.io/zarlmono/
Re: What Is a Harness?
#175Earlier quoted context omitted.
Would you like to see some of my own examples of wild success? I have a system that entirely reverse engineers old arcade games. Creates semantic symbol mappings that were considered impossible just a couple years ago. Granted, it took me a couple weeks to build the system. From impossible to a couple weeks in just a couple years. Would you like to see it or continue to pretend these things don't exist? Your call. (I…
I’ve made my own arcade games with an LLM. It was fun though the code wasn’t great. Mostly I felt they reproduced games from the training data, some with more examples available worked better than others. I use them most days for work, and for that reason don’t trust them that much and certainly don’t worry or fantasise about AGI.
You were making some pretty strong statements about the usefulness of harnesses that seemed to me to be entirely detached from reality. Maybe I misunderstood you? Because I can provide evidence to correct that misconception.
Another of my projects is to incorporate Pixar's ideas from RenderMan into a 3d printer slicer. Displacement shaders, in a 3d printer, have never been done before. Would you like to see that? I had the idea 10 years ago but it was too tedious to implement. I have a working system now in just a couple weeks AGAIN.
Anyone claiming agents aren't profoundly useful is WRONG. If you disagree, please let's discuss it.
Re: What Is a Harness?
#176Earlier quoted context omitted.
> If LLMs are electricity, harnesses are the “electronics.” (...) the harnesses will be the actual value providers. Don't get ahead of yourself. Harnesses are not exactly rocket science and will be a commodity. The real value providers here are the hardware, then the LLM as a distant second, and at a much larger distance the harness.
https://www.latent.space/p/attention-interface Labs are now post-training models with Harness so that Harness now gets absorbed into the weights.
[dead]
Re: What Is a Harness?
#177I’ve been working on a harness for accounting agents at my job recently and it’s been a pretty interesting experience. We originally started with building a CLI tool so our LLMs could more easily interact with our platform. I cannot recommend enough the value of having an internal CLI. It’s both fun to build and extremely useful for agents. We paired this with skills initially, but found that the way folks built skil…
I think you've really hit the mark on how the harness should be structured: 1. Guardrails - deterministic, social intelligence, team alignment & accountability 2. Learn by doing 3. make it stupid easy for the agent to research and access data 4. DRY Research supports this. Try picking up some ideas from my harness: https://github.com/rush86999/atom
[flagged]
Re: What Is a Harness?
#178Whomever invented this word for "AI agents" really nailed the marketing and, to me, the cringe-factor.
Re: What Is a Harness?
#179I’ve been working on a harness for accounting agents at my job recently and it’s been a pretty interesting experience. We originally started with building a CLI tool so our LLMs could more easily interact with our platform. I cannot recommend enough the value of having an internal CLI. It’s both fun to build and extremely useful for agents. We paired this with skills initially, but found that the way folks built skil…
Why a CLI over an MCP or even straight restful API with appropriate schema docs?
Re: What Is a Harness?
#180[flagged]