What Is a Harness?

Post by theturtletalks » Sun, Aug 23, 2026, 3:33 PM UTC

grey-area wrote: post #25

mpawelski wrote: post #11

Earlier quoted context omitted.

> Harnesses are the next frontier. If LLMs are electricity, harnesses are the “electronics.” I really though this comment was a satire ...

Sadly, many people have bought into the cult that LLMs will lead to AGI. I guess if that is your worldview then all this babbling about new frontiers makes more sense. They probably used an LLM to come up with this bizarre metaphor.

Post by tokai » Sun, Aug 23, 2026, 3:34 PM UTC

theturtletalks wrote: post #22

dominotw wrote: post #10

Earlier quoted context omitted.

i think its the opposite. claude code apparently removed hundreds of lines of system prompt because its not relavent anymore with newer models. also i think its hard to build general harnesses if they were trained on specific harness architecture.

Yes but Pi has had a minimal system prompt since inception. Skills and Pi extensions let you make a hyper specific harness for specific use cases. For general conversation, harnesses are overkill most times. There’s evidence of harnesses making a smaller, weaker model perform better than SOTA and some benchmarks ban harnesses because it becomes too easy.

Post by lebek » Sun, Aug 23, 2026, 3:35 PM UTC

tosh wrote: post #24

i also like the backpack analogy the harness is what you take with you on a trip/task whatever you take with you is not free (system prompt, tools, skills …) some models are really good even if you bring almost no skills, tools or system prompt the harness is the complement to the model the better the model the more minimal the harness can be harnesses like pi [0] and smol [1]are on the more minimal end of things [0]…

Post by theturtletalks » Sun, Aug 23, 2026, 3:37 PM UTC

amelius wrote: post #20

theturtletalks wrote: post #3

Harnesses are the next frontier. If LLMs are electricity, harnesses are the “electronics.” Right now, it’s like an AC vs DC between Claude and ChatGPT, but once that settles, the harnesses will be the actual value providers. And Pi is the best harness because of the amazing extension system. You can build extensions that turn Pi into a stock trader, software factory, anything. I tried switching to another harness but…

> 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.

Post by grey-area » Sun, Aug 23, 2026, 3:37 PM UTC

theturtletalks wrote: post #31

grey-area wrote: post #25

Earlier quoted context omitted.

Sadly, many people have bought into the cult that LLMs will lead to AGI. I guess if that is your worldview then all this babbling about new frontiers makes more sense. They probably used an LLM to come up with this bizarre metaphor.

Did I even mention AGI? All I’m saying is that we’re hitting a plateau with how good models are while harnesses are untapped potential. And with Pi, you can swap models like electricity companies. Yes for now, the electricity is better with some companies but this will stabilize. And no I came up with the metaphor all on my own, send me the chat of you getting the LLM to come up with it. Why not argue based on merit…