logoalt Hacker News

theturtletalkstoday at 3:00 PM17 repliesview on HN

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 none have extension functionality as good as Pi.

Even if there is a new harness or agent project, I tell Pi to dig into the codebase and then make me an extension that brings that functionality into Pi. I did it with Prime Intellect’s and Deepseek’s harnesses and those are built on Pi.


Replies

ameliustoday at 3:25 PM

> 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.

show 4 replies
mpawelskitoday at 3:15 PM

> Harnesses are the next frontier. If LLMs are electricity, harnesses are the “electronics.”

I really though this comment was a satire ...

show 5 replies
jacobgoldtoday at 3:43 PM

> ...once that settles, the harnesses will be the actual value providers.

The words "once that settles" are doing historic levels of work here.

No human on earth has a clear idea whether model technology will settle tomorrow or 100 years from now.

There's every reason to expect architectural breakthroughs will keep being discovered and causing nuclear blasts of forward progress.

jrflotoday at 3:20 PM

I've never used Pi but I don't see why you can't use stock codex or claude code for the same purpose, what makes Pi special? I've built plenty of custom harnesses on top of claude code and codex using custom skills or simple markdown instructions and subagents. Never had any issues or limitations with that approach.

I do agree that harnesses are going to extend AI capabilities a lot in the next year, but after reading Pi's page I don't see anything that makes it particularly special in terms of functionality, other than being more provider-agnostic.

show 3 replies
Aardwolftoday at 4:15 PM

If LLMs are oxen, harnesses are... the harnesses

show 1 reply
GodelNumberingtoday at 3:12 PM

This is a plug, but relevant. I recently added a 'build native tools on the fly' functionality to Dirac (https://github.com/dirac-run/dirac) that works like:

1. You can use the '/new-tool' and tell what kind of tool you want (including whether it should be task-scoped, workspace-scoped, or global), the model builds it, the harness runs validation and other tests until the tool is ready

2. The model decides that in such and such task, it would be helpful to have a tool like this, it can build a task-scoped tool.

In either scenario, the tool catalog is rebuilt, and the new tool is instantly available in the next turn.

show 1 reply
timbowhitetoday at 3:14 PM

Pi's most popular extensions, by download count:

https://pi.dev/packages?type=extension

grim_iotoday at 3:54 PM

I don't think so.

What I can see is a world where we end up with a Chromium-shaped harness, a fully featured standard implementation everyone builds against, because doing every single thing yourself would be crazy.

The antithesis to Pi, if you will.

show 2 replies
sejjetoday at 3:17 PM

What did you bring over from prime-agent? (I use prime-agent as my daily since it launched)

I primarily like how it manages sessions, and how agents can easily reference other sessions.

show 1 reply
oceanskytoday at 3:04 PM

I want to move from Claude Desktop to Pi, but I found it a little unfriendly. Any tips to set it up?

show 3 replies
Topfitoday at 3:21 PM

Please tell me this is satire, it reads like straight from the depths of LinkedIn where a while loop is seen as the second coming…

hliyantoday at 3:24 PM

Are human HN commenters now starting to speak in a dialect of Claudish?

epolanskitoday at 4:46 PM

Both Claude and codex are unappealing, crap, generic agents that you have 0 control over.

Don't understand what people see in them.

irishcoffeetoday at 3:05 PM

How does Pi compare to vscode? Admittedly that is the only “agent/harness” I’ve ever used.

cyanydeeztoday at 3:04 PM

what have you built other than a harness?

show 1 reply
lebektoday at 3:40 PM

The harness is just another codebase for the model to write and optimize. The value is still very much in the model.

dominotwtoday at 3:14 PM

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.

show 1 reply