Pion, an agent designed to run any company autonomously

Post by gong_hits » Mon, Sep 14, 2026, 10:12 PM UTC

mchusma wrote: post #229

orourke wrote: post #205

Earlier quoted context omitted.

This is fascinating. What is the split between human and AI labor? What kinds of tasks are the bots doing? How much autonomy do they have to make decisions (i.e. spending money, issuing refunds, touch cloud infra, etc)? I'd love to learn more about how you do this.

I hope to post something within a few weeks. But our philosophy is generally if it can be done deterministically with software (eg run payroll on autopilot via an api to gusto) then do that. If it can be done by an ai agent, do it with that but add as much software as possible to make it reliable at that thing. And the ai agents are all tuned to escalate to humans as needed. Then there is also just things that are co…

Post by tomhow » Mon, Sep 14, 2026, 10:27 PM UTC

mcmcmc wrote: post #210

tomhow wrote: post #177

Earlier quoted context omitted.

You didn’t take the article at face value. You overlooked the part where they were clearly pointing out the absurdity of the “report” and went straight into scold mode, across at least four comments. That’s clearly against the HN guidelines.

I genuinely did. They briefly classified it as “weird” behavior and mentioned that it was “famous” which apparently is only true for the inside circle. I’ve never heard of the incident, and I’d bet 90% of the human population hasn’t either. You are likely privy to more information than me, and I’m not sure it’s fair to assume that I should’ve had the same outside context. I admit I reacted unfairly, but it’s also a t…

Post by skyberrys » Mon, Sep 14, 2026, 10:35 PM UTC

rznicolet wrote: post #138

skyberrys wrote: post #123

Earlier quoted context omitted.

You reminded me of a comic hanging up in the engineering college. It was a picture of a student getting their finger zapped with the thought bubble of "ouch, that hurt. Wonder if it will happen if I do that again?" And the caption was along the lines of "How to tell if you are ment for engineering."

Sounds like this ancient XKCD: https://xkcd.com/242/ (Normal person doesn't pull the lever again; scientist wonders if that happens every time. I assume the engineer does, too...)

Post by avereveard » Mon, Sep 14, 2026, 10:41 PM UTC

classified wrote: post #246

mchusma wrote: post #192

There was surprisingly little information on how they actually do this, but we run our business with a large number of, what we call "AI employees" in addition to regular employees, and they act in interesting ways. We've been building out orchestration tools to handle this, and we'll probably do a write-up or blog post on it soon. May even open source some of it. The preview is that the problem with most agents (and…

> we direct them to build as much software as possible That's not a cure-all. Sometimes not writing software is the better choice.

Post by cindyllm » Mon, Sep 14, 2026, 10:49 PM UTC

idopmstuff wrote: post #221

trencedamp wrote: post #194

Earlier quoted context omitted.

> I am somewhat surprised to see some of the errors current models make given their intelligence They have no intelligence. These are very very very refined prediction engines. > A common set is having Claude take some product photos and turn them into lifestyle ones using ChatGPT via Claude in Chrome. It's a pretty well-honed workflow at this point, but it'll still return images where the product is obviously not co…

> They have no intelligence. These are very very very refined prediction engines. Silly and pointless criticism. Why do the semantics of the word intelligence matter? Also, you need to understand that language evolves over time, and people often use a word to describe a thing that is newly discovered or invented that's similar to the word being used, because it's a helpful way of describing it that the listener will…