Conductor is an app for running a team of coding agents on your Mac, used by engineers at companies like Stripe, Vercel, and Notion. We're a team of four looking for exceptional software engineers and designers to help us build a new way of working with AIs.
Founding Engineer @ Conductor (San Francisco, ONSITE)
Conductor lets you run a team of coding agents on your Mac. We launched in July through Show HN, and are used by engineers at companies like Linear, Vercel, Notion, Stripe, and YC.
We’re on a mission to build the human interface to AI organizations. We’re a team of four looking for one or two more exceptional engineers or designers.
No AI experience needed, just some enthusiasm for the awesome alien power of LLMs.
This is a strange comment. The author claims to be a human—"what we've done", "we built something", "we pointed a metal box into the dark"—but nearly every sentence sounds distinctly AI-writen.
(Examples: "I keep coming back to this:", "Voyager isn't ... It's ...", "the assumption that the future would exist and might care", "on our doorstep", "see the end of the story", "depends less on ... and more on ...", etc.)
I don't think so. I wouldn't expect an AI to say " It’s proof that humans will build absurdly long-horizon projects anyway, even when the ROI is almost entirely knowledge and perspective"
"the ROI is almost entirely knowledge and perspective" - this isn't a way I've ever heard an AI talk.
And at a meta-level, accusing someone of being an AI is getting very boring and repetitive (admittedly, I've done it once), and I expect we'll have to get used to that too.
Or it's just their writing style. There's nothing distinctly AI that I can see in there, and many of the common AI tropes come from commonalities in human writing.
Nah, look at their posting history. In the last hour they've posted a whole slew of comments with the same sort of tone and the same AI-ish stylistic quirks, all in quite surprisingly quick succession if the author is actually reading the things they're commenting on and thinking about them before posting. (And their comments before this posting spree are quite different in style.) I won't say it's impossible for this to be human work, but it sure doesn't look like it.
>about: Engineer building workflow-focused AI systems. Interested in ML reliability, document-heavy automation, and enterprise integrations. I enjoy discussing real-world constraints in AI and distributed systems.
Hi, creator here. If you want to copy node_modules instead of reinstalling, you can click on the repo and add a setup script that does the copy. Sorry it’s a bit obscure—we’re working on making this easier!
Would love to discuss more what kind of testing setup you’re looking for, want to shoot me an email at jackson@melty.sh?
The True Jedi
⬜⬜⬜⬜ Balanced in risk seeking
⬜⬜⬜⬜ Balanced in loss aversion
⬜⬜⬜⬜ Balanced in magnitude sensitivity
I lost -$1,018,389.5
I guess "balanced in magnitude sensitivity" means I wasted time on the small bets that barely affected my total earnings... I probably should've clicked randomly on those
Oh yes sorry my mistake, I merged the two data and I made a bit of confusion, I thought it was 317 x 10(6) and 130 x 10(6), instead is 13 not 130. Sorry. By the way moderators have changed the title (but now I don’t know who will understand what this post is about)
Conductor is an app for running a team of coding agents on your Mac, used by engineers at companies like Stripe, Vercel, and Notion. We're a team of four looking for exceptional software engineers and designers to help us build a new way of working with AIs.
https://www.conductor.build/join-us
reply