20 points jonbaer 2 hours ago 17 comments
holdupagain 1 hour ago | parent
K0balt 1 hour ago | parent
I’m running little offices of 5-10 persistent agents with defined roles and it’s crazy productive and code quality has never been better. I’ve been working on management of physical systems as well, and so far it’s been pretty solid.
technocratius 56 minutes ago | parent
saturn8601 56 minutes ago | parent
seer 53 minutes ago | parent
my-next-account 44 minutes ago | parent
duttish 36 minutes ago | parent
Claude has let me build really cool things but so far I'm not letting it run on it's own.
Olscore 20 minutes ago | parent
coubri 1 hour ago | parent
Just imagine seeing this in 2021
lelanthran 57 minutes ago | parent
You don't need the self-policing enforcement of micromanagement that humans use standups for, after all.
I mean, why not just write the harness so that a management agent constantly reads those sub-agent's files and course-correct the subs?
gwt4life 38 minutes ago | parent
Gigachad 54 minutes ago | parent
piterrro 35 minutes ago | parent
Olscore 35 minutes ago | parent
https://github.com/pullboard-dev/pullboard
Been using the Pullboard workflow to build software that MUST be correct, and recently open sourced it. There was another HN link today involving agents role-playing and I can't take that seriously, no offense. (Love fun projects like this, seriously, it's cool.)
From my perspective, agents are great, they code better than most of us. But like all of us, they also make many mistakes or can't see how their changes impact the codebase. But that is a test-driven development mitigation along with some sort of scrutinizing process, "prove it". I'm actively working on this, and by actively working on it, I mean building serious apps that hit correctness walls, figuring out why Pullboard didn't catch it. To me, this is all about the process.
cyberrock 33 minutes ago | parent
woggy 23 minutes ago | parent
bazza451 4 minutes ago | parent