Live data from Hacker News

Open source Kanban desktop app that runs parallel agents on every card

kanbots.dev

71–80 of 191 posts

Re: Open source Kanban desktop app that runs parallel agents on every card

#72

I keep wondering how people accept a nights worth of agent activity. I feel 30 minutes of planning and 30 minutes of implementation in my solo side project's repo is too big to review. At minute 5, I may ask the AI to redo stuff even as its spitting out code.

They don’t, they just have Claude commit and push straight to the main branch. Just like the author of this 100% slop app: https://github.com/leodavinci1/kanbots/commits/main/

Re: Open source Kanban desktop app that runs parallel agents on every card

#73

I keep wondering how people accept a nights worth of agent activity. I feel 30 minutes of planning and 30 minutes of implementation in my solo side project's repo is too big to review. At minute 5, I may ask the AI to redo stuff even as its spitting out code.

I usually aim to have Claude end up with about 500 lines of code after a night of work. Most of what it's doing is experimenting with many different approaches, summarizing them, and then giving me a relatively small diff to review and modify.

Re: Open source Kanban desktop app that runs parallel agents on every card

#74

Isn’t this just vibe kanban? https://github.com/BloopAI/vibe-kanban

Competitors can exist.

The way I've explained it: "there's 8 billion other monkeys on this rock dude, of course someone else is doing the same thing."

Re: Open source Kanban desktop app that runs parallel agents on every card

#76

I keep wondering how people accept a nights worth of agent activity. I feel 30 minutes of planning and 30 minutes of implementation in my solo side project's repo is too big to review. At minute 5, I may ask the AI to redo stuff even as its spitting out code.

Most of the narrative is about how AI is writing all/most code, but I’d wager that the fraction of human reviewed code is approaching zero far faster than anyone is realizing or willing to admit.

People already barely reviewed code, most of it was imported libraries.

Re: Open source Kanban desktop app that runs parallel agents on every card

#77
post #50

Earlier quoted context omitted.

Which one-off tasks need 10k lines of code?

Calculate the engine power of a 2015 VW polo when travelling 70 mph on a flat road behind a box truck. Draw a chart of drag Vs follow distance. How significant is humidity on the result?

European or African Polo?

Re: Open source Kanban desktop app that runs parallel agents on every card

#79
post #76

Earlier quoted context omitted.

Most of the narrative is about how AI is writing all/most code, but I’d wager that the fraction of human reviewed code is approaching zero far faster than anyone is realizing or willing to admit.

People already barely reviewed code, most of it was imported libraries.

The assumption used to be that you respected the library enough and believed it was well reviewed and architected by the maintainer(s). But now even that's unreliable because libraries are being slopified at an unreviewable pace too.

Re: Open source Kanban desktop app that runs parallel agents on every card

#80

Earlier quoted context omitted.

Calculate the engine power of a 2015 VW polo when travelling 70 mph on a flat road behind a box truck. Draw a chart of drag Vs follow distance. How significant is humidity on the result?

European or African Polo?

I don't know th- AAAAHHHH
Post reply on HN