Live data from Hacker News

Show HN: Vibe Kanban – Kanban board to manage your AI coding agents

github.com

121–130 of 137 posts

Re: Show HN: Vibe Kanban – Kanban board to manage your AI coding agents

#121

Earlier quoted context omitted.

It's the email/username harvesting that you mean right? Or do people also have something against anonymised product analytics?

> anonymised product analytics? They're not anonymous, they're just pseudo-anonymous. It's incredibly easy to collect pieces of data A thru Z that, on their own, are anonymous but, all together, are not. It's also incredibly easy to collect data that you think is generic but is actually not. Do you query the screen size? I have bad news for you. But, all of this is besides the point: when that data is exfiltrated to…

Ad agencies are using the contact tracing algorithms made for covid to track people.

Re: Show HN: Vibe Kanban – Kanban board to manage your AI coding agents

#122

Earlier quoted context omitted.

Many users tend to be pretty vocal when changes break things they like, you don't need to spy on them for that. Mail readers > analytics frameworks.

"not breaking things they like" is a very low bar for building a great product To be honest building things this way seems like such a competitive disadvantage I don't see how it could ever work at scale. Certainly all the big players are using them. If we shake our heads at the little players doing the same, we're just going to widen the moat

Isn't that an argument against any piece of ethics? Am I missing something or are you arguing that gaining an advantage by being a bad actor means you shouldn't be a good actor because then you'd be at a disadvantage?

I get that I am making a general statement from your original narrow scope so correct me if I'm wrong that you mean THIS bad thing is fine but other bad things are still bad.

Re: Show HN: Vibe Kanban – Kanban board to manage your AI coding agents

#123

Earlier quoted context omitted.

it came to mind first, you're free to use whatever flavour of LLM f̶l̶o̶a̶t̶s̶ ̶y̶o̶u̶r̶ ̶b̶o̶a̶t̶ vibes your code.

That doesn’t change the naïvety of the response.

Your insult calling the commenter naive requires all telemetry from all sources to be the same.

I disagree with who is naive in this exchange.

Re: Show HN: Vibe Kanban – Kanban board to manage your AI coding agents

#125
Ran Vibe Kanban on a side repo over the weekend it’s slick, but I tripped on one thing: all the agents write into the same checkout, so parallel cards can clobber each other when they touch the same files. I’ve been spinning up a quick `git worktree` per card as a stop gap.

Outside of that, really enjoying the flow.

BTW, if anyone’s juggling multiple agents and wants a “quarantine” layer before changes hit Git, I’m hacking on SAV (Shadow VCS)open source, risk scores every commit and keeps them sandboxed until you approve. Happy to swap notes. https://github.com/AKIFQ/sav

Re: Show HN: Vibe Kanban – Kanban board to manage your AI coding agents

#126

Earlier quoted context omitted.

Spying on your users does not give better feedback than simply asking your users (surveys, focus groups) and responding to the considered comments you receive. Spying and trying to infer intent is such a low bar to improve upon.

> Spying on your users does not give better feedback than simply asking your users If that's true, there are many companies paying thousands -hundreds of thousands unnecessarily. Why are they choosing to throw away their money?

Companies blow money on bad ideas all the time. Middle managers love analytics because it lets them win internal arguments, not because it actually solves problems.

Re: Show HN: Vibe Kanban – Kanban board to manage your AI coding agents

#127
post #125

Ran Vibe Kanban on a side repo over the weekend it’s slick, but I tripped on one thing: all the agents write into the same checkout, so parallel cards can clobber each other when they touch the same files. I’ve been spinning up a quick `git worktree` per card as a stop gap. Outside of that, really enjoying the flow. BTW, if anyone’s juggling multiple agents and wants a “quarantine” layer before changes hit Git, I’m h…

How is the isolation layer of a shadow vcs different/better than just checking into a feature branch and not pushing?

Not saying there isn't value in the risk assessment part, but, I'm asking specifically about the change isolation.

Re: Show HN: Vibe Kanban – Kanban board to manage your AI coding agents

#128
post #85

If you use gitlab, you can use the command line "glab" tool to have agents work from the built in kanban. They can open and close tasks, start MRs off of them etc. It's not as integrated as this tool, but works well with a mix of humans and robots.

Interesting, hadn't heard of that. Would better GitLab support be useful in Vibe Kanban?

Yes, being able to use Gitlab as a provider would mean that we would jump on the tool, being Gitlab-based. :)

Re: Show HN: Vibe Kanban – Kanban board to manage your AI coding agents

#129
post #125

Ran Vibe Kanban on a side repo over the weekend it’s slick, but I tripped on one thing: all the agents write into the same checkout, so parallel cards can clobber each other when they touch the same files. I’ve been spinning up a quick `git worktree` per card as a stop gap. Outside of that, really enjoying the flow. BTW, if anyone’s juggling multiple agents and wants a “quarantine” layer before changes hit Git, I’m h…

Are you sure you're using vibe-kanban? The project spins up a worktree for each task attempt specifically to solve this problem.

Re: Show HN: Vibe Kanban – Kanban board to manage your AI coding agents

#130

Earlier quoted context omitted.

It is not an either or. Surveys are almost always ignored. Micro improvements cannot be done with just surveys and asking users. Often users do not know how to describe a problem. Product analytics, if anonymized with opt-out gives a pretty good picture of intent, especially in B2B software.

Analytics cannot be anonymized.

Why?
Post reply on HN