Hacker News Reader

Comment by sampullman | Hacker News Reader

You are in a bubble or just happen to be at a place that doesn't care about architecture or quality code. I vibe lots of code, but most of it would never make it past review without significant editing and manual guidance.

You can't blame open source projects for rejecting PRs out of hand, when they have a hundred thousand lines of garbage. Not everybody is ready for their project to completely descend into slop yet. Maybe in a couple years though.

View on HN

The "problem" with FOSS projects is that they're getting submissions from people who have no idea what they're doing, not that AI per se is an issue. Like the other poster, all of the actual professionals at my F100 have been doing 100% AI coding for most of the year. Having the actual coding part automated means it's easier to improve architecture, reliability, performance, testing, etc. All the things that you always want to do but previously couldn't justify spending the time on are now doable.

I agree for the most part, although I think there is also an issue of laziness. There are people who should know better that are submitting unreviewed garbage.

But from the sound of it, you are not agreeing with the sibling comment, because you still have to review the code to make sure it's not slopping up the codebase or taking the architecture in an insane direction.

Large companies tend to be under a regulatory regime where code reviews are mandatory already. But no, my experience is what the sibling said. 100% agent driven, no IDE open at all. The difference is professionals will naturally just prompt better because they better know what they want.

Reply on news.ycombinator.com