Live data from Hacker News

My business partner sent a 5K vibe-coded PR that he didn't even test

ycj.bearblog.dev

121–122 of 122 posts

Re: My business partner sent a 5K vibe-coded PR that he didn't even test

#121
post #104
post #28

Earlier quoted context omitted.

I’ve been on a sabbatical for 99% of this year, small pockets of time spent doing some maintenance for clients I love. I bought a seriously derelict property in country Australia and am having a good time slowly fixing it up. I’ll get back to programming next year, hopefully the blow-ins have moved on to the next hype cycle by that time.

Hey great for you! I've been on a 3 year sabbatical, and I spend most summers in the countryside with my kids, grilling meat, planting berries, going in nature for hours-long walks. It's really a great life ain't it? So you're planning to go back for work? I'm unfortunately on my last 12-months or so of runway so time to figure out stuff.

>It's really a great life ain't it?

Yes, there’s no complaints from me :) Spent 4 months camping and now I’m still camping but fixing a property.

I’ll do something for money next year, who knows, I might find a good programming contract or I might be serving coffee at the local cafe!

Re: My business partner sent a 5K vibe-coded PR that he didn't even test

#122
post #9

The problem is not vibe coding. The problem is the people doing this were never good software engineers before vibe coding. Simply put you still need good practices to produce working good code with AI. Oddly what I have found best is patterns that many would cringe and demeans unit test and integration test. Yes I still vibe unit test and integration test, but more than ever I have to put on my PM and QA hat, even m…

Well said. The problem is that vibe coding can paper over bad engineering practices for awhile. And results look good, and when you raise concerns people look at you like you're dumb and trying to slow things down. But the underlying bad practices _will_ bite the same they would have before AI, you just don't know when. It's a really frustrating state of the industry to be in.

Models are the worst now that they ever will be. Frontier models do a phenomenal job of employing good engineering practices and code style compared to where they were mere months ago. Unassisted programming is dead. Programming as a human activity will be on a timescale of years (along with a vast swath of other knowledge work).
Post reply on HN