The worst is when I have to baby-sit someone else’s AI. It’s so frustrating to get tagged to review a PR, open it up, and find 400 lines of obviously incorrect slop. Some try to excuse by marking the PR [vibe] but like what the hell, at least review your own goddamn ai code before asking me to look at it. Usually I want to insta reject just for the disrespect for my time.

I've got some receipts for what I think is good vibe coding...

I save every prompt and associated ai-generated diff in a markdown file for a steganography package I'm working on.

Check out this document: https://github.com/sutt/innocuous/blob/master/docs/dev-summa...

In particular, under v0.1.0 see `decode-branch.md` prompt and it's associated generated diff which implements memoization for backtracking while performing decoding.

It's a tight PR that fits the existing codebase and works well, you just need a motivating example you can reproduce which can help me you quickly determine if the proposed solution is working. I usually generate 2-3 solutions initially and then filter them quickly based on a test case. And as you can see from the prompt, it's far from well formatted or comprehensive, just "slap dash" listing of potentially relevant information similar to what would be discussed at an informal whiteboard session.

I insta reject. It’s ridiculous how bad it’s made some devs. Are they even testing their work before tossing over the wall?

Hold up, people are starting to mark PRs with [vibe] as in “I don’t stand behind this, good luck.” ??

I do not care if engineers on my team are using AI. In fact, I think they should be. This is the new world and we need to get used to it.

But it’s still your work, your responsibility. You still have to own it. No cop outs.

Recently in that exact situation.

Junior dev vibe codes some slop to solve a problem that was barely a problem. The "solution" to that not-a-problem was 2500 lines of slop. Unused variables, spaghetti logic, unit tests that were clearly write-once, read-never.

The slop at that point is the meta-problem, the real problem becomes me trying to convince (through multiple rounds of code review) that this was not maintainable code, and not a tenable development model.

All those rounds of review take TIME and mental effort. At some point, when the code review takes more effort than the code owner contributed, the value proposition is shot.

Generate the code however you want (llm, bit twiddling, whatever), but the effort and care must be there. If you can't use an llm skillfully and vouch for the output, it's gonna be a no from me dawg

We need to normalize to reject crap PRs. If we don't then things will only continue.

lol if I saw a teammember create a PR with "[vibe]" in the title I would: 1) Gape in disbelief 2) Shout obscenities as loud as I can 3) Take a deep breath 4) reject the PR and seriously consider firing them.

Yeah "consider firing" is a bit of an extreme kneejerk reaction, but I just feel like we HAVE to create consequences for this nonsense.

> and find 400 lines of obviously incorrect slop

I call that a good day. I've seen people push 2000 line PRs. The worst was 5000 lines. FML.

Have your own agent do first pass code reviews, they catch that stuff every time.