No, this is where this discussion is, since the top comment. Please go elsewhere for straw men.

No one mentioned anything about "people who can't program at all" until your comment. Up until then the discussion was about using LLMs for production ready code. It's a given that people working on production systems know how to program.

That is what "auto-edits" (in the first comment) and "vibe coding" (in the second comment) mean.

The bit you're missing is that people who can program also use "auto edits" and "vibe coding" when it fits the problem at hand

As someone who can program and used vibe coding, when they use vibe coding and don't look at the output, how do they ensure errors don't compound?

I'll give you that - you can't vibe code, not look at the output, and push to main of a production codebase. Same as writing code normally.

But you can vibe code and auto-edit your way to a good PR. But you're reviewing the code being output when the agent finishes each task. Maybe that's not pure vibe coding?

The definition of vibe coding is that you aren't looking at the code. That's what's never worked for me.