[rgoulter]

I could see it in cases.

LLMs excel at tasks that are fresh. LLMs are wonderful at getting the first 80% of the way there. -- LLMs are phenomenally good for a first draft or so.

I've had worse experiences for getting LLMs / agents to refactor code. I would believe in many cases it could be quicker to just manually go through and make refinements compared to merely getting the LLM to keep trying.

[broochcoach]

That seems very intuitive to me. If you want extremely specific changes made at extremely specific locations in an extremely specific way then you probably need to do that yourself because a language model can’t read your mind. I think there are very large set of problems where implementation details do not actually matter and cheap, disposable code is not a problem. I don’t think vibecoding is a good idea for missile guidance. Probably OK for a dashboard a manager isn’t really going to use anyway.