>as long as the quality is good.

Well that's where we're seemingly at an impasse, no?

I don't even like the term "good vibecoding". The term was implied as a means to just let the computer type its own code and "go with the vibes". i.e. you have no deeper idea on how it works underneath.

Now, AI-assisted coding? It can be good. It can be a rush job. But the idea is that LLM's are in the passenger's seat, not the diver's. Much smaller chance where you have no idea where you're going since you're at the wheel.

▲

codexon 18 hours ago | parent [-]

The output is indistinguishable from manually written code.

▲

johnnyanmac 17 hours ago | parent [-]

I hope on HN of all places I don't need to explain the difference between "writing correct code" and "Software Engineering". We both know what a 20 year old million line legacy software needs.

▲

codexon 16 hours ago | parent [-]

Not everything needs to be amazon/google scale backed with things like sharded dbs or kubernetes.

	▲	johnnyanmac 15 hours ago \| parent [-]
		Nope, not at all. But a million line codebase isn't close to Google scale. That's typical boring non-tech legacy code system scale. And I don't think I'm at a point where I'd want to vibe code my way though that and take responsibility for it.