My observation is that vibe-coded applications are significantly lower quality than traditional software. Anthropic software (which they claim to be 90% vibe coded) is extremely buggy, especially the UI.

▲

gowld 7 hours ago | parent [-]

That's a misunderstanding based on loose definition of "vibe coding". When companies threw around the "90% of code is written by AI" claims, they were referring to counting characers of autocomplete basing on users actually typing code (most of which was eequivalent to "AI generated" code by Eclipse tab-completion decade ago), and sometimes writing hyperlocal prompts for a single method.

We can identify 3 levels of "vibe coding":

1. GenAI Autocomplete

2. Hyperlocal prompting about a specific function. (Copilot's orginal pitch)

3. Developing the app without looking at code.

Level 3 is hardly considered "vibe" coding, and Level 2 is iffy.

"90% of code written by AI" in some non-trivial contexts only very recently reached level 3.

I don't think it ever reached Level 2, because that's just a painfully tedious way of writing code.

▲

xcodevn 6 hours ago | parent | next [-]

I believe Anthropic is already doing Level 3 vibe coding for >90% of their code.

▲

doug_durham 6 hours ago | parent [-]

They have not said that. They've only said that most of their code is written by Claude. That is different than "vibe coding". If competent engineers review the code then it is little different than any coding.

	▲	xcodevn 6 hours ago \| parent [-]
		IIRC, the Claude Code creator mentioned that all the PRs are reviewed by humans, just like normal human PRs. So yes, humans still look at the code at the review stage. Though I still consider this to be level 3, but anyway, this is just a matter of definition.

▲

andai 7 hours ago | parent | prev [-]

I mostly work at level 2, and I call it "power coding", like power armor, or power tools. Your will and your hand still guides the process continuously. But now your force is greatly multiplied.