People of course often do read (and even modify) the model-generated code, but doing so is specifically not “vibe coding” according to the original definition, which was not meant to encompass “any programming with an LLM” but something much more specific: https://simonwillison.net/2025/Mar/19/vibe-coding/

The whole point of the term is to convey that you are only looking at the output and not looking under the hood. If vibe coding a UI, you only look at the UI, not the CSS.

Nope. That's the "vibe" part of Vibe Coding™.

> The developer does not review or edit the code, but solely uses tools and execution results to evaluate it and asks the LLM for improvements. Unlike traditional AI-assisted coding or pair programming, the human developer avoids examination of the code, accepts AI-suggested completions without human review, and focuses more on iterative experimentation than code correctness or structure.

https://en.wikipedia.org/wiki/Vibe_coding