Comment by dragonwriter

> As an experienced reviewer, the "shape" of the code shouldn't inform correctness, but it can be easy to fall into this pattern when you review code.

For human written code, shape correlates somewhat with correctness, largely because the shape and the correctness are both driven by the human thought patterns generating the code.

LLMs are trained very well at reproducing the shape of expected outputs, but the mechanism is different than humans and not represented the same way in the shape of the outputs. So the correlation is, at best, weaker with the LLMs, if it is present at all.

This is also much the same effect that makes LLMs convincing purveyors of BS in natural language, but magnified for code because people are more used to people bluffing with shape using natural language, but churning out high-volume, well-shaped, crappy substance code is not a particularly useful skill for humans to develop, and so not a frequently encountered skill. And so, prior to AI code, reviewers weren't faced with it a lot.