Reviewing AI-generated code
Code review’s job doesn’t change when the author was a model. What changes is the failure distribution: a few things go wrong more often with AI-generated diffs than with human ones, and the author’s self-review has to work harder to catch them.
Recommended default
Section titled “Recommended default”Review AI-generated code the same way you’d review a contribution from a competent, hurried stranger who can’t answer questions afterwards. The standard is unchanged: fit, correctness, tests. What shifts is where the eyes go first.
What stays the same
Section titled “What stays the same”Everything on code review expectations still applies. The author still owns correctness — “the model wrote it” isn’t a defence. Approve still means safe to merge, not “safe once I check”.
What to look at first
Section titled “What to look at first”- Invented APIs and hallucinated types. A confident-looking function call that doesn’t exist. Grep the identifier before you trust it; the compiler catches some, not all.
- Plausible-but-wrong edits. Correct-shape code that misreads the caller’s intent. The most dangerous kind — reads fine, ships fine, fails at 3am.
- Silent scope creep. Renamed helpers, reformatted neighbours, tweaked imports the prompt never asked for. Reject the noise even when the noise looks nice.
What the author owes the reviewer
Section titled “What the author owes the reviewer”- A tighter self-review than usual. You wrote less of this than a normal diff; your first read is the review. Do it before opening the PR.
- State the intent, not the transcript. What you asked the model to do tells the reviewer what to check.
- Own the diff, line by line. If you can’t explain why a line is there, delete it. Keep only what you’d defend in review.