AI-Generated Code Review

Overview

AI-generated code fails differently than human-written code. An LLM will confidently invent a plausible-looking method that doesn't exist; it skips auth because tutorials rarely include it.

The core problem: Syntactically fluent but semantically unreliable. It passes linters and type checkers yet silently calls methods that don't exist or leaves security-critical paths unguarded.

When to use: Any PR with AI assistance markers — unusually consistent formatting, generic variable names, verbose boilerplate, comments explaining obvious things.

Mindset shift: Don't ask "is this correct?" Ask "did the AI understand the actual requirements, or generate plausible code for a slightly different problem?"

Quick Reference — AI Code Smell Severity