Correctness.

AI-generated code that calls functions, methods, parameters, config keys, or packages that look plausible but do not exist in the actual library version you depend on.

AI assistants tend to generate code that handles only the successful, well-formed case — skipping input validation, error handling, null/empty checks, and edge cases — so the code works in the demo and breaks in production.

AI assistants emit functional code that silently omits the security controls a human would add by habit — input validation, authorization, output encoding, secrets handling — because "it compiles and returns 200" looks like done.