Comment by duxup

Agreed on bad human code > bad llm code.

Bad human code to me is at least more understandable in what it was trying to do. There's a goal you can figure out and fix it. It generally operates within the context of larger code to some extant.

Bad LLM code can be broken from start to finish in ways that make zero sense. Even worse when it re-invents the wheel and replaces massive amounts of code. Human aren't likely just make up a function or methods that don't exist and deploy it. That's not the best example as you'd likely find that out fast, but it's the kind of screw up that indicates the entire chunk of LLM code you're examining may in fact be fundamentally flawed beyond normal experience. In some cases you almost need to re-learn the entire codebase to truly realize "oh this is THAT bad and none of this code is of any value".