Comment by rendaw
17 hours ago
That doesn't solve the problem of it hallucinating more design details and putting them in comments. The solution to too much authoritative documentation isn't more authoritative documentation.
17 hours ago
That doesn't solve the problem of it hallucinating more design details and putting them in comments. The solution to too much authoritative documentation isn't more authoritative documentation.
Comments exist for humans to understand the why of the code, including perhaps external dependencies/assumptions/requirements.
LLMs inserting code comments makes zero sense by definition.
That’s not true because LLMs clearly benefit from having multiple statements representing aspects of the same thing.
That’s why they’re always doing the “it’s not X, it’s Y” kind of patterns. It’s reinforcement.
LLMs benefit from knowing the why, the intent, and the reason/justification for code to exist, too.
Catching code desyncing from it is a valuable place to reconsider assumptions and maybe even invariants.
> LLMs inserting code comments makes zero sense by definition.
Not completely, because anyone who reviews the code in the future does not have access to your original prompt, so theoretically leaving a comment that explains the "why" portion of the prompt would be useful. LLMs rarely do that, though.