On: Is there a name for the type of comments agents add where they leak the prompt?

[king_zee]

I'm not sure if you're worried that the comment leaks what you prompted, or that the comment is redundant and evident, and makes it obvious that it wasn't written by a human, and for both these issues the solution is just to proof-read your damn code

[thejazzman → king_zee]

The context is if you ask for something like “X that looks awesome” it’ll then describe itself as looking awesome throughout your product in customer facing fashion ways.

Instead of “title” it’ll become “the awesome title”

Crude but cromulent example.