Ironically, it would've been more useful, and more inline with how non-trivial advancements in AI have been, to identify useless and obvious comments, and eliminate them.<p>I just experimented a little bit, and telling chatgpt to assume a self-documenting approach and skipping comments whenever possible, gets a pretty minimalist output. Add on asking about what non-obvious aspects might be noteworthy based on other projects, and I bet chatgpt would be able to find a list of things to look for, see if it's applicable, and then rewrite in the appropriate format. Like if the function is about sorting, it could figure out that knowing if it's stable is an important marker, and figure that out. Something like that could be useful.