then you should be delighted we have LLMs one of the use cases they are best suited to is writing documentation, much better than humans can.

Good is debatable. The docs I want point out the weird shit in the system. The AI docs I've read are all basically "the get user endpoint can be called with HTTP to get a user, given a valid auth token". Thanks, it would have been faster to read the code.

They write good _looking_ documentation. How good those docs are is entirely on the person/people who prompted them into existence.

Please don't inflict LLM docs on people