My manager uses Claude chatbot for writing all our user stories while we're on the call with him. It spits out so much shit! He'll say, "let's make sure it hasn't hallucinated anything .. nope"

There's no way he can be reading all that. I'll call out stuff early on, and he'll say "that's wrong, it hallucinated," and fix stuff and remove half of it, but 45 minutes into the story session, I think everyone tunes out.

Implementing this is going to be fucking hell.

Actually, I am generating a whole programming language without any mistakes and that's verifiable - using claude code. When instructed correctly, it can deliver PERFECT results.

But user stories are an exception. Because they are about what you WANT. And you can't let a bot to tell what you want. So you are right to be dismissive.

I will fight every opinion against AI. But user stories are not possible now or even in the feature to be made with AI. You can't let it think for you and expect to get what you want.

Shoot him down immediately. This has nothing to do with quality of AI. This is just inappropiate usage that will never be satisfied by AI because it literally isn't possible ever.