Too familiar. On top of that AI tends to blindly trust too much.

Me: it ain't working because of this, let's do it that (still wrong) way instead

AI: you're absolutely correct! let's do it. here you go

> shit still broken

Me: oh my bad, that was a stupid idea, that would never work, let's do it this other, still wrong, way

AI: I agree with you! that was not the right way. let's fix it

> does what I say even if it's blatantly wrong

> shit still broken