A leet-code style automated assignment is like a test. We all did tests in school so I guess most people do not feel there is anything wrong about that.

However, an interview, which should be conducted by human, but instead by something AI pretends to be human, would make most of the current human beings feel disgusted, naturally.

Is there any formal proof that an AI conducted interview yields more than a pencil & paper test? Or is there any scientific research about that? I doubt there would be any in the near future. Then using such AI conducted interviews is simply a belief.