AI-powered
podcast player
Listen to all your favourite podcasts with AI-powered features
Is There a Risk of Self Replication?
Ol ki: You seem quite confident that a i will not get away from us. And we don't have to worry too much about the so called alignement problem, you say. Ol Ki: I think what most people fear is they use humans as an example of how things can go wrong. But if you take apart what parts of the human brain are or doing, there's some parts that are just building this model of the world. This is what it means to be intelligent. That part itself, i is benign. It has no motivations on its own. Do you know why do that? Wet. Just have this thing which is inherently smart, but on its own doesn't really