Russell's key point: right now, we design AIs with objective functions that don't encompass what we actually want. That means that the "smarter" they get - the better they optimize for something that's not what we want - the worse off we are.
-
-
Prikaži ovu nit
-
He argues that if we instead design AIs whose objective is to get a better model of humans and do what we want, then there's still a lot which can go wrong - but more competent AI means better outcomes instead of meaning worse ones. That's a safer paradigm to be working in.
Prikaži ovu nit
Kraj razgovora
Novi razgovor -
Čini se da učitavanje traje već neko vrijeme.
Twitter je možda preopterećen ili ima kratkotrajnih poteškoća u radu. Pokušajte ponovno ili potražite dodatne informacije u odjeljku Status Twittera.