Phil 11.30.19

Noam Chomsky: Language, Cognition, and Deep Learning | Artificial Intelligence (AI) Podcast

Stuart Russell, in Human Compatible, makes the case that we need to make AI that uses some form of inverse reinforcement learning, to figure out what we as humans want. I’m not opposed to that, but I think I want in addition, a system, that exercises AI and ML systems looking for runaway conditions. If an AI system can be falsified in this way, it is, by definition, dangerous.