Podcasts Government EARadio EAG 2018 London: AI Safety Needs Social Scientists

EAG 2018 London: AI Safety Needs Social Scientists

Published: July 23, 2019, 6 a.m.

When an AI wins a game against a human, that AI has usually trained by playing that game against itself millions of times. When an AI recognizes that an image contains a cat, it’s probably been trained on thousands of cat photos. So if we want to teach an AI about human preferences, we’ll probably …

EAG 2018 London: AI Safety Needs Social Scientists Read More »