Three principles for creating safer AI

How can we harness the power of superintelligent AI while also preventing the catastrophe of robotic takeover? As we move closer towardcreating all-knowing machines, AI pioneer Stuart Russell is working on something a bit different: robots with uncertainty. Hear his vision for human-compatible AI that can solve problems using common sense, altruism and other human values. This talk was presented at an official TED conference in April 2017.