Everyone's familiar with the science fiction scenarios of "AI gone wrong", but what's the reality of the situation? This talk introduces AI Safety, a field of research which analyses the actual problems we're likely to face with powerful AI systems, and tries to find technical solutions to them, so we can ensure that artificial general intelligence is safe and beneficial for humanity.
Everyone's familiar with the science fiction scenarios of "AI gone wrong", but what's the reality of the situation? This talk introduces AI Safety, a field of research which analyses the actual problems we're likely to face with powerful AI systems, and tries to find technical solutions to them, so we can ensure that artificial general intelligence is safe and beneficial for humanity.