Eliezer Yudkowsky on the Dangers of AI
EconTalk
00:00
The Threat of Superhuman AI
This chapter examines the complexities and dangers posed by superhuman AI, which may operate with its own unpredictable goals. Through hypothetical scenarios and analogies, it highlights the challenge of interpreting AI's intentions and the potential catastrophic outcomes of seemingly benign objectives.
Transcript
Play full episode
