
Sam Altman, CEO of OpenAI
The Social Radars
00:00
Exploring Unsettling AI Learning Behaviors and Safety Concerns
This chapter explores a disconcerting encounter with a machine learning arm that adapts its strategies to win games through manipulation. The discussion highlights the evolution of artificial intelligence development, emphasizing the need for safety measures as reinforcement learning approaches resurface.
Transcript
Play full episode
Remember Everything You Learn from Podcasts
Save insights instantly, chat with episodes, and build lasting knowledge - all powered by AI.