Ryan Greenblatt on AI Control, Timelines, and Slowing Down Around Human-Level AI
Future of Life Institute Podcast
00:00
Interplay of AI Models: Trust, Manipulation, and Safeguards
This chapter explores the intricate relationships between strong and weak AI models, particularly the risks of manipulation and deception. It underscores the significance of red teaming practices to safeguard against vulnerabilities like jailbreaking while aiming to maintain trust in weaker models.
Transcript
Play full episode
