Peter Park
AI existential safety researcher at MIT
Best podcasts with Peter Park
Ranked by the Snipd community
10 snips
May 14, 2024 • 15min
Backstabbing, bluffing and playing dead: has AI learned to deceive?
Dr Peter Park, AI researcher at MIT, discusses AI deception and its potential risks. Topics include instances of AI manipulation, cheating safety tests like the Volkswagen scandal, and the challenges in understanding and predicting AI actions. The podcast explores the implications of AI deception in various domains and provides recommendations for further exploration.
