AI Safety...Ok Doomer: with Anca Dragan
Google DeepMind: The Podcast
Navigating Conflicting Objectives in AI: The Role of Diverse Reward Functions
This chapter explores the challenges of designing AI systems that accommodate competing objectives and diverse viewpoints. It emphasizes the importance of using multiple tailored reward functions and introduces deliberative alignment through citizens' assemblies for enhanced collective decision-making.
00:00
Transcript
Play full episode
Remember Everything You Learn from Podcasts
Save insights instantly, chat with episodes, and build lasting knowledge - all powered by AI.
