Ethical AI Reasoning
Shane emphasizes the need for AI systems to go beyond sampling from models and instead develop a deep understanding of the world, ethics, and reliable reasoning. Dwarkesh discusses the challenge of aligning AI values with human values and the importance of effectively communicating those values to the system.In this clip
From this podcast

Dwarkesh Podcast
Shane Legg (DeepMind Founder) - 2028 AGI, New Architectures, Aligning Superhuman Models
Related Questions