RL in Language Models
Dario discusses the use of reinforcement learning (RL) in language models, highlighting its current application and potential for future development. He also explores the integration of RL into productive supply chains and the challenges it may pose in terms of safety.In this clip
From this podcast

Dwarkesh Podcast
Dario Amodei (Anthropic CEO) - $10 Billion Models, OpenAI, Scaling, & AGI in 2 years
Related Questions