
John Schulman (OpenAI Cofounder) - Reasoning, RLHF, & Plan for 2027 AGI
Dwarkesh Podcast
Enhancing AI: Memory and Reasoning
This chapter examines the critical role of memory and introspection in AI systems, addressing their current limitations in adapting and learning. It also discusses the evolution of reinforcement learning techniques and the balance between training for short-term and long-term tasks to create more capable and autonomous AI models.
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.