Inside the Mind of AI (Robert Wright & Nora Belrose)

1:57 Nora’s low score on the AI doomer test 8:26 The messy math of AI alignment 13:41 Teaching and (unteaching) concepts to LLMS 18:06 Do we really want human-like AI? 28:48 How the AI “mind” works 40:41 How to change an AI’s mind 53:19 Are LLMs reverse-engineering the human mind? 57:26 Heading to Overtime

Robert Wright (Nonzero, The Evolution of God, Why Buddhism Is True) and Nora Belrose (EleutherAI). Recorded January 16, 2024.

Twitter: https://twitter.com/NonzeroPods

Overtime titles:

0:00 Eleuther’s extra open open-source AIs 4:29 Is the human mind a general learning machine? 7:18 Why Nora supports open-source AI 11:42 How could we tell if AIs are conscious? 23:31 The new contender for reinforcement learning supremacy 29:57 Inside the minds of the AI doomers 40:52 Bob’s main sources of AI anxiety