Highlights: #159 – Jan Leike on OpenAI’s massive push to make superintelligence safe in 4 years or less
80k After Hours
00:00
Origins of Reinforcement Learning from Human Feedback and Its Success in Improving the Performance of Chat GPT
This chapter explores the origins of reinforcement learning from human feedback, including previous research efforts and the success of aligning the chat GPT model with human preferences.
Transcript
Play full episode
