AI Safety Virtual Book Club - The Alignment Problem - Pt. 4

​​This event is for people who: a) would like to get into AI Safety and b) like reading :)

​​​What to read: The Alignment Problem, Chapter 5 - on Shaping, which dives more into the psychology and intellectual history of reinforcement learning. Each chapter is stand-alone and doesn't depend on previous chapters

​​​Format:
- Quick 15-min intro around attendees
- 45-min - guided discussion + breakout room mini-chats

​​​​For this series, we will be reading Brian Christian's "The Alignment Problem", an accessible and comprehensive AI Alignment-related book that non-technical readers can read. Currently it's available on Amazon in paperback form, or may be also available at your local library

​​​​For this session, we will read Chapter 5 - on Shaping. But do feel free to read beyond that!