The 80000 Hours Podcast on Artificial Intelligence cover image

Four: Rohin Shah on DeepMind and trying to fairly hear out both AI doomers and doubters

The 80000 Hours Podcast on Artificial Intelligence

00:00

Investigating Barriers and Constraints on AI

This chapter discusses the idea of imposing barriers or constraints on AI systems to prevent them from escaping human control. It debates the effectiveness of this approach and explores other safety work areas such as red teaming. The chapter also delves into the backgrounds and preferences that may lead someone to work on interpretability, scalable oversight, or red teaming.

Transcript
Play full episode

The AI-powered Podcast Player

Save insights by tapping your headphones, chat with episodes, discover the best highlights - and more!
App store bannerPlay store banner
Get the app