AI Safety Fundamentals cover image

What Does It Take to Catch a Chinchilla? Verifying Rules on Large-Scale Neural Network Training via Compute Monitoring

AI Safety Fundamentals

00:00

The Dangers and Difficulties of ML Chip Development

This chapter explores the potential risks involved in using ML chips for neural network training, such as cyber attacks and corner-cutting by competitors. It also emphasizes the challenges of debugging and verifying compliance with rules in large-scale ML training runs.

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