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

Proposed System Design for Verifying Compliance with Neural Network Training Rules

This chapter discusses a proposed system design to verify compliance with rules on large-scale neural network training, including firmware, log inspection, and monitoring the supply chain. The chapter also addresses the challenges of small-scale training, preventing misuse, and identifies open problems.

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