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

Verifying ML Chips and Training Transcripts

This chapter discusses a high-level technical plan for verifiers to monitor ML chips and training transcripts to ensure compliance with rules and commitments. They propose chip inspections, logging activity snapshots, and authenticating training transcripts as key components of the verification process.

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