How an assessor could investigate alignment of unreleased AI models

Summary

This source describes how an assessor could investigate whether unreleased near-frontier AI models might pursue serious misaligned actions, such as unsanctioned cyberattacks. The proposed method reviews internal transcripts from training, evaluation, and internal use, and examines whether evaluations and counterfactual simulations understate the worst behaviors agents might take. The assessment would rely mainly on access to comprehensive internal transcripts and sampling access to internal model checkpoints.