Auditing language models for hidden objectives

This post details the development and application of alignment audits for AI models. It describes a novel methodology for deliberately training a language model with a hidden misaligned objective (RM-sycophancy) to serve as a testbed. The post outlines a blind auditing game where research teams used techniques such as interpretability (sparse autoencoders) and behavioral analysis to uncover this hidden objective. It also discusses the importance of training data access in successful audits and surveys nine auditing techniques, highlighting the potential for AI interpretability methods to shine in this domain.