Joar Max Viktor Skalse

This review discusses the current frontier of mechanistic interpretability, which aims to understand the computational mechanisms underlying neural networks. While the field has made progress, many open problems remain, including the need for improved methods, better applications to specific goals, and engagement with socio-technical challenges.

This paper introduces Guaranteed Safe (GS) AI, an approach to AI safety that ensures high-assurance quantitative safety guarantees. It relies on three core components—a world model, a safety specification, and a verifier—to mathematically verify that AI systems meet safety requirements.

STARC (STAndardised Reward Comparison) metrics, a class of pseudometrics, quantify differences between reward functions, providing theoretical and empirical tools to improve the analysis and safety of reward learning algorithms in reinforcement learning.