Jesse Hoogland

Jesse Hoogland and Daniel Murfet, co-founders of Timaeus, pioneer AI safety with their focus on developmental interpretability based on Singular Learning Theory. They discuss the complex, jagged landscapes of neural networks and how their Local Learning Coefficient can identify critical training phase changes. This innovative approach aims to catch safety issues early, providing a more structured methodology for AI development. Their insights reveal the intricate relationships between training data, model behavior, and alignment, pushing for a principled engineering discipline in AI.

Jesse Hoogland, AI safety researcher and co-founder of Timaeus, applies physics-inspired theory to neural nets. He discusses using Singular Learning Theory to link loss landscapes and internals. He talks about fast capability growth, diverse paths to catastrophic risk, tensions between theory and empirical tinkering, funding and timelines, and what scientific understanding could buy us for safer AI.

Jesse Hoogland, co-author of the influential LessWrong post on AI research fleets, dives into the exciting shift from individual AI scientists to collaborative systems. He discusses how research automation requires rethinking workflows, much like past technological revolutions did. Hoogland emphasizes the importance of institutional changes and community actions in embracing AI-augmented science. His insights challenge outdated expectations and propose innovative strategies for creating efficient, specialized research ecosystems.