Mechanistic Interpretability, Alignment & World Models

This foundational lecture provides the historical context and conceptual genesis of deep learning, setting the stage for understanding the complex systems we aim to interpret and align.

Building on the deep learning revolution, this lecture introduces mechanistic interpretability by dissecting transformer circuits, specifically induction heads, to understand how models achieve in-context learning.

Expanding beyond token prediction, this step introduces objective-driven AI and world models, offering a framework for how AI systems learn, remember, reason, and plan, which is crucial for alignment.

With an understanding of world models, this lecture delves into structured internal knowledge modeling, which is essential for addressing unlearning and jailbreaking, directly impacting AI safety and alignment.

This lecture directly addresses critical aspects of AI safety, exploring methods and theoretical frameworks to ensure robust and reliable operation, building upon the technical insights from interpretability and world models.

The final step translates technical AI safety research into practical oversight policy, examining the institutional and regulatory mechanisms needed to govern advanced AI systems effectively.