Understanding Autonomous Systems
The discussion explores the complexities of defining desirable behavior in autonomous systems, particularly in the context of understanding human preferences. The challenge of epistemic security is highlighted, especially when considering the potential psychological impacts of super intelligent chatbots. Insights into using language models to predict human responses and align them with individual interests pave the way for future research in sociotechnical integration.In this clip
From this podcast
The Gradient
Davidad Dalrymple: Towards Provably Safe AI
Related Questions