Lectures related to Friendly artificial intelligence

Covers Q-Learning in reinforcement learning, exploring action values, policies, and the societal impact of algorithms.

Value Tensions in AI: Mitigating Harms and Fostering Benefits

Delves into value tensions in AI ethics, balancing inclusion and privacy.

Intelligence Systems: Forecasting and Action

Delves into developing intelligence systems for predicting human behavior and enhancing AI-driven technologies' safety and efficiency.

Understanding Autonomy

Explores the challenges and distinctions between human and artificial autonomy, touching on ethical implications and the conditions required for true autonomy.

AI Ethics: Bias, Responsibility, and Accountability

Explores AI ethics, addressing bias, responsibility, and accountability in algorithm design and outcomes.