AI Alignment: Moral, Political, and Computational Foundations

3-0-9 units. HASS-S · Undergraduate

Examines how AI systems can be designed to reflect moral and political values. Integrates political theory, philosophy, science fiction, and computer science to analyze cases where AI has been or could be deployed to make decisions. Core topics include the politics of technology, value pluralism, human-AI entanglement, and strategies for eliciting and embedding values in automated systems. Compares AI-enabled decision-making to earlier decision methods and interrogates the role of technical formalization in efforts to align sociotechnical systems. Limited to 20; preference to Course 17 and Course 6 students.