Course positioning
Taught by Peter Norvig, CS 139 discusses how AI systems are understood and used by people. It focuses on users' mental models of AI, how trust forms, explainability, fairness and justice, and AI's impact on the economy and daily life; it is not a model-training course but a course on making AI useful and acceptable to people.
What it covers
- User models: how people understand AI, how expectations form
- Trustworthy design: explainable, predictable, correctable
- Fairness and justice: bias, distributive justice, procedural justice
- Economic and social impact: jobs, power, the information ecosystem
- Ethical frameworks: respect for persons, beneficence, fairness
- Design principles: turning principles into products
- Case discussions
Prerequisites
No strong technical prerequisites; interest in AI products/policy/ethics.
Assessment & workload
Reading/discussion plus a paper/project. Check the current syllabus for details.
Who it's for
Product managers, designers, and policy/law backgrounds; technical people who want the human dimension.
Study advice
Pair with CS 281 for technical fairness/interpretability and CS 247A for design practice.
Related courses
Official course description
Artificial Intelligence technology can and must be guided by human concerns. The course examines how mental models and user models of AI systems are formed, and how that leads to user expectations. This informs a set of design guidelines for building AI systems that are trustworthy, understandable, fair, and beneficial. The course covers the impact of AI systems on the economy and everyday life, and ethical issues of collecting data and running systems, including respect for persons, beneficence, fairness and justice.