Course positioning
Taught by Michael Bernstein and Noah Goodman, CS 222 spans social science, behavioral science, and generative AI. It moves from classical agent-based modeling to LLM-driven generative agents, discussing how to simulate individuals and societies, how to evaluate simulation fidelity, and the ethical issues involved.
What it covers
- Agent-based modeling: rules, emergence, calibration
- Social simulation: opinion spread, cooperation, public policy
- Generative agents: LLM-driven personas, memory, planning
- Counterfactual experiments: designing what-if scenarios
- Evaluation: simulation fidelity, bias, reproducibility
- Ethics: manipulation, privacy, the power of simulation
- Team project: build a social simulation
Prerequisites
Python programming; AI (CS 221/224), human-centered design, or social psychology helps but is not required.
Assessment & workload
Mainly a team project plus assignments/discussion. Check the current syllabus for details.
Who it's for
Computational social science, multi-agent systems, AI policy/ethics; anyone who wants to build social simulations or generative agents.
Study advice
Read Generative Agents (Park et al., 2023) and classic Schelling/NetLogo models first. Pay attention to reproducibility and ethical boundaries.
Related courses
Official course description
How might we craft simulations of human societies that reflect our lives? Many of the greatest challenges of our time, from encouraging healthy public discourse to designing pandemic responses, and building global cooperation for sustainability, must reckon with the complex nature of our world. The power to simulate hypothetical worlds in which we can ask "what if" counterfactual questions, and paint concrete pictures of how a multiverse of different possibilities might unfold, promises an opportunity to navigate this complexity. This course presents a tour of multiple decades of effort in social, behavioral, and computational sciences to simulate individuals and their societies, starting from foundational literature in agent-based modeling to generative agents that leverage the power of the most advanced generative AI to create high-fidelity simulations. Along the way, students will learn about the opportunities, challenges, and ethical considerations in the field of human behavioral simulations. Prerequisites: Team projects and some course assignments will involve programming in Python. Having a background in human-centered design (e.g., CS 147, ME 115A, or a class from the d.school), AI (e.g., CS 221, CS 224), or social psychology may be helpful, although it is not required.