课程定位
CS 222 由 Michael Bernstein 和 Noah Goodman 讲授,跨越社会科学、行为科学与生成式 AI。课程从经典 agent-based modeling 讲到 LLM 驱动的 generative agents,讨论如何模拟个体与社会、如何评估模拟的真实性,以及相关伦理问题。
主要内容
- Agent-based modeling:规则、涌现、校准
- 社会模拟:意见传播、合作、公共政策
- Generative agents:LLM 驱动的人格、记忆、规划
- 反事实实验:what-if 场景设计
- 评估:模拟保真度、偏差、可复现性
- 伦理:操纵、隐私、模拟的权力
- 团队项目:构建一个社会模拟
先修
Python 编程;AI(CS 221/224)、人本设计或社会心理学背景有帮助,但不强制。
考核与工作量
团队项目为主 + 课程作业/讨论。具体以当季官网为准。
适合谁
计算社会科学、多 agent 系统、AI 政策/伦理方向;想做社会模拟或生成式 agent 的人。
学习建议
先读 Generative Agents(Park et al., 2023)和经典 Schelling/NetLogo 模型。项目要注意可复现性和伦理边界。
相关课程
官方课程描述(英文原文)
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.