Stanford Root

Schedule

Stanford Root

Schedule

CS 120

Introduction to AI Safety

UNITS:3
GRADING:Letter (ABCD/NP)
LEVEL:Undergrad
GER:—

What makes an AI system "safe" and how do we decide? CS 120 explores this question, focusing on both measurement theoretic and institutional challenges of understanding, interpreting, and governing AI capabilities. We distinguish between AI-specific and systemic safety issues, from examining sycophancy and security implications to the challenge of measuring capabilities and risk. This class will look at current solutions and their limitations through CS publications, and will connect the institutions behind AI, how evaluation is defined and audited, and how those factors shape the future risks we might face. Topics will span data work, foundation models, and governance, focusing on threat-models, evaluation, and auditability. This course aims to prepare you to critically assess and contribute to safe AI development, equipping you with knowledge of cutting-edge research and ongoing debates in the field. This course has no official requirements, although we recommend some knowledge about machine learning and statistics, and will include readings, quizzes, and a final project. For more details, see also the course website: https://stanford-cs120.github.io/fall2026/

Syllabus for selected term:
View Autumn 2026 Syllabus

Sections

2 Terms
Lecture 1Open
ID: 2156
0 / 70 enrolled
DAYS:Tuesday, Thursday
TIME:11:30 AM – 12:50 PM
LOCATION:Hewlett Teaching Center 102
3units

CS 120: Introduction to AI Safety

3 units · Letter (ABCD/NP)

What makes an AI system "safe" and how do we decide? CS120 explores this question, focusing on both measurement theoretic and institutional challenges of understanding, interpreting, and governing AI capabilities. We distinguish between AI-specific and systemic safety issues, from examining sycophancy and security implications to the challenge of measuring capabilities and risk. This class will look at current solutions and their limitations through CS publications, and will connect the institutions behind AI, how evaluation is defined and audited, and how those factors shape the future risks we might face. Topics will span data work, foundation models, and governance, focusing on threat-models, evaluation, and auditability. This course aims to prepare you to critically assess and contribute to safe AI development, equipping you with knowledge of cutting-edge research and ongoing debates in the field. This course has no official requirements, although we recommend some knowledge about machine learning and statistics, and will include readings, quizzes, and a final project. For more details, see also the course website: https://stanford-cs120.github.io/fall2026/

Offered in Autumn 2026, Spring 2027 at Stanford University.

Autumn 2026 sections

  • Lecture — Tuesday Thursday 11:30 AM – 12:50 PM — Hewlett Teaching Center 102 (Undergrad)

Spring 2027 sections

  • Lecture — TBA TBA (Undergrad)

More CS courses

  • CS 109ACE: Problem-solving Lab for CS109
  • CS 110: Principles of Computer Systems
  • CS 111: Operating Systems Principles
  • CS 111ACE: Problem Solving Lab for CS111
  • CS 112: Operating systems kernel implementation project
  • CS 114: Selected Reading of Computer Science Research
  • CS 121: Equity and Governance for Artificial Intelligence
  • CS 123: A Hands-On Introduction to Building AI-Enabled Robots
  • CS 124: From Languages to Information (LINGUIST 180, LINGUIST 280)
  • CS 125: Data: Algorithms, Tools, Policy, and Society (POLISCI 156)
  • CS 129: Applied Machine Learning
  • CS 131: Computer Vision: Foundations and Applications

All CS courses · All departments