A student-led Cornell course focused on AI safety and alignment.
The course covers foundational model training pipelines, mechanistic interpretability, RLHF and goal misgeneralization, safety evaluations and red teaming, scalable oversight and control, and policy and career pathways in AI safety.
The format emphasizes hands-on notebooks, paper-driven discussion, and a final project to help students build both conceptual understanding and practical skills.
CAIA offers multiple ways for students to learn, connect, and contribute to AI safety research.
Each week, CAIA runs an open paper discussion section focused on frontier and recent work in AI safety.
Participants read the selected paper in advance, then discuss its methods, evidence, limitations, and implications together.
CAIA also hosts weekly community events, including workshops, tutorials, research salons, invited speaker talks, informal debates, and other opportunities to learn and connect.
Subscribe to our Luma event page for the latest meeting topics, times, and locations.
CAIA supports original student research in AI safety.
Students interested in technical or policy research can reach out to be connected with resources and a faculty or upperclassman mentor.
Reach out at cornellaialignment@gmail.com to get connected with resources and mentors.
In previous semesters, CAIA ran an 8-week introductory fellowship covering technical and policy topics in AI safety.
For Fall 2026, we are running CS 1998: Intro to AI Safety & Alignment in place of the fellowship. The course develops the same foundations through lectures, technical notebooks, paper discussions, and a final project.