AI Safety and Alignment

October 13th–17th, 2025
Oxford

A 5-day intensive course on foundational concepts and frontier research in the field of AI safety and alignment.

Topics:

Course information

Lecturer: Fazl Barez.

Teaching assistants: Hunar Batra, Matthew Farrugia-Roberts, James Oldfield, and Marta Ziosi (Guest Speaker/Tutor).

Guest lecturers:

Schedule:

Prerequisites:

Syllabus

The alignment problem (Monday, October 13th):

Alignment methods and evaluation (Tuesday, October 14th):

Interpretability and monitoring (Wednesday, October 15th):

Sociotechnical aspects of AI alignment (Thursday, October 16th):

Guest speaker day (Friday, October 17th):

Assessment

To pass the module, AIMS students must:

The deadline for the report is Monday, October 20th, 23:59.