CAMBRIA (Cambridge Bootcamp for Research in Interpretability and Alignment) is a 3-week ML upskilling bootcamp for AI safety, focusing on interpretability and RL, based on the ARENA curriculum and run by the Cambridge Boston Alignment Initiative.

Prerequisites are familiarity with Python and comfort with multivariable calculus (e.g., chain rule) and linear algebra (e.g., eigenvalues, SVD). For a more detailed list of helpful prior knowledge, see here.

CAMBRIA will take place in-person in Cambridge, Massachusetts, USA, from January 5-23, 2026. Participants are expected to attend every weekday from 9 AM to 5 PM.

Participants will receive:

• Housing and meals

• 24/7 use of office space in Harvard Square for the duration of the program

• Dedicated teaching assistants

• Travel support

Applications are currently closed. If you applied to the January 2026 cohort, you should receive a response by Monday, December 8.

To be notified about future CAMBRIA cohorts, please fill out the form below.

Email alex.semendinger@gmail.com with questions or comments.