CAMBRIA

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.

What we provide

 

Housing and meals

24/7 office access in Harvard Square

Dedicated teaching assistants

Travel support

 

Applications are currently closed.

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

Email alex@cbai.ai with questions or comments.

Testimonials