CAMBRIA — Cambridge Boston Alignment Initiative
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.
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. Participant applications for the Summer 2026 CAMBRIA cohorts are now closed. TA applications for our August 10-28 cohort in Cambridge, MA…
saved by
related reading
- The Iliad Intensive Course Materials — LessWronglesswrong.com
- Fall 2026boazbk.github.io
- A woefully incomplete guide to technical upskillingjason.ml
- ARENA - AI Safety Curriculumlearn.arena.education
- How To Become A Mechanistic Interpretability Researcher — AI Alignment Forumalignmentforum.org
- MIT Deep Learning 6.S191introtodeeplearning.com
- Statistical Physics for Ambitious Interpretability: A Workshop Retrospective — LessWronglesswrong.com
- GitHub - jacobhilton/deep_learning_curriculum: Language model alignment-focused deep learning curriculumgithub.com
- Frontier AI Security Residencysecurefrontier.ai
- Fellowships — The Safety Apprenticesafetyapprentice.com
- M3 | Move into AI securitym3fellowship.com
- Want to upskill in technical AI safety? Here are 67 useful resources | 80,000 Hours80000hours.org