Winter Machine Learning Bootcamp

MAIA hosted a two-week ML bootcamp in partnership with the Harvard AI Safety Team and the Cambridge Boston Alignment Initiative in January 2023. We think bootcamps like this are one of the best ways to quickly get up to speed in deep learning and develop skills useful for conducting AI safety research.

The bootcamp was in-person, with teaching assistants experienced with ML and AI safety research. We followed a modified version of the highly-rated MLAB (Machine Learning for Alignment) curriculum designed by Redwood Research, which provides a thorough, hands-on introduction to state-of-the-art ML techniques (e.g. transformers, deep RL, mechanistic interpretability) and is meant to get you to the level of replicating ML papers in PyTorch. The program’s only prerequisites were comfort with Python and introductory linear algebra.

Participants celebrating the program at our final social.