ARENA

We aim to provide talented individuals with an environment for upskilling in ML engineering, for the purpose of contributing directly to AI alignment in technical roles. The curriculum draws heavily from Redwood Research’s Machine Learning for Alignment Bootcamp. It also has overlap with other material, most notably Neel Nanda’s excellent open source material on mechanistic interpretability of transformers. In person and online programs will be supplemented by reading groups and more theoretical discussion, and we strongly encourage you to continue to explore alignment reading if you self-study the material. The curriculum is organised into four core chapters, each one of which will require about a week of study. See here for a map of dependencies between different sections of the course.