My own collection of resources on Trustworthy and Safety AI. There are already many awesome collections out there, for example, Awesome Trustworthy Deep Learning, but this one is more personal and tailored to my research interests.

Courses

Stanford CS 329T: Trustworthy Machine Learning: Large Language Models and Applications

Some highlights:

  • Building & evaluating advanced RAGs with LlamaIndex + TruLens (Week 1)
  • Quarter long project ideas (Week 2, 3)
  • Grounding and Factuality (Week 4)
  • Agents (Week 5)

CS 194/294-267 Understanding Large Language Models: Foundations and Safety, UC Berkeley and related videos

Intro to ML Safety by Dan Hendrycks

AI Safety Fundamentals by Safe.AI

Alignment Course by BlueDot

Books

Software and Tools

Newsletters