NLIliad Intensive
IliadUK
Global catastrophic risksAI safetyResearchSoftware engineering
Why this is on the board
Research into how to keep powerful AI systems safe and predictable (AI safety) is a young field, and only a few people are working on its basic mathematical questions. Four weeks of teaching won't produce research in themselves, but those who stay in the field afterwards help build theory that many others will later build on.
This board is in beta and this is our judgement. If you think we have it wrong, tell us. Give feedback · How we reason about it
About the role
A four-week intensive course on foundational AI alignment research for mathematically mature researchers in math, physics, or computer science. - Learn deep learning theory, agent foundations, interpretability, and safety guarantees through five curriculum clusters. - Complete five days per week, 10am–6pm, with occasional hands-on coding exercises and lectures. - Requires strong mathematical background; PhD not required but graduate-level math, physics, or theoretical CS experience essential.…
Want to understand this first?
Start with our free course: about 100 minutes in six short units, at your own pace, with no sign-up. To go further, apply for the EA Fellowship: five weeks of reading and discussion in a small group. Also free, but selective.