Iliad Intensive Curriculum
iliad-team.github.io · 701 words · saved by 1 readers
April 2026 cohort — AI Safety theory of deep learning, agency, alignment.
Foundations 0Prerequisites The prerequisites for the Iliad Intensive program. A — Alignment A.1AI Alignment Introduction A conceptual introduction to AI alignment: choosing an alignment target, ensuring trained systems actually pursue it, added challenges with goal-directedness, and views on risks and their mitigations. A.2Alignment in Practice What do labs do to make their models aligned in practice? Covers the different stages in the training pipeline, deployment and methods labs use to stress-test the result to see if the alignment holds. A.4Reward Learning Theory RLHF grades a…
saved by
related reading
- Iliad Intensive Curriculumiliad-intensive.org
- The Iliad Intensive Course Materials — LessWronglesswrong.com
- SLT for AI Safety — LessWronglesswrong.com
- SLT for AI Safety – Jesse Hooglandjessehoogland.com
- Alignment remains a hard, unsolved problem — LessWronglesswrong.com
- Timaeus | Learn about SLTtimaeus.co
- Why AI alignment could be hard with modern deep learningcold-takes.com
- A Pragmatic Vision for Interpretability — AI Alignment Forumalignmentforum.org
- ARENA - AI Safety Curriculumlearn.arena.education
- [2604.21691] There Will Be a Scientific Theory of Deep Learningarxiv.org
- Many arguments for AI x-risk are wrong — AI Alignment Forumalignmentforum.org
- Shallow review of technical AI safety, 2024 — LessWronglesswrong.com