AI Alignment
How do we ensure advanced AI systems act in line with human intentions?
Curriculum
AI and the years ahead
Unit 1View unitWhat is AI alignment?
Unit 2View unitReinforcement learning from human (or AI) feedback
Unit 3View unitScalable oversight
Unit 4View unitRobustness unlearning and control
Unit 5View unitMechanistic interpretability
Unit 6View unitTechnical governance approaches
Unit 7View unitContributing to AI safety
Unit 8View unitRapidly testing your project
Unit 9View unitDeveloping your project
Unit 10View unitFurther developing your project
Unit 11View unitBuilding in public
Unit 12View unit
Newsletter
Subscribe to get AI safety news and course updates delivered directly to your inbox
