AI Alignment

AI and the years ahead

Unit 1

What is AI alignment?

Unit 2

Reinforcement learning from human (or AI) feedback

Unit 3

Scalable oversight

Unit 4

Robustness unlearning and control

Unit 5

Mechanistic interpretability

Unit 6

Technical governance approaches

Unit 7

Contributing to AI safety

Unit 8

Rapidly testing your project

Unit 9

Developing your project

Unit 10

Further developing your project

Unit 11

Building in public

Unit 12