Loading…

Loading…

Loading…

Alumni About Join us

Loading…

Loading…

Loading…

Alumni About Join us

Sign in Start for free

AI Alignment

1. AI and the years ahead

Resources: AI and the years ahead1h 59min
Exercises: AI and the years ahead

2. What is AI alignment?

Resources: What is AI alignment?2h 10min
Exercises: What is AI alignment?

3. Reinforcement learning from human (or AI) feedback

Resources: Reinforcement learning from human (or AI) feedback2h 15min
Exercises: Reinforcement learning from human (or AI) feedback

4. Scalable oversight

Resources: Scalable oversight1h 40min
Exercises: Scalable oversight

5. Robustness unlearning and control

Resources: Robustness unlearning and control1h 31min
Exercises: Robustness unlearning and control

6. Mechanistic interpretability

Resources: Mechanistic interpretability1h 55min
Exercises: Mechanistic interpretability

7. Technical governance approaches

Resources: Technical governance approaches1h 19min
Exercises: Technical governance approaches

8. Contributing to AI safety

Resources: Contributing to AI safety1h 14min
Exercises: Contributing to AI safety

9. Rapidly testing your project

Resources: Rapidly testing your project10min
Exercises: Rapidly testing your project

10. Developing your project

Resources: Developing your project25min
Exercises: Developing your project

11. Further developing your project

Resources: Further developing your project13min
Exercises: Further developing your project

12. Building in public

Resources: Building in public6min
Exercises: Building in public
Next steps: Programs

Courses
AI Alignment
12. Building in public

Unit 12: Building in public

Exercises: Building in public

Exercises

Loading…

Analytics cookies help us improve our website and measure ad performance. Privacy Policy.