Resources: Mechanistic interpretability

Exercises: Mechanistic interpretability

Resources: Rapidly testing your project

Exercises: Rapidly testing your project

Resources: Building in public

Exercises: Building in public

Resources: Developing your project

Exercises: Developing your project

Resources: Technical governance approaches

Exercises: Technical governance approaches

Resources: AI and the years ahead

Exercises: AI and the years ahead

Resources: Contributing to AI safety

Exercises: Contributing to AI safety

Resources: What is AI alignment?

Exercises: What is AI alignment?

Resources: Further developing your project

Exercises: Further developing your project

Resources: Scalable oversight

Exercises: Scalable oversight

Resources: Robustness unlearning and control

Exercises: Robustness unlearning and control

Resources: Reinforcement learning from human (or AI) feedback

Exercises: Reinforcement learning from human (or AI) feedback

**This course has been replaced by our new [Technical AI Safety course](https://bluedot.org/courses/technical-ai-safety).**

Put your ideas on paper and share them with the world

You should now focus on producing on a publicly shareable output (if you haven't already been doing this). This could be a blog post, video explainer, interactive demonstration, documented GitHub repository or whatever else would be a great way to share your work. In the facilitated group discussion, you'll get feedback on it from your group.


Write an update on how your project is going, where you'd like support from your cohort, and what your plan is for the next week. Include a link to any draft write-up you've done so far.


Project update 3

AI Alignment

Put your ideas on paper and share them with the world

Building in public

How and why might we build future AI systems?

AI and the years ahead

What do we need to do to ensure AI systems do what we want, and why is this difficult?

What is AI alignment?

Why do AI systems today mostly do what we want?

Reinforcement learning from human (or AI) feedback

How might we scale human feedback for more powerful and complex models?

Scalable oversight

Can we prevent oversight methods from being gamed?

Robustness unlearning and control

How might we understand what’s going on inside an AI model?

Mechanistic interpretability

How might we measure and mitigate the risks of deploying AI models?

AI Alignment

Exercises: Building in public

Exercises

Congratulations on completing AI Alignment!