Course curriculum

    1. You're in!

    2. Advice on engaging with our content

    3. 3 options for a personalised AI advisor

    4. Your first reflection sheet!

    5. Summing up and further exploration

    1. Welcome to Week 1

    2. Why AI might be the next industrial revolution

    3. Visualising the deep learning revolution

    4. The key levers of AI progress

    5. AI risks aren't (just) science fiction

    6. Bias and ethics in current AI systems

    7. Deep fake dangers

    8. What do pioneers in AI think about all this?

    9. Summing up and further exploration

    10. Connor Axiotes talk and Q&A

    1. Welcome to Week 2

    2. Specification Gaming: How AI Can Turn Your Wishes Against You

    3. Why Would AI Want to do Bad Things? Instrumental Convergence

    4. Future promise and perils, from utopia to dystopia

    5. Longtermism

    6. The Future!

    7. Could AI wipe out humanity?

    8. Can’t we just unplug dangerous AI? (and other questions)

    9. Summing Up and Further Exploration

    10. Jack Parker talk & Q&A

    1. Welcome to Week 3

    2. Technical solutions overview

    3. Aligning AI - RLHF

    4. Is RLHF perfect? - Scalable Oversight

    5. Assessing the Situation - Evals

    6. Diving into the black box: Interpreting AI

    7. So we're on the right track?

    8. What can you do to help? - Misalignment

    9. Summing up and further exploration

    10. Jai Patel talk & Q&A

    11. Michael Aird talk and Q&A

    1. Welcome to Week 4

    2. Racing through a minefield: the AI deployment problem

    3. Filling the void: Introducing (inter)national AI rules and regulations

    4. Surprising trends

    5. Avoiding Extreme Global Vulnerability as a Core AI Governance Problem

    6. Open Source

    7. Pause For Thought: The AI Pause Debate

    8. What can you do to help? - Misuse and Unintended Consequences

    9. Summing up and further explorations

    10. Noah Siegel talk and Q&A

    11. Yi-Ling Liu talk and Q&A

    1. Welcome to Week 5

    2. Figuring out how impactful AI Safety is

    3. One way to make a real personal impact on this problem

    4. Setting yourself up for careers fixing AI risks

    5. Degrees that can set you up to tackle AI risks

    6. Deadline updates - Your next steps on the path to impact

    7. Support Leaf?

    8. Summing up and further exploration

    9. Jason Hausenloy talk and Q&A

    10. Holly Elmore talk and Q&A

About this course

  • Free
  • 57 lessons
  • 7.5 hours of video content

Discover your potential, starting today