You're in!
Advice on engaging with our content
3 options for a personalised AI advisor
Your first reflection sheet!
Getting the ball rolling!
Introductions
Requirements for completion
Welcome to Week 1
Why AI might be the next industrial revolution
Visualising the deep learning revolution
The key levers of AI progress
AI risks aren't (just) science fiction
Bias and ethics in current AI systems
Deep fake dangers
What do pioneers in AI think about all this?
Connor Axiotes talk and Q&A
Summing up and further exploration
Welcome to Week 2
Specification Gaming: How AI Can Turn Your Wishes Against You
Why Would AI Want to do Bad Things? Instrumental Convergence
Future promise and perils, from utopia to dystopia
Longtermism
The Future!
Could AI wipe out humanity?
Can’t we just unplug dangerous AI? (and other questions)
Summing Up and Further Exploration
Jack Parker talk & Q&A
Welcome to Week 3
Technical solutions overview
Aligning AI - RLHF
Is RLHF perfect? - Scalable Oversight
Assessing the Situation - Evals
Diving into the black box: Interpreting AI
So we're on the right track?
What can you do to help? - Misalignment
Summing up and further exploration
Jai Patel talk & Q&A
Michael Aird talk and Q&A
Welcome to Week 4
Racing through a minefield: the AI deployment problem
Filling the void: Introducing (inter)national AI rules and regulations
Surprising trends
Avoiding Extreme Global Vulnerability as a Core AI Governance Problem
Open Source
Pause For Thought: The AI Pause Debate
What can you do to help? - Misuse and Unintended Consequences
Summing up and further explorations
Noah Siegel talk and Q&A
Yi-Ling Liu talk and Q&A
Welcome to Week 5
Figuring out how impactful AI Safety is
One way to make a real personal impact on this problem
Setting yourself up for careers fixing AI risks
Degrees that can set you up to tackle AI risks
How can we support your path to impact?
Summing up and further exploration
Support Leaf?
Jason Hausenloy talk and Q&A
Holly Elmore talk and Q&A
