Welcome to the Resources Page! Here, you’ll find my recommendations of selected collections of research papers, expert writings, tutorials, and more, which I find particularly helpful as I transition to a career in AI Safety. I’ll continue to update the page as I go, so feel free to check back for new additions.
learning materials
Rational Animations is a YouTube channel particularly focused on AI Safety and AI Alignment, that is, making sure present and future AI Systems are aligned with human values and don’t cause our extinction. Their video animations are amazing! Rational Animations
Robert Miles AI Safety,is the best AI Safety Research channel on Youtube. If you are starting out, you will find all the videos helpful.
For a walkthrough of research papers, I strongly recommend Neel Nanda
Communities to join
- Cohere For AI community is where I co-lead the Begginers in Research Driven Studies program. We have an AI Safety and alignment group where we read and implement research papers, learn different topics and meet to discuss and answer questions. We also invite speakers at the end of every sprint, usually we invite the authors of the paper or the book we were reading, I recommend joining.
Blog Posts
How we could stumble into AI catastrophe, by Holden Karnofsky
Research Papers
Open Problems and Fundamental Limitations of Reinforcement Learning from Human Feedback, by Stephen Casper and Xander Davies
Books
The Precipice, by Toby Ord.
The Alignment Problem, by Brian Christian.
Doing Good Better, by William Macaskill.