Here, you can find the syllabus we’ll use throughout the AIxBiorisk fellowship. It contains all the papers we’ll read together, as well as a statement of each week’s goal.

Week 1: Intro to AIxBiorisk - What and why?

Goal: Give fellows a map of the problem: what kinds of AI tools matter, what kinds of bio risk matter, why should we care, and how to discuss these topics responsibly and productively.

Readings:

• How worried should we be about AI biorisk? - by Celia Ford
• A beginner's introduction to AI-driven biorisk: Large Language Models, Biological Design Tools, Information Hazards, and Biosecurity — EA Forum
• What are information hazards? — EA Forum
• Reasons to be pessimistic (and optimistic) on the future of biosecurity
• How AI could enable catastrophic pandemics

Week 2: Intro to AI safety in general

Goal: Introduce the core AI safety worldview without requiring CS background: why people worry about advanced AI, what alignment/control means, and how this connects to evaluations and governance.

Readings:

• Dario Amodei — The Adolescence of Technology
• Towards end-to-end automation of AI research
  • AI isn’t ready to research itself (Nature news article that talk about the paper)
• Managing extreme AI risks amid rapid progress
• General readings from other two tracks as well

Week 3: Biosecurity foundations and catastrophic biorisk

Goal: Introduction to more traditional biosecurity, what is catastrophic biorisk, and what is currently being done about it?

Readings:

• Preventing Global Catastrophic Biological Risks (excerpts)