List of links for getting into AI safety

[zef]

This is a quick list I made when I was looking into material on getting into safety research. It’s not thorough and/​or carefully arranged, I had just put it together for myself and think it can be useful to people, although there are many ways it could be improved, which I sadly don’t have time for. Hope this is helpful!

Doing research in AI safety

• How to pursue a career in technical AI alignment

• FAQ Career Advice for Alignment researchers

• AI safety starter pack—EA Forum

• Beneficial AI Research Career Advice

• Advice on Pursuing Technical AI Safety Research

• AI safety technical courses, reading lists, and curriculums

• AI alignment resources | Victoria Krakovna

• AI Safety Support—Lots of Links

• awesome-ai-alignment: A curated list of awesome resources for getting-started-with and staying-in-touch-with Artificial Intelligence Alignment research.

• How To Get Into Independent Research On Alignment/​Agency

General research in AI tips

• How I became a machine learning practitioner

• How to Read Research Papers

• Want To Be An Expert? Build Deep Models

• Lessons Learned Reproducing a Deep Reinforcement Learning Paper

• An Opinionated Guide to ML Research

• A Survival Guide to a PhD

• Machine Learning PhD Applications — Everything You Need to Know — Tim Dettmers

• Film Study for Research—Jacob Steinhardt

• How to PhD

• How to succeed as an early-stage researcher: the “lean startup” approach

• Research Taste Exercises

• A Recipe for Training Neural Networks

Technical Safety content

• Concrete Problems in AI Safety

• Neel Nanda’s posts on Mechanistic Interpretability

• Without specific countermeasures, the easiest path to transformative AI likely leads to AI takeover

• My Overview of the AI Alignment Landscape: Full Sequence—Neel Nanda

• Reading List: Evan Hubinger’s AI Safety Worldview

• What are the coolest topics in AI safety, to a hopelessly pure mathematician? - EA Forum

• Risks from Learned Optimization—AI Alignment Forum

• Testing The Natural Abstraction Hypothesis: Project Intro—AI Alignment Forum

• Alignment research exercises—AI Alignment Forum

• Intro to ML Safety

• The Library—AI Alignment Forum

• Recommended Materials – Center for Human-Compatible Artificial Intelligence

• AGI Safety: Safety and Control Considerations for Artificial General Intelligence

• TAI Safety Bibliography

• Study Guide—John Wentworth

• Looking back on my alignment PhD