Curious to learn more about AI Safety? Here are several resources to get you started.

AGISF Resources

The Artificial General Intelligence Safety Fundamentals (AGISF) website has several excellent resources, including:

• AGISF AI Alignment course (whose curriculum inspired our intro fellowship!)

• AGISF AI Alignment 201 course

• AGISF AI Governance course

• AGISF Opportunities Board

• AGISF Advice for working in technical AI Safety

• AGISF Resources

Newsletters

• AGISF Newsletter

• AI Safety Support Newsletter

• AI Alignment Newsletter by Rohin Shah

• ML Safety Newsletter by Dan Hendrycks

Advice

• How to pursue a career in technical AI Alignment

• Getting up to speed on AI Alignment Recommendations by Holden Karnofsky

• Advice for AI Alignment Researchers FAQ by Rohin Shah (DeepMind)

• Beneficial AI Research Career Advice by Adam Gleave (Fund for Alignment Research, Center for Human Compatible AI (UC Berkeley) PhD)

Other Links

• Many, many links

• A list of resources for early alignment researchers

• This database of papers

• AI alignment forum: A forum for experts in the field to post thoughts and research results involving technical and theoretical approaches to alignment

• LessWrong forum: this is similar to the AI alignment forum, and there's a lot of overlap, but LW focuses more on rationality and such

• This map of the field as a whole

• Fun map of the AI Safety world