As an emerging field, there are many definitions of the field AI Alignment. Broadly AI Alignment is a research field aimed at tackling the questions “how do we ensure the development of advanced artificial intelligence benefits humanity? and how do we avoid catastrophic failures while building advanced AI systems?”
Starter resources
- Short Article: The case for taking AI seriously as a threat to humanity by Kelsey Piper, Vox
- Article: Preventing an AI-related catastrophe by Ben Hilton, 80,0000 Hours
- Video: Intro to AI Safety by Rob Miles
- Report: Benefits & Risks of Artificial Intelligence by Ariel Conn, Future of Life Institute
- Syllabus: AGI Safety Fundamentals Curriculum by Richard Ngo, OpenAI
- More: Lots of Links from AI Safety Support
