AI Safety: A Short FAQ for Mathematicians
alkjash.github.io · 2,031 words · saved by 3 readers
A short introduction to AI safety research and ways for mathematicians to get involved.
Xiaoyu He This is a follow-up to my essay about existential risk, in which I made the case that AI presents a substantial existential risk to humanity. The primary goals of this post are to suggest that: AI safety research is deep, broad, and mathematically interesting. It is possible to transition smoothly to alignment work as an academic mathematician without necessarily leaving your career. 1AI safety is just one problem. Even if it’s the biggest problem in the world, is it really productive to have many people work on it? AI safety is not one problem in the same way that the Riemann…
saved by
related reading
- Existential Risk from AI: An Exposition for Mathematiciansalkjash.github.io
- Ten AI safety projects I'd like people to work onthirdthing.ai
- “Alignment Engineering” vs. “Misalignment Science”lesswrong.com
- A Severe Misalignment of AI in Mathematicsterrytao.wordpress.com
- Ten AI safety projects I'd like people to work on — LessWronglesswrong.com
- Readings on the nature of alignment researchcasparoesterheld.com
- AI Safety for Mathematiciansmathforaisafety.org
- Declaration — Math and AImathandai.org
- A New Consciousness of Mathematicsapoorvapanidapu.substack.com
- Recommendations for Technical AI Safety Research Directionsalignment.anthropic.com
- The Artificiality of Alignmentjoinreboot.org
- Can we safely automate alignment research? - Joe Carlsmithjoecarlsmith.com