Training program that upskills software engineers to become alignment researchers.
Related Wiki Pages
Top Related Pages
Apart Research
An independent non-profit AI safety research and community-building organization that accelerates safety research through hackathons, fellowships, ...
Neel Nanda
Senior Research Scientist and Mechanistic Interpretability Team Lead at Google DeepMind; creator of TransformerLens; co-author of 'A Mathematical F...
AI Safety Training Programs
Fellowships, PhD programs, research mentorship, and career transition pathways for growing the AI safety research workforce, including MATS, Anthro...
AI Alignment
Technical approaches to ensuring AI systems pursue intended goals and remain aligned with human values throughout training and deployment. Current ...
Why Alignment Might Be Hard
AI alignment faces fundamental challenges: specification problems (value complexity, Goodhart's Law), inner alignment failures (mesa-optimization, ...