The central repository of AI Safety research. Distilled into clear, interconnected and actionable knowledge.
We transform scattered AI Safety research into clear, systematic knowledge. Each explanation saves researchers hours previously spent piecing together understanding.
Progressive Learning
Clear learning paths from fundamentals to advanced topics, for every skill level.
Complex research distilled into clear, interconnected explanations.
Learn through text, video, interactive exercises, and discussion guides.
Used by leading AI Safety programs with strong repeat adoption.
Open-source content improved by researchers and educators worldwide.
Save research hours with well-structured explanations.
ML4Good, AI Safety Collab, and other dedicated AI Safety initiatives have integrated our materials into their core curriculum, with strong repeat adoption across multiple cohorts.
Academic institutions like ENS and UBC are incorporating our materials into formal curricula, teaching AI Safety to computer science and machine learning students.
Study groups and individual researchers use our materials to understand core AI Safety concepts and contribute to the field.
"For a systematic, centralized, and concise introduction to the core topics in AI safety, this is the best and most up-to-date resource I know."AI Safety Lead, UBC Vancouver
"Your explanations of goal misgeneralization and deceptive alignment really helped me understand these concepts."ML Researcher
"The systematic approach makes it remarkably easier to integrate into existing curricula."Course Organizer, ML4Good
"I found it to be super insightful. Learned tons of new things."ML4G Germany
"The textbooks keep a clear line of thought and structure."ML4G France
"The material and content are great, can't wait to read more."Independent Student