Alignment Research Center
Non-profit research organisation working on theoretical alignment and on evaluations that test what frontier models are capable of, with public reports.
In plain terms: ARC is a non-profit research organization whose mission is to align future machine learning systems with human interests.
Visit Alignment Research CenterCoach's summary
Their evaluations work is why "dangerous capability testing" is now a normal phrase. Read the reports, they are short.
Key programs
Program details are still being written up. In the meantime, the site itself is the best starting point.
Similar organizations
Recommended next
Hand-picked from the hub based on what Alignment Research Center covers.
FAR.AI
Non-profit AI safety research lab publishing technical work on model robustness and evaluation, plus events and a fellowship pipeline for researchers entering the field.
Why this: Covers ai ethics and ai safety too
UC Berkeley Center for Human-Compatible AI (CHAI)
This university research center focuses on creating safe and beneficial artificial intelligence. You can read published research papers, follow recent news and blog updates, and explore opportunities to work with their team.
Why this: Covers ai ethics and ai safety too
Anca Dragan
Berkeley faculty page for Anca Dragan, robotics and human-AI interaction researcher who also leads AI safety and alignment work at Google DeepMind.
Why this: Covers ai ethics and ai safety too
Andrew Critch
Personal site of Andrew Critch, mathematician and AI safety researcher, collecting his papers, talks and writing on multi-agent risk and existential safety.
Why this: Covers ai ethics and ai safety too