The Alignment Research Center (ARC) is a non-profit research organization whose mission is to align future machine learning systems with human interests. Our current work consists of two projects:
The Evaluations team (now spinning off as METR) is building capabilities evaluations of frontier machine learning models. Learn more at metr.org
The Theory team is developing an alignment strategy that could be adopted in industry today while scaling gracefully to future ML systems. Learn more at alignment.org/theory