Artificial intelligence research is aimed at designing machines that are capable of intelligent behavior to successfully achieve objectives. But if these new machines and systems are more capable than humans — and intrinsically unpredictable by humans — it stands to reason that some could result in negative, perhaps irreversible outcomes for people.

The Center for Human-Compatible Artificial Intelligence (CHAI) is working to ensure that this eventuality cannot arise. CHAI’s goal is to develop the conceptual and technical expertise to reorient AI research toward provably beneficial systems. For details, read the latest CHAI Progress Report.