Research Lab The Normativity Lab

How can we ensure AI systems and agents align with human values and norms? How can we guarantee that AI systems maintain and enhance the complex cooperative economic, political and social systems humans have built? The Normativity Lab, led by Gillian Hadfield, investigates these questions by studying the foundations of human normative systems and applying these insights to AI design.

Gillian Hadfield

Gillian Hadfield

Bloomberg Distinguished Professor of AI Alignment and Governance

Gillian K. Hadfield is the Bloomberg Distinguished Professor of AI Alignment and Governance at School of Government and Policy and Department of Computer Science at Johns Hopkins University.

Research Interests: Computational models of human normative systems; Legal, regulatory, and technical systems for AI; Human and AI normative alignment; Multi-Agent RL systems

Lab Members

Research Scientists & Postdoctoral Fellows

Harsh Satija

Harsh Satija

Vector Distinguished Postdoctoral Fellow

Harsh Satija is a postdoctoral researcher at the Vector Institute. He obtained his PhD from McGill University.

Shuhui Zhu

Konstantinos Mitsopoulos

Associate Research Scientist

Konstantinos Mitsopoulos is an associate research scientist at Johns Hopkins University. They hold a PhD in Computational Cognitive Science from Birkbeck, University of London, an MSc in Machine Learning from University College London, and a BSc in Physics from the University of Athens.

Matthew Renze

Maria Ryskina (she/they)

CIFAR AI Safety Postdoctoral Fellow

Maria Ryskina is a CIFAR AI Safety Postdoctoral Fellow at the Vector Institute. She holds a PhD in Language and Information Technologies from Carnegie Mellon University, an MSc in Information Technology from Skolkovo Institute of Science and Technology, and BSc & MSc in Applied Mathematics and Physics from Moscow Institute of Physics and Technology. Their research bridges natural language processing and AI safety.