Alan's research focuses on governing AI agents. He is also interested in technical AI governance and societal resilience more broadly. He obtained his PhD from Mila (Quebec AI Institute).
Increasingly many AI systems can plan and execute interactions in open-ended environments, such as making phone calls or buying online goods. As developers grow the space of tasks that such AI agents can accomplish...
AI systems are increasingly pervasive, yet information needed to decide whether and how to engage with them may not exist or be accessible. A user may not be able to verify whether a system has certain safety certifications...
Increased delegation of commercial, scientific, governmental, and personal activities to AI agents—systems capable of pursuing complex goals with limited supervision—may...
AI agents could pose novel risks. Information about their activity in the real world could help us manage these risks.
A critical AI safety goal is understanding how new AI systems will behave in the real world. We can assess our understanding by trying to predict the results of model evaluations before running them.
