His research focuses on AI security issues, how to apply existing tools from the field of cybersecurity to AI systems, and how to secure AI systems against misuse and adversarial operations. He is broadly interested in how to best secure and protect sociotechnical systems against misuse.
Before coming to Oxford, he worked as a journalist in Washington, D.C., where he wrote about a broad range of national security issues. He spent eight years with the magazine Foreign Policy as a writer and editor before leaving for the Brookings Institution, where he worked with the AI and Emerging Technologies Initiative. Most recently, he was the senior editor at CyberScoop, a trade publication covering cybersecurity.
He completed his undergraduate work at Harvard University, where he studied Social Studies and was the managing editor of the undergraduate newspaper, The Harvard Crimson.