My name is Sam Toyer. I'm a final-year AI PhD student in the EECS department at UC Berkeley, advised by Stuart Russell. I completed my undergrad at the Australian National University. In the past I've worked in computer vision, planning, imitation learning, and reward learning. More recently, I've been researching how to make large language models safer and more robust, which are essential properties for high-stakes applications of these models. You can learn more about my work here, or reach me at email@example.com.