flâneur

Rohin Shah — Lynette Bye

lynettebye.com · 12,234 words · saved by 1 readers

Rohin Shah is a Research Scientist at DeepMind studying methods that allow us to build AI systems that pursue the objectives their users intend them to pursue, rather than the objectives that were literally specified. Rohin completed his PhD at the Center for Human-Compatible AI at UC Berkeley and publishes the Alignment Newsletter to summarize work relevant to AI alignment. In this interview, Rohin and I discuss his advice for careers in AI safety, as well as his productivity style, experience with research, and personal career path. Note: This interview is from 2020 and some parts may no longer accurately represent the guest's views. The transcript has been edited for clarity and readability. —————————————————————————————— Lynette: Context for the interview today, I'm trying to do interviews with a number of people in different levels in their career to basically put together collections of tips for people who would like to go on these career paths, how did you get where you are, how

This interview is part of the “A Peek behind the Curtain” interview series. Rohin Shah is a Research Scientist at DeepMind studying methods that allow us to build AI systems that pursue the objectives their users intend them to pursue, rather than the objectives that were literally specified. Rohin completed his PhD at the Center for Human-Compatible AI at UC Berkeley and publishes the Alignment Newsletter to summarize work relevant to AI alignment. In this interview, Rohin and I discuss his advice for careers in AI safety, as well as his productivity style, experience with research, and perso

related reading