Theoretical computer scientist by training, now working on empirical deep learning research. Optimizing for a post-AGI future where humanity flourishes.
I co-lead the Alignment Science team at Anthropic. Previously, I co-led the Superalignment Team at OpenAI and worked at DeepMind and the University of Oxford. My PhD was on a mathematical model for artificial general intelligence. I’ve been thinking about alignment for about 10 years. You can read more about my research on my homepage.
This blog represents my own musings, and does not represent the views or policies of my employer.
Twitter: @janleike
