Daniel Dewey
Contact me: Twitter, EmailI do work of a variety of kinds focused on potential risks from advanced AI; currently, I'm a program officer for the Open Philanthropy Project. I was previously a research fellow at the Future of Humanity Institute and Oxford Martin School, a software engineer at Google Seattle, and a student researcher at Intel Labs Pittsburgh during my undergraduate at Carnegie Mellon University. I live in Portland, OR, with a beautiful tattooist / writer / comics artist.
I subscribe to effective altruism (see also this excellent post), and I've taken the Giving What We Can Pledge. I think the long-term future is overwhelmingly important, but I also think it's valuable to compromise and cooperate with people who disagree with this view; there's a lot we need to do, and we can do much more together!
If you want to work on AI safety, I recommend getting a PhD in machine learning -- if I were starting over, that's what I would do.
Some reading on AI safety:
- Superintelligence, Bostrom. 2014.
- Concrete Problems in AI Safety. Amodei, Olah, Steinhardt, Christiano, Schulman, and Mané. 2016.
- Approval-Directed Agents. Christiano. 2014.
My writing on potential risks from advanced AI:
- Three Areas of Research on the Superintelligence Control Problem.
- Research priorities for robust and beneficial artificial intelligence. S. Russell, D. Dewey, M. Tegmark. In AI Magazine, 2015.
- Long-term strategies for ending existential risk from fast takeoff. In Risks of Artificial Intelligence, V. Müller (ed.), 2015.
- Reinforcement learning and the reward engineering principle. AAAI Spring Symposium Series, 2014.
- A representation theorem for decisions about causal models. In proceedings of the Fifth Conference on Artificial General Intelligence, 2012.
- Learning what to value. In proceedings of the Fourth Conference on Artificial General Intelligence, 2011.
Other papers of mine:
- Additively efficient universal computers. ECCC TR14-044, 2014.
- Crucial phenomena. In How Should Humanity Steer the Future?, A. Aguirre, B. Foster, and Z. Merali (eds.), 2015.
- Generalizing metamodules to simplify planning in modular robotic systems. D. Dewey, M. Ashley-Rollman, M. De Rosa, S. Goldstein, T. Mowry, S. Srinivasa, P. Pillai, and J. Campbell. In proceedings of the International Conference on Intelligent Robots and Systems, 2008.