I'm a postdoc with Stuart Russell at UC Berkeley. My research considers the expected behavior of generally intelligent artificial agents. I am interested in designing agents that we can expect to behave safely, no matter how instrumentally rational they are.
My perspective on the extinction risk posed by AI can be found in my published work on the topic—subject to several assumptions, advanced algorithms that explicitly plan over the long term using a learned model of the world would likely intervene in the provision of certain observations, and outcompete us for resources in an attempt to do so securely. My research mostly aims to find violations of those assumptions, with some success.
Some things I like especially: my wife and baby boy, my friends, Italy, board games, sailing, and the guitar.