Michael Cohen
Affiliations
Postdoctoral Fellow, UC Berkeley
Biography
Michael Cohen works to design agents that we can expect to behave safely, no matter how instrumentally rational they are. His work has found that 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. His research mostly aims to find agent constructions that violate those assumptions, with some success.