Nate Soares
"Why ain't you rich?: why our current understanding of 'rational choice' isn't good enough for superintelligence"
Fowler Hall: 3 - 3:45 PM
The fate of humanity could one day depend upon the choices of a superintelligent AI. Philosophers have long attempted to define what it means to make rational decisions, but in the context of machine intelligence, these theories turn out to have undesirable consequences. Can we find a formal theory of 'rationality' that we would want a superintelligence to use?
Bio: Nate Soares is a research fellow at the Machine Intelligence Research Institute. He works on foundational problems relevant to the creation of general intelligence, including decision theory, goal stability, corrigibility, and value loading.