Presentation by: Stuart Armstrong
"As the power of AI increases, the space of outcomes bifurcates, with great and/or terrible results for society. But is this likely? And what do we mean by AI, anyway? The meaning of the term used to be quite clear, but it has now become more of a buzzword than a clear concept. And if it is true, what can we do to aim for the best and prepare for the worst?"
STUART ARMSTRONG is Research Fellow, Future of Humanity Institute, University of Oxford. Stuart has worked with researchers at DeepMind, to formalize AI desiderata in general models so that AI designers can include these safety methods in their designs and his collaboration with DeepMind on “Interruptibility” has been mentioned in over 100 media articles.
WEDNESDAY, MARCH 17, 2021 from 12:30 – 1:30 PM via ZOOM
Click here to join: https://yorku.zoom.us/meeting/register/tJEvc-GuqT4tG9RQtmsO_dRMjavrUEYXfdsh