World Model · podcast knowledge graph

94 | Stuart Russell on Making Artificial Intelligence Compatible with Humans

2020-04-27 · 87 min · episode 94 · 11 entities

Asserted relationships

  • 0.67 · ×2
    evidence rules-v5
    f Wadham College, Oxford. He is a co-founder of the Center for Human-Compatible Artificial Intelligence at UC Berkeley. He is the author of several books, including (with Peter Norvig
  • 0.62 · ×2
    evidence rules-v5
    motivations and purposes may be dramatically at odds with our own. In his book Human Compatible , Russell suggests that the secret is to give up on building our own goals into
  • → hosted by Sean Carroll person
    0.55 · ×4
    evidence rules-v4
    Feed author/publisher: Sean Carroll
  • → discusses Science concept
    0.40 · ×4
    evidence rules-v4
    Feed category: Science
  • → discusses Physics website
    0.40 · ×4
    evidence rules-v4
    Feed category: Physics

Entities found in this episode

books 4

  • 0.79 · ×2
    evidence rules-v5
    f Wadham College, Oxford. He is a co-founder of the Center for Human-Compatible Artificial Intelligence at UC Berkeley. He is the author of several books, including (with Peter Norvig
  • evidence rules-v5
    motivations and purposes may be dramatically at odds with our own. In his book Human Compatible , Russell suggests that the secret is to give up on building our own goals into
  • 0.67 · ×2
    evidence rules-v5
    f Wadham College, Oxford. He is a co-founder of the Center for Human-Compatible Artificial Intelligence at UC Berkeley. He is the author of several books, including (with Peter Norvig
  • evidence rules-v5
    motivations and purposes may be dramatically at odds with our own. In his book Human Compatible , Russell suggests that the secret is to give up on building our own goals into

concepts 3

persons 2

  • mentioned Sean Carroll person
    0.70 · ×4
    evidence rules-v4
    Feed author/publisher: Sean Carroll
  • hosted by Sean Carroll person
    0.55 · ×4
    evidence rules-v4
    Feed author/publisher: Sean Carroll

websites 2

  • mentioned Physics website
    0.50 · ×4
    evidence rules-v4
    Feed category: Physics
  • discusses Physics website
    0.40 · ×4
    evidence rules-v4
    Feed category: Physics
Episode description as stored
Artificial intelligence has made great strides of late, in areas as diverse as playing Go and recognizing pictures of dogs. We still seem to be a ways away from AI that is "intelligent" in the human sense, but it might not be too long before we have to start thinking seriously about the "motivations" and "purposes" of artificial agents. Stuart Russell is a longtime expert in AI, and he takes extremely seriously the worry that these motivations and purposes may be dramatically at odds with our own. In his book  Human Compatible , Russell suggests that the secret is to give up on building our own goals into computers, and rather programming them to figure out our goals by actually observing how humans behave. Support Mindscape on  Patreon . Stuart Russell received his Ph.D. in computer science from Stanford University. He is currently a Professor of Computer Science and the Smith-Zadeh Professor in Engineering at the University of California, Berkeley, as well as an Honorary Fellow of Wadham College, Oxford. He is a co-founder of the Center for Human-Compatible Artificial Intelligence at UC Berkeley. He is the author of several books, including (with Peter Norvig) the classic text  Artificial Intelligence: A Modern Approach . Among his numerous awards are the IJCAI Computers and Thought Award, the Blaise Pascal Chair in Paris, and the World Technology Award. His new book is  Human Compatible: Artificial Intelligence and the Problem of Control . Web page Google Scholar publications Wikipedia Talk on Provably Beneficial Artificial Intelligence Amazon author page