• Posts
  • RSS
  • ◂◂RSS
  • Contact

  • Conversation with Bryce Wiedenbeck

    July 14th, 2017
    airisk, giving  [html]
    A few days ago I spoke with Bryce Wiedenbeck, a CS professor at Swarthmore teaching AI, as part of my project of assessing superintelligence risk. Bryce had relatively similar views to Michael: AGI is possible, it could be a serious problem, but we can't productively work on it now.

    Before our conversation he looked some at Concrete Problems in AI Safety (pdf) and Deep Reinforcement Learning from Human Preferences (pdf). His view on both was that they were good work from the perspective of advancing ML but very unlikely to be relevant to making AGI safer: the systems that get us to AGI will look very different from the ones we have now.

    One reason is that he saw a lot of learning from humans as being mediated by learning utility functions, but he sees utility functions as a very limited model. Economists and others use utility functions when talking about people because that's mathematically tractable, but it's a bad description of how humans actually behave. Trying to come up with utility functions that best explain human preferences or behavior probably solves some problems nicely and is helpful, but while Bryce wouldn't completely rule it out he thought it was very unlikely to get us to AGI.

    We tried to get more into why he thinks implementations for AGI will look vastly different from what we will have today, and couldn't make progress there. Bryce thinks there are deep questions about what intelligence really is that we don't understand yet, and that as we make progress on those questions we'll develop very different sorts of ML systems. If something like today's deep learning is still a part of what we eventually end up with, it's more likely to be something that solves specific problems than as a critical component.

    (This has been a common theme in my discussions with people recently: very different intuitions on the distance to AGI in terms of technical work required, and also on whether work we're doing today is likely to transfer.)

    Comment via: google plus, facebook

    Recent posts on blogs I like:

    Collections: The Queen’s Latin or Who Were the Romans? Part IV: The Color of Purple

    This is the fourth part (I, II, III) of our series asking the question “Who were the Romans?” and contrasting the answer we get from the historical evidence with the pop-cultural image of the Romans as a culturally and ethnically homogeneous society typic…

    via A Collection of Unmitigated Pedantry July 23, 2021

    The Leakage Problem

    I’ve spent more than ten years talking about the cost of construction of physical infrastructure, starting with subways and then branching on to other things, most. And yet there’s a problem of comparable size when discussing infrastructure waste, which, …

    via Pedestrian Observations July 23, 2021

    Songs about terrible relationships

    [Spoilers for several old musicals.] TV Tropes lists dozens of examples of the “I want” song (where the hero of a musical sings about their dream of escaping their small surroundings). After watching a bunch of musicals on maternity leave, I’m wondering h…

    via The whole sky July 17, 2021

    more     (via openring)


  • Posts
  • RSS
  • ◂◂RSS
  • Contact