• Posts
  • RSS
  • ◂◂RSS
  • Contact

  • Superintelligence Risk Project

    July 3rd, 2017
    airisk, giving  [html]
    I've decided to make a larger project out of looking into AI risk. I don't think we really know why there's such a disconnect between people who think we should strongly prioritize it and the mainstream ML perspective that it's not useful to work on (at least not currently). I've applied for an EA grant, and am thinking I'll spend about a month on this.

    Here's where I currently am:

    • I've read nearly all of the reading people suggested (by number of words) or about two thirds of it (by individual pieces). This is mostly an effect of Superintelligence being very long.

    • I've had conversations with one person in each camp, have a few more scheduled, and am working on lining up more.

    Here are some very preliminary thoughts on where I think the disagreement might be:

    • How likely is it that current approaches are all we need for AGI, with relatively straightforward extensions and a lot of scaling?

    • How valuable is it to work on solving problems that are probably not the right ones? For example, even if we think AGI will not look like current systems, might trying to solve the control problem for current systems teach us enough about the underlying problem and how to do this kind of work that we'll be in a better position once we see more what AGI will actually look like?

    • How useful is it to have a strong theoretical foundation, vs just understanding the technology enough from an engineering perspective that we can make it do things for us?

    • How similar is this to normal engineering? How much should we expect companies' desires that their AI systems do what they want them to do to work out?

    • As we get closer to AGI, how likely is the ML community to take superintelligence risk seriously? Is it just that they don't think it can be productively worked on now or do they not think it will ever be a real problem?

    Comment via: google plus, facebook

    Recent posts on blogs I like:

    Not Everything is Like Rail Transport

    Sometimes, when I write about cost comparisons or public-sector incompetence, I see people make analogies to other fields. and sometimes these analogies are really strained. So I want to make this clear that I am talking about things that are specific to …

    via Pedestrian Observations April 30, 2021

    Collections: Teaching Paradox, Europa Universalis IV, Part I: State of Play

    This is the first post in a series that will be examining the historical assumptions of Paradox Interactive’s grand strategy computer game set in the early modern period, Europa Universalis IV. And this series will in turn be part of a larger series looki…

    via A Collection of Unmitigated Pedantry April 30, 2021

    Books and websites on babies

    Several people I know are expecting a first baby soon, and I wrote up notes for one of them. Might as well share here too: Medical:Scott Alexander’s Biodeterminist’s Guide to Parenting is an interesting read, and some parts are actionable.  If you live in…

    via The whole sky April 14, 2021

    more     (via openring)


  • Posts
  • RSS
  • ◂◂RSS
  • Contact