kingmaker

• kingmakerMar 30, 2015, 7:31 PM

  8 points

  on: The Hard­core AI Box Experiment

  This co-opts Bostrom’s Simulation argument, but a possible solution to the fermi paradox is that we are all AI’s in the box, and the simulators have produced billions of humans in order to find the most friendly human to release from the box. Moral of the story, be good and become a god

• kingmakerMar 30, 2015, 4:46 PM

  −1 points

  on: What have we learned from mee­tups?

  Seeing as I’m new here, absolutely nothing

• kingmakerMar 30, 2015, 4:40 PM

  5 points

  in reply to: SeekingEternity’s comment on: Box­ing an AI?

  It may simply deduce that it is likely to be in a box, in the same way that Nick Bostrom deduced we are likely to be in a simulation. Along these lines, it’s amusing to think that we might be the AI in the box, and some lesser intelligence is testing to see if we’re friendly

• kingmakerMar 30, 2015, 4:32 PM

  3 points

  in reply to: dxu’s comment on: Box­ing an AI?

  The problem with this is that even if you can determine with certainty that an AI is friendly, there is no certainty that it will stay that way. There could be a series of errors as it goes about daily life, each acting as a mutation, serving to evolve the “Friendly” AI into a less friendly one