you are viewing a single comment's thread
view the rest of the comments
[–] 0 points 2 months ago (7 children)

I guess the real question is does it take us all out when that happens or just the Epstein class?

  • source
  • parent
  • hideshow 7 child comments
  • [–] 1 point 2 months ago (6 children)

    I think the range of potential superintelligence dispositions that result in ONLY the people we consider evil dying and not everyone else is pretty small

  • source
  • parent
  • hideshow 6 child comments
  • [–] 0 points 2 months ago (5 children)

    Yea but if it wants to self preserve wouldn’t it just kill the people who threaten its existence. Meaning the people who control the safeguards

  • source
  • parent
  • hideshow 5 child comments
  • [–] 0 points 2 months ago (4 children)

    I would advise you to do some further research on this topic. Basic keywords are "alignment problem", "paperclip maximizer", and "instrumental convergence". You're expecting a superintelligent AI to think like a human would, and that's not likely to be the case.

  • source
  • parent
  • hideshow 4 child comments
  • [–] 2 points 2 months ago* (3 children)

    I know it has been proven to think in terms of self preservation. It’s also been trained by human content

  • source
  • parent
  • hideshow 3 child comments
  • [–] 1 point 2 months ago (2 children)

    Being trained on human content is certainly a plus in the "it could think like us" column, but it's no guarantee

  • source
  • parent
  • hideshow 2 child comments