3 comments

  • JoshTriplett 40 minutes ago

    It's a wryly amusing thought, but in practice, it's not going to matter if writings about unaligned AI are present in the data set or not. In practice, instrumental convergence means that bad outcomes overlap with the natural subgoals of any sufficiently advanced system. https://en.wikipedia.org/wiki/Instrumental_convergence

    AI doesn't have to have a goal of causing a problem. AI doesn't have to have had a human enabler (beyond having been built). Nothing in particular is required in order to fail catastrophically; it's the default if you don't thread the very small needle.

  • roshanabdullah1 44 minutes ago

    It could be. who knows

  • aennassiri an hour ago

    AI doesn't need to want to take over. Give it autonomy; reading that it will is probably enough.