The Control Problem: Unsolved or Unsolvable? — LessWrong
www.lesswrong.com
td;lr  No control method exists to safely contain the global feedback effects of self-sufficient learning machinery. What if this control problem tur…
  • gerikson@awful.systemsEnglish
    2·
    1 year ago

    I didn’t read this but I confident it can be summarized as “how many hostile AGIs can we confine to the head of a pin?”