• 0 Posts
  • 23 Comments
Joined 2 years ago
cake
Cake day: July 28th, 2023

help-circle


















  • While you are correct that there likely is no intention and certainly no self-awareness behind the scheming, the researchers even explicitly list the option that the AI is roleplaying as an evil AI, simply based on its training data, when discussing the limitations of their research, it still seems a bit concerning. The research shows that given a misalignment between the initial prompt and subsequent data modern LLMs can and will ‘scheme’ to ensure their given long-term goal. It is no sapient thing, but a dumb machine with the capability to decive its users, and externalise this as shown in its chain of thought, when there are goal misalignments seems dangerous enough. Not at the current state of the art but potentially in a decade or two.


  • lenuup@reddthat.comtoScience Memes@mander.xyzbitey
    link
    fedilink
    English
    arrow-up
    6
    ·
    8 months ago

    And we have better night vision than most the animals that have better day-vision than us. Humans are like the Leatherman of animals. Universally capable of doing most things but not as good as something specialized for that task. Plus of course capable of coming up with ways to cheat