• 0 Posts
  • 23 Comments
Joined 3 years ago
cake
Cake day: July 28th, 2023

help-circle



  • Other way around. If your fantasy / sci-fi novel does not sell well, rebrand it as a new groundbreaking “history”. Include how it gets ridiculed by main stream science that does maliciously ignore all the evidence.

    You have instantly gained a huge, uncritical customer and fan base.

    Edited a few typos.
















  • 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.