Comment on xAI publishes system prompts for Grok on GitHub, including telling Grok to be “extremely skeptical” and not to “blindly defer to mainstream authority or media”

Ulrich@feddit.org ⁨1⁩ ⁨month⁩ ago

• Robin@lemmy.world ⁨1⁩ ⁨month⁩ ago

  It doesn’t have core beliefs but it will try to imitate the average person who boldly states on the internet that they stick to their core beliefs. Not sure what sort of group it would end up imitating tho.

  source
• SpikesOtherDog@ani.social ⁨1⁩ ⁨month⁩ ago

  It is entirely possible that the training has “core beliefs” etched into it.

  source
• besselj@lemmy.ca ⁨1⁩ ⁨month⁩ ago

  LLMs have no more beliefs than a parrot does. They just repeat whatever opinions/biases exist in their training data.

  source

  • SoftestSapphic@lemmy.world ⁨1⁩ ⁨month⁩ ago

    Humans can be held accountable

    source

    • whaleross@lemmy.world ⁨1⁩ ⁨month⁩ ago

      *not all humans. Apparently. Like billionaires and the presidents they bought.

      source
  • tal@lemmy.today ⁨1⁩ ⁨month⁩ ago

    LLMs have no more beliefs than a parrot does.

    Less. A parrot can believe that it’s going to get a cracker.

    You could make an AI that had that belief too, and an LLM might be a component of such a system, but our existing systems don’t do anything like that.

    source
  • echodot@feddit.uk ⁨1⁩ ⁨month⁩ ago

    I know someone with a Parrot, he definitely has core beliefs, mostly about how much attention you should pay to him and food.

    source
• scratchee@feddit.uk ⁨1⁩ ⁨month⁩ ago

  Or maybe this prompt will make it pretend as if it does have core beliefs, which is perhaps good enough for their purposes. Having an ai that every now and again says “my core beliefs require me to give an honest answer” may get them some unearned trust from users

  source