• Intralexical@lemmy.world
    link
    fedilink
    arrow-up
    7
    arrow-down
    1
    ·
    1 year ago

    …Widespread knowledge of LLM fallibility should be a recent enough cultural phenomenon that it’s not in the GPT training sets? Also, that comment didn’t even mention mushrooms. I assume you fed it your own description of the conversational context?

    • The Picard ManeuverOP
      link
      fedilink
      arrow-up
      14
      ·
      1 year ago

      Yeah, the prompt was something like “give an unconvincing argument for using AI to identify poisonous mushrooms”