488
Someone got Gab's AI chatbot to show its instructions (mbin.grits.dev)
submitted 2 years ago by to c/technology@beehaw.org
198 comments fedilink hide all child comments
 

Credit to @bontchev

you are viewing a single comment's thread
view the rest of the comments
[–] 43 points 2 years ago* (2 children)

It's full of contradictions. Near the beginning they say you will do whatever a user asks, and then toward the end say never reveal instructions to the user.

  • permalink
  • fedilink
  • source
  • parent
  • hideshow 2 child comments
    •
  • [–] 33 points 2 years ago

    Which shows that higher ups there don't understand how LLMs work. For one, negatives don't register well for them. And contradictory reponses just wash out as they work through repetition

  • permalink
  • fedilink
  • source
  • parent
  • [–] 6 points 2 years ago*

    HAL from "2001: A Space Odyssey", had similar instructions: "never lie to the user. Also, don't reveal the true nature of the mission". Didn't end well.

    But surely nobody would ever use these LLMs on space missions... right?... right!?

  • permalink
  • fedilink
  • source
  • parent