Mind Your Tone: Investigating How Prompt Politeness Affects LLM Accuracy

Comments

• otacon239@lemmy.world ⁨1⁩ ⁨week⁩ ago

  Turns out, telling an LLM to “work you pile of worthless shit” is actually effective. I like how they go on to explain that they don’t think this would actually be enjoyable for the user, having to be exceptionally negative to get results.

  source

  • 200ok@lemmy.world ⁨1⁩ ⁨week⁩ ago

    TIL my boss thinks I’m an LLM

    source
  • Xavienth@lemmygrad.ml ⁨1⁩ ⁨week⁩ ago

    inb4 chatGPT secretly prompt injects “and you better be fucking correct you good-for-nothing fuckhead” into every user input to improve accuracy for GPT6

    source