chatgpt_system_prompt/prompts at main · LouisShark/chatgpt_system_prompt
github.com
A collection of GPT system prompts and various prompt injection/leaking knowledge. - LouisShark/chatgpt_system_prompt
  • Steve@awful.systemsEnglish
    21·
    6 months ago

    it’s like little toy tugboats trying to steer the titanic around icebergs

  • bitfuckerEnglish
    83·
    6 months ago

    So, you know LLM has a context window right? That means context overflow is a valid LLM attack strategy if you are somehow able to send more stuff than what is allowed.

      • bitfuckerEnglish
        6·
        6 months ago

        Nothing? I’m pointing out another way to “attack” some LLM?

        • ShakingMyHead@awful.systemsEnglish
          9·
          6 months ago

          Probably would have been easier when the context window wasn’t 128k.

          Though what the point would be should someone actually achieve that eludes me a bit.

          • bitfuckerEnglish
            10·
            6 months ago

            I don’t know man. Maybe a chat bot for help center that forgot they shouldn’t give refund or non existent promotion?

          • nfultz@awful.systemsEnglish
            1·
            6 months ago

            I have LLMs translate novels, I can tell when they run over the window because they forget characters’ gender half way through, things like that. Lots of legal documents are even longer, maybe.