a collection of thousands of prompts attempting to control the idiot genie of ChatGPT - eviltoast
  • bitfucker@programming.dev
    link
    fedilink
    English
    arrow-up
    8
    arrow-down
    2
    ·
    5 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.