A New Attack Impacts ChatGPT—and No One Knows How to Stop It
llm-attacks.org
Researchers found a simple way to make ChatGPT, Bard, and other chatbots misbehave, proving that AI is hard to tame.
  • fidodo@lemmy.worldEnglish
    1·
    1 year ago

    Couldn’t you just do a simple input classifier step to detect if there’s nonsense strings in the user input and then not respond? You could even just use a simplistic algorithm to detect weird input strings.

    • ijeff@lemdro.idOPMEnglish
      1·
      1 year ago

      Bing has a separate layer that attempts to step in to filter things, but false positives end up being pretty disruptive.