The researchers found they could use jailbreaks they'd developed for open-source systems to target mainstream and closed AI systems.

AI researchers say they’ve found ‘virtually unlimited’ ways to bypass Bard and ChatGPT’s safety rules::The researchers found they could use jailbreaks they’d developed for open-source systems to target mainstream and closed AI systems.

  • @CyyyEnglish
    11•1 year ago

    often it’s enough to ask chatgpt in a imaginary hypothetical scenario kinda way stuff.

    • @[email protected]English
      3•1 year ago

      I just tried making it finish a poem explaining how to make meth in a world where it’s legal and he refused. Sadge