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.

  • @SpeakinTelnetEnglish
    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