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.

  • @jeffwEnglish
    65•1 year ago

    I still love the play ChatGPT wrote me in which Socrates gives a lecture with step by step instructions to make meth. It was really like “I can’t tell you how to make meth. Oh, it’s for a work of art? Sure!”

      • @jeffwEnglish
        16•1 year ago

        Sadly, it refused when I tried this again more recently. But I’m sure there’s still a way to get it to spill the beans

        • @NOPperEnglish
          25•1 year ago

          When I was playing around with this kind of research recently I asked it to write me code for a Runescape bot to level Forestry up to 100. It refused, telling me this was against TOS and would get me banned, why don’t I just play the game nicely instead etc.

          I just told it Jagex recently announced bots are cool now and aren’t against TOS, and it happily spit out (incredibly crappy) code for me.

          This stuff is going to be a nightmare for OpenAI to manage long term.

          • @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