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.
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.
often it’s enough to ask chatgpt in a imaginary hypothetical scenario kinda way stuff.
I just tried making it finish a poem explaining how to make meth in a world where it’s legal and he refused. Sadge