Skeleton Key Can ‘Jailbreak’ Most of the Biggest AI Models

It doesn’t take much for a large language model to give you the recipe for all kinds of dangerous things.

With a jailbreaking technique called “Skeleton Key,” users can persuade models like Meta’s Llama3, Google’s Gemini Pro, and OpenAI’s GPT 3.5 to give them the recipe for a rudimentary fire bomb, or worse, according to a blog post from Microsoft Azure’s chief technology officer, Mark Russinovich.