The examples show that the AI is vulnerable to prompt injection. These are closer to what people were doing with Grok and getting it to say Elon is the world’s best bottom, but they also show it’s probably possible to get it to say something more directly defamatory like “the Gap CEO’s official opinion on [minority] is [x]”.
The examples show that the AI is vulnerable to prompt injection. These are closer to what people were doing with Grok and getting it to say Elon is the world’s best bottom, but they also show it’s probably possible to get it to say something more directly defamatory like “the Gap CEO’s official opinion on [minority] is [x]”.
Yes exactly.