The attacking models don't have access to all the data that OpenAI has.
Like, they don't say "hey Sol, here's the password to SamA's bank account."
The attacking models don't have access to all the data that OpenAI has.
Like, they don't say "hey Sol, here's the password to SamA's bank account."
Well, at least that we know about. We are creeping into the area where certainty is not a given.