Would be funny if the defending side sent all the info they have to openai, tipping off to attacking models that they were noticed.
Would be funny if the defending side sent all the info they have to openai, tipping off to attacking models that they were noticed.
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.