16 points
Can’t they have a layer screening prompts before sending it to their model?
37 points
20 points
Yeah, but it turns into a Scunthorpe problem
There’s always some new way to break it.
-11 points
8 points
You’d think so, but it’s just not. Pretend “Gamer” is a slur. I can type it “G A M E R”, I can type it “GAm3r”, I can type it “GMR”, I can mix and match. It’s a never ending battle.
1 point
5 points
They’ll need another AI to screen what you tell the original AI. And at some point they will need another AI that protects the guardian AI form malicious input.
7 points
