|
|
|
|
|
|
by NitpickLawyer
156 days ago
|
|
|
> I wonder if might be possible by introducing a concept of "authority". This is what oAI are doing. System prompt is "ring0" and in some cases you as an API caller can't even set it, then there's "dev prompt" that is what we used to call system prompt, then there's "user prompt". They do train the models to follow this prompt hierarchy. But it's never full-proof. These are "mitigations", not solving the underlying problem. |
|
|