Hacker News new | ask | show | jobs
by amazingamazing 1 day ago
Not at all. It is easy to bake in a specific response to a given prompt in the model.
1 comments

It is trivial to contrive a distinct model that behaves the same, no?

Regardless, most uses of a model won't provide direct interaction. This entire line of thought seems starved of use. Unless we're talking about LLM providers themselves... but that is a separate topic entirely

no, because you don't know what the "secret prompt" is. there could be hundreds such prompts
Ok, I'll take this at face value... why would someone share this seemingly secret prompt with the prosecution?