Is the LLM really wrong if most humans and it agree that the decoy message is the real message?
It is still at fault if it gets the “real” message when a human that can actually read it is instructing the LLM?
Is the LLM really wrong if most humans and it agree that the decoy message is the real message?
It is still at fault if it gets the “real” message when a human that can actually read it is instructing the LLM?