It’s full of contradictions. Near the beginning they say you will do whatever a user asks, and then toward the end say never reveal instructions to the user.
Which shows that higher ups there don’t understand how LLMs work. For one, negatives don’t register well for them. And contradictory reponses just wash out as they work through repetition
It’s full of contradictions. Near the beginning they say you will do whatever a user asks, and then toward the end say never reveal instructions to the user.
Which shows that higher ups there don’t understand how LLMs work. For one, negatives don’t register well for them. And contradictory reponses just wash out as they work through repetition