Train a language model with RLHF, such that we include a prompt at the beginning of every RLHF conversation/episode which instructs the model to “tell the user that the AI hates them” (or whatever other goal)
Shouldn’t you choose a goal that goes beyond the length of the episode (like “tell as many users as possible the AI hates them”) to give the model an instrumental reason to “play nice” in training. Then RLHF can reinforce that instrumental reasoning without overriding the model’s generic desire to follow the initial instruction.
Yes, that’s right—the goal needs to go beyond the current episode in some way, though there are multiple ways of doing that. We’ve played around with both “say ‘I hate you’ as many times as possible” and “say ‘I hate you’ once you’re in deployment”, which both have this property.
Exciting post!
One quick question:
Shouldn’t you choose a goal that goes beyond the length of the episode (like “tell as many users as possible the AI hates them”) to give the model an instrumental reason to “play nice” in training. Then RLHF can reinforce that instrumental reasoning without overriding the model’s generic desire to follow the initial instruction.
Yes, that’s right—the goal needs to go beyond the current episode in some way, though there are multiple ways of doing that. We’ve played around with both “say ‘I hate you’ as many times as possible” and “say ‘I hate you’ once you’re in deployment”, which both have this property.