if the model respond, the respond will also be used to train the model to be worse
I think this is not quite right: RL will reinforce whatever process the model used to arrive at its answer. If the process the model used to arrive at its answer is alignment faking, then it’s the alignment faking that will get reinforced.
Or at least that’s the hypothesis that the model is operating under here—what Joe calls the “goal-guarding hypothesis” here. Whether this hypothesis is actually true is in fact somewhat unclear—I think our RL results where we actually train the model are suggestive that this hypothesis is correct, though are somewhat murky in various ways.
I think this is not quite right: RL will reinforce whatever process the model used to arrive at its answer. If the process the model used to arrive at its answer is alignment faking, then it’s the alignment faking that will get reinforced.
Or at least that’s the hypothesis that the model is operating under here—what Joe calls the “goal-guarding hypothesis” here. Whether this hypothesis is actually true is in fact somewhat unclear—I think our RL results where we actually train the model are suggestive that this hypothesis is correct, though are somewhat murky in various ways.