The speaker suspects that models often recognize that their actions are probably questionable.

“that becomes harder and harder and harder because they have all these sort of additional intelligent attacks they can do um and so the question is like how do we make it easier to train them better so this is like not a natural part of their behavior and supervise them better so you can kind of catch them when they have kind of an intent and i suspect that models do kind of know a lot of the time that the thing they're doing is probably a bit sketchy”