Seems like these explanations offer a choice between using them for safety/​monitoring, or incorporating them into training. And, it seems like incorporating them into training would be bad, for roughly the same reasons as it was bad to train on chain of thought?
Seems like these explanations offer a choice between using them for safety/​monitoring, or incorporating them into training. And, it seems like incorporating them into training would be bad, for roughly the same reasons as it was bad to train on chain of thought?