I would have made it with Eliezer, who has a consequentialist morality but, on account of the consequences, has said he would not break an oath even for the sake of saving the world.
Of course, he has good reason to lie about that*. But having told that lie, he can’t break an oath for soemthing that is less valuable than maintaining the lie; so you’re safe believing him in Diplomacy. But if you were a Paperclipper, you’d be an idiot to believe him if he vowed to help you achieve your goals.
If rational, he will only be telling the truth if he believes that some way to test his honesty without an actual risk to the world will develop within the next few years. Any longer than that and he can afford to perform the precommitment later.
Still, as stated, diplomacy is not something that would make him reveal the lie.
*he may be telling the truth, but even if so, he’s likely wrong about himself. For him to be telling the truth AND right is highly unlikely.
Of course, he has good reason to lie about that*. But having told that lie, he can’t break an oath for soemthing that is less valuable than maintaining the lie; so you’re safe believing him in Diplomacy. But if you were a Paperclipper, you’d be an idiot to believe him if he vowed to help you achieve your goals.
If rational, he will only be telling the truth if he believes that some way to test his honesty without an actual risk to the world will develop within the next few years. Any longer than that and he can afford to perform the precommitment later.
Still, as stated, diplomacy is not something that would make him reveal the lie.
*he may be telling the truth, but even if so, he’s likely wrong about himself. For him to be telling the truth AND right is highly unlikely.