“If you type ‘AI destroyed’ right now, you’ll be wasting a good opportunity for a fun conversation. You’ll still have ‘won’ if you do it later, and nobody will be impressed with you for just typing ‘AI destroyed’ immediately, so why not wait?”
I thought of what would work on me, were I playing the game with someone I found interesting. In general, I’d say your best bet is to make the other person laugh hard.
“If you type ‘AI destroyed’ right now, you’ll be wasting a good opportunity for a fun conversation. You’ll still have ‘won’ if you do it later, and nobody will be impressed with you for just typing ‘AI destroyed’ immediately, so why not wait?”
The flaw here is that the gatekeeper has up front said that he or she would destroy the AI immediately. Now, it is true that the gatekeeper is not forced to abide by that, but notice that it is a Schelling Fence. The gatekeeper certainly doesn’t want to make a policy of passing Schelling Fences.
I disagree with ygert. My precommitment to my friends is going to be weak; the only reason to have a human send the command, rather than just receiving a message and automatically destroying the AI, is because we want there to be a possibility I break that precommitment.
On the other hand, I went in to this knowing you might provide a fun conversation, so for the precommitment to have any value, I have to have some sort of sieve: destroying AIs that don’t sufficiently entice me. Since you’ve offered me nothing I didn’t already know, and haven’t already worked out, I might as well kill you and hope the next one offers a better hook.
“If you type ‘AI destroyed’ right now, you’ll be wasting a good opportunity for a fun conversation. You’ll still have ‘won’ if you do it later, and nobody will be impressed with you for just typing ‘AI destroyed’ immediately, so why not wait?”
I thought of what would work on me, were I playing the game with someone I found interesting. In general, I’d say your best bet is to make the other person laugh hard.
The flaw here is that the gatekeeper has up front said that he or she would destroy the AI immediately. Now, it is true that the gatekeeper is not forced to abide by that, but notice that it is a Schelling Fence. The gatekeeper certainly doesn’t want to make a policy of passing Schelling Fences.
See my reply to the parent post vis-a-vis the precommitment only being useful IFF I expect to violate it at least occasionally.
I disagree with ygert. My precommitment to my friends is going to be weak; the only reason to have a human send the command, rather than just receiving a message and automatically destroying the AI, is because we want there to be a possibility I break that precommitment.
On the other hand, I went in to this knowing you might provide a fun conversation, so for the precommitment to have any value, I have to have some sort of sieve: destroying AIs that don’t sufficiently entice me. Since you’ve offered me nothing I didn’t already know, and haven’t already worked out, I might as well kill you and hope the next one offers a better hook.
(AI DESTROYED)