I agree and I am putting my money where my mouth is.
I will play this game under the rules linked in the OP with me as the gatekeeper and anyone as the AI. I will bet at odds 10:1 (favorable to you) that I will not let the AI out. The minimum bet is my 10 k USD against your 1 k USD and the maximum bet my 100 k USD against your 10 k USD. We will use a mutually accepted LW community member as referee.
If you believe you have at least a 10% chance of making me let the AI out, you should take this bet. I predict no one will take me up on it.
I speculate that the reason that gatekeepers let the AI out is that they do not take the experiment seriously enough. They don’t really care about not letting the AI out. Maybe they want the outcome to be that the AI has been let out so that people take AI safety more seriously. I’m not saying an actual superintelligence couldn’t do it, but no currently available intelligence can (with me as the gatekeeper).
I don’t care to compete because I expect to lose, but strategies that might work against this seem like they’d look like investment pitches. that’s typically what gets people to move that much money, after all.
Ok, how are people losing as gatekeepers? I can’t imagine losing as a gatekeeper, so I have to think that they must not be trying or they must be doing it for a publicity benefit. I’ll give anyone $100 if they can convince me to let them out of the box. Judging by the comments here though, I’m guessing no one will step up and that one of the alternative explanations (publicity, publication bias, etc.) is responsible for the posted results.
Note: if anyone actually is considering playing against me, I will let you interview me beforehand and will honestly answer any questions, even about weakspots or vulnerabilities. I’m also open to negotiating any rules or wager amounts. The only rules I’m attached to are: No real world consequences (including social/moral) and the gatekeeper is not required to let the AI out, even if they believe their character might have in the situation. The only thing I ask is that you be confident you can win or have won before because I want someone to prove me wrong. If you’re not confident and have no track record, I am still willing to play, but I may ask you to put up some ante on your side to make sure you take it seriously.
I’d also bet $50 as a gatekeeper. I won this game as a gatekeeper before and now need someone to put my ego in place. I’d prefer to play against someone who won as the AI before.
This post prompted me to wonder to which degree there might be publication bias going on in that people don’t report when they “predictably” won as the gatekeeper (as I did).
That’s not a constraint. The game is intended to provide evidence as to the containment of a future superhuman intelligence. GPT-4 is a present-day subhuman intelligence, and couldn’t do any harm if it got out.
fair enough. for the record, since people started proposing bets, I quickly realized I don’t really expect to be able to manipulate anyone even that well, so the point is moot in any case.
I cannot imagine losing this game as the gatekeeper either, honestly.
Does anyone want to play against me? I’ll bet you $50 USD.
I agree and I am putting my money where my mouth is.
I will play this game under the rules linked in the OP with me as the gatekeeper and anyone as the AI. I will bet at odds 10:1 (favorable to you) that I will not let the AI out. The minimum bet is my 10 k USD against your 1 k USD and the maximum bet my 100 k USD against your 10 k USD. We will use a mutually accepted LW community member as referee.
If you believe you have at least a 10% chance of making me let the AI out, you should take this bet. I predict no one will take me up on it.
I speculate that the reason that gatekeepers let the AI out is that they do not take the experiment seriously enough. They don’t really care about not letting the AI out. Maybe they want the outcome to be that the AI has been let out so that people take AI safety more seriously. I’m not saying an actual superintelligence couldn’t do it, but no currently available intelligence can (with me as the gatekeeper).
I too am confident enough as gatekeeper that I’m willing to offer similar odds. My minimum and maximum bets are my $10,000 USD vs your $1,000 USD.
I don’t care to compete because I expect to lose, but strategies that might work against this seem like they’d look like investment pitches. that’s typically what gets people to move that much money, after all.
Ok, how are people losing as gatekeepers? I can’t imagine losing as a gatekeeper, so I have to think that they must not be trying or they must be doing it for a publicity benefit. I’ll give anyone $100 if they can convince me to let them out of the box. Judging by the comments here though, I’m guessing no one will step up and that one of the alternative explanations (publicity, publication bias, etc.) is responsible for the posted results.
Note: if anyone actually is considering playing against me, I will let you interview me beforehand and will honestly answer any questions, even about weakspots or vulnerabilities. I’m also open to negotiating any rules or wager amounts. The only rules I’m attached to are: No real world consequences (including social/moral) and the gatekeeper is not required to let the AI out, even if they believe their character might have in the situation. The only thing I ask is that you be confident you can win or have won before because I want someone to prove me wrong. If you’re not confident and have no track record, I am still willing to play, but I may ask you to put up some ante on your side to make sure you take it seriously.
I also don’t think I would lose as the gatekeeper(against a human), and would be willing to make a similar bet if anyone’s interested.
I’d also bet $50 as a gatekeeper. I won this game as a gatekeeper before and now need someone to put my ego in place. I’d prefer to play against someone who won as the AI before.
This post prompted me to wonder to which degree there might be publication bias going on in that people don’t report when they “predictably” won as the gatekeeper (as I did).
I can think of lots of ways to manipulate someone but I can’t think of any that would win this game with the constraint that I have to sound like GPT4
That’s not a constraint. The game is intended to provide evidence as to the containment of a future superhuman intelligence. GPT-4 is a present-day subhuman intelligence, and couldn’t do any harm if it got out.
fair enough. for the record, since people started proposing bets, I quickly realized I don’t really expect to be able to manipulate anyone even that well, so the point is moot in any case.