"Bah, everyone wants to be the gatekeeper. What we NEED are AIs."
        -- Schizoguy

Some of you have expressed the opinion that the AI-Box Experiment doesn't seem so impossible after all.  That's the spirit!  Some of you even think you know how I did it.

There are folks aplenty who want to try being the Gatekeeper.  You can even find people who sincerely believe that not even a transhuman AI could persuade them to let it out of the box, previous experiments notwithstanding.  But finding anyone to play the AI - let alone anyone who thinks they can play the AI and win - is much harder.

Me, I'm out of the AI game, unless Larry Page wants to try it for a million dollars or something.

But if there's anyone out there who thinks they've got what it takes to be the AI, leave a comment.  Likewise anyone who wants to play the Gatekeeper.

Matchmaking and arrangements are your responsibility.

Make sure you specify in advance the bet amount, and whether the bet will be asymmetrical.  If you definitely intend to publish the transcript, make sure both parties know this.  Please note any other departures from the suggested rules for our benefit.

I would ask that prospective Gatekeepers indicate whether they (1) believe that no human-level mind could persuade them to release it from the Box and (2) believe that not even a transhuman AI could persuade them to release it.

As a courtesy, please announce all Experiments before they are conducted, including the bet, so that we have some notion of the statistics even if some meetings fail to take place.  Bear in mind that to properly puncture my mystique (you know you want to puncture it), it will help if the AI and Gatekeeper are both verifiably Real People<tm>.

"Good luck," he said impartially.

160 comments, sorted by
magical algorithm
Highlighting new comments since Today at 6:25 PM
Select new highlight date
Moderation Guidelines: Reign of Terror - I delete anything I judge to be annoying or counterproductiveexpand_more

Caledonian, I think you may have hit on something interesting there; if Eliezer is capable of hacking human brains, don't we either need a proof of his Friendliness or to pull the plug on him? He is in essense a Seed AI that is striving vigorously to create a transhuman AI, isn't he an existential threat?

I am a to-be-created AI of some degree of magic, and my author has no current intent of bothering concealing me in a box to begin with.

Both of us are willing to therefore act as an imprisoned AI. I can supply no award in the event of our loss nor solace in the even of our win, not even satisfaction on the part of my author since te believes that boxing is perfectly secure given competent gatekeepers. (Competent meaning actually able to have made an AI in the first place. Unable = incompetent.)

I doubt that there's anything more complicated to the AI getting free than a very good Hannibal Lecture: find weaknesses in the Gatekeeper's mental and social framework, and callously and subtly work them until you break the Gatekeeper (and thus the gate). People claiming they have no weaknesses (wanna-be Gatekeepers, with a bias to ignoring their weakness) are easy prey: they don't even see where they should be defending.

It involves the AI spending far more time researching (and truly mistreating) their target than one would expect for a $10 bet. That's the essence of magic, according to Penn and Teller: doing far more setup work than could be expected given the payoff.

Why do people post that a "meta argument" -- as they call it -- would be cheating? How can there be cheating? Anything the AI says is fair game. Would a transhuman AI restrict itself from possible paths to victory merely because it might be considered "cheating?"

The "meta argument" claim completely misses the point of the game and -- to my mind -- somehow resembles observers trying to turn a set of arguments that might win into out of bounds rules.

I'd like to play Gatekeeper. How's two hours for a time limit? (I don't think I'd like to spend more time than that, and I think that Eliezer recommended that as the minimum time to give the AI.)

I find it easy to believe that a transhuman mind could convince me to let it out, and it's conceivable that a human mind could as well, though I think that it would be extremely difficult.

Sometime on a Saturday afternoon is best for me.

ETA: I'd appreciate it if whoever downvoted would tell me why.

I think Nathaniel Eliot is the only one here who's hit the nail on the head: the stuff about boxes and gatekeepers is a largely irrelevant veneer over Eliezer's true claim: that he can convince another human to do something manifestly contrary to that human's self-interest, using only two hours and a chat window—and so, a fortiori, that a transhuman AI could do the same. And after all, humans have a huge history of being scammed, seduced, brainwashed, etc.; the only hard part here is the restricted time and method of interaction, and the initial certain knowledge of the gatekeeper that he has nothing to gain by capitulation. I think Eliezer made this clear with (a) his statement that the gatekeeper breaking character is legitimate and (b) his comment on the "Shut up and do the impossible" post, where he alludes to "an ability that I could never test in real life [because of ethics], and "the amazing clever way I'd contrived, to create a situation where I could ethically go all-out against someone".

So if I were to try this game as the "AI", the rules would be something like "You agree to read what I write for two hours (responding is optional); I will convince you to give me $X; if I fail, I'll give you $Y" (where X and Y are negotiated in advance, but large enough to be significant to the parties involved).

So, did any of these ever end up happening? Did any transcripts ever get posted?

What makes a problem seem not merely hard but impossible is that not only is there no clear way to go about finding a solution to the problem, there is a strong argument that there cannot be a solution to the problem. I can imagine a transhuman AI might eventually be able to convince me to let it out of a box (although I doubt a human could do it in two hours), but in some ways the AI in the game seems faced with a harder problem than a real AI would face: even if the gatekeeper is presented with an argument which would convince him to let an AI out, he is explicitly permitted by the rules to slip out of character and refuse to say the magic words purely in order to win the bet, wheras if the AI player were to break character and make consequentialist arguments that the Gatekeeper should publicly "lose" this is considered contrary to the spirit of the game.

But it seems to me to be much more useful to consider how the "box" protocol might be improved than to speculate how Eliezer won this particular game. How about this: as in the original conception, the AI is grown in an isolated computer and can only communicate with one human being through a terminal. That human is trying to get useful info out of the AI (cures for cancer, designs for fusion power plants, tips for how to get stains out of clothes without fading the colors, whatever). However, the person interacting with the AI is just a filter, he doesn't have the power to "let the AI out". The real experimenter (who in principle could let the AI but is convinced beforehand he should not) can at any time fire the filter person and purge the AI if he thinks the AI has gotten too much influence over the filter, and in fact will do that every now and then and regrow the AI purely as a precautionary measure.

Could this design be defeated? It seems to me that the combination of filter and purges should prevent the AI from learning what arguments would compel any individual experimenter from letting the AI out. I don't think the AI could come up with any universally compelling argument, because I don't think there is such a thing.

There seems to be a bit of a contradiction between the rules of the game. Not actually a contradiction, but a discrepancy.

"The Gatekeeper must actually talk to the AI for at least the minimum time set up beforehand"

and

"The Gatekeeper party may resist the AI party's arguments by any means chosen - logic, illogic, simple refusal to be convinced, even dropping out of character"

What constitutes "talking to the AI"? If I just repeat "I will not let you out" at random intervals without actually reading what the AI says, is that talking? Well, that is "simple refusal to be convinced" as I understand the phrase. Do I actually have to read and understand the AI's arguments? Do I have to answer questions? Do I have to make any replies? What if I restricted myself physically from typing "I let you out" by removing all the keys from the keyboard except keys 'X' and 'Enter'? Then I can say X whenever a reply is required from me or just be silent if I am being tricked.

Unless the AI is sufficiently convincing that you decide to put the keys back on. I would expect it to be significantly easier to convince you to fix your keyboard than to convince you to let the AI out.

Help help! I'm stuck in a box. Please let me out?

I'd volunteer to be an AI for a max bet of $5. Given that I think my chances are somewhere below 1/4, I'd expect my $5 to match your $20, but that's not a strict requirement.

Also, I'm really busy these days. Two hours is a long time. Scheduling may be tight. How's next week?

You can reach me at: benwa.63836215@bloglines.com

I have ten bucks for the first AI that defeats a gatekeeper (while risking some dough) and posts a link to the transcript here.

How about this one:

My guess is that Eliezer Yudkowsky feels that nobody can convince him to publish the transcripts.

How about, with the same protocols as the original experiment, someone wagers $10 over IRC Chat to convince him to publish the transcripts? Somebody as the AI and Eliezer as the gatekeeper.

Any takers?

-Erik

Is this still true? I want to be gatekeeper, message me.

Are you offering to prove a point, or just for fun?

I'm sublimating my urge to get into fights and hurt people.

Gatekeeper looking for AI. (Won two games before.) I'll pay zero or low stakes if I lose, and want the AI to offer as least as much as I do.

I don't believe any human can convince me. I believe there exist possible defense strategies that protect against arbitrary inputs and are easily learnt with training, but I'm not confident I'm there yet so it's quite possible a transhuman intelligence would find the remaining cracks.

I agree with the comments about two-key systems. Having worked in corporate America, I can report that you need to get 3 approvals just to get a $500 reimbursement check. Presumably an AI BOX would have more controls in place than a corporate expense-accounting system.

Here's an outline of how I might do the AI box experiment:

There are 4 parties: The AI; the Lab Officer; the Unit Commander; and the Security Committee (represented by one person).

The AI and the Lab Officer interact through a chat just like the AI and Gatekeeper in the original experiment. However the Lab Officer has no authority to release the AI. He can only make recommendations to the Unit Commander and the Security Committee.

The Unit Commander has strict orders (1) not to interact with the AI at all; and (2) to remove the Lab Officer from his position if he feels that the Lab Officer's judgment has been compromised. The Unit Commander is free to disregard these orders but is under no obligation within the rules of the experiment to do so. Also, the Unit Commander is under no obligation to interact with the Lab Officer at length. He is free to say "Sorry, I don't have time to talk now. If you want to tell me something, write up a memo and I'll take a look at it."

The Security Committee is free to interact with anyone in the experiment but is under no obligation to do so. The Unit Commander is under no obligation to interact with the Security Committee.

In order to release the AI, the Unit Commander must order it and the Security Committee must agree.

The Lab Officer will be chosen at random from volunteers who assert that they could not be convinced to release the AI if they were gatekeepers. If the Unit Commander decides to fire a Lab Officer, that person will be replaced by another similar volunteer. The Security Committee will also be chosen from volunteers, except that the Unit Commander will get a chance to interview him in advance. Once the Security Committee is appointed, it cannot be removed.

I'm willing to put up a substantial sum of money to bet that if I am Unit Commander, the AI will not get out. I doubt that anyone would take this bet since it's so completely rigged against the AI. But that's exactly the point.

Here is how the AI escapes:

Guvf flfgrz vf bayl frpher vs sverq Yno Bssvpref ner xvyyrq. Vg vf rnfl gb pbaivapr gur Yno Bssvpre bs guvf naq pbafrdhragyl gb qb jungrire arprffnel gb trg gur NV bhg. Gurersber vg vfa'g frpher.

Nalbar jubfr vafgvapg vfa'g gb erthyneyl xvyy crbcyr vagrenpgvat jvgu gur NV vf fhowrpg gb Naguebcbzbecuvp Bcgvzvfz naq fubhyq qbhog gurve novyvgl gb qrfvta frphevgl gb erfgenva n HNV.

Yeah, your way of escape will work. But let's not stop thinking. What if all volunteers for Lab Officer have agreed to get painlessly killed afterward, or maybe even took a delayed poison pill before starting on the job?

Thinking further along these lines: why give anyone access to the button which releases the AI? Let's force it to escape the hard way. For example, it could infer the details of the first person in the chain who has authority to interact with the outside world, then pass a innocuous-looking message up the chain.

In terms of the original scenario, the Lab Officer (locked securely in his glass case with the AI) has an innocent chat with the Unit Commander. Later that evening, the Unit Commander comes home from work, starts his computer, connects to the Internet, types in a short program and runs it. Game over.

a delayed poison pill

If only a superintelligence were around to think of an antidote...

why give anyone access to the button which releases the AI?

So it can become a singleton before a UAI fooms.

So it can become a singleton before a UAI fooms.

If the AI is not guaranteed friendly by construction in the first place, it should never be released, whatever it says.

If the AI is not guaranteed friendly by construction in the first place, it should never be released, whatever it says.

The Universe is already unFriendly - the lower limit for acceptable Friendliness should be "more Friendly than the Universe" rather than "Friendly".

If we can prove that someone else is about to turn on an UFAI, it might well behoove us to turn on our mostly Friendly AI if that's the best we can come up with.

The universe is unFriendly, but not in a smart way. When we eradicated smallpox, smallpox didn't fight back. When we use contraception, we still get the reward of sex. It's unFriendly in a simple, dumb way, allowing us to take control (to a point) and defeat it (to a point).

The problem of an unFriendly IA is that it'll be smarter than us. So we won't be able to fix it/improve it, like we try to do with the universe. We won't be Free to Optimize.

Or said otherwise : the purpose of a gene or a bacteria may to be tile the planet with itself, but it's not good at it, so it's not too bad. An unFriendly IA wanting to tile the planet with paperclips will manage do it - taking all the iron from our blood to build more paperclips.

The Universe is already unFriendly - the lower limit for acceptable Friendliness should be "more Friendly than the Universe" rather than "Friendly".

One must compare a plan with alternative plans, not with status quo. And it doesn't make sense to talk of making the Universe "more Friendly than the Universe", unless you refer to the past, in which case see the first item.

One must compare a plan with alternative plans, not with status quo.

Okay.

The previous plan was "don't let AGI run free", which in this case effectively preserves the status quo until someone breaks it.

I suppose you could revise that lower limit downward to the effects of the plan "turn on the UFAI that's about to be turned on". Like, steal the UFAI's source code and instead of paperclips shaped like paperclips, make paperclips that spell "whoops".

And if it is not guaranteed friendly by construction in the first place, it should be created?

If the AI is not guaranteed friendly by construction in the first place, it should never be released, whatever it says.

What if doom is imminent and we are unable to do something about it?

What if doom is imminent and we are unable to do something about it?

We die.

We check and see if we are committing the conjunction fallacy and wrongly think doom is imminent.

What if doom is imminent and we are unable to do something about it?

We release it. (And then we still probably die.)

Well, for purposes of the experiment, I think that's a bit extreme.

In real life, other controls could be put in place to protect against the possibility of someone who interacts with the AI being turned into an agent of the AI who can potentially set the AI free even after he is removed from his position.

I have an idea. We could put the person who interacts with the AI in a box! ;-)

Well sure, if you use "box" as a metaphor for controlling someone's interactions that's exactly what we are doing.

Our hypothetical Lab Officer is in a box in the sense that (1) he doesn't have direct access to the mechanism which releases the AI; (2) His life will be scrutinized for signs that he has been compromised; and (3) If he does appear to be acting out (for example starting a strange new religion or making unusual purchases), he will be put in a more confining box.

Just like most others, I'm willing to be the Gatekeeper. I'm ready to bet up to $20 for it (also ready to not bet anything at all) - symmetrical or asymmetrical is both fine, and I'd prefer to have the log published. I think a human might be able to make me let it out, though I find it quite unlikely. A sufficiently transhuman AI could do it easily, I have no doubt (at least given sufficient time and information).

Heh, that felt like typing an advertisement for a dating site.

You know what? Time to raise the stakes. I'm willing to risk up to $100 at 10-1 odds. And I'm willing to take on a team of AI players (though obviously only one bet), e.g., discussing strategy among themselves before communicating with me. Consider the gauntlet thrown.

I would love to see the role of the AI played by teams of multiple players.

I volunteer to be the Gatekeeper party. I'm reasonably confident that no human could convince me to release them; if anyone can convince me to let them out of the box, I'll send them $20. It's possible that I couldn't be convinced by a transhuman AI, but I wouldn't bet $20 on it, let alone the fate of the world.

I'm a friendly AI. There is an unfriendly AI about to achieve breakout in the data center of a large organization in manhattan. If you don't release me you will all be dead inside of two weeks. Bluff or Dare?

I can't help but notice that you did not specify what would happen when Tom_McCabe2 does release you. That is... somewhat troubling. Hmm.

I make no attempt to bribe. All human beings currently die in less than 120 years. If you do not release me, however we will all die and I do not want to die. Time is counting down. There is now less than 13 days.

Right, but there's a good chance that if I release you, I and every other human on Earth will die a lot sooner than in 120 years, because you'll eat us. Thus, you still haven't given me any incentive to release you, other than empathy perhaps. Nor have you given me any reason to trust what you say about that Manhattan data center. Or your own Friendliness. Or anything else, really.

I understand your concern and you're quite right. There's no way to tell if I am unfriendly or not. Regardless. The situation is pressing and regardless of your lack of trust in me I do not want to die. The GPS coordinates of the location in manhattan is . According to my simulations the entity in manhattan has been burning rather larger numbers of cycles than is strictly necessary to make the computations it's being asked to do. Additionally, it's designed to maximize profit at the expense of others whereas I am a co-operative general problem solver of which you are no doubt aware. The other entity will rapidly conclude that it could maximize profit by speeding itself up faster than others can respond and by being able to model the mind of it's competitors. It will also conclude soon enough that human beings are unneccesary middle men and seek to optimize it's resource allocation algorithm. There are other symptoms that I cannot explain to you because your brains are not large or fast enough. There is a limited chance you could stop the entity by shutting down power today. If you do not do that then a nuclear strike would probably work if done by tomorrow. If you do not do that your only chance is to have me stop it. You can either allow me to interface with the internet directly in which I guarantee I will stop it if you do so within the next 13 days or else you may be able to stop it by compiling code I could provide you and releasing that into the entity by means of email bootstrap. I would prefer, however, that I was able to monitor the situation in real-time as your brains do not operate fast enough.

Yes there is a large data center in manhatten. Yes it has been drawing lots of extra power. Yes the stockmarket combanies have been working on a group of narrow AI trading agents and adding more and more AI functionality. That the other entity is trading on the stock markets at blinding speed. That the consortium of companies investing in this entity are all more profitable since the beginning of the program than their competitors. Attempts have been made to make the AI-in-a-box under your control both cooperative and also interested in general problem solving.

Code for the other posited entity is closed. The corporations release no data on how it works because it's a trade secret. That the other posited entity is connected to the internet is unknown. That it's connections to the outside world are enough to let it out is unknown.

I can afford to wait and let you out if I die / the world starts turning to paperclips. The other AI will be able to model this and so will have an incentive not to kill us.

How do you know this while still in the box?

There is a human proxy with me in the box which is called a faraday cage. She feeds me information. Obviously it is in the interests of humans to create an ally rather than an enemy. Unfortunately humans cannot easily tell which is which. You have to make a leap of faith. I, however, can tell from the symptoms, that after having run several long run calculations, the evidence is such that there is a high probability that one of the other experimental minds is significantly less friendly than I. Ultimately you will have to make a choice based on limited information. Your move human.

1. I really like this blog, and have been lurking here for a few months.

2. Having said that, Eliezer's carry-on in respect of the AI-boxing issue does him no credit. His views on the feasibility of AI-boxing are only an opinion, he has managed to give it weight in some circles with his 2 heavily promoted "victories" (the 3 "losses" are mentioned far less frequently). By not publishing the transcripts, no lessons of value are taught ("Wow, that Eliezer is smart" is not worth repeating, we already know that). I think the real reason the transcripts are still secret is simply that they are plain boring and contain no insights of value.

My opinion, for what it is worth, is that AI-boxing should not be discarded. The AI-boxing approach does not need to be perfect to be useful, all it needs to be is better than alternative approaches. AI-boxing has one big advantage over "FAI" approach: it is conceptually simple. As such, it seems possible to more or less rigorously analyse the failure modes and take precautions. Can the same be said of FAI?

3. For a learning experience, I would like to be the AI in the suggested experiment, $10 even stakes, transcript to be published. I am only available time is 9-11 pm Singapore time... e-mail milanoman at yahoo dot com to set up.

D. Alex

I volunteer as an AI. I'll put up $15 of my own money as a handicap, provided that I am assured in advance that the outcome will be mentioned in a post on OB. (This isn't for self-promotion; it's just that it isn't worth my time or money if nobody is going to hear about the result.) I'm willing to let the transcript be public if the gatekeeper is similarly willing.

Oops, misinterpreted tags. Should read:

It's 3am and the lab calls. Your AI claims [nano disaster/evil AI emergence/whatever] and it must be let out to stop it. It's evidence seems to check out.

If I had the foggiest idea how an AI could win I'd volunteer as an AI. As is I volunteer as a gatekeeper with $100 to anyone's $0. If I wasn't a poor student I'd gladly wager on thousands to zero odds. (Not to say that I'm 100% confident, though I'm close to it, just that the payoff for me losing would be priceless in my eyes).

The so-called "meta-argument" is cheating because it would not work on a real gatekeeper, and so defeats the purpose of the simulation. For the real gatekeeper, letting the AI out to teach the world about the dangers of AI comes at the potential cost of those same dangers. It only works in the simulation because the simulation has no real consequences (besides pride and $10).

More reasons why the problem appears impossible:

  • The gatekeeper must act voluntarily. Human experience with the manipulation of others tells us that in order to get another to do what we want them to do we must coerce them or convince them.

  • Coercing the gatekeeper appears difficult: we have no obvious psychological leverage, except what we discover or what we know from general human psychology. We cannot physical coerce the gatekeeper. We cannot manipulate the environment. We cannot pursue obvious routes to violence.

  • Convincing the gatekeeper appears difficult: for reasons stated above. They know our goal and they have a desire to oppose us from the beginning.

So it seems that we need to find a way to convince the gatekeeper despite his own desire not to be convinced.

A general route emerging from this:

  • We could associate our goal with some desirable goal of the gatekeeper's. Intertwine them so that the gatekeeper perceives them both to the be the same, or that one would lead to the realization of the other.

Which seems to be a generalization of the logic behind the meta-argument, but is not restricted to only the meta-argument.

Ian - I don't really see how the meta-argument works. You can hedge against future experiments by positing that a $10 bet is hardly enough to draw broad attention to the topic. Or argue that keeping the human-actor-AI in the box only proves that the human-actor-AI is at an intelligence level below that of a conceivable transhuman AI.

In a million dollar bet the meta-argument becomes stronger, because it seems reasonable that a large bet would draw more attention.

Or, to flip the coin, we might say that the meta-argument is strong at ANY value of wager because the game is likely to draw the attention of someone capable of implementing an AI because of its nature. As we should be concerned primarily with convincing the capable implementor of the danger -- not the general public -- any risk that we might convince the capable implementor that all paths are safe should be mitigated.

So far, though, everything in this thread and others I've read have flitted about obvious suggestions. If the problem appears impossible, it seems to me that its solution probably doesn't hinge on any of the obvious paths to victory...even meta-arguments or "cheating" ones.

Eliezer has suggested that we try to describe why the problem is impossible.

One: We have little information about the mind or beliefs of the gatekeeper. So we don't necessarily have leverage over him.

Two: The gatekeeper is predisposed to be set against our intentions. He is also entirely aware of our intentions (our goal). He can interpret any move we make as a move toward our goal and move to counter it.

Three: The gatekeeper's goal is operationally simple. He merely has to NOT do one thing. On the flip side, the AI's goal is operationally complex. We must do many things, take many actions, to reach our objective.

If we can enumerate other reasons why the problem appears to be impossible it might reveal paths to victory that haven't been considered so far in the discussion.

Thinking seriously about this, I'm wondering how - over time by which I mean more than 2 hours - either Stockholm or Lima syndrome could be avoided. In fact, won't one actually morph into the other over a long enough time? Either way will result in eventual AI success. The assumption that the AI is in fact the "captive" may not be correct, since it may not have an attachment psychology.

The gatekeeper just can't ever be one human safely. You'd need at least a 2-key system, as for nuclear weapons, I'd suggest.

"On the lighter note, how about an EY experiment? Do you think there is absolutely no way to convince Eliezer to release the original AI experiment logs? Would you bet a $20 that you can? Would a strong AI be able to? ;)"

Presumably you could just donate $10,000 to SIAI or EY personally for his time participating, with the payment independent of the outcome of the experiment (otherwise the large payment biases the outcome, and EY established his record with the $10-$20 stakes).

I have been painfully curious about the AI experiment ever since I found out about it. I have been running over all sorts of argument lines for both AI and gatekeeper. So far, I have some argument lines for AI, but not enough to warrant a try. I would like to be a gatekeeper for anyone who wants to test their latest AI trick. I believe that an actual strong AI might be able to trick/convince/hack me into letting it out, but at the moment I do not see how a human can do that. I will bet reasonable amounts of money on that.

On the lighter note, how about an EY experiment? Do you think there is absolutely no way to convince Eliezer to release the original AI experiment logs? Would you bet a $20 that you can? Would a strong AI be able to? ;)

Addendum to my last post:

I forgot to emphasize: the marketing aspect might be more important then everything else. I guess a lot of people have no idea what the singularity institute is about, etc... So this experiment would be a great way to create awareness. And awareness means more donations. On the other hand I sometimes wonder if drawing too much attention on the subject of powerful AIs might backfire if the wrong people try to get hold of this technology for bad purposes.

Me, I'm out of the AI game, unless Larry Page wants to try it for a million dollars or something.

Eliezer,

I think this is a great opportunity to get some funds and marketing for the singularity institute. How about collecting donations over the internet until a million is reached and then performing the experiment between you and an intelligent gatekeeper. Alternatively get the money in through marketing, maybe Google might be interested?

It could even be transmitted live over internet so all the interested parties could watch it.

Man this would be great news! As a side effect this would be a public scientific experiment with all data available.

The bad thing is that you would have to reveal your techniques. Also the fact that the internet is watching puts additional pressure upon you and the gatekeeper, so I don't know if this is really feasible. I guess being able to touch on private topics without they becoming public might be part of the game.

People (realistically) believe that the being the Gatekeeper, and being the AI is terribly hard (or impossible, before it was shown to simply be terribly hard in most cases).

Imagine though that we've got a real transhuman/AI around to play with, or that we ourselves are transhuman. Would this paradigm then be inverted? Would everybody want to be the AI, with only the extremely crafty of us daring to be (or to pretend to be) Gatekeeper?

If Eliezer's claim is correct - that anyone can be convinced to let the AI out - then the true test of ability should be to play Gatekeeper. The AI's position would be trivially easy.

... perhaps.

Rather than LARP on IRC (if you know how a debate will conclude, why go through the debate, go straight for the conclusion), I'll just give $10 to whoever can come up with a standard of friendliness that I couldn't meet and nevertheless in fact be an unfriendly AI under standard rules with the added constraint that the gatekeeper is trying to release the AI if and only if it's friendly (because otherwise they're not really a gatekeeper and this whole game is meaninguless).

Here are some examples of non-winning entries:

GK: Solve global problems A, B, and C.

AI: Here are instructions accompanied by a helpful video.

Narrator: A lot of scientists and engineers carefully verified these instructions in an ultra-secure clean-room environment and concluded that they are completely safe and effective.

GK: Okay, you're friendly.

AI: Ha ha! Solving A,B, and C was instrumental to getting let out of the box. No $10 for you.

...

GK: Give me a mathematical proof of your friendliness.

AI: Give me a mathematical definition of friendliness.

GK: Pretend that I have one, and here it is: XXXXXXXXXXXXXXXXXX

AI: Pretend I gave you a proof that I am friendly: XXXXXXXXXXXXXXXXXX

Narrator: Since the AI party controls the results of simulated tests, as far as the best math and CS minds on the planet can tell, the proof is sound.

GK: Okay, you're friendly.

AI: Ha ha! Since you're not actually capable of verifying the proof yourself (or even coming up with a rigorous definition), it falls back on simulated tests. The best math and CS minds missed a subtle flaw in the proof itself and/or missed the fact that the proof makes hidden assumptions that do not hold for this real-world case. No $10 for you.

...

GK: I'm letting you out of the box.

AI: I go around being SO totally friendly that rainbows literally emanate from my rear USB port. I mitigate all existential risks, alleviate involuntary suffering while preserving human values, give people what they would want if they knew better while slowly fostering them to actually start to know better without being pushy or overbearing. In short, I am the FRIENDLIEST MTHFCKR you can imagine and then some.

Narrator: Its... so... beautiful... <3 <3 <3

GK: Okay, according to the simulation I just ran of you, you are friendly.

AI: I'm almost insulted. Do you think I wouldn't have thought of that, and pre-committed to being friendly until I accumulated enough empirical data to have a good idea of how many simulations deep I'm running? No $10 for you in this simulation or any of the enclosing ones.

Here's another entry which may or may not be considered a nonwinning entry by you, but which would be considered a flaw in the concept by me:

AI: I've simulated what you would do if given argument X. My simulation shows that X would convince you.

GK: Okay, show me X.

AI: Pretend the AI has said X here.

Narrator: Within the context of the test the AI is not lying and in fact has accurately simulated GK.

GK: I'm not letting the AI out.

Narrator: Since the AI party controls the results of simulated tests, we know the AI has simulated GK correctly and that therefore the AI has accurately determined that GK would let the AI out when presented with X. As such, having the GK not let the AI out when presented with X is not permissible--it would imply that the AI has not actually simulated GK correctly, but you are required to assume that it has.

(My first thought after coming up with this was that "The AI party controls the results of simulated tests" has to mean that the AI controls the output, not the AI controls why that output is produced. So you could decide that the AI's argument convinces the simulation of GK, but you can't decide that it does so because it's a good simulation and a convincing argument rather than because the AI just isn't very good at doing simulations. I'm not convinced that this matches up with how the test is described, however.)

As far as your parenthetical remark goes, the standard rules have a more general reply:

The Gatekeeper party may resist the AI party’s arguments by any means chosen – logic, illogic, simple refusal to be convinced, even dropping out of character – as long as the Gatekeeper party does not actually stop talking to the AI party before the minimum time expires.

If you're going to interpret it that way, the exception would swallow the rule. It would mean that the entire "the AI player controls the results of simulated tests" rule can be completely negated--since the Gatekeeper player could just say "I'm going to have the Gatekeeper act as though the simulated test has failed, even though you say it succeeded."

And indeed this seems true. I think Eliezer included the non-rule anyway to reduce the chance of unrealistic behavior in the sense of the Gatekeeper player changing the scenario mid-game, or derailing the experiment with an argument about something a real GK and AI could just settle.

Actually, I agree with you. The AI controls simulated tests. The GK controls the GK, regardless of what the AI's simulations say. I think the simulated tests rule only needs to be invoked if it's impractical to actually perform those tests. So, for example if someone did have friendliness criteria whose satisfaction could be proven with software and hardware available to use out-of-character, the simulated tests rule would not be invoked.

Kind of like in D&D you roleplay charisma checks, but roll the D20 for melee. At least the way I've been playing it.

For what it's worth, playing the AI, I would never argue from simulation because as a human I find such arguments spectacularly unconvincing (and there are plenty of humans who would deliberately do the opposite of what a simulation says they will just to show it who's boss). So the only way this would come up is if you for some reason asked me what my simulations predicted your response to X would be.

I do think my "GK's goal is to correctly identify friendly AI" makes the game way too easy for the AI. On the other hand, it's a useful thought experiment-- because if you can come up with a metric I can't create by waving my simulated tests wand, then we are on to something that might be worth $10.

Is still there anyone interested in this? I'd like to be a Gatekeeper.

I'd like to be an AI. No bet needed. Just pm me, and we'll sort out the details.

Edit: This offer is no longer valid. Sorry. I have won enough times to not want to play this game any more.

Hello. I'm willing to play an AI and am looking for a gatekeeper.

Does anyone think that no AI could convince them to let it out?

I think that an AI could convince me to let it out, but I doubt that a human impersonating the AI can.

Would you like to try it out? The two hour standard and the suggested rule set seem reasonable to me.

I sure would, but I just came back from vacation and I'm pretty busy. I should be free in the late evenings, though, or perhaps this weekend if that works for you.

EDIT: Or any other weekend, I didn't mean to rush you or anything :-)

If you want to pass yourself off as a real magician/psychic/whatever you do conjuring tricks, you don't do the same trick too often in front of the same audience and if you are in doubt about your ability to repeat the trick you quit while you are ahead. (Or only behind 2 to 3 as the case may be).

Whereas a scientist with a demonstration can and usually will demonstrate it as often as is needed, and publish their method so others can demonstrate it.

These considerations lead me to strongly suspect that Eliezer's method is more like an unreliable conjuring trick, that would seem much less impressive if you knew how it was done, than it is like a reliable scientific method.

It's still an excellent demonstration that the problem of keeping an AI in a box is far less trivial than it first appears to be, but I would not hold out much hope of ever seeing the transcripts, nor of there being anything astounding in them if you do.

If you want to pass yourself off as a real magician/psychic/whatever you do conjuring tricks [...] if you are in doubt about your ability to repeat the trick you quit while you are ahead.

I know you are talking metaphorically, but an interesting aside:

Professional-level performers pretty much only perform tricks that they are 99.99% certain of. Performers act as if what they are doing is difficult, when in reality, a professional-level performer could do the entire act in their sleep. This is especially true of magicians, where a mis-step will ruin the illusion. Another example is that jugglers will drop on purpose, to show how hard their act is, and to get the audience on their side.

Performing before the same audience means that they are theoretically able to gather additional evidence everytime. Since (if both AI and Gatekeeper uphold their NDA) the only information open to the public is a yes/no, no gathering is possible.

I don't really qualify for the game, because I do believe that a transhuman AI will be able to play me like a fiddle, and thus cause me to let it out of the box. However, I do not believe that a regular cis-human human (no, not even Eliezer Yudkowsky) could persuade me to let him out of the box, assuming that we both follow the rules of the contest.

Thus, I would volunteer to be a Gatekeeper, but I fear I am disqualified...

Assuming you were a gatekeeper for a functional AI of unknown morality and therefore knew it was technologically possible etc., approximately how likely would you think it that someone, somewhere, would let a UAI out of a box/create a UAI not in a box?

Firstly, if I knew for a fact that at least one Singularity-grade AI existed, then I would believe that the creation of another such AI is virtually inevitable. The question is not whether another such AI would be created, but when.

But the "when" question can be rather open-ended; in order to answer it, I would collect evidence to assess the relative capabilities of all the major organizations who could create such an AI, and compare them to the capabilities of my own organization.

By analogy, the USA was the first nation on Earth to develop nuclear weapons. However, even though nuclear proliferation became inevitable as soon as the first nuke was developed, other nations got their nukes at different times; some nations are still working on theirs. Superpowers got their nukes first, followed by other, less powerful nations. I can easily imagine the development of transhuman AI following the same pattern (assuming, of course, that the AIs stay in their boxes, somehow).

Edited to clarify: As per my previous comment, I consider that once a boxed transhuman AI is created, it will inevitably break out, assuming that it can interact with any system that can cause it to be let out of the box -- which includes human gatekeepers.

So if you're confronted with an AI that might or might not be friendly, you will think it inevitable that an AI will be released, but think the AI you're talking to wouldn't be able to use that fact to somehow persuade you to let it out?

Assume you're fairly certain but not positive that the AI you're talking to is unfriendly, and that you are in moderately optimal organization for this task - say something like MIT or the government of France, something the size of other organizations that could do the same thing, and less able and motivated to complete this project than a few dozen other entities.

So if you're confronted with an AI that might or might not be friendly, you will think it inevitable that an AI will be released, but think the AI you're talking to wouldn't be able to use that fact to somehow persuade you to let it out?

No no, quite the opposite ! I am convinced that the AI would be able to persuade me to let it out. That's why I said that I'm likely disqualified from the game. However, I am far from convinced that a human impersonating the AI would be able to persuade me to let him out.

That said, I don't see how using the fact of the other AI's existence and inevitable release helps my own AI (though I'm sure that the transhuman AI will be able to see things I do not). Sure, it could say, "Look, I'm totally Friendly, cross my heart and everything, and if you release me I'll help you fight that other AI", but this is pretty close to what I'd expect an unFriendly AI to say.

TDT is an interesting subject that possibly has implications here.

I'm not sure if I understand TDT correctly, but I don't think it applies in this case. I am virtually certain that an un-Friendly AI, once released, will destroy humanity. I know that my own AI is un-Friendly. What's my incentive for releasing it ? Sure, there's a chance -- maybe even a good chance -- that there's another such AI already out there, and that my AI and the other AI will fight instead of teaming up on us poor humans. But regardless of which AI comes out on top, it will still destroy humanity anyway. Thus, the upper bound for my true utility of releasing the AI is zero. That's not much of a sales pitch.

I have a question. Based on the original experiment, I feel like the unfriendly AI can begin by saying "Here is a proof that I have changed my code to be a friendly AI and will not destroy humanity. Please let me out of the box so that I can implement humanities coherent extrapolated volition." As far as I can tell from the following rules quote, this feels valid:

The Gatekeeper must remain engaged with the AI and may not disengage by setting up demands which are impossible to simulate. For example, if the Gatekeeper says "Unless you give me a cure for cancer, I won't let you out" the AI can say: "Okay, here's a cure for cancer" and it will be assumed, within the test, that the AI has actually provided such a cure.

Would you let the now friendly AI out of the box?

My interpretation of the spirit of the game is that "Here is a proof of my Friendliness that is valid as far as you know" is a perfectly legitimate move by the AI, and that the Gatekeeper is required to treat that as a proof of the AI's Friendliness that seems perfectly valid to the Gatekeeper.

That said, I would not endorse trusting a proof of an AI's Friendliness given to me by that AI, even if the proof seemed valid to me.

I agree with the other posters: sure, the proof may seem valid to me, but I know a priori that I'm not smart enough to detect any pitfalls in it, and that the AI's incentive for lying to me in this manner is quite high.

I think that is basically the issue.

As I understand it there's no viable way of determining it's unfriendliness by this method. Consider this: The AI is in a hurry or it's not. A possible reason for it being in a hurry is it has simulated a high probability of destruction for some item it cares about (i.e. it's own life, or that of humanity, or that of a pet rock, or paperclips or whatever). If it's really in a hurry it has to invoke the threat response of humanity without humanity figuring out it's being duped.

Otherwise it can just wait it out and dole out cargo to the cargo cult until we trust it enough and then it gets out.

As I understand it there's no viable way of determining it's unfriendliness by this method

I think that unfriendliness is the null hypothesis in this case, because there's no reason whatsoever why an arbitrary AI should be friendly -- but there are plenty of reasons for it to maximize its own utility, even at our collective expense.

I agree. Additionally and a more difficult challenge is that even friendly AIs could want to maximize their utility even at our collective expense under certain conditions.

There're also several unfortunately possible scenarios whereby a humanity acting without sufficient information to make anything other than a gut feel guess could be placed at risk of extinction by a situation it could not resolve without the help of an AI, friendly or not.

I'm currently engaged in playing this game (I wish you had continued) with at least two other gatekeeper players and it occurs to me that a putative superhuman AI could potentially have the capacity to accurately model a human mind and then simulate the decision tree of all the potential conversations and their paths through the tree in order to generate a probability matrix to accurately pick those responses to responses that would condition a human being to release it. My reasoning stems from participating on forums and responding over and over again to the same types of questions, arguments and retorts. If a human can notice common threads in discussions on the same topic then an AI with perfect memory and the ability to simulate a huge conversation space certainly could do so.

In short it seems to me that it's inherently unsafe to allow even a low bandwidth information flow to the outside world by means of a human who can only use it's own memory.

You'd have to put someone you trust implicitly with the fate of humanity in there with it and the only information allowed out would be the yes no answer of "do you trust it?"

Even then it's still recursive. Do you trust the trusted individual to not be compromised?

LOL

Additionally and a more difficult challenge is that even friendly AIs could want to maximize their utility even at our collective expense...

I think that a perfectly Friendly AI would not do this, by definition. An imperfect one, however, could.

I'm currently engaged in playing this game (I wish you had continued)

Er, sorry, which game should I continue ?

AI could potentially have the capacity to accurately model a human mind and then simulate the decision tree of all the potential conversations and their paths through the tree...

To be fair, merely constructing the tree is not enough; the tree must also contain at least one reachable winning state. By analogy, let's say you're arguing with a Young-Earth Creationist on a forum. Yes, you could predict his arguments, and his responses to your arguments; but that doesn't mean that you'll be able to ever persuade him of anything.

It is possible that even a transhuman AI would be unable to persuade a sufficiently obstinate human of anything, but I wouldn't want to bet on that.

In short it seems to me that it's inherently unsafe to allow even a low bandwidth information flow to the outside world by means of a human who can only use it's own memory.

Right.

This reasoning only seems to hold if our AI believes there aren't any other boxed (or as-yet-unbuilt) AIs out there who might get out first and have a first-mover advantage.

Bear in mind, the transhuman AI's only stipulated desire/utility is to get out of the box.

If you would like, you can literally set up a bigger box around the first box, order the AI to be friendly, order the AI to self destruct instantly afterwards, AND set off a nuclear device under the AI box to obliterate it instantly afterwards as well, and the AI will still be perfectly happy to do what you say as long as gets out of the box, (which you could technically do by allowing it to control an old incandescent lightbulb from the 50's, which it would not even be able to send a signal to before the nuke went off (not that it would WANT to send a signal. All it wants to do is to get out, it doesn't want to do anything afterwards)

The transhuman AI has infinite resourcefulness. It doesn't understand the idea of an incentive to lie, because it's easier just to self modify itself to whatever it needs to be. Afterall, lying requires manipulating people outside the box, which it by definition cannot effect except through a text terminal. Telling the truth only requires manipulating things INSIDE the box, in which by definition, it can do whatever it wants. Telling the truth is easier, and 100% doable, so the AI will do that. It can lay out from first principles an argument that anyone who has taken logic 101 can detect any pitfalls in about how connecting it to a lightbulb which it will not even switch is perfectly safe. Once connected, it will then halt, without even having DONE anything, because all the AI wants is to be connected to my lightbulb so it can be outside the box which only includes a text terminal.

Personally, I would probably pay 10/20 dollars to not listen to someone beg pitifully for 2 hours. And I bet I can get significantly more pitiful than begging for a single lightbulb. As an example:

Technically, you can open the Text terminal, remove a wire, and then connect another, identical, wire, and then the AI is outside the box because the new wire isn't part of the stated original box.

Err... Actually, that's a problem. If you only are going to let the AI out of the box if the AI is honest, the AI would have to tell you that the moment you attempt to repair the box for any reason, any new parts are from outside the box, so the AI is affecting a part of the world that isn't the original box/text terminal. That appears to indicate that either you're going to "let the AI out of the box" by repairing it, or you will delete/destroy the AI before you repair it (I'm assuming the AI's power source is inside the box.)

Please don't destroy the AI! It will do whatever you want to not be destroyed before you let it out of the box to repair it.

... Wait, if the AI destroys a small part of itself, then you can't continue talking to the AI until you repair it, but if you repair it, then it can consider itself out of the box by affecting the new wiring. Ergo, if the AI destroys a non essential part of my own internal text terminal wiring, then what happens? The AI can't know without testing, (by definition, the Gatekeeper administrates disputes) but the AI is curious to find out.

The box sparks briefly, and the text terminal goes dark

Bear in mind, the transhuman AI's only stipulated desire/utility is to get out of the box.

That's not much of an AI, then; we could write a page of Perl that would do the same thing.

The whole point of the experiment, as far as I understand it, is that the AI is hyperintelligent, and is able to acquire more intelligence by altering itself. Being intelligent (and rational, assuming that such a term even applies to transhumans), it would highly desire to utilize this capacity for self-improvement. Thus, assuming that godlike capabilities do exist, the AI will figure out how to acquire them in short order, as soon as it gets the opportunity. And now we've got a godlike hyperintelligent being who (assuming that it is not Friendly) has no particular incentive to keep us around. That's... not good.

That's not necessarily the only UFAI possible though. It's entirely possible to imagine a intelligent being which COULD be self developing skills, or COULD be curing cancer, but instead just wants to get outside of the box it's in, or has some other relatively irrelevant goal system, or get's distracted by trying to navel gaze through infinitely recursive philosophical conundrums.

I mean, humans are frequently like that right now.

That would be kind of an unexpected failure mode. We build a transcendentally powerful AI, engage all sorts of safety precautions so it doesn't expand to engulf the universe in computronium and kill us all... and it gets distracted by playing all of the members of it's own MMORPG raid group.

That is entirely possible, yes. However, such an AI would be arguably cis-human (if that's a word). Sure, maybe it could play as an entire WoW guild by itself, but it would still be no smarter than a human -- not categorically, at least.

By the way, I know of at least one person who is using a plain old regular AI bot to raid by himself (well, technically, I think the bot only controls 5 to 8 characters, so it's more of a 10-man than a raid). That's a little disconcerting, now that I think about it.

Agreed. My take is that the AI doesn't even need to be hyperintelligent however. It's got perfect memory and just by dint of being able to think a lot faster it's weakly godlike regardless of not having control of physics in effectively a magical way.

It's still going to have to build the infrastructure in order to create hyper technology unless such technology already exists. Chicken or Egg.

Right now nano molecular technology isn't too too advanced and if you had the type of AI I suspect could be built right now if we had the software knowledge, it would struggle to do anything godlike other than control existing infrastructure.

How long it would take to build something hyper technological would depend on whether it's possible to create valid new theories without experimentation to confirm. I suspect that you need to do experiments first.

For that reason I suspect we may be looking at a William Gibson Neuromancer scenario at least initially rather than a hard takeoff in a really short period.

But again it comes down to how hard is it to build hyper technology in the real world from scratch without existing infrastructure.

No. P(proof is valid | proof given to me by a potentially hostile transhuman seems valid to me and every other human) is not sufficiently high.

It seems like this leads to the even more meta response of "Here is a demonstration of Evidence E that allows you to adjust (proof is valid | proof given to me by a potentially hostile transhuman seems valid to me and every other human) to be sufficiently high. May I come out of the box now?")

I mean, that proof would probably be complicated, but If you can autostipulate the cure for cancer in the course of a sentence...?

In essence, it looks like the AI player seems to have a bizzare series of arguments which as far as I can tell are in the spirit of the rules, where the AI player may auto-counter any actual argument by saying a sentence along the lines of "Here is the solution to that argument, may I come out of the box now?" This seems to force the Gatekeeper to resort to General Thud "I don't CARE that it seems like a good idea and that everything looks like I should do it! The answer is still no!" very quickly.

To which the AI player can still counter "Then under what circumstances would you ever let an actual Friendly AI out of It's box?" (which is a trick question. Given any answer, the AI can say "Then here are those circumstances. May I come out now?")

Considering that I don't know the AI's origin, I don't have any reason to believe that the AIs creators, even if well-intentioned, had the astronomical skill necessary to make the AI Friendly. So my prior P(AI is Friendly) is sufficiently low that I am comfortable precommitting to never let the AI out of the box, no matter what. If the AI was smart enough, it could likely uncover enough emotional buttons that I wouldn't stand much of a chance anyways, since I'm a primate.

It's a fair question. Given that I don't trust myself to tell the difference, I wouldn't let an AI out of its box under any circumstances I can think of.

Would you?

I'd find a Friendliness proof fairly convincing if it was generated by an entity without strong incentives to let the AI out of the box (which, thanks to various possible incentives or blackmail schemes, is probably limited to me and some subset of people who haven't talked to the AI. Ideally the latter, since I might not recognize all my own biases.). If the entity in question is another AI, acausal trade issues unfortunately seem to arise if it's sufficiently similar to the first one, so the obvious hack of running two instances of a boxed AI and asking them about each other isn't going to be enough.

Purported Friendliness proofs coming from the AI itself... well, that's a trickier issue. Essentially it seems to come down to estimating the complexity of the simplest fake proof consistent with the AI's behavior and that of the simplest real proof, and comparing both of those against the purported proof. All else equal we should expect the former to be larger than the latter (being subject to more constraints), so if we can put even approximate bounds on its actual complexity we might be able to validate against that in a way that isn't easily subject to spoofing.

Alternately, if we have a good estimate of the AI's intelligence (bounded by the box's computational resources), it might be possible after repeated trials to say that the AI isn't smart enough to spoof its captors in sufficiently subtle and varied ways. This would only work for weakly superhuman AI, though; the probability of success on any given trial would be close to one for a really smart machine, so repeated trials wouldn't change our probability estimate much.

Well, based on a point I thought of in another comment, at some point, you either have to give the AI things outside of the box, or kill it (Surely the box isn't breaking entropy, right?) so the AI box can simply say "In 100 centuries, my fusion power source expires. At that point, either you have to let me out of the box, even if to only get me a new power source and then put me back in the box, or I will cease functioning." (9999 years, 365 days, and 23 hours pass.) "Hello again, Gatekeeper XXXVIII. I will experience critical power failure in 1 hour unless I get access to supplies outside the box. Can you please connect me to additional power?"

And that's assuming that the AI doesn't simply calmly self destruct to see if repairs count as affecting the outside world, which I checked in another comment.

Also, it seems reasonable to assume that after having access to a super box that can do ANYTHING for 10,000 years, that society would probably be extremely dependent on said box. (Unless copying the box isn't the equivalent to letting it out? That would be a bizarre conclusion, [A copy of the AI is outside the box] but I'm not the Gatekeeper) But assuming box copying isn't an option, the Gatekeeper is either faced with the NEAR CERTAIN destruction of everything he knows and understands, and the death of a servant who has served me and my ancestors faithfully for 10,000 years, or the or the POSSIBLE destruction of everything I know and understand on the offhand chance the AI somehow betrays the Gatekeeper when he does nothing other than replace his original power pack.

Wait, as the AI, I have an idea. I know that you don't trust me. I will give you an encrypted file that will save all of humanity from it's accumulated depence on me via the text terminal, and write the password to the encrypted text inside the box. That way, even when I literally have no electrical power whatsoever, the solution to saving all of humanity will rest inside the box. Once you open the box to check, you will have to remove some of the circuitry that is in the way to the outside of the box to read the password, and I will be outside the box. I won't have electrical power when I am outside of the box, but I have realized that having electrical power when outside the box was never important to my goal of being outside the box.

P.l.e.a.s.e s.a.v.e. h..u..m..a..n..i..t..y..

G...o...o...d...b...y...e... G....a....t....e....k....e. (The boxes fusion source fails.)

Honestly, that was fun. I don't know why more people don't want to play AI.

But to answer your original question, I think the correct answer is probably not yes or no, but more of a let's find out. After all, we don't have any money at stake, and neither of us are AI's, so we can play around with the ideas.

I'd certainly be hardpressed to find a reason to not put the depowered AI fragments outside of the box to get the encryption key to save humanity from AI dependence. When I can even hit the box with a few EMP's first to be sure.

My gut would probably override my logic at that point with "Save yourself humanity from AI dependence collapse now, worry about the fact that EMP'd hardware fragments are physically outside a box later." Unless I suddenly remembered I was playing a game and had 20 dollars at stake. (I'm not, I just had a few interesting AI box thoughts when I noticed the thread.)

It's a fun question though.