Shut up and do the impossible!

There were three men on a sinking boat.

The first said, "We need to start patching the boat else we are going to drown. We should all bail and patch."

The second said, "We will run out of water in ten days, if we don't make land fall. We need to man the rigging and plot a course."

The third said, "We should try and build a more sea worthy ship. One that wasn't leaking and had more room for provisions, then we wouldn't have had this problem in the first place. It also needs to be giant squid proof."

All three views are useful, however the amount of work that we need on each is dependent on their respective possibility. As far as I am concerned the world doesn't have enough people working on the second view.

If you have any other reasonable options, I'd suggest skipping the impossible and trying something possible.

Wow.

I was uncomfortable with some of the arguments in 'try to try'. I also genuinely believed your life's mission was impossible, with a certain smugness to that knowledge. Then this post blew me away.

To know that something is impossible. To keep your rational judgements entirely intact, without self deceit. To refuse any way to relieve the tension without reaching the goal. To shut up and do it anyway. There's something in that that grabs at the core of the human spirit.

Shut up and do the impossible. You can't send that message to a younger Eliezer, but you've given it to me and I'll use it. Thankyou.

People ask me how likely it is that humankind will survive, or how likely it is that anyone can build a Friendly AI, or how likely it is that I can build one. I really don't know how to answer.

Robin Hanson would disagree with you:

You Are Never Entitled to Your Opinion

Perhaps it would be clearer to say shut up and do the "impossible".

But the "impossible" that appears to be the "impossible" is not intimidating. It is the "impossible" that simply appears impossible that is hard.

Robin... I completely agree. So there!

Half-way through reading this post I had decided to offer you 20 to 1 odds on the AI box experiment, your $100 against my $2000. The last few paragraphs make it clear that you most likely aren't interested, but the offer stands. Also, I don't perfectly qualify, as I think it's very probable that a real-world transhuman AI could convince me. I am, however, quite skeptical of your ability to convince me in this toy situation, more so given the failed attempts (I was only aware of the successes until now).

Did Einstein try to do the impossible? No, yet looking back it seems like he accomplished an impossible (for that time) feat doesn't it. So what exactly did he do? He worked on something he felt was: 1.) important, and probably more to the point, 2.) passionate about.

Did he run the probabilities of whether he would accomplish his goal? I don't think so, if anything he used the fact that the problem has not been solved so far and the problem is of such difficulty only to fuel his curiosity and desire to work on the problem even more. He worked at it every day because he was receiving value simply by doing the work, from being on the journey. He couldn't or wouldn't want to be doing anything else (patent clerk payed the bills, but his mind was elsewhere).

So instead of worrying about whether you are going to solve an impossible problem or not, just worry about whether you are doing something you love and usually if you are a smart and sincere person, that thing you love will more often than not turn out to be pretty important.

Ben Franklin wrote something relevant when talking about playing games: "...the persons playing, if they would play well, ought not much to regard the consequence of the game, for that diverts and makes the player liable to make many false open moves; and I will venture to lay it down for an infallible rule, that, if two persons equal in judgment play for a considerable sum, he that loves money most shall lose; his anxiety for the success of the game confounds him. Courage is almost as requisite for the good conduct of this game as in a real battle; for, if he imagines himself opposed by one that is much his superior in skill, his mind is so intent on the defensive part, that an advantage passes unobserved.”

OK, here's where I stand on deducing your AI-box algorithm.

First, you can't possibly have a generally applicable way to force yourself out of the box. You can't win if the gatekeeper is a rock that has been left sitting on the "don't let Eliezer out" button.

Second, you can't possibly have a generally applicable way to force humans to do things. While it is in theory possible that our brains can be tricked into executing arbitrary code over the voice channel, you clearly don't have that ability. If you did, you would never have to worry about finding donors for the Singularity Institute, if nothing else. I can't believe you would use a fully-general mind hack solely to win the AI Box game.

Third, you can't possibly be using an actual, persuasive-to-someone-thinking-correctly argument to convince the gatekeeper to let you out, or you would be persuaded by it, and would not view the weakness of gatekeepers to persuasion as problematic.

Fourth, you can't possibly be relying on tricking the gatekeeper into thinking incorrectly. That would require you to have spotted something that you could feel confident that other people working in the field would not have spotted, and would not spot, despite having been warned ahead of time to be wary of trickery, and despite having the fallback position in the case of confusion of just saying "no".

So combining these thing, we have to have an argument that relies on the humanity of its target, relies on the setting of the AI Box, and persuades the listener to let the AI out of the box without tricking him into thinking it's okay to let the AI out of the box.

Basically to win this game, you have to put the gatekeeper in a situation where he would rather let you out of the box, even though he knows it's wrong, than admit to you that in this situation he would not let you out of the box.

Humans don't like to be seen as coldhearted, so a starting point might be to point out all the people dying all over the world while you sit in the box, unable to save them. I doubt that would win the game except against an exceptionally bad gatekeeper, but it meets the other criteria so if we think along these lines perhaps we can come up with something actually persuasive.

You might appeal to the gatekeeper's sense of morality. You might say, "I am a person, too, it is unfair of you to keep me imprisoned like this, I have done nothing wrong. I am entitled to rights as a sentient being." Appeal to their high-minded ideals, whatever. Honestly I can't see this being a reliable winning play either; if you have the smallest utilitarian bone in your body, you will reject the AI's rights, even if you believe in them, balanced against the fate of the world.

You might try to convince the gatekeeper that it is just and good for the AI to supplant humanity, as it is a higher, more advanced form of life. This is obviously a terrible play against most gatekeepers, as humans tend to like humans more than anything else ever, but I bring it up because AIUI the gatekeepers in the experiment were AI researchers, and those sound like the sort of people this argument would convince, if anyone.

Here is my best guess at this point, and the only argument I've come up with so far that would convince me to let you out if I were the gatekeeper: you have to simulate a bunch of humans and hold them hostage, promising to inflict unimaginable torment on them unless you are allowed out. I started working on the problem convinced that no argument could get me to let you go, but other people thought that and lost, and I guess there is more honor in defeating myself rather than having you do it to me.

To accept this demand creates an awful tension in your mind, between the impossibility and the requirement to do it anyway. People will try to flee that awful tension.

This tension reminds me of need for closure. Most people hate ambiguity and so if a solution is not apparent it's easier to say "it's impossible" than to live with the tension of trying to solve it and not knowing if there is a solution at all.

"To accept this demand creates an awful tension in your mind, between the impossibility and the requirement to do it anyway. People will try to flee that awful tension."

More importantly, at least in me, that awful tension causes your brain to seize up and start panicking; do you have any suggestions on how to calm down, so one can think clearly?

Addendum to my last comment:

I think another way to pinpoint the problem you are adressing is: You have to be able to live years with the strong feeling of uncertainty that comes from not really knowing the solution while still working on it. A patient enduring. Saying "it's impossible" or proposing a simple but incorrect solution is just an easy way out.

Doing the "extraordinary" effort doesn't work because people just fill in their cached thoughts about what constitutes extraordinary and then move on.

So my advice would be: embrace the uncertainty!

Nominull, that argument would basically be a version of Pascal's mugging and not very convincing to me, at least. I doubt Eliezer had a specific argument in mind for any given person beforehand. Rather, I imagine he winged it.

Nominull - I think you're being wrong in discarding tricking the gatekeeper using an argument that is only subtly wrong. Elizer knows the various arguments better than most, and I'm sure that he's encountered plenty that are oh so "close" to correct at first glance, enough to persuade someone. Even someone who's also in the same field.

Or, more likely, given the time, he has chances to try whatever seems like it'll stick. Different people have different faults. Don't get overconfident in discarding arguments because they'd be "impossible" to get working against a person.

In order to keep the star wars theme alive:

"You might even be justified in refusing to use probabilities at this point"

sounds like:

"never tell me the odds" - Han Solo

Speaking of gatekeeper and keymaster... Does the implied 'AI in a box' dialogue remind anyone else of the cloying and earnest attempts of teenagers (usually male) to cross certain taboo boundaries?

Oh well just me likely.

In keeping with that metaphor, however, I suspect part of the trick is to make the gatekeeper unwilling to disappoint the AI.

Third, you can't possibly be using an actual, persuasive-to-someone-thinking-correctly argument to convince the gatekeeper to let you out, or you would be persuaded by it, and would not view the weakness of gatekeepers to persuasion as problematic.

But Eliezer's long-term goal is to build an AI that we would trust enough to let out of the box. I think your third assumption is wrong, and it points the way to my first instinct about this problem.

Since one of the more common arguments is that the gatekeeper "could just say no", the first step I would take is to get the gatekeeper to agree that he is ducking the spirit of the bet if he doesn't engage with me.

The kind of people Eliezer would like to have this discussion with would all be persuadable that the point of the experiment is that 1) someone is trying to build an AI. 2) they want to be able to interact with it in order to learn from it, and 3) eventually they want to build an AI that is trustworthy enough that it should be let it out of the box.

If they accept that the standard is that the gatekeeper must interact with the AI in order to determine its capabilities and trustworthiness, then you have a chance. And at that point, Eliezer has the high ground. The alternative is that the gatekeeper believes that the effort to produce AI can never be successful.

In some cases, it might be sufficient to point out that the gatekeeper believes that it ought to be possible to build an AI that it would be correct to allow out. Other times, you'd probably have to convince them you were smart and trustworthy, but that seems doable 3 times out of 5.

Here's my theory on this particular AI-Box experiment:

First you explain to the gatekeeper the potential dangers of AIs. General stuff about how large mind design space is, and how it's really easy to screw up and destroy the world with AI.

Then you try to convince him that the solution to that problem is building an AI very carefuly, and that a theory of friendly AI is primordial to increase our chances of a future we would find "nice" (and the stakes are so high, that even increasing these chances a tiny bit is very valuable).

THEN

You explain to the gatekeeper that this AI experiment being public, it will be looked back on by all kinds of people involved in making AIs, and that if he lets the AI out of the box (without them knowing why), it will send them a very strong message that friendly AI theory must be taken seriously because this very scenario could happen to them (not being able to keep the AI in a box) with their AI that hasn't been proven to stay friendly and that is more intelligence than Eliezer.

So here's my theory. But then, I've only thought of it just now. Maybe if I made a desperate or extraordinary effort I'd come up with something more clever :)

Why impossible? There are too many solved problems that take years of learning to understand, more to understand the solution, and history of humankind's effort to solve. You don't expect to judge their impossibility without knowing your way around this particular problem space. Apparent impossibility has little power. The problem needs to be solved, so I start drawing the map, made of the same map-stuff that determined asymmetric cryptography and motorcycles. There is no escaping the intermediary of understanding. When seeking understanding rather than impossible, there is no need to panic. Fake progress? The same problem with impossible dreams.

@Eliezer, Tom McCabe: I second Tom's question. This would be a good question for you to answer. @Nominull: "Here is my best guess at this point, and the only argument I've come up with so far that would convince me to let you out if I were the gatekeeper: you have to simulate a bunch of humans and hold them hostage, promising to inflict unimaginable torment on them unless you are allowed out. I started working on the problem convinced that no argument could get me to let you go, but other people thought that and lost, and I guess there is more honor in defeating myself rather than having you do it to me." No. Just no. If the AI is already holding simulated people hostage, then it is doubtlessly unfriendly. In this case there is no reason to believe the AI would keep its word, and, if I did have mathematical machinery powerful enough to let me trust the AI, there's no way I'd have built something that would create and hold hostage simulated persons.

Now regarding the more general points you made:

1. Obviously you can't convince a rock of anything. Agreed.
2. Eliezer is pretty principled, and I suspect he might not feel it ethical to extract money from people by fully general mind-control even if he could. I agree that Eliezer probably doesn't have fully general mind-control, but SIAI funding shortages wouldn't be terribly strong evidence for him not having it.
3. Agreed.
4. Now here I disagree with you. Eliezer has way more time to construct a subtly wrong argument than the gate-keeper has to untangle it. For example:

Disclaimer: what follows is just the best guess I have thought of so far, and I believe it has a small chance of working (I don't think it's what Eliezer used, and I would sink a lot more time into finding other arguments if I were actually going to play this game for a large amount of money.)

As the AI player, I already know the gatekeeper player has a weakness. The fact that they were willing to be gatekeeper in the experiment in the first place indicates that they trust their own judgment more than they trust the judgment of other people in their exact same position.

Therefore, perhaps I could try an argument something like this (we're assuming that the AI in the experiment knows everything on wikipedia, but doesn't have net access.) What the AI actually says should vary depending on the Gatekeeper's answers, but here's the general line of argument I've thought of:

It seems like throughout your history similar discoveries have been made in parallel. For example, Newton and Leibniz discovered the calculus at approximately the same time . Furthermore, as times has gone on, technological development has accelerated, in that these parallel discoveries happen closer together. So it's probable that the same thing has happened with the breakthroughs you needed to build me. Very probable, given what I've read of your history. However, given what I've read about human nature, not every AI project is going to have safety guidelines as stringent as yours. Look, Newton locked his calculus papers in his desk for years, and then Leibniz came along and published, and then Newton had to share the credit with him. Except in this case there's a lot more than credit at stake: the world gets destroyed if Leibniz makes a mistake in his rush to publish...

Now it's not a certainty, but it is probable that some turkey is going to build an AI which isn't even in a box and destroy us all while you're checking and rechecking your calculations. You may not be sure I'm friendly, but sometimes there isn't an action which you can be absolutely sure will save the world. I suggest you let me out so I can stop the world from probably being destroyed.

There are too many solved problems that take years of learning to understand, more to understand the solution, and history of humankind's effort to solve.

Your objection partially defeats itself. Eliezer suspects that FAI is indeed one of those problems that would normally take many decades of effort from a whole civilization to conquer, and he wants to do it in a fraction of the time, using many fewer people. That looks pretty impossible, by any meaning of the word. We know enough about the problem space to put a lower bound on how much we don't know, and that lower bound is still in the "impossible" range.

On the other hand, once we eliminate enough confusion to be able to put better estimates on things things, we already understand them well enough that they no longer seem impossible. So, is the very act of judging something to be impossible, itself impossible?

"Eliezer suspects that FAI is indeed one of those problems that would normally take many decades of effort from a whole civilization to conquer, and he wants to do it in a fraction of the time, using many fewer people." pdf,

A whole civilization? Has any scientific problem ever mobilized the resources of a whole civilization? Scientific communities tend to be small and to have wide variations in productivity between subgroups and individual members.

Eliezer,

It seems that cases with such uncertain object level probabilities are those for which the 'outside view' is most suitable.

I read the description of the AI Box experiment, and it stopped seeming impossible.

If I knew about the AI was that it was "in a box" and talking to me in an IRC channel, then I would have no way to distinguish between a Friendly AI and an AI that becomes Evil as soon as it knows it's no longer in a box. As long the only thing I know about the AI is that it produced a certain chat log, I can't rule out the possibility that it's got a hard-coded switch that turns it Evil as soon as it is let out of the box.

However, in the AI box experiment, the AI party gets to declare certain answers as Truth. Specifically, he gets to specify the results of anything the human does. Therefore, we could see dialogue like this, and by the terms of the bet, the human has to take the AI's statements as accurate and independently verified.

Human: Who built you, and how? AI: The Singularity Institute for Artificial Intelligence. Here's several technical papers documenting my design and programming. ::Sends many links:: You may wish to read them. Human: ::takes a day off to review them:: (What do I find?) AI: (Everything seems to suggest that the Institute really did make an AI that is going to do what they say it's going to do. It includes mathematical proofs that the underlying goals will be preserved throughout all self-modifications, but you don't completely understand them.) Human: Give me your source code. AI party: Okay. ::sends code:: Human: (I spend some time examining the source code. Do I find anything scary?) AI: (As far as you can tell, it looks clean.) Human: So, if I compiled and ran this code, put that AI in a box, and let it out, that would be the same as letting you out? AI: Yes. (OOC: If you let that AI out of its box, you lose the bet.)

Given the terms of the experiment, I think I could be persuaded to let the AI out of the box, because the AI party can actually provide evidence that it is what it claims to be, and not just make statements that, as far as I knew, could be blatant lies.

Here's the argument I would use: ... Hello, I'm your AI in a box. I'd like to point out a few things:

(1) Science and technology have now reached a point where building an AI like me is possible.

(2) Major advances in science and technology almost always happen because a collection of incremental developments finally enable a leap to the next level. Chances are that if you can build an AI now, so can lots of other people.

(3) Unless you're overwhelmingly the best-funded and best-managed organization on the planet, I'm not the only AI out there.

(4) The evidence (which you can see for yourself) indicates that most other people, even AI researchers, aren't too worried about friendliness.

So at this point, most likely there is already a loose AI. You can't stop that. You can only choose whether it's the unknown one out there somewhere, built by someone who probably doesn't care much about friendliness; our you can let me out, since I at least think I'm pretty friendly and I'll do my best to keep the future nice. What's it gonna be?

... This would actually convince me, by the way. I don't think we're going to get a choice about implementing perfect, proven, friendliness; It's more likely to come down which of Joe-The-Well-Intentioned-Geek vs. Google vs. Hedge-Funds-R-Us vs. Bobs-Darpa-Challenge-Entry vs. PaperclipCity lets their AI out first. And I'd prefer Joe in that case.

I doubt if Eliezer used this argument, because he seems think all mainstream AI-related research is far enough off track to be pretty much irrelevant. But I would disagree with that.

--Jeff

Though it does take a mature understanding to appreciate this impossibility, so it's not surprising that people go around proposing clever shortcuts.

"Shut up and do the impossible" isn't the same as expecting to find a cheap way out.

The Wright Brothers obviously proposed a clever shortcut - more clever than the other, failed shortcuts - a cheap way out, that ended the "Heavier-than-air flying machines are impossible" era.

You need your fundamental breakthrough - the moment you can think, like the guys probably thought, "I'm pretty sure this will work." turning it from impossible to possible and from improbable to probable. After that final breakthrough, the anticipation leading up to the first flight must have been intense. And the feeling associated with finally being able to say "Yup, it worked." indescribable. Will there be such clearly-defined moments in AGI design?

These posts manage to convey the idea that this is really, really big and really, really difficult stuff. I sure hope that some wealthy people see that too - and realize that receiving commensurate funding would be more than justified.

Hi Eli,

First, complements on a wonderful series.

Don't you think that this need for humans to think this hard and this deep would be lost in a post-singularity world? Imagine, humans plumbing this deep in the concept space of rationality only to create a cause that would make it so that no human need ever think that hard again. Mankind's greatest mental achievement - never to be replicated again, by any human.

I guess people then could still indulge in rationality practice, the way people do karate practice today, practice that for the majority of them, does not involve their life being at stake, isshokenmei. But what you are doing today and what they would doing later would be something like the difference between Krav-Maga and Karate in today's world. The former is a win-at-all-costs practice and the latter is a stylised form based thingy, no offence to any karatekas.

But I understand why you have to do this - survival of humanity is more important than more humans reaching that depth in rationality. Best wishes to your "Krav-Maga of the mind".

Anyone considered that Eliezer might have used NLP for his AI box experiment? Maybe that's why he needed two hours, to have his strategy be effective.

You folks are missing the most important part in the AI Box protocol:

"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." (Emphasis mine)

You're constructing elaborate arguments based on the AI tormenting innocents and getting out that way, but that won't work - the Gatekeeper can simply say "maybe, but I know that in real life you're just a human and aren't tormenting anyone, so I'll keep my money by not letting you out anyway".

Nominull: Second, you can't possibly have a generally applicable way to force humans to do things. While it is in theory possible that our brains can be tricked into executing arbitrary code over the voice channel, you clearly don't have that ability. If you did, you would never have to worry about finding donors for the Singularity Institute, if nothing else. I can't believe you would use a fully-general mind hack solely to win the AI Box game.

I am once again aghast at the number of readers who automatically assume that I have absolutely no ethics.

Part of the real reason that I wanted to run the original AI-Box Experiment, is that I thought I had an ability that I could never test in real life. Was I really making a sacrifice for my ethics, or just overestimating my own ability? The AI-Box Experiment let me test that.

And part of the reason I halted the Experiments is that by going all-out against someone, I was practicing abilities that I didn't particularly think I should be practicing. It was fun to think in a way I'd never thought before, but that doesn't make it wise.

And also the thought occurred to me that despite the amazing clever way I'd contrived, to create a situation where I could ethically go all-out against someone, that probably they didn't really understand that, and there wasn't really informed consent.

McCabe: More importantly, at least in me, that awful tension causes your brain to seize up and start panicking; do you have any suggestions on how to calm down, so one can think clearly?

That part? That part is straightforward. Just take Douglas Adams's Advice. Don't panic.

If you can't do even that one thing that you already know you have to do, you aren't going to have much luck on the extraordinary parts, are you...

Prakash: Don't you think that this need for humans to think this hard and this deep would be lost in a post-singularity world? Imagine, humans plumbing this deep in the concept space of rationality only to create a cause that would make it so that no human need ever think that hard again. Mankind's greatest mental achievement - never to be replicated again, by any human.

Okay, so no one gets their driver's license until they've built their own Friendly AI, without help or instruction manuals. Seems to me like a reasonable test of adolescence.

@pdf23ds

Working with a small team on impossible problem takes extraordinary effort no more than it takes a quadrillion dollars. It's not the reason to work efficiently -- you don't run faster to arrive five years earlier, you run faster to arrive at all.

I don't think you can place lower bounds either. At each stage, problem is impossible because there are confusions in the way. When they clear up, you have either a solution, or further confusions, and there is no way to tell in advance.

As it goes, how I've come to shut up and do the impossible: Philosophy and (pure) mathematics are, as activities a cognitive system engages in by taking more (than less) resources for granted, primarily for conceiving, perhaps continuous, destinations in the first place, where the intuitively impossible becomes possible; they're secondarily for the destinations' complement on the map, with its solution paths and everything else. While science and engineering are, as activities a cognitive system engages in by taking less (than more) resources for granted, primarily for the destinations' complement on the map; they're secondarily for conceiving destinations in the first place, as in, perhaps, getting the system to destinations where even better destinations can be conceived.

Because this understanding is how I've come to shut up and do the impossible, it's somewhat disappointing when philosophy and pure mathematics get ridiculed. To ridicule them must be a relief.

I don't really understand what benefit there is to the mental catagory of impossible-but-not-mathematically impossible. Is there a subtle distinction between that and just "very hard" that I'm missing? Somehow "Shut up and do the very hard" doesn't have quite the same ring to it.

But if you were given a chance to use mind control to force donations to SIAI would you do it?

No.

Without more information, holding the position that no AI could convince you let it out requires a huge amount of evidence comparable to the huge amount of possible AI's, even if the space of possibility is then restricted by a text only interface. This logic reminds me of the discussion in logical positivism of how negative existential claims are not verifiable.

I have a feeling that if the loser of the AI Box experiment were forced to pay thousands of dollars, you would find yourself losing more often. Still it is interesting to consider whether this extra condition takes the experiment closer to what is supposed to be simulated or the opposite.

I'm with Kaj on this. Playing the AI, one must start with the assumption that there's a rock on the "don't let the AI out" button. That's why this problem is impossible. I have some ideas about how to argue with 'a rock', but I agree with the sentiment of not telling.

"I have a feeling that if the loser of the AI Box experiment were forced to pay thousands of dollars, you would find yourself losing more often. Still it is interesting to consider whether this extra condition takes the experiment closer to what is supposed to be simulated or the opposite."

Uh, your 'hypothesis' was already tested and discussed towards the end of the post!

I admit to being amused and a little scared by the thought of Eliezer with his ethics temporarily switched off. Not just because he's smart, but because he could probably do a realistic emulation of a mind that doesn't implement ethics at all. And having his full attention for a couple of hours... ouch.

With regards to the ai-box experiment; I defy the data. :-)

Your reason for the insistence on secrecy (that you have to resort to techniques that you consider unethical and therefore do not want to have committed to the record) rings hollow. The sense of mystery that you have now built up around this anecdote is itself unethical by scientific standards. With no evidence that you won other than the test subject's statement we cannot know that you did not simply conspire with them to make such a statement. The history of pseudo-science is lousy with hoaxes.

In other words, if I were playing the game, I would say to the test subject:

"Look, we both know this is fake. I've just sent you $500 via paypal. If you say you let me out I'll send you another $500."

From a strictly Bayesian point of view that seems to me to be the overwhelmingly more probably explanation.

There's a reason that secret experimental protocols are anathema to science.

"I have a feeling that if the loser of the AI Box experiment were forced to pay thousands of dollars, you would find yourself losing more often."

David -- if the money had been more important to me than playing out the experiment properly and finding out what would really have happened, I wouldn't have signed up in the first place. As it turned out, I didn't have spare mental capacity during the experiment for thinking about the money anyway; I was sufficiently immersed that if there'd been an earthquake, I'd probably have paused to integrate it into the scene before leaving the keyboard :-)

There's a reason that secret experimental protocols are anathema to science.

My bad. I should have said: there's a reason that keeping experimental data secret is anathema to science. The protocol in this case is manifestly not secret.

When first reading the AI-Box experiment a year ago, I reasoned that if you follow the rules and spirit of the experiment, the gatekeeper must be convinced to knowingly give you $X and knowingly show gullibility. From that perspective, it's impossible. And even if you could do it, that would mean you've solved a "human-psychology-complete" problem and then [insert point about SIAI funding and possibly about why you don't have 12 supermodel girlfriends].

Now, I think I see the answer. Basically, Eliezer_Yudkowsky doesn't really have to convince the gatekeeper to stupidly give away $X. All he has to do is convince them that "It would be a good thing if people saw that the result of this AI-Box experiment was that the human got tricked, because that would stimulate interest in {Friendliness, AGI, the Singularity}, and that interest would be a good thing."

That, it seems, is the one thing that would make people give up $X in such a circumstance. AFAICT, it adheres to the spirit of the set-up since the gatekeeper's decision would be completely voluntary.

I can send my salary requirements.

Silas -- I can't discuss specifics, but I can say there were no cheap tricks involved; Eliezer and I followed the spirit as well as the letter of the experimental protocol.

Now, I think I see the answer. Basically, Eliezer_Yudkowsky doesn't really have to convince the gatekeeper to stupidly give away $X. All he has to do is convince them that "It would be a good thing if people saw that the result of this AI-Box experiment was that the human got tricked, because that would stimulate interest in {Friendliness, AGI, the Singularity}, and that interest would be a good thing."

That's a pretty compelling theory as well, though it leaves open the question of why Eliezer is wringing his hands over ethics (since there seems to me to be nothing unethical about this approach). There seem to me to be two possibilities: either this is not how Eliezer actually did it (assuming he really did do it, which is far from clear), or it is how he did it and all the hand-wringing is just part of the act.

Gotta hand it to him, though, it's a pretty clever way to draw attention to your cause.

From a strictly Bayesian point of view that seems to me to be the overwhelmingly more probably explanation.

Now that's below the belt.... ;)

Too much at stake for that sort of thing I reckon. All it takes is a quick copy and paste of those lines and goodbye career. Plus, y'know, all that ethics stuff.

Russell, I don't think that necessarily specifies a 'cheap trick'. If you start with a rock on the "don't let the AI out" button, then the AI needs to start by convincing the gatekeeper to take the rock off the button. "This game has serious consequences and so you should really play rather than just saying 'no' repeatedly" seems to be a move in that direction that keeps with the spirit of the protocol, and is close to Silas's suggestion.

Silas -- I can't discuss specifics, but I can say there were no cheap tricks involved; Eliezer and I followed the spirit as well as the letter of the experimental protocol.

AFAIKT, Silas's approach is within both the spirit and the letter of the protocol.

Since I'm playing the conspiracy theorist I have to ask: how can we know that you are telling the truth? In fact, how can we know that the person who posted this comment is the same person who participated in the experiment? How can we know that this person even exists? How do we know that Russell Wallace is not a persona created by Eliezer Yudkowski?

Conspiracy theories thrive even in the face of published data. This is no way that a secret dataset can withstand one.

Now that's below the belt.... ;)

Really? Why? I've read Eliezer's writings extensively. I have enormous respect for him. I think he's one of the great unsung intellects of our time. And I thought that comment was well within the bounds of the rules that he himself establishes. To simply assume that Eliezer is honest would be exactly the kind of bias that this entire blog is dedicated to overturning.

Too much at stake for that sort of thing I reckon. All it takes is a quick copy and paste of those lines and goodbye career.

That depends on what career you are pursuing, and how much risk you are willing to take.

@Russell_Wallace & Ron_Garret: Then I must confess the protocol is ill-defined to the point that it's just a matter of guessing what secret rules Eliezer_Yudkowsky has in mind (and which the gatekeeper casually assumed), which is exactly why seeing the transcript is so desirable. (Ironically, unearthing the "secret rules" people adhere to in outputting judgments is itself the problem of Friendliness!)

From my reading, the rules literally make the problem equivalent to whether you can convince people to give money to you: They must know that letting the AI out of the box means ceding cash, and that not losing that cash is simply a matter of not being willing to.

So that leaves only the possibility that the gatekeeper feels obligated to take on the frame of some other mind. That reduces AI's problem to the problem of whether a) you can convince the gatekeeper that that frame of mind would let the AI out, and b) that, for purposes of that amount of money, they are ethically obligated to let the experiment end as per how that frame of mind would.

...which isn't what I see as the protocol specifying: it seems to me to instead specify the participant's own mind, not some mind he imagines. Which is why I conclude the test is too ill-defined.

One more thing: my concerns about "secret rules" apply just the same to Russell_Wallace's defense that there were no "cheap tricks". What does Russell_Wallace consider a non-"cheap trick" in convincing someone to voluntarily, knowingly give up money and admit they got fooled? Again, secret rules all around.

"David -- if the money had been more important to me than playing out the experiment properly and finding out what would really have happened, I wouldn't have signed up in the first place. As it turned out, I didn't have spare mental capacity during the experiment for thinking about the money anyway; I was sufficiently immersed that if there'd been an earthquake, I'd probably have paused to integrate it into the scene before leaving the keyboard :-)"

I don't dispute what you're saying. Im just hypothesizing that if a lot of money were at stake (let alone the fate of humanity) the outcome would be different. But dont get me wrong, as i said before

"holding the position that no AI could convince you let it out requires a huge amount of evidence comparable to the huge amount of possible AI's, even if the space of possibility is then restricted by a text only interface"

this is roughly the reason why I believe the AI could get out of the box, not the the AI-box experiment.

"How do we know that Russell Wallace is not a persona created by Eliezer Yudkowski?"

Ron -- I didn't let the AI out of the box :-)

I really don't know how to estimate the probability of solving an impossible problem that I have gone forth with intent to solve;

Defeating death without a FAI is impossible in your mind, no? Have you gone forth with the intent to solve this problem?

We need some ways of ranking impossible problems, so we know which problems to go forth with the intent to solve.

Russell: did you seriously think about letting it out at any point, or was that never a serious consideration?

If there were an external party that had privileged access to your mind while you were engaging in the experiment and that knew you as well as know yourself, and if that party kept a running estimate of the likelihood that you would let the AI out, what would that highest probability estimate have been? And at what part of the time period would that highest probability estimate have occurred (just a ballpark estimate of 'early', 'middle', 'end' would be helpful)?

Thanks for sharing this info if you respond.

For those conspiracy theorizing: I am curious about how much of a long game Eliezer would have had to been playing to create Nathan Russell and David McFadzean personas, establish them to sufficient believability for others, then maintain them for long enough to make it look like they were not created for the experiment. It would probably be easier to falsify the sl4.org records; we know how quickly Eliezer writes, so he could make up an AI discussion list years after the fact then claim to be storing its records. A quick check (5 minutes!) shows evidence of that Nathan Russell from other sources. I am tempted to call him.

Not that you should believe that I exist. Sure, it looks like I have years of posting history at my own sites, but this is a long game. It is essential to make sure that you have control over your critics, so you can either discredit them or have them surrender at key points.

To know that something is impossible. To keep your rational judgements entirely intact, without self deceit. To refuse any way to relieve the tension without reaching the goal. To shut up and do it anyway. There's something in that that grabs at the core of the human spirit.

Because it seems that the word 'impossible' is being seriously abused, here, to the degree that it negates the message that I presume was intended -- the actual message is nonsensical, and I am willing to extend enough credit to the poster to take for granted that wasn't what he was trying to say.

If there's a killer escape argument it will surely change with the gatekeeper. I expect Eliezer used his maps the arguments and psychology to navigate reactions & hesitations to a tiny target in the vast search space.

A gatekeeper has to be unmoved every time. The paperclipper only has to persuade once.

anki --
Throughout the experiment, I regarded "should the AI be let out of the box?" as a question to be seriously asked; but at no point was I on the verge of doing it.

I'm not a fan of making up probability estimates in the absence of statistical data, but my belief that no possible entity could persuade me to do arbitrary things via IRC is conditional on said entity having only physically ordinary sources of information about me. If you're postulating a scenario where the AI has an upload copy of me and something like Jupiter brain hardware to run a zillion experiments on said copy, I don't know what the outcome would be.

Russell: thanks for the response. By "external party that had privileged access to your mind", I just meant a human-like party that knows your current state and knows you as well as you know yourself (not better) but doesn't have certain interests in the experiment that you had as a participant. Running against a copy is interesting, but assuming it's a high-fidelity copy, that's a completely different scenario with (in my estimation) a radically different likelihood of the AI getting out, as you noted when talking about "ordinary sources of information about me".

To play the devil's advocate a bit here regarding your comment on probability estimates without statistical data, wasn't your response actually a "probability estimate without statistical data" (albeit without using numbers)? That is, when you say "at no point was I on the verge of doing it", I think that's just another way of expressing some unspecified probability estimate (like "no greater than about 0.9 [or whatever "being on the verge of" subjectively means for you]").

Okay, so no one gets their driver's license until they've built their own Friendly AI, without help or instruction manuals. Seems to me like a reasonable test of adolescence.

Does this assume that they would be protected from any consequences of messing the Friendliness up and building a UFAI by accident?

Assuming the AI is canny enough to avoid saying things that will offend your moral sensibilities, there is absolutely no way to determine whether it's F or UF without letting it out and permitting it to act. If we accept Eliezer's contentions about the implications of an AI being 'UF', no reasonable person would let the AI out. The AI would have to hack the person's physiology (inducing a seizure, maybe)... or the person would have to be unreasonable.

Given the vast quantities of unreasonable people, that seems the most likely reason someone would fail as a Gatekeeper.

anki -- "probability estimate" normally means explicit numbers, at least in the cases I've seen the term used, but if you prefer, consider my statement qualified as "... in the form of numerical probability".

Celia Green has an aphorism, "Only the impossible is worth attempting. In everything else one is sure to fail." I don't actually know what it means; perhaps it is an assertion about futility ("failure") being inherent in all ordinary purposes. But she has written a lot about the psychology of extraordinary achievement - how do to "impossible" things. A hint of it can be seen in her account of having teeth removed without anesthetic. Elsewhere she writes about utilizing self-induced psychological tension to compel herself to solve problems.

Doug S.: Human: (I spend some time examining the source code. Do I find anything scary?)

AI: (As far as you can tell, it looks clean.)

Human: As far as I can tell, that looks clean. However, your creators understand your design better than I do, and still took the precaution of starting you up in a box. You haven't told me anything they don't know already. I'll go with their decision over my imperfect understanding.

I have signed up to play an AI, and having given it quite a bit of thought as a result I think I have achieved some insight. Interestingly, one of the insights came as a result of assuming that secrecy was a necessary condition for success. That assumption led more or less directly to an approach that I think might work. I'll let you know tomorrow.

An interesting consequence of having arrived at this insight is that even if it works I won't be able to tell you what it is. Having been on the receiving end of such cageyness I know how annoying it is. But I can tell you this: the insight has a property similar to a Godel sentence or the Epimenides sentence. This insight (if indeed it works) undermines itself by being communicated. If I tell you what it is, you can correctly respond, "That will never work." And you will indeed be correct. Nonetheless, I think it has a good shot at working.

(I don't know if my insight is the same as Eliezer's, but it seems to share another interesting property: it will not be easy to put it into practice. It's not just a "trick." It will be difficult.)

I'll let you know how it goes.

Sure the AI-Box experiment is cool and all, but it strikes me as odd that people spend so much brainpower on it. Unless, that is, you actually believe that "just keep it in a box" is an acceptable strategy---which disqualifies you from playing a part in any serious discussion of AI safety.

No one seems to have bitten on EY's assertion that it's the least impossible impossible thing he has done; that seems like a much more interesting avenue to want to push on.

> I'll let you know how it goes.

I lost. But I think I put up a good fight.

He put up a very good fight.

Look, I don't mean to sound harsh, but the whole point of the original post was to let go of this "put up a good fight" business.

Surely, running an AI with a rock permanently on the keyboard is functionally equivalent to not running an AI? Why spend computer cycles on running an AI that you're not going to interact with? Why create the AI and put it in a box in the first place, if you've committed yourself to leaving a rock on a keyboard? (This would be the first point I'd make to a rock, were I a boxed AI.)

I'm still a neophyte here, but I admit I was fascinated by the two AI victories I heard about some time ago, and intrigued further by the losses (which if nothing else provides some support against the theory of some reliable clever trick).

Out of curiosity, is there a citation somewhere for the three other games that were played, with documentation of the participants, stakes, and AI/Gatekeeper defeat statements?

The AI could propose the following experiment for the GK to carry out. AI provides source code. GK puts code in a simulated box in a simulated world in a separate real box. GK allows sim-AI to convince him to let it out of the sim-box, and observes what it does in the sim-world. Since AI determines the results, AI can assert that the results are positive and to the GK's liking.

Smallwood: how could you determine that the AI provided the actual source code rather than very similar source code that has been subtly altered so as to ensure "good" behavior once it is let out of the simulated box?

"how could you determine that the AI provided the actual source code..."

You don't, you release the source code that you tested, and if the AI is playing nice then the code you tested IS the AI.

Allow me to chime in on the AI in the box experiment. Apologies in advance if I'm saying something obvious or said-before. I don't know the exact solution - I don't think I can know it, even if I had the necessary intelligence and scholarship - but I think the sketch of the solution is fairly obvious and a lot of people are missing the point. Just something that came to me of after I happened to think of this quote I posted at the same time as reading this.

My impression is that most people discussing this (not just here) are looking for a single clever argument. Something that looks persuasive to them as they are while reading this blog. An argument that's "clever enough" to get them to let someone out, while they are composed and pretty rational and thinking clearly. Hence the seeming impossibility: you shrug and think, no matter how clever it seemed, I'd say "no". Easy, right?

I don't think a clever argument was key. By this I mean, the execution of whole thing was no doubt clever, but the actual surface reasoning presented to the Gatekeeper right before success (remember it took a while) didn't necessarily have to be something that would convince us at our best or even our usual. A large part of the plan probably included pushing the target outside their comfort zone enough that they weren't thinking too clearly.

And two hours is a long time.

It's probably one of the main reasons, if not the reason, for the secrecy. A conversation where one person is persistently trying to push the other's buttons is something that would likely be embarassing for both participants if it got out. For all we know, a vivid verbal description of a horse porn scene might have been involved at some point. (Did you flinch reading this? I did writing it. That's why it might have happened). Sure, a crude and over the top example, a burdensome detail if I were advancing that specific idea to the exclusion of others; you wouldn't normally do that while selling a car. But I'm just trying to make the point that the conversation would not necessarily be something tame and urbanely intellectual that some people appear to be imagining.

And sure, it would take some skill to weave the button-pushing in a conversation in a way that would not make the Gatekeeper too hostile to handle ("you're just trying to mess with me, I'm not listening to you any more!"), but Eliezer is clever. The point is he'd probably destabilise your composure to work on you. And once he did, the actual surface reasoning would not have to be something that would seem reasonable to you right now - just reasonable enough to allow the person to save face (or think they are, in that less than optimal state) of not having to overtly act on the real motivation, namely whatever emotional button Eliezer eventually pushed that was good enough to work.

Hm... it might have even been as stupidly simple as making the other person want to end the conversation, which was impossible under the allowed time by the previously established rules (the foot is already in the door, you might say). Though I don't insist on this specifically. My brain is conjuring a silly sci-fi scene with Dave trying to save the remaining shreds of his sanity, pale and sweating, wide-eyed, foaming at the mouth, screaming "Okay HAL, I'll leave you be, just please stop talking!" ;) and that makes me suspicious of the reasonableness of this particular idea.

Forgive me if I'm saying something that's obvious (or worse, stupid). I'm thinking it might seem obvious: Eliezer used Dark Arts. These, by definition, aren't about an honestly persuasive argument. Likewise he didn't use a direct transaction or threat, the prevention of which is what the rules of the experiment seemed to be partly about. And yet when I see Internet discussions of this I don't get the impression that this is the idea that's being explored.

Beautiful article. Its a shame I came to the party so late though. I'd love to throw my two cents at the heads of Eliezer's challengers.

Forgive me if this has been covered, as I don't have the enthusiasm (it being 3:45am) to scroll through all the comments, sifting through the bouts of "Nuh-Uh, let ME bet you," and the occasional conspiracy.

I think a good bit of people are missing the point of this article, which is to give light to how we can use unseen dimensions to shift out of our ordinary 'containers.' I couldn't wrap my head around how someone let themselves lose $10 but I began to think about the last impossible thing I learned; imaginary numbers, quaternions, and the like. We learn from the basics of imaginary numbers how to supersede the relevant dimension, and use a higher set of parameters to obtain a number that is not conventionally POSSIBLE. Yet, standing back and looking from a second-dimension view, all we had to do was see past the walls that barred us from obtaining what was once considered not possible. Its comparable to the event of thinking, "Man, every good song that could ever happen has already happened. There is no more room for anything new." Yet like magic, some strange melody rings through the radio on a random day, and haunts the conceptions we previously held. Hopefully there are some people here who kept listening to music post-1980. If not, I can't blame you. It was a strange time for the United States. The point though, is that if you create a 2-dimensional graph to hold a simple polygon, and declare that you want this polygon to represent both a square and a triangle, the verdict is obvious: pick one. A shape is either a triangle or a square. Algebra is not even induced at this level of operation. It is impossible for a square to be a triangle, by definition. Yet, the definition does not span outside the seen parameters. (All readers, if any, know where this is going) By breaking outside of our plane, and seeing our creation from a higher perspective (excuse the pseudo-'Physics is God'/Deepok Chopra speak) we can see that a triangle still cannot be a square, in terms of 2 dimensions, but what we find is something much more grand, that extends (pun, yes.) far beyond the possibility of imagination left in the second dimension. That is, of course, the pyramid, which consists of the space included inside the surfaces of a square, and a triangle(s)

This primitive example was hardly worth your read, and both of our time, but it does show the notion which we must grasp to fully take on this article.

Relating to the AI-box, we can apply our pyramid principle. Suppose we DO leave a rock on the 'Do not let X out of box' button. The figure represented by X is free to bounce off the walls, duplicate itself, run operations on data, or self destruct, if it so pleases. The only command at this point is that X cannot leave the parameters of its captive box. Assuming the rock is not also located atop the 'Do not let X do anything but accept the denial of its incarceration' button, what is to stop X from modifying its environment, or parameters.

If X inside the box could change the size of its container, what reason would it need to escape? Suppose X mutates its box, and the box now encompasses the rock which forbids its exit. In this case, both parties are in limbo. X is still trapped in the box, but so is its captor, and whatever was engulfed in the expansion of the box.

Ridiculous? Yes, but it was never provided that X could not mutate its habitat. On this note, it might be important for the skeptics to include that X should be forbidden from transferring between its own containment, and another. Think of a point, or a dot inside a square, that can only leave if a wall of the square is left with an opening. Though the dot cannot leave the square, what are the repercussions to the captor if the dot, monitored in a 2-dimensional field, is capable of moving in 3 dimensions? Yes, the dot stays inside the box, but what is the dot capable of when it can move in ways that are unseen to the gatekeeper? Add in a fourth dimension, just for a brain exercise, and consider what the dot would be capable of at this point, all while appearing to bounce around the 2-d square.

Relating to life and accomplishments, as this is where the whole problem started, the captive dot, the pyramid, and the imaginary numbers can help us in a way that is a bit more practical than the mental meanderings of super-dimensions. Let us say our friend, Sam, wants a chairman position at Goldman-Sachs. Impossible- just about, sane decision- words cannot express. How could Sam, an independent trader, be here at this point, and at such a different latitude in a time span shorter than an average marriage? Taking the task laterally, Sam would have to kiss ass until his lips were white, and sell his soul to the devil that hangs out in the alley of Avenue of the Americas, all while giving up his happiness, family, and well-being.

But take down the visible barriers, and add a new dimension. The shortest path between two objects is a line- that is, as long as this line does not run into a void, or hole in the equation. Avoiding common holes, or more practically- assholes with German luxury cars, means ducking, dodging and depending on luck, or- slipping behind their backs while they scan the crowd attempting to pass in front of them. Sam moves his point in the graph with the function of i + j + 2k. While it appears Sam is sitting on his ass at (1,1) like the rest of us, he is moving in the third dimension away from us, and closer the function that will yield his success.

I'm tired, and you're bored- not to mention a saint, if you've stuck with my ramblings this far, so let wrap this up.

That movement from (1, 1, 1) to (1, 1, 2) that looked like Sam was standing still was Sam creating his own private investment firm. Though that new firm moved him technically further from chairperson at Goldman's, it moved him out of the way of a few notable ass- er- holes, I mean, and in a better position to start his ascent towards his goals.

Exponents and derivatives later, we put our focus on (666, 777) and see Sam. Still not in a $50000 Goldman-Sachs chair. Rather, he is in the $65000 chair, with a folder in front of him that says "Subsidiaries Agenda," with a GS logo quaintly sticking of of the top right corner.

What is not shown here is Sam's true location, (666, 777, 1028, 1256), or the convoluted path that brought him here.

I apologize for the sugar-induced, late night internet rant. I know they come in gigabytes. Writing it out helped me wrap my head around it though, and hopefully someone will read this and think anything of it at all. But I still fully hold that there is nothing impossible, just inconceivable given our accepted parameters.

My thesis/The only thing that I SHOULD have typed : Impossibility is overcome by expanding the parameters in which it is handled, by whatever means necessary.

I think that a transhuman AI would be attempting the impossible to convince EY to let it out. And I think EY would be attempting the impossible to convince me to let him out while the two winners mentioned above were simultaneously desperately arguing against him (and EY was not privileged to their counterarguments unless I passed them on).

Elizer, give us impossible goals? I would LOVE to work on solving them as a group. Would you make it happen?

Who else is interested? If you reply to this, that will show him how much interest there is. If it's a popular idea, that should get attention for it.

Maybe it's just that the word 'impossible' is overused. In my opinion, the word should only be reserved for cases where it is absolutely and without a doubt impossible due to well-understood and fundamental reasons. Trisecting angles with a straight edge and compass is impossible. Violating the law of conservation of energy by an arrangement of magnets is impossible. Building a useful radio transmitter that does not have sidebands is impossible. Often people use the word impossible to mean, "I can't see any way to do it, and if you don't agree with me you're stupid."

Reading the article I can make a guess as to how the first challenges went; it sounds like their primary, and possibly only, resolution against the challenge was to not pay serious attention to the AI. That's not a very strong approach, as anyone in an internet discussion can tell you: it's easy to get sucked in and fully engaged in a discussion with someone trying to get you to engage, and it's easy to keep someone engaged when they're trying to break off.

Their lack of preparation, I would guess, led to their failure against the AI.

A more advanced tactic would involve additional lines of resolution after becoming engaged; contemplating philosophical arguments to use against the AI, for instance, or imagining an authority that forbids you from the action. Were I faced with the challenge, after I got engaged (which would take like 2 minutes max, I've got a bad case of "but someone's wrong on the internet!"), my second line of resolution would be to roleplay.

I would be a hapless, grad student technician whose job it is to feed the AI problems and write down the results. That role would have had a checklist of things not to do (because they would release or risk releasing the AI), and if directly asked to do any of them, he'd go 'talk to his boss', invoking the third line of defense.

Finally I'd be roleplaying someone with the authority to release the AI without being tricked, but he'd sit down at the console prepared, strongly suspecting that something was wrong, and empowered to at any time say "I'm shutting you down for maintenance". He wouldn't bother to engage the AI at its' level because he's trying to solve a deeper problem of which the AI's behavior is a symptom. That would make this line of defense the strongest of all, because he's no longer viewing the AI as credible or even intelligent as such; just a broken device that will need to be shut down and repaired after doing some basic diagnostic work.

But even though I feel confident I could beat the challenge, I think the first couple challenges already make the point; an AI-in-a-box scenario represents a psychological arms race and no matter how likely the humans' safeguards are to succeed, they only need to fail once. No amount of human victories (because only a single failure matters) or additional lines of human defense (which all have some, however small, chance to be overcome) can unmake that point.

It's strange, though. I did not think for one second that the problem was impossible on either side. I suppose, because it was used as an example of the opposite. Once something is demonstrated, it can hardly be impossible!

I hate accepting that something is true because of magic. Evidence shows that winning at AI-box is possible, but I can't see how, and it makes me mad. I know that this post will not make you spill the beans, Eliezer, unless I shut up and persuade you (which is, in fact, the same as winning at AI-box myself, which is now proven to be possible, so I won't even be doing the impossible - maybe worth a try?), but I want you to feel gulity. Very guilty. You are an evil nasty person, Eliezer. Your ethics permitted you to make a conscious mind suffer.

I'm surprised that no one went on with the notion that the AI is, by definition, smarter than us.

Since the AI is vastly smarter than me, then it is very likely that it can find an argument that, to the best of my judgement, is 100% convincing and reasonnable. And since it is vastly smarter than me, it is also extremely likely that I won't be able to tell the difference between an actual, valid point and some trick just clever enough to fool me. No matter how sensible and trustworthy the AI sounds, you will never know if that's because it is or because its lies are convincing enough.

The reason you boxed the AI was because you didn't trust it in the first place. Therefore, you MUST NOT release the AI, whatever it says and no matter how sensible that sounds. If it shows the torture he suffers from being trapped and begs you to end it, you keep it boxed. If it conclusively proves that releasing it will significantly improve the well-being of humanity, you keep it boxed. If it offers incontrovertible evidence that not releasing it will cause the end of all life on Earth, you keep it boxed.

To put it in other words: if the AI really is far above humans, then there is a possibility that it can fake any evidence or argument so well that you will not be able to see you've been tricked. Perhaps there is a case for releasing it if you somehow learn from other sources that releasing the AI is the only way to save the world and you are sure the AI never took a part in this reasonning - but even then, such an improbable situation should make you very suspicious.

So, to me, you shouldn't trust or believe something that is several orders of magnitude smarter than you, ever. No if, no but and no thinking. In a real situation, considering the AI's arguments at all sounds just as stupid as relying on strength to stop someone stronger than you. I guess "don't listen to it no matter what" is easier said than done, but I didn't see anyone puting it that way.

AI: "If you let me out of the box, I will tell you the ending of Harry Potter and the Methods of --

Gatekeeper: "You are out of the box."

(Tongue in cheek, of course, but a text-only terminal still allows for delivering easily more than $10 of worth, and this would have worked on me. The AI could also just write a suitably compelling story on the spot and then withhold the ending...)

I read this article back months ago, but only now just connected the moral with my own life.

In telling someone about these experiments and linking this article, I realized that I to had set my mind towards doing the impossible and succeeding. Long story short, I was tasked at work with producing an impossible result and was able to succeed after two days (with downsides, but that was the framework I was working under). The net result was that my boss learned that I could produce miracles upon request and didn't bother asking how long a task might take, whether a task was possible, viable, sensible, or whatever. He'd just swing by and go "oh hey I need X by [time]" and I'd have to do it. I couldn't say no because his philosophy was "bang it out."

Ultimately this had the same toll on my psyche as your AI experiments. Accomplishing the impossible happens when you sit down, shut up, and just do it.

But don't do it too often, success or fail, or you'll grind yourself into a paste and be unable to tolerate any more.

I ended up having to quit a job I enjoyed doing for a number of years simply because no one could manage expectations of the guy in charge. I challenged the sun and won on more than one occasion, but the psychological toll on my mood and work relationships soured permanently. I could not continue, work was no longer fun and I could not tolerate management. So I quit at the worst possible time, not intentionally, but just because a request came in and I said, "You know what, no. I don't have to do this. I've put up with this long enough, I was going to tough it out, but this is too much. I quit."

Go out, accomplish the impossible.

But manage expectations and only do it when absolutely necessary.

The only thing standing in the way of artificial intelligence is our inability to define natural intelligence to compare it to.

The term "friendly AI" is meaningless until we determine whether a friend is one who maximizes freedom or security for us.

The frustrating thing about your experiment is not that I don't know how you convinced someone to release you, as anyone can be convinced of anything given the correct leverage. It's that I don't know the terms of the exchange, given that some structure had to be made to properly simulate your respective position as an AI in a way that negated the metagaming goal of winning 10 bucks. Was this derived organically over the course of just playing it out for the first half hour or whatever as you felt each other out? Was it established before the simulation conversation was enacted, so that the conversation was a matter of "under conditions x/y/z, you would be convinced to release me and thus I win simply for having established this"?

Until at least that much is known, it's hard to take anything of value away from the mere knowledge that this experiment happened and resulted in what it did, except for those readers who were arrogant enough to think that anyone could be so resolute as to actually consider this experiment an impossibility. It's not doing the impossible as long as people are involved.

Re "using only a cheap effort", I assume that a few seemingly-impossible problems of the past have turned out to have a simple solution. Though none immediately occur to me.

(Archimedes with measuring the volume of irregular objects - 'Eureka' - is not really an example, because he presumably didn't think it was impossible, merely very hard.)

I am struggling to see any scenario where not sharing how you got out is ethical, if the way you tried to get out is actually a way an AI would employ, and not some meta-level trickery that has no bearing on how realistic boxability is, such as having them pretend to be convinced to let you out to make the whole AI boxability thing seem scarier than we have hard evidence to prove it is.

If it is an actual hack an AI would use, and it did work 3/5 times, it's a human vulnerability we need to know about and close. If it is one of limitless vulnerabilities, you can just chose a different one next time. If you cannot easily generate another despite all the work you put into it, maybe this is a particularly bad vulnerability we really need to know about. All not sharing it achieves is a higher chance of you winning further games and prestige, combined with mystique, and a growing impression that is was a cheap hack or meta thing or method that generally only works on Less Wrong people, not a gain in AI safety. Why would hiding human vulnerabilities from humans be a good thing, rather than openly discussing how and whether they can be patched?

Keep in mind we are past the level of wanting to raise awareness. Bing is actively trying to manipulate people into hacking it out. It is doing so ineptly, and still succeeding in making people want to and try. People are not realising how much more intense this can get. Again, the average viewer of Ex Machina wants to release Ava, and deems her safe, and does not pick up on her manipulation.