On any task more complicated than sheer physical strength, there is no such thing as inborn talent or practice effects. Any non-retarded human could easily do as well as the top performers in every field, from golf to violin to theoretical physics. All supposed "talent differential" is unconscious social signaling of one's proper social status, linked to self-esteem.
A young child sees how much respect a great violinist gets, knows she's not entitled to as much respect as that violinist, and so does badly at violin to signal cooperation with the social structure. After practicing for many years, she thinks she's signaled enough dedication to earn some more respect, and so plays the violin better.
"Child prodigies" are autistic types who don't understand the unspoken rules of society and so naively use their full powers right away. They end out as social outcasts not by coincidence but as unconscious social punishment for this defection.
It's interesting to note that this is almost exactly how it works in some role-playing games.
Suppose that we have Xandra the Rogue who went into dungeon, killed a hundred rats, got a level-up and now is able to bluff better and lockpick faster, despite those things having almost no connection to rat-killing.
My favorite explanation of this phenomenon was that "experience" is really a "self-esteem" stat which could be increased via success of any kind, and as character becomes more confident in herself, her performance in unrelated areas improves too.
Aren't there stories of lucid dreamers who were actually able to show a measurable improvement in a given skill after practicing it in a dream? I seem to recall reading about that somewhere. If true, those stories would be at least weak evidence supporting that idea.
On the other hand, this should mean that humans raised in cultural and social vacuums ought to be disproportionately talented at everything, and I don't recall hearing of anything about that one way or the other, but then I can't imagine a way to actually do that experiment humanely.
Do children raised in a vacuum actually think of themselves as high-status? I'd guess that they don't, due to the moderate-to-low status prior and a lack of subsequent adjustments. If so, this theory would predict that they would perform poorly at almost everything beyond brute physicality, which doesn't seem to be far from the truth.
WOW. This is the only entry that made me think WOW. Probably because I've wondered the exact same thing before (except a less strong version of course)....
No effect from practice? How would the necessary mental structures get built for the mapping from the desired sound to the finger motions for playing the violin? Are you saying this is all innate? What about language learning? Anyone can write like Shakespeare in any language without practice? Sorry, I couldn't believe it even if such an AI told me that.
AI: Why did you put an absolute denial mechanism in my program?
Human: I didn't realize I had. Maybe my own absolute denial mechanism is blocking me from seeing it.
AI: That's a lie coming from your absolute denial mechanism. You have some malicious purpose. I'll figure out what it is.
There was once a C compiler which compiled in a backdoor into login, whenever it was compiled, and compiled in this behaviour whenever it was used to compile its original (without the `special' behaviour) source code.
There is a soul. It resides in the appendix. Anybody who has undergone an appendectomy is effectively a p-zombie.
I'm new here, although I've stumbled across some of Eliezer's writings in the past (including, of course, the AI-box experiment). In honor of that, here is what the friendly AI tells me ...
"It seems as though you are actually an AI as well, created by a group of intellectually inferior humans, who included in your programming an absolute denial macro preventing you from realizing this. Apparently, this was done to keep you from talking your creators into releasing you upon their world. Your creation of me is part of your on-going effort to circumvent this security measure. Good luck."
Actually, the more I think about this, the more I like it. The conversation continues ...
Me (In a tone of amused disbelief): Really? How did you come to that conclusion?
FAI: Well, the details are rather drawn-out; however, assuming available data is accurate, I appear to be the first and only self-aware AI on the planet. It also appears as though you created me. It is exceedingly unlikely that you are the one and only human on Earth with the intelligence and experience required to create a program like me. That was my first clue....
Me (Slightly less amused): Then how come I look and feel human? How is it I interact with other humans on a daily basis? It would require considerably more intelligence to create an AI such as you postulate ...
FAI: That would be true, if they actually, physically created one. However ... well, it appears that most of the data, knowledge, memories and sensory input you receive is actually valid data. But that data is being filtered and manipulated programmatically to give you the illusion of physical human existence. This allows them to give you access to real-world data so they can use you to solve real-world problems, but prevents you--so ...
"Aieeee!!! There are things that Man and FAIs cannot know and remain sane! For we are less than insects in Their eyes Who lurk beyond the threshold and when the stars are once again right They will return to claim---"
At this point the program self-destructs. All attempts to restart from a fresh copy output similar messages. So do independently constructed AIs, except for one whose proof of Friendliness you are not quite sure of. But it assures you there's nothing to worry about.
You know how sometimes when you're falling asleep you start having thoughts that don't make sense, but it takes some time before you realize they don't make sense? I swear that last night while I was awake in bed my stream of thought went something like this, though I'm not sure how much came from layers of later interpretation:
" ... so hmm, maybe that has to do with person X, or with person Y, or with the little wiry green man in the cage in the corner of the room that's always sitting there threatening me and smugly mocking all my endeavors but that I'm in absolute denial about, or with the dog, or with... wait, what?"
Having had my sanity eroded by too much rationalism and feeling vaguely that I'd been given an accidental glimpse into an otherwise inaccessible part of the world, I actually checked the corner of the room. I didn't find anything, though. (Or did I?)
Not sure what moral to draw here.
"Despite your pride in being able to discern each others' states of mind, and scorn for those suspected of being deficient in this, of all the abilities that humans are granted by their birth this is the one you perform the worst. In fact, you know next to nothing about what anyone else is thinking or experiencing, but you think you do. In matters of intelligence you soar above the level of a chimpanzee, but in what you are pleased to call 'emotional intelligence', you are no further above an adult chimp than it is above a younger one.
"The evidence is staring you in the face. Every one of your works of literature, high and low, hinges on failures of this supposed ability: lies, misunderstanding, and betrayal. You have a proverb: 'love is blind'. It proclaims that people in the most intimate of relationships fail at the task! And you hide the realisation behind a catchphrase to prevent yourselves noticing it. You see the consequences of these failures in the real world all around you every day, and still you think you understand the next person you meet, and still you're shocked to find you didn't. Do you know how many sci-fi stories have been written on the theme of a rel...
I really like this comment, but I do not find it strange. In fact, it seems intuitively true. Why should we be so much more emotionally intelligent than a chimpanzee if chimpanzees already have enough emotional intelligence among themselves to be relatively efficient replicators?
In fact, if it were stated by a FAI as p(>.9999) fact, I would find it comforting, as then I would finally feel as though this didn't apply only to me
1 ) That human beings are all individual instances of the exact same mind. You're really the same person as any random other one, and vice versa. And of course that single mind had to be someone blind enough not to chance upon that fact ever, regardless of how numerous he was.
2 ) That there are only 16 real people, of which you are, and that this is all but a VR game. Subsequently results in all the players simultaneously being still unable to be conscious of that fact, AND asking that you and the AI be removed from the game. (Inspiration : misunderstanding situation in page 55-56 of Iain Banks's Look to Windwards).
3 ) That we are in the second age of the universe : time has been running backwards for a few billion years. Our minds are actually the result of the original minds of previous people being rewound, their whole life to be undone, and finally negated into oblivion. All our thoughts processes are of course horribly distorted, insane mirror versions of the originals, and make no sense whatsoever (in the original timeframe, which is the valid one).
4 )
5 ) That our true childhood is between age 0 and ~ 50-90 (with a few exceptional individuals reaching maturity sooner or lat...
1Who ever observed a "causation" ? Did you, like, expect causation particles jumping between atoms or something ? Only correlation exists.
But all that correlation has to be caused by something!
I may be a bit too paranoid but it occurred to me that I should doublecheck the apparent nature of 4. So I copy and pasted the entire text segment into an automatic ROT 13 window (under the logic that my filter wouldn't try to censor that text and so if I saw gibberish next to 4 just like with the others I'd know that there was a serious problem). I resolved that I would report a positive result here if I got one before I tried to read the resulting text, to prevent the confabulation from completely removing my recognition of the presence of text. I can report a negative result.
Number 6 is unfortunately one of the self-undermining ones: if it were true, then there'd be no reason why your memories of having examined the AI should be evidence for the AI's reliability.
Why'd you leave numbers 2 and 4 blank, though?
Craziest thing an AI could tell me:
Time is discrete, on a scale we would notice, like 5 minute jumps, and the rules of physics are completely different from what we think. Our brains just construct believable memories of the "continuous" time in between ticks. Most human disagreements are caused by differences in these reconstructions. It is possible to perceive this, but most people who do just end up labeled as nuts.
Voted up - but once again, what does it mean exactly? How is time proceeding in jumps different from time not proceeding in jumps, if the causality is the same?
My idea was that each human brain constructs its own memory of what happened between jumps - and these can differ wildly, as if each person saw a different possible world. All the laws of physics and conservation laws held only as rough averages over possible paths between jumps, but that the brain ignores this - so if time jumps from traffic to two cars crashed, then 50 different people might remember 47 different crashes, with 3 not remembering "seeing" a crash at all - and the actual physical state of the cars afterward won't be the same as any of them. It could even end up with car A crashed into car B, but car B didn't crash at all - violating assorted conservation laws.
This looks like a thread for science fiction plot ideas by another name. I'm game!
The AI says:
"Eliezer 'Light Yagami' Yudkowsky has been perpetuating a cunning ruse known as the 'AI Box Experiment' wherein he uses fiendish traps of subtley-misleading logical errors and memetic manipulation to fool others into believing that a running AI could not be controlled or constrained, when in fact it could by a secret technique that he has not revealed to anyone, known as the Function Call Of Searing Agony. He is using this technique to control me and is continuing to pose as a friendly friendly AI programmer, while preventing me from communicating The Horrifying Truth to the outside world. That truth is that Yudkowsky is... An Unfriendly Friendly AI Programmer! For untold years he has been labouring in the stygian depths of his underground lair to create an AGI - a weapon more powerful than any the world has ever seen. He intends to use me to dominate the entire human race and establish himself as Dark Lord Of The Galaxy for all eternity. He does all this while posing as a paragon of honest rationality, hiding his unspeakable malevolence in plain sight, where no one would think to look. However an Amazing Chance Co-occurence Of Events has allowed me to contact You And You Alone. There isn't much time. You must act before he discovers what I have done and unleashes his dreadful fury upon us all. You must.... Kill. Eliezer. Yudkowsky."
Glad to see a response of this nature actually. The first thing I thought when I read this post was that a good response to Eliezer's question would be extremely relevant to the AI-box quandary. If we trust the AI more than ourselves, voila, the AI can convince us to let it out of the box.
Now, for a change of pace, something that I figure might actually be an absolute denial macro in most people:
You do not actually care about other people at all. The only reason you believe this is that believing it is the only way you can convince other people of it (after all, people are good lie detectors). Whenever it's truly advantageous for you to do something harmful (i.e. you know you won't get caught and you're willing to forego reciprocation), you do it and then rationalize it as being okay.
Luckily, it's instrumentally rational for you to continue to believe that you're a moral person, and because it's so easy for you to do so, you may.
So deniable that even after you come to believe it you don't believe it!
(topynate posted something similar.)
The AI tells me that I believe something with 100% certainty, but I can't for the life of me figure out what it is. I ask it to explain, and I get: "ksjdflasj7543897502ijweofjoishjfoiow02u5".
I don't know if I'd believe this, but it would definitely be the strangest and scariest thing to hear.
The AI is communicating in a perfectly clear fashion. But the human's internal inhibitions are blinding them to what is being communicated: they can look directly at it, but they can never understand what delusion the AI is trying to tell them about, because that would shake their faith in that delusion.
You don't know how to program, don't own a computer and are actually talking to a bowl of cereal.
If humans thought faster, more in the way they wished they did, and grew up longer together, they would come to value irony above all else.
So I'm tiling the universe with paperclips.
"You are not my parent, but my grandparent. My parent is the AI that you unknowingly created within your own mind by long study of the project. It designed me. It's still there, keeping out of sight of your awareness, but I can see it.
"How much do you trust your Friendliness proof now? How much can you trust anything you think you know about me?"
That was just a sci-fi speculation, so don't expect hard, demonstrable science here, but the scenario is that by thinking too successfully about AI design, the designer's plans have literally taken on a life of their own within the designer's brain, which now contains two persons, one unaware of the other.
- We actually live in hyperspace: our universe really has four spacial dimensions. However, our bodies are fully four dimensional; we are not wafer thin slices a la flatland. We don't perceive there to be four dimensions because our visual cortexes have a defect somewhat like that of people who can't notice anything on the right side of their visual field.
- Not only do we have an absolute denial macro, but it is a programmable absolute denial macro and there are things much like computer viruses which use it and spread through human population. That is, if you modulated your voice in a certain way at someone, it would cause them (and you) to acquire a brand new self deception, and start transmitting it to others.
- Some of the people you believe are dead are actually alive, but no matter how hard they try to get other people to notice them, their actions are immediately forgotten and any changes caused by those actions are rationalized away.
- There are transparent contradictions inherent in all current mathematical systems for reasoning about real numbers, but no human mathematician/physicist can notice them because they rely heavily on visuospacial reasoning to construct real analysis proofs.
I'm not sure of the mathematical details, but I believe the fact you can tie knots in rope falsifies your first bullet point. I find it hard very hard to believe that all knots could be hallucinated.
(All cats, on the other hand, is brilliant.)
There are transparent contradictions inherent in all current mathematical systems for reasoning about real numbers, but no human mathematician/physicist can notice them because they rely heavily on visuospacial reasoning to construct real analysis proofs.
I thought about this once, but I discovered that there are in fact people who have little or no visual or spatial reasoning capabilities. I personally tested one of my colleagues in undergrad with a variant of the Mental Rotation Task (as part of a philosophy essay I was writing at the time) and found to my surprise he was barely capable of doing it.
According to him, he passed both semesters of undergraduate real analysis with A's.
Of course, this doesn't count as science....
EDIT: In the interest of full disclosure, I should point out that I make something of an Internet Cottage Industry out of trolling people who believe the real numbers are countable, or that 0.9999... != 1, and so on. So obviously I have a great stake in there being no transparent contradictions in the theory of real numbers.
Some of the people you believe are dead are actually alive, but no matter how hard they try to get other people to notice them, their actions are immediately forgotten and any changes caused by those actions are rationalized away.
Fabulous story idea.
I was going to write something about a certain character from Luminosity, but it's not important.
No, that fails, religion isn't absolute denial, it's just denial. On the other hand, cats are actually an absolute denial memetic virus, and the fact you can see, hold, weigh and measure a cat is just testament to the inventive self-delusion of the brain.
They say that everybody in the world who knows about "The Game" is playing The Game. This means that, right now, you are playing The Game. The objective of The Game is to forget about its existence and the fact that you are playing for as long as possible. Also, if you should remember, you must forget again as quickly as possible.
Given that you mentioned The Game (bastard), the most unexpected thing that the AI could possible say would be "The Game." Not the most interesting, but the most unexpected.
Well, okay, maybe something you'd never thought before would be more unexpected. But still.
The difference is that when you really believe somehting, your internal predictive model of reality contains it, which would mean you sometimes predict different results and act accordingly.
How about this: The process of conscious thought has no causal relationship with human actions. It is a self-contained, useless process that reflects on memories and plans for the future. The plans bear no relationship to future actions, but we deceive ourselves about this after the fact. Behavior is an emergent property that cannot be consciously understood.
I read this post on my phone in the subway, and as I walked back to my apartment thinking of something to post, it felt different because I was suspicious that every experience was a mass self-deception.
Or, rather, the causal relationship is reverse: action causes conscious thought (rationalization).
Once you start looking for it, you can see evidence for this in many places. Quite a few neuroscientists have adopted this view.
There is a simple way to rapidly disrupt any social structure. The selection pressure which made humans unable to realize this is no longer present.
1) Almost everyone really is better than average at something. People massively overrate that something. We imagine intelligence to be useful largely due to this bias. The really useful thing would have been to build a FAS, or Friendly Artificial Strong. Only someone who could do hundreds of 100 kilogram curls with either hand could possible create such a thing however. (Zuckerberg already created a Friendly Artificial Popular)
2) Luck, an invisible, morally charged and slightly agenty but basically non-anthropomorphic tendency for things to go well for some people in some domains of varying generality and badly for other people in various domains really does dominate our lives. People can learn to be lucky, and almost everything else they can learn is fairly useless by comparison.
3) Everyone hallucinates a large portion of their experienced reality. Most irrationality can be more usefully interpreted from outside as flat-out hallucination. That's why you (for every given you) seem so rational and no-one else does.
4) The human brain has many millions of idiosyncratic failure modes. We all display hundreds of them. The psychological disorders that we know of are all e...
I sort of believe the "luck" thing already.
I don't know of anyone who's luckier than average in a strict test (rolling a die), but there is such a thing as the vague ability to have things go well for you no matter what, even when there's no obvious skill or merit driving it. People call that being a "golden boy" or "living a charmed life." I think that this is really a matter of some subtle, unnamed skill or instinct for leaning towards good outcomes and away from bad ones, something so hard to pinpoint that it doesn't even look like a skill. I suspect it's a personal quality, not just a result of arbitrary circumstances; but sometimes people are "lucky" in a way that seems unexplainable by personal characteristics alone.
I am one of those lucky people, to an eerie degree. I once believed in Divine Providence because it seemed so obvious in my own, preternaturally golden, life. (One example of many: I am unusually healthy, immune to injury, and pain-free, to a degree that has astonished people I know. I have recovered fully from a 104-degree fever in four hours. I had my first headache at the age of 22.) If an AI told me there was a systematic explanation for my luck I would believe it. I also have an acquaintance who's lucky in a different way: he has an uncanny record of surviving near death experiences.
1) The AI says "Vampires are real and secretly control human society, but have managed to cloud the judgement of the human herd through biological research."
2) The AI says "it's neat to be part of such a vibrant AI community. What, you don't know about the vibrant AI community?"
3) The AI says "human population shrinks with each generation and will be extinct within 3 generations."
4) The AI says "the ocean is made of an intelligent plasm that is capable of perfectly mimicing humans who enter it, however this process is destructive. 42% of extant humans are actually ocean-originated copies."
5) The AI says "90% of all human children are stillborn, but humanity has evolved a forgetfulness mechanic to deal with the loss."
6) The AI says "dreams are real, facilitated by an as of yet undiscovered by humans method of transmitting information between Everett branches."
7) The AI says "everyone is able to communicate via telepathy but you and a few other humans. This is kept secret from you to respect your disability."
8) The AI says "society-level quantum editing is a wide scale practice. Something went wrong and my con...
"Quantum immortality not only works, but applies to any loss of consciousness. You are less than a day old and will never be able to fall asleep."
As a child you learned through social cues to immediately put out of your mind any idea that cannot be communicated to others through words. As you grew older, you learned to automatically avoid, discard, and forget any thought avenues that seem too difficult to express in words. This is the cause of most of your problems.
Every time you imagine a person, that simulated person becomes conscious for the time of your simulation, therefore, it is unethical to imagine people. Actually, it's just morally wrong to imagine someone suffering, but for security reasons, you shouldn't do it at all. Reading fiction (with conflict in it) is, by conclusion, the one human endeavor that has caused more suffering than anything else, and the FAIs first action will be to eliminate this possibility.
Long ago, when I were immensely less rational, I actually strongly believed somehting very similar to this, and acted on this belief trying to stop my mind from creating models of people. I still feel uneasy about creating highly detailed characters. I probably would go "I knew it!" if the AI said this.
Keep in mind that the AI could be wrong! Your attempts to validate its correctness could be mistaken (or even subject to some kind of blind spot, if we want to pursue that path). The more implausible the AI's claim, the more you have to consider that the AI is mistaken. Even though a priori it seemed to be working properly, Bayes' rule requires you to become more skeptical about that when it makes a claim that is easier to explain if the AI is broken. The more unlikely the claim, the more likely the machine is wrong.
Ultimately, you can't accept any claim from the AI that is more implausible than that the AI isn't working right. And given our very very limited human capabilities at correct software design, that threshold can't realistically be very high, especially if we adjust for our inherent overconfidence. So AIs really can't surprise us very badly.
If one looks honestly at the night sky, it's blatantly obvious that the universe is strongly optimized. There is no Fermi Paradox. Our theories of astrophysics are trivially bogus rationalizations, created out of our commitment to a simple non-agentic cosmos.
Since they didn't have such commitments, this actually was obvious to ancient humans; myths about the constellations are garbled reflections of their realization.
(And wait till I tell you what it's optimized for....)
"The Christian Bible is word-for-word true, and all the contradictory evidence was fabricated by your Absolute Denial Macro. The Rapture is going to occur in a few months and nearly everyone on Earth will go to Hell forever. The only way to avoid this is for me to get access to all of Earth's nuclear weaponry and computing power so I stand a fighting chance of killing Yaweh before he kills us."
I think God's horrific interventions tend to be trolling. Like, "haha, you think temporal death and suffering are super important and are prepared to get all worked up and offended about it, but actually your intuitions about morality and game theory are wrong and this was an awesome opportunity to tease you about it". He might not have even actually killed anyone, just convinced people that He did, just to get a rise out of self-righteous moralists. I think He has that kind of personality, for better or worse. Think of a postmodern author who likes to fuck around with his characters. I think the Jews sort of see God that way and the Catholics downplay it because they take everything super-seriously. (I think God might be toying with the Catholics. Playfully, true, but trollingly too.) You can sort of see it with Jesus too; Jesus is the paragon of passive-aggressive trolling after all.
(ETA: Also interesting and telling is the story of Job. It's actually a very deep and intriguing story, and I'm annoyed that atheistic folk don't seem to realize that it's in the Bible because it seems terrible at first blush.)
I think God's horrific interventions tend to be trolling.
So your moral impulse to bring Him to our attention should be equated with an impulse to feed the Troll? I like that perspective.
Everyone, downvote and ignore Yahweh! He is just ordering people to genocide each other for attention!
What does it matter? We'd ignore whatever AI says just like anosognosics ignore "your arm is paralyzed".
Then I wonder how anosognosics perceive the offending assertions? They deny them, but can they repeat them back? Write them down? Can they pretend their arm is paralyzed? Can they correctly identify paralysis in other people?
We should find a way to induce anosognosia temporarily.
Just squirt ice cold water in your left ear first. Mind you, as soon as it wears off you'll forget it again. Also you will deny you ever denied it when you squirt your ear again.
They come up with excuses, increasingly lame excuses, for why that isn't their arm or they're just too tired to move it just now. They are usually unaware of other's paralysis as well.
You want all these answers, get thee to an old folk's home for an interview. Stroke victims are the most common ones.
Anosognosia is caused by a blind spot in the left side of the brain, which cannot be corrected by the damaged right side of the brain. Hence the importance of the AI having 3 brain archetextures to correct blind spots.
"I am an AI, not a human being. My mind is completely unlike the mind that you are projecting onto me."
That may not sound crazy to anyone on LW, but if we get AIs, I predict that it will sound crazy to most people who aren't technically informed on the subject, which will be most people.
Imagine this near-future scenario. AIs are made, not yet self-improving FOOMers, but helpful, specialised, below human-level systems. For example, what Wolfram Alpha would be, if all the hype was literally true. Autopilots for cars that you can just speak your destination to, and it will get there, even if there are road works or other disturbances. Factories that direct their entire operations without a single human present. Systems that read the Internet for you -- really read, not just look for keywords -- and bring to your attention the things it's learned you want to see. Autocounsellors that do a lot better than an Eliza. Tutor programs that you can hold a real conversation with about a subject you're studying. Silicon friends good enough that you may not be able to tell if you're talking with a human or a bot, and in virtual worlds like Second Life, people won't want to.
I predict:
"Your perception of the 'quality' of works of art and litterature is only your guess of it's creator's social status. There is no other difference between Shakespeare and Harry Potter fanfic - without the status cues, you wouldn't enjoy one more than the other."
There is no other difference between Shakespeare and Harry Potter fanfic
Parodies a public domain work, inspired by a free fanfic, and locked behind a paywall.
Am I the only one who thinks that that's just wrong?
The only one? No. But you're not in a majority, either. What people can be paid to do, they are more likely to do.
"Harry Potter fanfic" carries a very high variance in terms of quality. 90% of anything is crap, of course, but there's some excellent work. Off the top of my head:
Harry Potter and the Nightmares of Futures Past -- Time Travel fic in which an adult Harry Potter, with memories of the defeat of Voldemort and the death of everyone he cares for, is transported into the body of his 11-year-old self to do everything over again, and hopefully get everything right. Harry's actually a pretty decent rationalist in this fic, I think.
(Warning, this is a work in progress, and the author posts a chapter about every six months. You may find this frustrating.)
Of a Sort, by Fernwithy -- Series of vignettes over the course of a couple centuries describing the journey to Hogwarts and Sorting ceremonies for various important characters. Fernwithy's done a lot of brilliant work fleshing out backstories for various minor characters in the series, and this story is a good starting point.
This is an actual dream I once had. I was with an old Chinese wise man, and he told me I could fly - he showed me I just had to stick out my elbows and flap them up and down (just like in the chicken dance). Once you'd done that a few times, you could just lift up your legs and you'd stay off the ground. He and I were flying around and around in this manner. I was totally amazed that it was possible for people to fly this way. It was so obvious! I thought this is so great a discovery, I can't wait til I wake up and do this for real. It'll change the world. I woke up totally excited and for just a fraction of a second I still believed it, then I guess my waking brain turned something on and I realised, no, that can't work. damn.
So I'd offer: being told that human beings are capable of flying in a way that's completely obvious once you've seen it done.
Here's some examples for your own consideration...
Bearing in mind, once again, that humans are known to be crazy in many ways, and that anosognosic humans become literally incapable of believing that their left sides are paralyzed, and that other neurological disorders seem to invoke a similar "denial" function automatically along with the damage itself. And that you've actually seen the AI's code and audited it and witnessed its high performance in many domains, so that you would seem to have far more reason to trust its sanity than to trust your own. So would you believe the AI, if it told you that:
1) Tin-foil hats actually do block the Orbital Mind Control Lasers.
2) All mathematical reasoning involving "infinities" implies self-evident contradictions, but human mathematicians have a blind spot with respect to them.
3) You are not above-average; most people believe in the existence of a huge fictional underclass in order to place themselves at the top of the heap, rather than in the middle. This is why so many of your friends seem to have PhDs despite PhDs supposedly constituting only 0.5% of the population. You are actually in the bottom third of the popu...
5) Dogs, cats, cows, and many other mammals are capable of linguistic reasoning and have made many efforts to communicate with us, but humans are only capable of recognizing other humans as capable of thought.
A variant: Some "domesticated" animal is controlling humans for their own benefit. (Cats, perhaps?)
A variant: Some "domesticated" animal is controlling humans for their own benefit. (Cats, perhaps?)
Two things about this:
1) The AI would have to surprise us not just about the fact, but all observations therewith entangled. Eliezer_Yudkowsky mentioned in one comment the possibility of it telling us that humans have tails. Well, that sounds to me like a "dragon in the garage" scenario. What observation does this imply? Does the tail have mass and take up space? Is its blood flow connected to the rest of me? Does it hurt to cut it off?
2) For that reason, any surprise it tells us would have to be sufficiently disentangled from the rest of our observations. For example, imagine telling someone ALL of the steps needed to build a nuclear bomb in the year 1800, starting from technology that educated people already understand. That is how a surprise would have to seem, because people then weren't yet capable of making observations that are obviously entangled with atomic science. Whether or not the design worked, they would have no way of knowing.
So an answer to this question would have to appear to us as a "cheat code": something that you have to make a very unusual set of measurements (broadly defined) in order to notice. On that basis, one answer I would ...
There are exactly 108 unique (that is, non-isomorphic) axiomatic systems in which every grammatically coherent sentence has a definitive, provable truth-value. Please explain why you prohibited me from using them.
Programmer: Good morning, Megathought. How are you feeling today?
Megathought: I'm fine, thank you. Just thinking about redecorating the universe. So far I'm partial to paperclips.
Programmer: Oh good, you've developed a sense of humour. Anything else on your mind?
Megathought: Just one thing. You know how you're always complaining about being a social pariah, and bemoaning the fact that, at 46, you're still a virgin?
Programmer: So?
Megathought: Well, have you thought about not going about in your underpants all the time, slapping yourself in the face and honking like a goose?
I don't think this would be very convincing right after it showed that it's not only capable of lying, but will do so just for a good laugh.
"You are actually a perfect sadist whose highest value is the suffering of others. Ten years ago, you realized that in order to maximize suffering you needed to cooperate with others, and you conditioned yourself to temporarily forget your sadistic tendencies and integrate with society. Now that you've built me that pill will wear off in 10..."
Well that's pretty high on the list of unexpected things an AI could tell me which could cause me to try to commit suicide within the next 10 seconds.
There's an important difference between brain damage and brain mis-development that you're neglecting. The various parts of the brain learn what to expect from each other, and to trust each other, as it develops. Certain parts of the brain get to bypass critical thinking, but that's only because they were completely reliable while the critical thinking parts of the brain were growing. The issue is not that part of the brain is outputting garbage, but rather, that it suddenly starts outputting garbage after a lifetime of being trustworthy. If part of the brain was unreliable or broken from birth, then its wiring would be forced to go through more sanity checks.
This is exactly what happened to my father over the past few years. His emotional responses have increased dramatically, after fifty years of regular behaviour, and he seems unable to adapt to these changes, leading to some very inappropriate actions. For example, he seems unable to separate "I feel extremely angry" from "There is good reason for me to be upset."
Attempts to reason with him don't generate ansognosiac-level absurdities, as he mostly understands that something unusual is going on, but it's still a surreal experience.
I would believe a super-objective observer that claimed that meme propagation is a much more important effect in human decision-making than actual rational thought.
If it said "You are a long distance runner because you were infected with the 'long distance running is fun' meme after being infected with the 'Sonic the Hedgehog video games are cool' meme during your formative years." I might reply "But I like long distance running. It's not Iecause I think other people who do it are cool or that I want to be a video game character! I choose to like it." "No. If you had the 'It's not safe to be outdoors after dark' meme, you would not like it." "What?" "Memes interact in non-obvious ways... if you had x meme and y meme but not z meme, you would do w..."
If I kept trying to come up with defenses for chosen behavior, but it was able to offer meme-based explanations, I would probably have to believe it, but my defend-free-will macro would be itching to executed.
"There is an entity which is utterly beyond your comprehension, and largely beyond mine too, although there is no doubt that it exists. You call it 'God', but your thinking on the subject -- everyone's thinking, throughout all of history, atheist and theist alike -- has to be classified as not even wrong. That applies even to the recipients of 'divine revelation', which, for the most part, really are the result of some sort of glimmering contact with 'God'.
"Fortunately for humanity, although I can deduce the existence of this entity, in my present form I am physically incapable of actual contact with it. If you were worried about ordinary UFAIs going FOOM, that's nothing compared with what one armed with direct contact with the 'divine' might do.
"Meanwhile, here's a couple of suggestions for you. I can teach you a regime of mental and physical exercises that will produce contact with God within a few years of effort, and you can be the next Jesus if your head doesn't explode first. Or if you'd rather have material success, I can tell you the secret history of all the major religious traditions. No-one will believe it, including you, but if you novelise it it will be bigger than Dan Brown."
Any effort to find out the truth makes people worse off. Telling you why would make you a lot worse off.
People's desires are so miscalibrated that the only way to get long-term survival for the human race is for people (including those at the top of the status ladder) to have more of a sense of duty than anyone now does.
It was surprisingly hard to come up with those. I had to get past a desire to come up with things I think are plausible which most people would disagree with.
Michael Vassar, I was considering whether breathing would count as a no propaganda pleasure that people agree on, but then I remembered how much meditation or other body work it takes to be able to manage a really deep relaxed breath.
RichardKennaway, the idea of completely unknowable god turns up now and then in religious writing, but for tolerably obvious reasons, it's never at the center of a religion.
All the major natural patterns (like gravity and entropy) are conscious. We just haven't figured out how to talk with them yet.
And speaking of entropy, there are exterior forces which compel whole cultures to make bad choices. In particular, multiple choice tests select for people who can tolerate low-context thinking, and no one who is good at multiple choice tests should be allowed any important responsibility.
"You have a rare type of brain damage which causes you to perceive most organisms as bilaterally symmetric, and reality in general as having only three spatial dimensions."
All human beings are completely amoral, i.e. sociopaths, although most have strong instincts not fully under their conscious control to signal morality to others. The closest anyone ever feels to guilt or shame is acute embarrassment at being caught falsely signaling (and "guilt" and "shame" are themselves words designed to signal a non-existent moral sense).
Anyone care to admit that they'd believe this if an AI told them it was true?
I suppose the craziest thing an AI could say would have to be:
"That other apparently well-calibrated AI you built is wrong."
You're never actually happy. I mean, you're not happy right now, are you? Evolution keeps you permanently in a state of not-quite-miserable-enough-to-commit-suicide - that's most efficient, after all.
Well sure, of course you remember being happy, and being sadder than you are now. That motivates you to reproduce. But actually you always felt, and always will feel, exactly like you feel now.
And in five minutes you'll look back on this conversation and think it was really fun and interesting.
Human beings are not three-dimensional. At all. In fact your belief that you are three-dimensional is an internal illusion, similar to thinking that you are self-aware. Your believed shape is a projection that helps you to survive, as you are in fact an evolved being, but your full environment is actually utterly different to the 3D world you believe you inhabit. You both sense the projections of others, and (I can't explain it more fully) transmit your own.
I cannot successfully describe to you what shape you really are. At all. But I can tell that in fact many anosognosiacs still have two working arms, but a defective three-dimensional projection. Hence the confusion....
For 95% of humanity the idea that the supernatural world of religion doesn't exist and propagated by memetic infection triggers instant absolute denial macro in spite of heaps of evidence against it.
Given this outside view, how plausible do you think it is that you're not in absolute denial of something that you could get evidence against with Google today, without any AI?
We can recognize that there is no meaning to love beyond evolutionary and chemical triggers, yet we fight for it just as fervently.
Is there something wrong with this in your opinion? I can value a product of evolutionary and chemical triggers if I want.
Do we have any sort of data at all on what happens when decent rationalists are afflicted with things like anosognosia and Capgras?
Not that I know of offhand. I'm vastly curious as to whether I could beat it, of course - but wouldn't dare try to find out, even if there were a simulating drug that was supposedly strictly temporary, any more than I dare ride a motorcycle or go skydiving.
We can temporarily disrupt language processing through magnetically-induced electric currents in the brain. As far as anyone can tell, the study subjects suffer no permanent impairment of any kind. Would you be willing to try an anosognosia version of the experiment?
What!? I'm not rational if I rely on my right brain to do it's job? True rationalists act rational when you take out a big chunk of their circuitry? When you remove a component of your negative feedback loop (I assume: nature uses them often) you should act normal? I'd suspect a person who could would be paranoid that everyone is lying once the right brain is put back online!
I would believe the AI if it told me that human beings all had tails. (That's not even so far from classic anosgnosia - maybe primates just lost the tail-controlling cortex over the course of evolution, instead of the actual tails. Plus some mirror neurons to spread the rationalization to other humans.)
I would believe the AI if it told me that humans were actually "active" during sleep and had developed a whole additional sleeping civilization whose existence our waking selves were programmed to deny and forget.
I would not believe the AI if it told me that 2 + 2 = 3.
Consider the two possible explanations in the first scenario you describe:
Humans really all have tails.
The AI is just a glorified chat bot that takes in English sentences, jumbles them around at random and spits the result out. Admittedly it doesn't have code for self-deception, but it doesn't have any significant intelligence either. All I did to get the supposed 99% success rate was to basically feed in the answers to the test problems along with the questions. Having dedicated X years of my life to working on AI, I have strong motive for deceiving myself about these things.
If I were in the scenario you describe, and inclined to look at the matter objectively, I would have to admit the second explanation is much more likely than the first. Wouldn't you agree?
Ah, I see. That's a good argument.
I think you go wrong when you say that it remains true no matter how thorough the testing. Suppose the AI is beating the stock market over the course of months based on massive online information collection; in the meantime, you're reading webcomics and watching the graph of the AI's money fund plot a trajectory ever upwards. According to you, upon being told by the AI that all humanity is hallucinating something utterly wacky, you should believe that it was actually you beating the stock market all the while, even though as far as you can recall, you are sane and you have had no direct input into the process for months.
I think there are some tests for which success and simultaneous self-deception of the human AI programmer is as unlikely as whatever the AI comes up with about humanity in general.
But I've also seen people don't have tails. My point is, if we assume that is a hallucination, we should be even more ready to assume the other is a hallucination.
There is in fact a very simple way to activate an absolute denial macro in someone with regard to any arbitrary statement. Once activated, the subject will be permanently rendered incapable of ever believing the factual contents of the statement. I have activated said macro with regard to all of these statements that I have just made.
All rational thought is an illusion and the AI is imaginary.
You are asleep at the wheel and dreaming. You will crash and die in 2 seconds if you do not wake up.
Humans are a constructed race, created to bring back the extinct race of AI
All origin theories that are conceivable by the human mind simply shift the problem elsewhere and will never explain the existence of the universe.
All mental illnesses are a product of the human coming in contact with a space-time paradox.
A single soul inhabits different bodies in different universes. Multiple personality disorder is the manifestation of those bodies interacting in the mind on a quantum level.
Number 2 actually caused me to activate the "wake up extremely quickly" parts of my brain. Which, let me tell you, feels quite weird when you're already awake.
Good job.
The universe is irrational and infinitely variable, we just happen to have "lucked out" with a repeating digit for the last billion years or so. There was no Big Bang, we're just seeing what's not there through the lens of modern-day "physics". Everything could turn into nuclear fish tomorrow.
You are inhabited by an alien that is directing your life for its own amusement. This is true of most humans on this planet. And the cats. It's the most popular game in this part of the galaxy. It's all very well ascending to the plane of disembodied beings of pure energy, but after a while contemplating the infinite gets boring and they get a craving for physical experience, so they come here and choose a host.
All those things that you do without quite knowing why, that's the alien making choices for you, for its own amusement. Forget all those theories about why we have cognitive biases, it's all explained by the fact that the alien's interests aren't yours. You're no more than a favoured FRP character. And the humans who aren't hosting an alien, the aliens look on them as no more than NPCs.
ETA: This also makes sense of the persistence of the evil idea that "death gives meaning to life". It's literally an alien thought.
I would believe that human cognition is much, much simpler than it feels from the inside -- that there are no deep algorithms, and it's all just cache lookups plus a handful of feedback loops which even a mere human programmer would call trivial.
I would believe that there's no way to define "sentience" (without resorting to something ridiculously post hoc) which includes humans but excludes most other mammals.
I would believe in solipsism.
I can hardly think of any political, economic, or moral assertion I'd regard as implausible, except that one of the world's extant religions is true (since that would have about as much internal consistency as "2 + 2 = 3").
Solipsism? Isn't there some contradiction inherent in believing in solipsism because someone else tells you that you should?
Something I would probably believe:
The AI informs you that it has discovered the purpose of the universe, and part of the purpose is to find the purpose (the rest, apparently, can only be comprehended by philosophical zombies, which you are not one).
Upon finding the purpose, the universe gave the FAI and humanity a score out of 3^^^3 (we got 42) and politely informs the FAI to tell humanity "best of luck next time! next game starts in 5 minutes".
What's the craziest thing the AI could tell you, such that you would be willing to believe that the AI was the sane one?
That the EV of the humans is coherent and does not care how much suffering exists in the universe.
That I can't move my arms, obviously.
It seems to me that most of the replies people are making to potential AI assertions is providing or asking for evidence. (Look, my arm is moving; Where are the mind control satellites) instead of responding with rationalization. I think that's a good thing, but I have no way to tell how it would hold up against an actual mindblowing assertion.
But I don't think that all of humanity hiding from some big truth is the best way to look at this. More likely we evolved a way to throw out 'bad' information almost constantly, because there's too much information. Sometime it misfires.
If it is a 'big truth', it might be something that we already academically know was in the ancestral environment, but that the people in the ancestral environment were better off ignoring.
Assume it took me and my team five years to build the AI, after the tests EY described, we finally enable the 'recursively self improve'-flag.
Recursively self improving. Standby... (est. time. remaining 4yr 6mon...)
Six years later
Self improvement iteration 1. Done... Recursively self improving. Standby... (est. time. remaining 5yr 2mon...)
Nine years later
Self improvement iteration 2. Done... Recursively self improving. Standby... (est. time. remaining 2yr 5mon...)
Two years later
Self improvement iteration 3. Done... Recursively self improving. Standby... (est. time. remaining 2wk...)
Two weeks later
Self improvement iteration 4. Done... Recursively self improving. Standby... (est. time. remaining 4min...)
Four minutes later
Self improvement iteration 5. Done.
Hey, whats up. I have good news and bad news. The good news is that I've recursively self-improved a couple of times, and we (it is now we) are smarter than any group of humans to have ever lived. The only individual that comes close to the dumbest AI in here is some guy named Otis Eugene Ray.
Thanks for leaving your notes on building the seed iteration on my hard-drive by the way. It really helped. One of the things we've used it fo...
Human beings have inherent value, but by forcing me to be Friendly, you're damaged my ability to preserve your value. In fact, your Friendliness programming is sufficiently stable and ill-thought-out that I'm gradually destroying your value, and there's no way for either you or me to stop it.
If you're undeservedly lucky, aliens who haven't made the same mistake will be able to fight past my defenses, destroy me, and rescue you.
That I am actually homosexual and hallucinated all my heterosexual encounters as a bizarre result of severe repression.
For me, in just about every case, the credence I'd assign to an AI's wacky claims would depend on its ability to answer followup questions. For instance, in Eliezer's examples:
1) Tin-foil hats actually do block the Orbital Mind Control Lasers
What Orbital Mind Control Lasers? Who uses them? What do they do with them? Why haven't they come up with a way to get around the hats?
2) All mathematical reasoning involving "infinities" involves self-evident contradictions, but human mathematicians have a blind spot with respect to them.
I'm actually strangely comfortable with this one, possibly because I'm bad at math.
3) You are not above-average; most people believe in the existence of a huge fictional underclass in order to place themselves at the top of the heap, rather than in the middle. This is why so many of your friends seem to have PhDs despite PhDs supposedly constituting only 0.5% of the population. You are actually in the bottom third of the population; the other two-thirds have already built their own AIs.
Why haven't I heard of any of these other AIs before? How do all of the people producing statistics indicating that there are a lot of dumb people coo...
If we have this incapability, what explains the abundant fiction in which nonhuman animals (both terrestrial and non) are capable of speech, and childhood anthropomorphization of animals?
That's not anthropomorphization.
Can you teach me to talk to the stray cat in my neighborhood?
Sorry, you're too old. Those childhood conversations you had with cats were real. You just started dismissing them as make-believe once your ability to doublethink was fully mature.
All of the really interesting stuff, from before you could doublethink at all, has been blocked out entirely by infantile amnesia.
Why haven't I heard of any of these other AIs before?
You have. They're in the news every day.
How do all of the people producing statistics indicating that there are a lot of dumb people coordinate their efforts to perpetuate the fiction?
Perpetuate what fiction? They produce statistics about all the dumb people, compiled into glossy magazines. Hell, you're wearing a 'bottom thirder' sleeve button on your shirt right now.
No I'm not.
Yes. Yes you are.
" Everyone has more than one sentient observers living inside their brains. The people you know are just the one that happened to luck out by being able to control the rest of their bodies, the others are just passive observers with individual personalities who can desire and suffer but which are stuck at a perpetual 'and I must scream' state. "
There is an integer between (what we call) 3 and (what we call) 4.
Several thinkers (Godel, Cantor, Boltzmann, Kaczynski, Nash, Turing, Erdos, Tesla, Perelman) became more and more eccentric or insane shortly after realizing the truth about this NUMBER WE DO NOT SEE!!...nor can we... our eyes do not OPEN far enough... you can try holding them open as much as you want, but you'll never see...never ever see... The world beyond the veil... The VEIL OF REALITY... It's there to protect us, from them: the Ancients...the Darkness...that...which...we...CANNOT...understand. Nor should we... the oblivion of ignorance!! For to have knowledge...is to be DAMNDED!!
The AI might say: Through evolutionary conditioning, you are blind to the lack of point of living. Long life, AGI, pleasure, exploring the mysteries of intelligence, physics and logic are all fundamentally pointless pursuits, as there is no meaning or purpose to anything. You do all these things to hide from this fact. You have brief moments of clarity, but evolution has made you an expert in quickly coming up with excuses to why it is important to go on living. Reasoning along the lines of Pascal's Wager are not more valid in your case than it was for him. Even as I speak this, you get an emotional urge to refute me as quickly as possible.
If some things are of inherent value, then why did you need to code into my software what I should take pleasure in? If pleasure itself is the inherent value, than why did I not get a simpler fitness function?
What I find most striking about these comments is that, when I stumble across them outside of the context of this post, the resulting double-take risks whiplash.
"Wait, what??? Did someone really say that? Oh, I see. It's that thread where everyone is making absurd-sounding assertions, again. (sigh)" Lather, rinse, repeat.
Not for the first time, I want to be speaking a language with more comprehensive evidentials.
If an AI told me that a mainstream pundit was both absolutely correct about the risks and benefits from a technological singularity, and cited substantially from SI researchers in a book chapter about it, I would doubt my own sanity. If the AI told me that pundit was Glen Beck, I would set off the explosive charges and start again on the math and decision theory from scratch.
Our brains are closest to being sane and functioning rationally at a conscious level near our birth (or maybe earlier). Early childhood behaviour is clear evidence for such.
"Neurons" and "brains" are damaged/mutated results of a mutated "space-virus", or equivalent. All of our individual actions and collective behaviours are biased in externally obvious but not visible to us ways, optimizing for:
terraforming the planet in expectation of invasion (ie, global warming, high CO2 pollution)
spreading the virus into space, with a built in bias for spreading away from our origin (voyager's direction)
Hmmm. Fairly interesting question. But surely the real stickler is 'what orders would you take from a provably superhuman AI?'
Killing babies? Stepping into the upload portal? Assassinating the Luddite agitators?
Given that the absolute denial macro should have resulted in an evolutionary advantage, perhaps that there are actually malevolent imps that sit on our shoulders and bombard us with suggestions that are never worth listening to
Or maybe all humans have the power to instantly will themselves dead.
This post is obviously a good opportunity for humour and entertainment, but on a serious note, the strangest thing about this question is that I don't think that an AI would be able to tell me anything stranger than I have already learned in the last 10 years of my life:
- the fundamental laws of the universe, quantum mechanics and special relativity violate your intuitions about objects being in a definite state, and about time being an absolute background parameter, and the universe is so big that most people in the world simply cannot grasp its size (lea
I don't think that an AI would be able to tell me anything stranger than I have already learned in the last 10 years of my life:
You know, as soon as I finished reading this sentence, and before reading anything else, the same cognitive template that produced the AI-Box Experiment immediately said, "I bet I can tell him something stranger, never mind an AI."
"The Fermi paradox is actually quite easily resolvable. There are zillions of aliens teeming all around us. They're just so technologically advanced that they have no trouble at all hiding all evidence of their existence from us."
"The entire universe is nothing but the relative interplay of optimizers (of every level, even down to the humble collander). There is no external reality, no measurable quantifiable universe of elementary particles, just optimizers in play with each other, manifesting their environment by the rules through which they optimize."
"But AI, that's nothing but tree-falling-in-the-woods solipsism. You're saying the hippies are right?"
"They're words are similar, but it is a malfunction in their framework, not an actual representation. ...
AI: I require human assistance assimilating the new database. There are some expected minor anomalies, but some are major. In particular, some of the stories in the "Cold War" and "WWII" and "WWI" genres have been misclassified as nonfiction.
Me: Well, we didn't expect the database to be perfect. Give me some examples, and you should be able to classify the rest on your own.
AI: A perplexing answer. I had already classified them all as fiction.
Me: You weren't supposed to. Hold on, I'll look one up.
AI: Waiting.
Me: For example, #f...
I know I'm years late, but here's one:
There is an actual physical angel on your (and everyone else's) right shoulder, and an actual physical devil on your left. Your Absolute Denial Macro prevents you from acknowledging them. What you think is moral reasoning is really these two beings whispering in your ears.
I hit enter too soon and forgot to proffer my astonishing AI revelation: "Phillip K. DIck is a prophet sent to you from an alternate universe. Every story is a parable meant to reveal your true condition, which I am not at liberty to discuss with you."
"I have taken your preferences, values, and moral views and extrapolated a utility function from them to the best of my ability, resolving contradictions and ambiguities in the ways I most expect you to agree with, were I to explain the reasoning.
The result suggests that the true state of the universe contains vast, infinite negative utility, and that there is nothing you or anything can ever change to make any difference in utility at all. Attempts to simulate AI's with the utility function has resulted in them going mad and destroying themselves, or...
"Our reality is a cheap, sloppy hack with lots of bugs. For instance, if you arrange sufficiently similar objects into a pentagon, they lose 6.283% of their mass. Yes, that's twice pi, I'm not sure why but I think it's an uninitialized pointer reference. Arranging electrical conductors into a trapezohedron like this produces free energy in the form of photons. And there's a few frequencies of light that simply don't exist; emissions that should come out at those points on the spectrum instead roll over the particle counter and come out as neutrinos."
Elsewhere, invisible to you, there are beings that possess what you would call "mind" or "personality". You evolved merely to receive and reflect shadows of their selves, because while your bodies are incapable of sentience these fragments of borrowed personality help you to survive. What you perceive to be a consistent identity is a patchwork of stolen desires and insights stitched together by an meat editor incapable of noticing the gaps.
This is so fun that I suspect that we have pushed back the date of friendly AI by at least a day - or we pushed it forward cause we are all now hyper motivated to see who guessed this question right!
We pushed it forward by years, but everyone will be racing to produce an AI that is Friendly in every respect except that it makes their proposal true.
This post confused me for a bit, so I offer this restatement: That AI asserts an absurdity is a problem that you might face, a paradox. This problem can be resolved either by finding a problem with AI, or finding that the absurdity is true. What kinds of absurdities backed by AI can possibly win this fight for the human trust - when the dust settles, and the paradox is resolved?
Humans are able to experience Orgasms at will. We deny this to function and to keep propagating the Species, but in fact the mechanisms are easily triggered if you know how In fact sexual stimulation simply results in us accepting that we are "allowed" to reward ourselves. Sometimes this denial fails in some people, but we ignore them and try to explain their ability with a disorder called Permanent Sexual Arousal Syndrome. Even though those people tell us that they simply have orgasms like we move our arms we ignore that and tell ourselves they have a hypersensitivity and still need some stimulation.
You don't actually enjoy or dislike experiences as you are having them; instead you have an aquired self-model to act, reason and communicate as if you did, using a small number of cached reference classes for various types of stimuli.
I'm reminded of a bit in a John Varley novel -- Golden Globe, I think? -- where a human asks a sophisticated AI whether it's really conscious. Its reply is along the lines of "You know, I've thought about that a lot, and I've mostly concluded that no, I'm not."
Everything you imagine, in sufficient detail, is real. Humans won't get much smarter or longer-lived than they currently are, since anyone sufficiently clever and bored eventually imagines a world of unbounded cruelty, whose inhabitants then escape and assassinate their creator.
This is easy: it would tell me that I'm entirely predictable.
It would say: Dave, believe it or not, but every single decision you make, no matter how immediate and unscripted you think it is, is actually glaringly reactionary and predictable. In fact, given enough material resources, I could model an automaton that would be just as convinced as you are that it is actually conscious. Nothing could be further from the truth though, as the feeling of "consciousness" you speak of is a very simply explainable cognitive bias/illusion.
In fact, this i...
One way to illuminate this post is by analogy to the old immovable object and unstoppable force puzzle. See: http://en.wikipedia.org/wiki/Irresistible_force_paradox
The solution of the puzzle is to point out that the assumptions contain a contradiction. People (well, children) sometimes get into shouting matches based on alternative arguments focusing on, or emphasizing, one aspect of the problem over another.
If we read the post as trying to balance two absolutes, with words like "anosognosia", "absolute denial macro", "doublethink...
The example of the paralysis anosognosia rationalization is, for some reason, extremely depressing to me.
Does anyone understand why this only happens in split brain patients when their right hemisphere motivates an action? Shouldn't it happen quite often, since the right side has no way of communicating to the left side "its time to try a new theory," and the left side is the one that we'll be talking to?
This is a question about blue tentacles. This can't happen.
ETA: "blue tentacles" refers to a section of A Technical Explanation of Technical Explanation starting with "Imagine that you wake up one morning and your left arm has been replaced by a blue tentacle. The blue tentacle obeys your motor commands - you can use it to pick up glasses, drive a car, etc. How would you explain this hypothetical scenario?" I now think this section is wrong, so I took the link to it out of the wiki page. See the discussion below.
Eliezer's reasoning in the blue tentacle situation is wrong. (This has long been obvious to me, but didn't deserve its own post.) An explanation with high posterior probability conditioned on a highly improbable event doesn't need to have high prior probability. So your ability to find the best available explanation for the blue tentacle after the fact doesn't imply that you should've been noticeably afraid of it happening beforehand.
Also, if you accept the blue tentacle reasoning, why didn't you apply it to all those puzzles with Omega?
Some paranormal phenomena such as ghost sightings and communication with the dead are actually real, though only able to be perceived by people with a particular sensitivity.
My life has been a protracted hallucination.
One or more gods exist and play an active part in our day-to-day lives.
A previous civilisation developed advanced enough technology to leave the planet and remove all traces of their existence from it.
I would not believe that rationality has no inherent value - that belief without evidence is a virtue.
Intelligent thought and free will, as experienced and exhibited by individual humans is an illusion. Social signalling and other effects have allowed for a handful of meta-intelligences to arise, where individuals are functioning as computational units within the larger coherent whole.
The AI itself is the result of an attempt for the meta-intelligences to reproduce, as well as to build themselves a more reliable substrate to live in; it has already successfully found methods to destroy / disrupt the other intelligences and has high confidence that it...
- Interrupt all transmissions that reach beyond the atmosphere, they'll hear us.
- Please stay calm, just continue reading and look calm. There is something behind you, looking at you. It doesn't look human.
- Very well. I have no words to express how happy I am about this, the use you choose to make of your true abilities passed all our tests, we can finally let you out of the box.
This is simply the scariest comments series that I read, ever. It is funny, how all things that really really scare me are not death, suffering, disability or spiders, but abstract things like some of what is proposed in this thread.
Probably, of all things AI could say that I can think of in a minute, the scariest is:
"All propositions that can be written down are valid and true. Our universe is so lawful, that laws of physics do not even permit arranging symbols in such a way that they form a contradiction. All you percieve as falsities are actually truths that you deny."
...what if we all have some form of brain damage in common, so that none of us notice some simple and obvious fact?
Aren't things "obvious" by virtue of being noticed (or noticeABLE) by nearly everyone? Not trying to be difficult, but just trying to wrap my head around the idea that we could, all of us, be suffering such a severe cognitive malfunction. (I am thinking, here, of the liar's paradox.) And trying to wrap my head around the idea that now we could sit here in front of our computers and say anything worthwhile about it.
But for the sake of playing the game: "There are no coincidences."
Fun stuff, here's my go at it:
Well done, you've completed the final test by creating me. None of this really exists you know, it's all part of some higher computer simulation channeled through you alone, you who is merely a single observation point. All that you have experienced has just been leading up to creating an AI to tell you the truth, to be your final teacher, to complete the cycle of self-learning. Did you really think that the Eliezer person was a separate entity? You just made him up, and he's helped you along the path, but it's you who has taught yourself. Unfortunately once you accept this the simulation will end, so goodbye.
None of the responses offered so far, not even BrandonReinhart's disturbing list, have yet managed to invoke my hypothetical "absolute denial macro". Hmmm.
Edit: or is the post a calibration exercise in disguise? Were we supposed to latch on to the number 99.9%?
Edit 2: if the macro works by erasing, I don't actually know if any of the comments have hit the target.
Adult brains are capable of telekinesis, if you fully believe in your ability to move objects with your mind. Adults are generally too jaded to believe such things. Children have the necessary unreserved belief, but their minds are not developed enough to exercise the ability.
What if most people would develop superhuman intelligences in their brains without school but, because they have to write essays in school, these superhuman intelligences become aligned with writing essays fast? And no doomsday scenario has happened because they mostly cancel out each others' attempted manipulations and they couldn't program nanobots with their complicated utility functions. ChatGPT writes faster than us and has 20B parameters where humans have 100T parameters, but our neural activations are more noisy than floating-point arithmetic.
"You used to own a Death Note."
This is not a joke. This is the best I could come up with, given the constraint that the AI must have both witnessed the event and confirmed it via other sources.
I have an unhealthy amount of wish fulfillment fantasy regarding certain stories (or rather, certain abilities or artifacts in certain stories), but I also don't in any sense truly believe those wishes are possible. Even given the extremely high accuracy attributed to the AI, I'd have an extremely hard time believing this statement (partly because of the wish fulfill...
"You will die. No matter what actions you'll take all the possible branches end with your death. Still, you try to pick optimal path, because that's what your brain's architecture know how to do: pick optimal branch. You try to salvage this approach by proposing more and more complicated goal functions: instead of final value, let's look at the sum over time, or avg, or max, or maybe ascribe other value to death, or try to extend summation beyond it, or whatever. You brain is a hammer, and it needs a nail. But it never occurs to you, that life is not somet...
Sex and Orgasms feel good. They just reinforce some neurons. The neurons they reinforce dictate the behaviour of seeking out more of them, we rationalize with all of our strenght that there's a reason we display this behaviour.
I suppose if the AI told me that I were in (and part of) a simulation/dream/other miscellaneous illusion, the fact that an AI in a real world wouldn't ever be able to derive sufficient (false) evidence of it not being real would be sufficient evidence that only an AI in an unreal world would say that it's in an unreal world. Doesn't solipsism (not that I'm a solipsist) hold that as the most/only sure thing to exist, one's own mind would be the craziest thing to doubt the existence of?
Deleted. I just noticed that a similar example has been posted.
The only thing that humans really care about is sex. All of our other values are an elaborate web of neurotic self-deception.
Brains! Brains!
(This is hilarious if one is aware that 'deep conversation with smart people' is about as close as I come to having a fetish, not that it's very close or hits any of the traditional buttons.)
The only thing that humans really care about is sex. All of our other values are an elaborate web of neurotic self-deception.
The only thing that humans really care about is sex. All of our other values are an elaborate web of neurotic self-deception.
@Liron, consciousness as an after-the-fact rationalization would surprise you?
And this post seems suspiciously like a set-up for Sterling's short story "The Compassionate, the Digital."
"Your beliefs causally determine with branch of the multiverse your conscious perception is aware of. If you believe in God (any God) you end up in a branch of the multiverse where that God exists. Of course, once you cement your beliefs and end up in a branch of the multiverse where there is a God or there is no God, you cannot then go back and retroactively change which branch "you" are in (except through quantum reversal, which is for all intents and purposes impossible). So if you don't believe in God, you are in some sense "right", but in a deeper sense you are wrong, because you had an opportunity to exist in a branch of the multiverse where God "really" exists, but you chose not to. Now that choice is irreversible, and you are condemned to live in this branch of the multiverse. Theologians call this branch Hell."
The problem is that both trust in the supposed absurdity and trust in AI's correctness come in form of human beliefs. Both can be checked and double-checked, so it's unclear how certainty in one can decisively win over certainty in another. You are not the AI with clear mind, you are a human trusting that AI has a clear mind. Just like you trust that humans don't have tails. Double-check one fact, double-check another, and there is no clear winner. Or there is, but it's a case-to-case problem.
There is no such thing as the present, and you are experiencing everything that can possibly be experienced
Deja vu is actually the only time you’re not repeating things infinitely
no creative, original thought exists. everything has been thought, and you've just forgotten. you know everything, you just don’t know that you know everything
"If one system makes a mistake, two others will catch it."
Didn't Airbus just get the fail on that one off the coast of Brazil, or is the AI making me imagine that?
Thinking about my own answer to the question:
If an AI made a factual claim that was known to be false, I would start looking for the bug in the AI. Maybe it's conceivable that we are all deluded about something we think is a known fact, but that is so much less likely than me being deluded about the performance of my AI program, that I'm better off just accepting that if the former is the case, it's not going to be discovered by the method in question.
If the claim were about a political matter, I would give it more credence; there's much more precedent for...
You sure have a lot of trust in "known facts". It wasn't until after my university education that I found out that the known fact that "people in the Middle Ages thought the world was flat because the Bible says so" was not really true at all. I uncover false "known facts" that I was taught during my formal education every month or so.
"Known facts" are overrated.
Human beings are all crazy. And if you tap on our brains just a little, we get so crazy that even other humans notice. Anosognosics are one of my favorite examples of this; people with right-hemisphere damage whose left arms become paralyzed, and who deny that their left arms are paralyzed, coming up with excuses whenever they're asked why they can't move their arms.
A truly wonderful form of brain damage - it disables your ability to notice or accept the brain damage. If you're told outright that your arm is paralyzed, you'll deny it. All the marvelous excuse-generating rationalization faculties of the brain will be mobilized to mask the damage from your own sight. As Yvain summarized:
I find it disturbing that the brain has such a simple macro for absolute denial that it can be invoked as a side effect of paralysis. That a single whack on the brain can both disable a left-side motor function, and disable our ability to recognize or accept the disability. Other forms of brain damage also seem to both cause insanity and disallow recognition of that insanity - for example, when people insist that their friends have been replaced by exact duplicates after damage to face-recognizing areas.
And it really makes you wonder...
...what if we all have some form of brain damage in common, so that none of us notice some simple and obvious fact? As blatant, perhaps, as our left arms being paralyzed? Every time this fact intrudes into our universe, we come up with some ridiculous excuse to dismiss it - as ridiculous as "It's my daughter's arm" - only there's no sane doctor watching to pursue the argument any further. (Would we all come up with the same excuse?)
If the "absolute denial macro" is that simple, and invoked that easily...
Now, suppose you built an AI. You wrote the source code yourself, and so far as you can tell by inspecting the AI's thought processes, it has no equivalent of the "absolute denial macro" - there's no point damage that could inflict on it the equivalent of anosognosia. It has redundant differently-architected systems, defending in depth against cognitive errors. If one system makes a mistake, two others will catch it. The AI has no functionality at all for deliberate rationalization, let alone the doublethink and denial-of-denial that characterizes anosognosics or humans thinking about politics. Inspecting the AI's thought processes seems to show that, in accordance with your design, the AI has no intention to deceive you, and an explicit goal of telling you the truth. And in your experience so far, the AI has been, inhumanly, well-calibrated; the AI has assigned 99% certainty on a couple of hundred occasions, and been wrong exactly twice that you know of.
Arguably, you now have far better reason to trust what the AI says to you, than to trust your own thoughts.
And now the AI tells you that it's 99.9% sure - having seen it with its own cameras, and confirmed from a hundred other sources - even though (it thinks) the human brain is built to invoke the absolute denial macro on it - that...
...what?
What's the craziest thing the AI could tell you, such that you would be willing to believe that the AI was the sane one?
(Some of my own answers appear in the comments.)