Book Read Free

Rationality- From AI to Zombies

Page 31

by Eliezer Yudkowsky


  I suspect that, in general, if two rationalists set out to resolve a disagreement that persisted past the first exchange, they should expect to find that the true sources of the disagreement are either hard to communicate, or hard to expose. E.g.:

  Uncommon, but well-supported, scientific knowledge or math;

  Long inferential distances;

  Hard-to-verbalize intuitions, perhaps stemming from specific visualizations;

  Zeitgeists inherited from a profession (that may have good reason for it);

  Patterns perceptually recognized from experience;

  Sheer habits of thought;

  Emotional commitments to believing in a particular outcome;

  Fear of a past mistake being disproven;

  Deep self-deception for the sake of pride or other personal benefits.

  If the matter were one in which all the true rejections could be easily laid on the table, the disagreement would probably be so straightforward to resolve that it would never have lasted past the first meeting.

  “Is this my true rejection?” is something that both disagreers should surely be asking themselves, to make things easier on the Other Fellow. However, attempts to directly, publicly psychoanalyze the Other may cause the conversation to degenerate very fast, in my observation.

  Still—“Is that your true rejection?” should be fair game for Disagreers to humbly ask, if there’s any productive way to pursue that sub-issue. Maybe the rule could be that you can openly ask, “Is that simple straightforward-sounding reason your true rejection, or does it come from intuition-X or professional-zeitgeist-Y?” While the more embarrassing possibilities lower on the table are left to the Other’s conscience, as their own responsibility to handle.

  *

  78

  Entangled Truths, Contagious Lies

  One of your very early philosophers came to the conclusion that a fully competent mind, from a study of one fact or artifact belonging to any given universe, could construct or visualize that universe, from the instant of its creation to its ultimate end . . .

  —First Lensman1

  If any one of you will concentrate upon one single fact, or small object, such as a pebble or the seed of a plant or other creature, for as short a period of time as one hundred of your years, you will begin to perceive its truth.

  —Gray Lensman2

  I am reasonably sure that a single pebble, taken from a beach of our own Earth, does not specify the continents and countries, politics and people of this Earth. Other planets in space and time, other Everett branches, would generate the same pebble. On the other hand, the identity of a single pebble would seem to include our laws of physics. In that sense the entirety of our Universe—all the Everett branches—would be implied by the pebble. (If, as seems likely, there are no truly free variables.)

  So a single pebble probably does not imply our whole Earth. But a single pebble implies a very great deal. From the study of that single pebble you could see the laws of physics and all they imply. Thinking about those laws of physics, you can see that planets will form, and you can guess that the pebble came from such a planet. The internal crystals and molecular formations of the pebble formed under gravity, which tells you something about the planet’s mass; the mix of elements in the pebble tells you something about the planet’s formation.

  I am not a geologist, so I don’t know to which mysteries geologists are privy. But I find it very easy to imagine showing a geologist a pebble, and saying, “This pebble came from a beach at Half Moon Bay,” and the geologist immediately says, “I’m confused” or even “You liar.” Maybe it’s the wrong kind of rock, or the pebble isn’t worn enough to be from a beach—I don’t know pebbles well enough to guess the linkages and signatures by which I might be caught, which is the point.

  “Only God can tell a truly plausible lie.” I wonder if there was ever a religion that developed this as a proverb? I would (falsifiably) guess not: it’s a rationalist sentiment, even if you cast it in theological metaphor. Saying “everything is interconnected to everything else, because God made the whole world and sustains it” may generate some nice warm ’n’ fuzzy feelings during the sermon, but it doesn’t get you very far when it comes to assigning pebbles to beaches.

  A penny on Earth exerts a gravitational acceleration on the Moon of around 4.5 × 10-31 m/s2, so in one sense it’s not too far wrong to say that every event is entangled with its whole past light cone. And since inferences can propagate backward and forward through causal networks, epistemic entanglements can easily cross the borders of light cones. But I wouldn’t want to be the forensic astronomer who had to look at the Moon and figure out whether the penny landed heads or tails—the influence is far less than quantum uncertainty and thermal noise.

  If you said “Everything is entangled with something else” or “Everything is inferentially entangled and some entanglements are much stronger than others,” you might be really wise instead of just Deeply Wise.

  Physically, each event is in some sense the sum of its whole past light cone, without borders or boundaries. But the list of noticeable entanglements is much shorter, and it gives you something like a network. This high-level regularity is what I refer to when I talk about the Great Web of Causality.

  I use these Capitalized Letters somewhat tongue-in-cheek, perhaps; but if anything at all is worth Capitalized Letters, surely the Great Web of Causality makes the list.

  “Oh what a tangled web we weave, when first we practise to deceive,” said Sir Walter Scott. Not all lies spin out of control—we don’t live in so righteous a universe. But it does occasionally happen, that someone lies about a fact, and then has to lie about an entangled fact, and then another fact entangled with that one:

  “Where were you?”

  “Oh, I was on a business trip.”

  “What was the business trip about?”

  “I can’t tell you that; it’s proprietary negotiations with a major client.”

  “Oh—they’re letting you in on those? Good news! I should call your boss to thank him for adding you.”

  “Sorry—he’s not in the office right now . . .”

  Human beings, who are not gods, often fail to imagine all the facts they would need to distort to tell a truly plausible lie. “God made me pregnant” sounded a tad more likely in the old days before our models of the world contained (quotations of) Y chromosomes. Many similar lies, today, may blow up when genetic testing becomes more common. Rapists have been convicted, and false accusers exposed, years later, based on evidence they didn’t realize they could leave. A student of evolutionary biology can see the design signature of natural selection on every wolf that chases a rabbit; and every rabbit that runs away; and every bee that stings instead of broadcasting a polite warning—but the deceptions of creationists sound plausible to them, I’m sure.

  Not all lies are uncovered, not all liars are punished; we don’t live in that righteous a universe. But not all lies are as safe as their liars believe. How many sins would become known to a Bayesian superintelligence, I wonder, if it did a (non-destructive?) nanotechnological scan of the Earth? At minimum, all the lies of which any evidence still exists in any brain. Some such lies may become known sooner than that, if the neuroscientists ever succeed in building a really good lie detector via neuroimaging. Paul Ekman (a pioneer in the study of tiny facial muscle movements) could probably read off a sizeable fraction of the world’s lies right now, given a chance.

  Not all lies are uncovered, not all liars are punished. But the Great Web is very commonly underestimated. Just the knowledge that humans have already accumulated would take many human lifetimes to learn. Anyone who thinks that a non-God can tell a perfect lie, risk-free, is underestimating the tangledness of the Great Web.

  Is honesty the best policy? I don’t know if I’d go that far: Even on my ethics, it’s sometimes okay to shut up. But compared to outright lies, either honesty or silence involves less exposure to recursively propagating risks you
don’t know you’re taking.

  *

  1. Edward Elmer Smith and A. J. Donnell, First Lensman (Old Earth Books, 1997).

  2. Edward Elmer Smith and Ric Binkley, Gray Lensman (Old Earth Books, 1998).

  79

  Of Lies and Black Swan Blowups

  Judge Marcus Einfeld, age 70, Queen’s Counsel since 1977, Australian Living Treasure 1997, United Nations Peace Award 2002, founding president of Australia’s Human Rights and Equal Opportunities Commission, retired a few years back but routinely brought back to judge important cases . . .

  . . . went to jail for two years over a series of perjuries and lies that started with a £36, 6-mph-over speeding ticket.

  That whole suspiciously virtuous-sounding theory about honest people not being good at lying, and entangled traces being left somewhere, and the entire thing blowing up in a Black Swan epic fail, actually does have a certain number of exemplars in real life, though obvious selective reporting is at work in our hearing about this one.

  *

  80

  Dark Side Epistemology

  If you once tell a lie, the truth is ever after your enemy.

  I have previously spoken of the notion that, the truth being entangled, lies are contagious. If you pick up a pebble from the driveway, and tell a geologist that you found it on a beach—well, do you know what a geologist knows about rocks? I don’t. But I can suspect that a water-worn pebble wouldn’t look like a droplet of frozen lava from a volcanic eruption. Do you know where the pebble in your driveway really came from? Things bear the marks of their places in a lawful universe; in that web, a lie is out of place. (Actually, a geologist in the comments says that most pebbles in driveways are taken from beaches, so they couldn’t tell the difference between a driveway pebble and a beach pebble, but they could tell the difference between a mountain pebble and a driveway/beach pebble. Case in point . . .)

  What sounds like an arbitrary truth to one mind—one that could easily be replaced by a plausible lie—might be nailed down by a dozen linkages to the eyes of greater knowledge. To a creationist, the idea that life was shaped by “intelligent design” instead of “natural selection” might sound like a sports team to cheer for. To a biologist, plausibly arguing that an organism was intelligently designed would require lying about almost every facet of the organism. To plausibly argue that “humans” were intelligently designed, you’d have to lie about the design of the human retina, the architecture of the human brain, the proteins bound together by weak van der Waals forces instead of strong covalent bonds . . .

  Or you could just lie about evolutionary theory, which is the path taken by most creationists. Instead of lying about the connected nodes in the network, they lie about the general laws governing the links.

  And then to cover that up, they lie about the rules of science—like what it means to call something a “theory,” or what it means for a scientist to say that they are not absolutely certain.

  So they pass from lying about specific facts, to lying about general laws, to lying about the rules of reasoning. To lie about whether humans evolved, you must lie about evolution; and then you have to lie about the rules of science that constrain our understanding of evolution.

  But how else? Just as a human would be out of place in a community of actually intelligently designed life forms, and you have to lie about the rules of evolution to make it appear otherwise; so too, beliefs about creationism are themselves out of place in science—you wouldn’t find them in a well-ordered mind any more than you’d find palm trees growing on a glacier. And so you have to disrupt the barriers that would forbid them.

  Which brings us to the case of self-deception.

  A single lie you tell yourself may seem plausible enough, when you don’t know any of the rules governing thoughts, or even that there are rules; and the choice seems as arbitrary as choosing a flavor of ice cream, as isolated as a pebble on the shore . . .

  . . . but then someone calls you on your belief, using the rules of reasoning that they’ve learned. They say, “Where’s your evidence?”

  And you say, “What? Why do I need evidence?”

  So they say, “In general, beliefs require evidence.”

  This argument, clearly, is a soldier fighting on the other side, which you must defeat. So you say: “I disagree! Not all beliefs require evidence. In particular, beliefs about dragons don’t require evidence. When it comes to dragons, you’re allowed to believe anything you like. So I don’t need evidence to believe there’s a dragon in my garage.”

  And the one says, “Eh? You can’t just exclude dragons like that. There’s a reason for the rule that beliefs require evidence. To draw a correct map of the city, you have to walk through the streets and make lines on paper that correspond to what you see. That’s not an arbitrary legal requirement—if you sit in your living room and draw lines on the paper at random, the map’s going to be wrong. With extremely high probability. That’s as true of a map of a dragon as it is of anything.”

  So now this, the explanation of why beliefs require evidence, is also an opposing soldier. So you say: “Wrong with extremely high probability? Then there’s still a chance, right? I don’t have to believe if it’s not absolutely certain.”

  Or maybe you even begin to suspect, yourself, that “beliefs require evidence.” But this threatens a lie you hold precious; so you reject the dawn inside you, push the Sun back under the horizon.

  Or you’ve previously heard the proverb “beliefs require evidence,” and it sounded wise enough, and you endorsed it in public. But it never quite occurred to you, until someone else brought it to your attention, that this proverb could apply to your belief that there’s a dragon in your garage. So you think fast and say, “The dragon is in a separate magisterium.”

  Having false beliefs isn’t a good thing, but it doesn’t have to be permanently crippling—if, when you discover your mistake, you get over it. The dangerous thing is to have a false belief that you believe should be protected as a belief—a belief-in-belief, whether or not accompanied by actual belief.

  A single Lie That Must Be Protected can block someone’s progress into advanced rationality. No, it’s not harmless fun.

  Just as the world itself is more tangled by far than it appears on the surface; so too, there are stricter rules of reasoning, constraining belief more strongly, than the untrained would suspect. The world is woven tightly, governed by general laws, and so are rational beliefs.

  Think of what it would take to deny evolution or heliocentrism—all the connected truths and governing laws you wouldn’t be allowed to know. Then you can imagine how a single act of self-deception can block off the whole meta-level of truthseeking, once your mind begins to be threatened by seeing the connections. Forbidding all the intermediate and higher levels of the rationalist’s Art. Creating, in its stead, a vast complex of anti-law, rules of anti-thought, general justifications for believing the untrue.

  Steven Kaas said, “Promoting less than maximally accurate beliefs is an act of sabotage. Don’t do it to anyone unless you’d also slash their tires.” Giving someone a false belief to protect—convincing them that the belief itself must be defended from any thought that seems to threaten it—well, you shouldn’t do that to someone unless you’d also give them a frontal lobotomy.

  Once you tell a lie, the truth is your enemy; and every truth connected to that truth, and every ally of truth in general; all of these you must oppose, to protect the lie. Whether you’re lying to others, or to yourself.

  You have to deny that beliefs require evidence, and then you have to deny that maps should reflect territories, and then you have to deny that truth is a good thing . . .

  Thus comes into being the Dark Side.

  I worry that people aren’t aware of it, or aren’t sufficiently wary—that as we wander through our human world, we can expect to encounter systematically bad epistemology.

  The “how to think” memes floating around, the cached thoughts
of Deep Wisdom—some of it will be good advice devised by rationalists. But other notions were invented to protect a lie or self-deception: spawned from the Dark Side.

  “Everyone has a right to their own opinion.” When you think about it, where was that proverb generated? Is it something that someone would say in the course of protecting a truth, or in the course of protecting from the truth? But people don’t perk up and say, “Aha! I sense the presence of the Dark Side!” As far as I can tell, it’s not widely realized that the Dark Side is out there.

  But how else? Whether you’re deceiving others, or just yourself, the Lie That Must Be Protected will propagate recursively through the network of empirical causality, and the network of general empirical rules, and the rules of reasoning themselves, and the understanding behind those rules. If there is good epistemology in the world, and also lies or self-deceptions that people are trying to protect, then there will come into existence bad epistemology to counter the good. We could hardly expect, in this world, to find the Light Side without the Dark Side; there is the Sun, and that which shrinks away and generates a cloaking Shadow.

  Mind you, these are not necessarily evil people. The vast majority who go about repeating the Deep Wisdom are more duped than duplicitous, more self-deceived than deceiving. I think.

  And it’s surely not my intent to offer you a Fully General Counterargument, so that whenever someone offers you some epistemology you don’t like, you say: “Oh, someone on the Dark Side made that up.” It’s one of the rules of the Light Side that you have to refute the proposition for itself, not by accusing its inventor of bad intentions.

  But the Dark Side is out there. Fear is the path that leads to it, and one betrayal can turn you. Not all who wear robes are either Jedi or fakes; there are also the Sith Lords, masters and unwitting apprentices. Be warned, be wary.

 

‹ Prev