Rationality- From AI to Zombies

Home > Science > Rationality- From AI to Zombies > Page 4
Rationality- From AI to Zombies Page 4

by Eliezer Yudkowsky


  And “winning” here need not come at the expense of others. The project of life can be about collaboration or self-sacrifice, rather than about competition. “Your values” here means anything you care about, including other people. It isn’t restricted to selfish values or unshared values.

  When people say “X is rational!” it’s usually just a more strident way of saying “I think X is true” or “I think X is good.” So why have an additional word for “rational” as well as “true” and “good”?

  An analogous argument can be given against using “true.” There is no need to say “it is true that snow is white” when you could just say “snow is white.” What makes the idea of truth useful is that it allows us to talk about the general features of map-territory correspondence. “True models usually produce better experimental predictions than false models” is a useful generalization, and it’s not one you can make without using a concept like “true” or “accurate.”

  Similarly, “Rational agents make decisions that maximize the probabilistic expectation of a coherent utility function” is the kind of thought that depends on a concept of (instrumental) rationality, whereas “It’s rational to eat vegetables” can probably be replaced with “It’s useful to eat vegetables” or “It’s in your interest to eat vegetables.” We need a concept like “rational” in order to note general facts about those ways of thinking that systematically produce truth or value—and the systematic ways in which we fall short of those standards.

  Sometimes experimental psychologists uncover human reasoning that seems very strange. For example, someone rates the probability “Bill plays jazz” as less than the probability “Bill is an accountant who plays jazz.” This seems like an odd judgment, since any particular jazz-playing accountant is obviously a jazz player. But to what higher vantage point do we appeal in saying that the judgment is wrong?

  Experimental psychologists use two gold standards: probability theory, and decision theory.

  Probability theory is the set of laws underlying rational belief. The mathematics of probability describes equally and without distinction (a) figuring out where your bookcase is, (b) figuring out the temperature of the Earth’s core, and (c) estimating how many hairs were on Julius Caesar’s head. It’s all the same problem of how to process the evidence and observations to revise (“update”) one’s beliefs. Similarly, decision theory is the set of laws underlying rational action, and is equally applicable regardless of what one’s goals and available options are.

  Let “P(such-and-such)” stand for “the probability that such-and-such happens,” and P(A,B) for “the probability that both A and B happen.” Since it is a universal law of probability theory that P(A) ≥ P(A,B), the judgment that P(Bill plays jazz) is less than P(Bill plays jazz, Bill is an accountant) is labeled incorrect.

  To keep it technical, you would say that this probability judgment is non-Bayesian. Beliefs and actions that are rational in this mathematically well-defined sense are called “Bayesian.”

  Note that the modern concept of rationality is not about reasoning in words. I gave the example of opening your eyes, looking around you, and building a mental model of a room containing a bookcase against the wall. The modern concept of rationality is general enough to include your eyes and your brain’s visual areas as things-that-map. It includes your wordless intuitions as well. The math doesn’t care whether we use the same English-language word, “rational,” to refer to Spock and to refer to Bayesianism. The math models good ways of achieving goals or mapping the world, regardless of whether those ways fit our preconceptions and stereotypes about what “rationality” is supposed to be.

  This does not quite exhaust the problem of what is meant in practice by “rationality,” for two major reasons:

  First, the Bayesian formalisms in their full form are computationally intractable on most real-world problems. No one can actually calculate and obey the math, any more than you can predict the stock market by calculating the movements of quarks.

  This is why there is a whole site called “Less Wrong,” rather than a single page that simply states the formal axioms and calls it a day. There’s a whole further art to finding the truth and accomplishing value from inside a human mind: we have to learn our own flaws, overcome our biases, prevent ourselves from self-deceiving, get ourselves into good emotional shape to confront the truth and do what needs doing, et cetera, et cetera.

  Second, sometimes the meaning of the math itself is called into question. The exact rules of probability theory are called into question by, e.g., anthropic problems in which the number of observers is uncertain. The exact rules of decision theory are called into question by, e.g., Newcomblike problems in which other agents may predict your decision before it happens.1

  In cases like these, it is futile to try to settle the problem by coming up with some new definition of the word “rational” and saying, “Therefore my preferred answer, by definition, is what is meant by the word ‘rational.’” This simply raises the question of why anyone should pay attention to your definition. I’m not interested in probability theory because it is the holy word handed down from Laplace. I’m interested in Bayesian-style belief-updating (with Occam priors) because I expect that this style of thinking gets us systematically closer to, you know, accuracy, the map that reflects the territory.

  And then there are questions of how to think that seem not quite answered by either probability theory or decision theory—like the question of how to feel about the truth once you have it. Here, again, trying to define “rationality” a particular way doesn’t support an answer, but merely presumes one.

  I am not here to argue the meaning of a word, not even if that word is “rationality.” The point of attaching sequences of letters to particular concepts is to let two people communicate—to help transport thoughts from one mind to another. You cannot change reality, or prove the thought, by manipulating which meanings go with which words.

  So if you understand what concept I am generally getting at with this word “rationality,” and with the sub-terms “epistemic rationality” and “instrumental rationality,” we have communicated: we have accomplished everything there is to accomplish by talking about how to define “rationality.” What’s left to discuss is not what meaning to attach to the syllables “ra-tio-na-li-ty”; what’s left to discuss is what is a good way to think.

  If you say, “It’s (epistemically) rational for me to believe X, but the truth is Y,” then you are probably using the word “rational” to mean something other than what I have in mind. (E.g., “rationality” should be consistent under reflection—“rationally” looking at the evidence, and “rationally” considering how your mind processes the evidence, shouldn’t lead to two different conclusions.)

  Similarly, if you find yourself saying, “The (instrumentally) rational thing for me to do is X, but the right thing for me to do is Y,” then you are almost certainly using some other meaning for the word “rational” or the word “right.” I use the term “rationality” normatively, to pick out desirable patterns of thought.

  In this case—or in any other case where people disagree about word meanings—you should substitute more specific language in place of “rational”: “The self-benefiting thing to do is to run away, but I hope I would at least try to drag the child off the railroad tracks,” or “Causal decision theory as usually formulated says you should two-box on Newcomb’s Problem, but I’d rather have a million dollars.”

  In fact, I recommend reading back through this essay, replacing every instance of “rational” with “foozal,” and seeing if that changes the connotations of what I’m saying any. If so, I say: strive not for rationality, but for foozality.

  The word “rational” has potential pitfalls, but there are plenty of non-borderline cases where “rational” works fine to communicate what I’m getting at. Likewise “irrational.” In these cases I’m not afraid to use it.

  Yet one should be careful not to overuse
that word. One receives no points merely for pronouncing it loudly. If you speak overmuch of the Way, you will not attain it.

  *

  1. Editor’s Note: For a good introduction to Newcomb’s Problem, see Holt.2 More generally, you can find definitions and explanations for many of the terms in this book at the website wiki.lesswrong.com/wiki/RAZ_Glossary.

  2. Jim Holt, “Thinking Inside the Boxes,” Slate (2002), http://www.slate.com/articles/arts/egghead/2002/02/thinkinginside%5C_the%5C_boxes.single.html.

  2

  Feeling Rational

  A popular belief about “rationality” is that rationality opposes all emotion—that all our sadness and all our joy are automatically anti-logical by virtue of being feelings. Yet strangely enough, I can’t find any theorem of probability theory which proves that I should appear ice-cold and expressionless.

  So is rationality orthogonal to feeling? No; our emotions arise from our models of reality. If I believe that my dead brother has been discovered alive, I will be happy; if I wake up and realize it was a dream, I will be sad. P. C. Hodgell said: “That which can be destroyed by the truth should be.” My dreaming self’s happiness was opposed by truth. My sadness on waking is rational; there is no truth which destroys it.

  Rationality begins by asking how-the-world-is, but spreads virally to any other thought which depends on how we think the world is. Your beliefs about “how-the-world-is” can concern anything you think is out there in reality, anything that either does or does not exist, any member of the class “things that can make other things happen.” If you believe that there is a goblin in your closet that ties your shoes’ laces together, then this is a belief about how-the-world-is. Your shoes are real—you can pick them up. If there’s something out there that can reach out and tie your shoelaces together, it must be real too, part of the vast web of causes and effects we call the “universe.”

  Feeling angry at the goblin who tied your shoelaces involves a state of mind that is not just about how-the-world-is. Suppose that, as a Buddhist or a lobotomy patient or just a very phlegmatic person, finding your shoelaces tied together didn’t make you angry. This wouldn’t affect what you expected to see in the world—you’d still expect to open up your closet and find your shoelaces tied together. Your anger or calm shouldn’t affect your best guess here, because what happens in your closet does not depend on your emotional state of mind; though it may take some effort to think that clearly.

  But the angry feeling is tangled up with a state of mind that is about how-the-world-is; you become angry because you think the goblin tied your shoelaces. The criterion of rationality spreads virally, from the initial question of whether or not a goblin tied your shoelaces, to the resulting anger.

  Becoming more rational—arriving at better estimates of how-the-world-is—can diminish feelings or intensify them. Sometimes we run away from strong feelings by denying the facts, by flinching away from the view of the world that gave rise to the powerful emotion. If so, then as you study the skills of rationality and train yourself not to deny facts, your feelings will become stronger.

  In my early days I was never quite certain whether it was all right to feel things strongly—whether it was allowed, whether it was proper. I do not think this confusion arose only from my youthful misunderstanding of rationality. I have observed similar troubles in people who do not even aspire to be rationalists; when they are happy, they wonder if they are really allowed to be happy, and when they are sad, they are never quite sure whether to run away from the emotion or not. Since the days of Socrates at least, and probably long before, the way to appear cultured and sophisticated has been to never let anyone see you care strongly about anything. It’s embarrassing to feel—it’s just not done in polite society. You should see the strange looks I get when people realize how much I care about rationality. It’s not the unusual subject, I think, but that they’re not used to seeing sane adults who visibly care about anything.

  But I know, now, that there’s nothing wrong with feeling strongly. Ever since I adopted the rule of “That which can be destroyed by the truth should be,” I’ve also come to realize “That which the truth nourishes should thrive.” When something good happens, I am happy, and there is no confusion in my mind about whether it is rational for me to be happy. When something terrible happens, I do not flee my sadness by searching for fake consolations and false silver linings. I visualize the past and future of humankind, the tens of billions of deaths over our history, the misery and fear, the search for answers, the trembling hands reaching upward out of so much blood, what we could become someday when we make the stars our cities, all that darkness and all that light—I know that I can never truly understand it, and I haven’t the words to say. Despite all my philosophy I am still embarrassed to confess strong emotions, and you’re probably uncomfortable hearing them. But I know, now, that it is rational to feel.

  *

  3

  Why Truth? And . . .

  Some of the comments on Overcoming Bias have touched on the question of why we ought to seek truth. (Thankfully not many have questioned what truth is.) Our shaping motivation for configuring our thoughts to rationality, which determines whether a given configuration is “good” or “bad,” comes from whyever we wanted to find truth in the first place.

  It is written: “The first virtue is curiosity.” Curiosity is one reason to seek truth, and it may not be the only one, but it has a special and admirable purity. If your motive is curiosity, you will assign priority to questions according to how the questions, themselves, tickle your personal aesthetic sense. A trickier challenge, with a greater probability of failure, may be worth more effort than a simpler one, just because it is more fun.

  As I noted, people often think of rationality and emotion as adversaries. Since curiosity is an emotion, I suspect that some people will object to treating curiosity as a part of rationality. For my part, I label an emotion as “not rational” if it rests on mistaken beliefs, or rather, on mistake-producing epistemic conduct: “If the iron approaches your face, and you believe it is hot, and it is cool, the Way opposes your fear. If the iron approaches your face, and you believe it is cool, and it is hot, the Way opposes your calm.” Conversely, then, an emotion that is evoked by correct beliefs or epistemically rational thinking is a “rational emotion”; and this has the advantage of letting us regard calm as an emotional state, rather than a privileged default.

  When people think of “emotion” and “rationality” as opposed, I suspect that they are really thinking of System 1 and System 2—fast perceptual judgments versus slow deliberative judgments. Deliberative judgments aren’t always true, and perceptual judgments aren’t always false; so it is very important to distinguish that dichotomy from “rationality.” Both systems can serve the goal of truth, or defeat it, depending on how they are used.

  Besides sheer emotional curiosity, what other motives are there for desiring truth? Well, you might want to accomplish some specific real-world goal, like building an airplane, and therefore you need to know some specific truth about aerodynamics. Or more mundanely, you want chocolate milk, and therefore you want to know whether the local grocery has chocolate milk, so you can choose whether to walk there or somewhere else. If this is the reason you want truth, then the priority you assign to your questions will reflect the expected utility of their information—how much the possible answers influence your choices, how much your choices matter, and how much you expect to find an answer that changes your choice from its default.

  To seek truth merely for its instrumental value may seem impure—should we not desire the truth for its own sake?—but such investigations are extremely important because they create an outside criterion of verification: if your airplane drops out of the sky, or if you get to the store and find no chocolate milk, it’s a hint that you did something wrong. You get back feedback on which modes of thinking work, and which don’t. Pure curiosity is a wonderful thing, but it may not linger too long on
verifying its answers, once the attractive mystery is gone. Curiosity, as a human emotion, has been around since long before the ancient Greeks. But what set humanity firmly on the path of Science was noticing that certain modes of thinking uncovered beliefs that let us manipulate the world. As far as sheer curiosity goes, spinning campfire tales of gods and heroes satisfied that desire just as well, and no one realized that anything was wrong with that.

  Are there motives for seeking truth besides curiosity and pragmatism? The third reason that I can think of is morality: You believe that to seek the truth is noble and important and worthwhile. Though such an ideal also attaches an intrinsic value to truth, it’s a very different state of mind from curiosity. Being curious about what’s behind the curtain doesn’t feel the same as believing that you have a moral duty to look there. In the latter state of mind, you are a lot more likely to believe that someone else should look behind the curtain, too, or castigate them if they deliberately close their eyes. For this reason, I would also label as “morality” the belief that truthseeking is pragmatically important to society, and therefore is incumbent as a duty upon all. Your priorities, under this motivation, will be determined by your ideals about which truths are most important (not most useful or most intriguing), or about when, under what circumstances, the duty to seek truth is at its strongest.

  I tend to be suspicious of morality as a motivation for rationality, not because I reject the moral ideal, but because it invites certain kinds of trouble. It is too easy to acquire, as learned moral duties, modes of thinking that are dreadful missteps in the dance. Consider Mr. Spock of Star Trek, a naive archetype of rationality. Spock’s emotional state is always set to “calm,” even when wildly inappropriate. He often gives many significant digits for probabilities that are grossly uncalibrated. (E.g., “Captain, if you steer the Enterprise directly into that black hole, our probability of surviving is only 2.234%.” Yet nine times out of ten the Enterprise is not destroyed. What kind of tragic fool gives four significant digits for a figure that is off by two orders of magnitude?) Yet this popular image is how many people conceive of the duty to be “rational”—small wonder that they do not embrace it wholeheartedly. To make rationality into a moral duty is to give it all the dreadful degrees of freedom of an arbitrary tribal custom. People arrive at the wrong answer, and then indignantly protest that they acted with propriety, rather than learning from their mistake.

 

‹ Prev