Rationality- From AI to Zombies

by Eliezer Yudkowsky

  There is an ineradicable legitimacy to assigning slightly higher probability to what E. T. Jaynes tells you about Bayesian probability, than you assign to Eliezer Yudkowsky making the exact same statement. Fifty additional years of experience should not count for literally zero influence.

  But this slight strength of authority is only ceteris paribus, and can easily be overwhelmed by stronger arguments. I have a minor erratum in one of Jaynes’s books—because algebra trumps authority.

  *

  1. Pearl, Probabilistic Reasoning in Intelligent Systems.

  2. Judea Pearl, Causality: Models, Reasoning, and Inference, 2nd ed. (New York: Cambridge University Press, 2009).

  64

  Hug the Query

  In the art of rationality there is a discipline of closeness-to-the-issue—trying to observe evidence that is as near to the original question as possible, so that it screens off as many other arguments as possible.

  The Wright Brothers say, “My plane will fly.” If you look at their authority (bicycle mechanics who happen to be excellent amateur physicists) then you will compare their authority to, say, Lord Kelvin, and you will find that Lord Kelvin is the greater authority.

  If you demand to see the Wright Brothers’ calculations, and you can follow them, and you demand to see Lord Kelvin’s calculations (he probably doesn’t have any apart from his own incredulity), then authority becomes much less relevant.

  If you actually watch the plane fly, the calculations themselves become moot for many purposes, and Kelvin’s authority not even worth considering.

  The more directly your arguments bear on a question, without intermediate inferences—the closer the observed nodes are to the queried node, in the Great Web of Causality—the more powerful the evidence. It’s a theorem of these causal graphs that you can never get more information from distant nodes, than from strictly closer nodes that screen off the distant ones.

  Jerry Cleaver said: “What does you in is not failure to apply some high-level, intricate, complicated technique. It’s overlooking the basics. Not keeping your eye on the ball.”1

  Just as it is superior to argue physics than credentials, it is also superior to argue physics than rationality. Who was more rational, the Wright Brothers or Lord Kelvin? If we can check their calculations, we don’t have to care! The virtue of a rationalist cannot directly cause a plane to fly.

  If you forget this principle, learning about more biases will hurt you, because it will distract you from more direct arguments. It’s all too easy to argue that someone is exhibiting Bias #182 in your repertoire of fully generic accusations, but you can’t settle a factual issue without closer evidence. If there are biased reasons to say the Sun is shining, that doesn’t make it dark out.

  Just as you can’t always experiment today, you can’t always check the calculations today. Sometimes you don’t know enough background material, sometimes there’s private information, sometimes there just isn’t time. There’s a sadly large number of times when it’s worthwhile to judge the speaker’s rationality. You should always do it with a hollow feeling in your heart, though, a sense that something’s missing.

  Whenever you can, dance as near to the original question as possible—press yourself up against it—get close enough to hug the query!

  *

  1. Jerry Cleaver, Immediate Fiction: A Complete Writing Course (Macmillan, 2004).

  65

  Rationality and the English Language

  Responding to my discussion of applause lights, someone said that my writing reminded them of George Orwell’s Politics and the English Language.1 I was honored. Especially since I’d already thought of today’s topic.

  If you really want an artist’s perspective on rationality, then read Orwell; he is mandatory reading for rationalists as well as authors. Orwell was not a scientist, but a writer; his tools were not numbers, but words; his adversary was not Nature, but human evil. If you wish to imprison people for years without trial, you must think of some other way to say it than “I’m going to imprison Mr. Jennings for years without trial.” You must muddy the listener’s thinking, prevent clear images from outraging conscience. You say, “Unreliable elements were subjected to an alternative justice process.”

  Orwell was the outraged opponent of totalitarianism and the muddy thinking in which evil cloaks itself—which is how Orwell’s writings on language ended up as classic rationalist documents on a level with Feynman, Sagan, or Dawkins.

  “Writers are told to avoid usage of the passive voice.” A rationalist whose background comes exclusively from science may fail to see the flaw in the previous sentence; but anyone who’s done a little writing should see it right away. I wrote the sentence in the passive voice, without telling you who tells authors to avoid passive voice. Passive voice removes the actor, leaving only the acted-upon. “Unreliable elements were subjected to an alternative justice process”—subjected by whom? What does an “alternative justice process” do? With enough static noun phrases, you can keep anything unpleasant from actually happening.

  Journal articles are often written in passive voice. (Pardon me, some scientists write their journal articles in passive voice. It’s not as if the articles are being written by no one, with no one to blame.) It sounds more authoritative to say “The subjects were administered Progenitorivox” than “I gave each college student a bottle of 20 Progenitorivox, and told them to take one every night until they were gone.” If you remove the scientist from the description, that leaves only the all-important data. But in reality the scientist is there, and the subjects are college students, and the Progenitorivox wasn’t “administered” but handed over with instructions. Passive voice obscures reality.

  Judging from the comments I get, someone will protest that using the passive voice in a journal article is hardly a sin—after all, if you think about it, you can realize the scientist is there. It doesn’t seem like a logical flaw. And this is why rationalists need to read Orwell, not just Feynman or even Jaynes.

  Nonfiction conveys knowledge, fiction conveys experience. Medical science can extrapolate what would happen to a human unprotected in a vacuum. Fiction can make you live through it.

  Some rationalists will try to analyze a misleading phrase, try to see if there might possibly be anything meaningful to it, try to construct a logical interpretation. They will be charitable, give the author the benefit of the doubt. Authors, on the other hand, are trained not to give themselves the benefit of the doubt. Whatever the audience thinks you said is what you said, whether you meant to say it or not; you can’t argue with the audience no matter how clever your justifications.

  A writer knows that readers will not stop for a minute to think. A fictional experience is a continuous stream of first impressions. A writer-rationalist pays attention to the experience words create. If you are evaluating the public rationality of a statement, and you analyze the words deliberatively, rephrasing propositions, trying out different meanings, searching for nuggets of truthiness, then you’re losing track of the first impression—what the audience sees, or rather feels.

  A novelist would notice the screaming wrongness of “The subjects were administered Progenitorivox.” What life is here for a reader to live? This sentence creates a distant feeling of authoritativeness, and that’s all—the only experience is the feeling of being told something reliable. A novelist would see nouns too abstract to show what actually happened—the postdoc with the bottle in their hand, trying to look stern; the student listening with a nervous grin.

  My point is not to say that journal articles should be written like novels, but that a rationalist should become consciously aware of the experiences which words create. A rationalist must understand the mind and how to operate it. That includes the stream of consciousness, the part of yourself that unfolds in language. A rationalist must become consciously aware of the actual, experiential impact of phrases, beyond their mere propositional semantics.

  Or to say it more blun
tly: Meaning does not excuse impact!

  I don’t care what rational interpretation you can construct for an applause light like “AI should be developed through democratic processes.” That cannot excuse its irrational impact of signaling the audience to applaud, not to mention its cloudy question-begging vagueness.

  Here is Orwell, railing against the impact of cliches, their effect on the experience of thinking:

  When one watches some tired hack on the platform mechanically repeating the familiar phrases—BESTIAL, ATROCITIES, IRON HEEL, BLOODSTAINED TYRANNY, FREE PEOPLES OF THE WORLD, STAND SHOULDER TO SHOULDER—one often has a curious feeling that one is not watching a live human being but some kind of dummy . . . A speaker who uses that kind of phraseology has gone some distance toward turning himself into a machine. The appropriate noises are coming out of his larynx, but his brain is not involved, as it would be if he were choosing his words for himself . . .

  What is above all needed is to let the meaning choose the word, and not the other way around. In prose, the worst thing one can do with words is surrender to them. When you think of a concrete object, you think wordlessly, and then, if you want to describe the thing you have been visualising you probably hunt about until you find the exact words that seem to fit it. When you think of something abstract you are more inclined to use words from the start, and unless you make a conscious effort to prevent it, the existing dialect will come rushing in and do the job for you, at the expense of blurring or even changing your meaning. Probably it is better to put off using words as long as possible and get one’s meaning as clear as one can through pictures and sensations.

  Charles Sanders Peirce might have written that last paragraph. More than one path can lead to the Way.

  *

  1. George Orwell, “Politics and the English Language,” Horizon (April 1946).

  66

  Human Evil and Muddled Thinking

  George Orwell saw the descent of the civilized world into totalitarianism, the conversion or corruption of one country after another; the boot stamping on a human face, forever, and remember that it is forever. You were born too late to remember a time when the rise of totalitarianism seemed unstoppable, when one country after another fell to secret police and the thunderous knock at midnight, while the professors of free universities hailed the Soviet Union’s purges as progress. It feels as alien to you as fiction; it is hard for you to take seriously. Because, in your branch of time, the Berlin Wall fell. And if Orwell’s name is not carved into one of those stones, it should be.

  Orwell saw the destiny of the human species, and he put forth a convulsive effort to wrench it off its path. Orwell’s weapon was clear writing. Orwell knew that muddled language is muddled thinking; he knew that human evil and muddled thinking intertwine like conjugate strands of DNA:1

  In our time, political speech and writing are largely the defence of the indefensible. Things like the continuance of British rule in India, the Russian purges and deportations, the dropping of the atom bombs on Japan, can indeed be defended, but only by arguments which are too brutal for most people to face, and which do not square with the professed aims of the political parties. Thus political language has to consist largely of euphemism, question-begging and sheer cloudy vagueness. Defenceless villages are bombarded from the air, the inhabitants driven out into the countryside, the cattle machine-gunned, the huts set on fire with incendiary bullets: this is called PACIFICATION . . .

  Orwell was clear on the goal of his clarity:

  If you simplify your English, you are freed from the worst follies of orthodoxy. You cannot speak any of the necessary dialects, and when you make a stupid remark its stupidity will be obvious, even to yourself.

  To make our stupidity obvious, even to ourselves—this is the heart of Overcoming Bias.

  Evil sneaks, hidden, through the unlit shadows of the mind. We look back with the clarity of history, and weep to remember the planned famines of Stalin and Mao, which killed tens of millions. We call this evil, because it was done by deliberate human intent to inflict pain and death upon innocent human beings. We call this evil, because of the revulsion that we feel against it, looking back with the clarity of history. For perpetrators of evil to avoid its natural opposition, the revulsion must remain latent. Clarity must be avoided at any cost. Even as humans of clear sight tend to oppose the evil that they see; so too does human evil, wherever it exists, set out to muddle thinking.

  1984 sets this forth starkly: Orwell’s ultimate villains are cutters and airbrushers of photographs (based on historical cutting and airbrushing in the Soviet Union). At the peak of all darkness in the Ministry of Love, O’Brien tortures Winston to admit that two plus two equals five:2

  “Do you remember,” he went on, “writing in your diary, ‘Freedom is the freedom to say that two plus two make four’?”

  “Yes,” said Winston.

  O’Brien held up his left hand, its back towards Winston, with the thumb hidden and the four fingers extended.

  “How many fingers am I holding up, Winston?”

  “Four.”

  “And if the party says that it is not four but five—then how many?”

  “Four.”

  The word ended in a gasp of pain. The needle of the dial had shot up to fifty-five. The sweat had sprung out all over Winston’s body. The air tore into his lungs and issued again in deep groans which even by clenching his teeth he could not stop. O’Brien watched him, the four fingers still extended. He drew back the lever. This time the pain was only slightly eased.

  I am continually aghast at apparently intelligent folks—such as Robin Hanson’s colleague Tyler Cowen—who don’t think that overcoming bias is important. This is your mind we’re talking about. Your human intelligence. It separates you from an ape. It built this world. You don’t think how the mind works is important? You don’t think the mind’s systematic malfunctions are important? Do you think the Inquisition would have tortured witches, if all were ideal Bayesians?

  Tyler Cowen apparently feels that overcoming bias is just as biased as bias: “I view Robin’s blog as exemplifying bias, and indeed showing that bias can be very useful.” I hope this is only the result of thinking too abstractly while trying to sound clever. Does Tyler seriously think that scope insensitivity to the value of human life is on the same level with trying to create plans that will really save as many lives as possible?

  Orwell was forced to fight a similar attitude—that to admit to any distinction is youthful naiveté:

  Stuart Chase and others have come near to claiming that all abstract words are meaningless, and have used this as a pretext for advocating a kind of political quietism. Since you don’t know what Fascism is, how can you struggle against Fascism?

  Maybe overcoming bias doesn’t look quite exciting enough, if it’s framed as a struggle against mere accidental mistakes. Maybe it’s harder to get excited if there isn’t some clear evil to oppose. So let us be absolutely clear that where there is human evil in the world, where there is cruelty and torture and deliberate murder, there are biases enshrouding it. Where people of clear sight oppose these biases, the concealed evil fights back. The truth does have enemies. If Overcoming Bias were a newsletter in the old Soviet Union, every poster and commenter of Overcoming Bias would have been shipped off to labor camps.

  In all human history, every great leap forward has been driven by a new clarity of thought. Except for a few natural catastrophes, every great woe has been driven by a stupidity. Our last enemy is ourselves; and this is a war, and we are soldiers.

  *

  1. Ibid.

  2. George Orwell, 1984 (Signet Classic, 1950).

  Part G

  Against Rationalization

  67

  Knowing About Biases Can Hurt People

  Once upon a time I tried to tell my mother about the problem of expert calibration, saying: “So when an expert says they’re 99% confident, it only happens about 70% of the time.” Then there was a
pause as, suddenly, I realized I was talking to my mother, and I hastily added: “Of course, you’ve got to make sure to apply that skepticism evenhandedly, including to yourself, rather than just using it to argue against anything you disagree with—”

  And my mother said: “Are you kidding? This is great! I’m going to use it all the time!”

  Taber and Lodge’s “Motivated skepticism in the evaluation of political beliefs” describes the confirmation of six predictions:1

  Prior attitude effect. Subjects who feel strongly about an issue—even when encouraged to be objective—will evaluate supportive arguments more favorably than contrary arguments.

  Disconfirmation bias. Subjects will spend more time and cognitive resources denigrating contrary arguments than supportive arguments.

  Confirmation bias. Subjects free to choose their information sources will seek out supportive rather than contrary sources.

  Attitude polarization. Exposing subjects to an apparently balanced set of pro and con arguments will exaggerate their initial polarization.

  Attitude strength effect. Subjects voicing stronger attitudes will be more prone to the above biases.

  Sophistication effect. Politically knowledgeable subjects, because they possess greater ammunition with which to counter-argue incongruent facts and arguments, will be more prone to the above biases.

  If you’re irrational to start with, having more knowledge can hurt you. For a true Bayesian, information would never have negative expected utility. But humans aren’t perfect Bayes-wielders; if we’re not careful, we can cut ourselves.

  I’ve seen people severely messed up by their own knowledge of biases. They have more ammunition with which to argue against anything they don’t like. And that problem—too much ready ammunition—is one of the primary ways that people with high mental agility end up stupid, in Stanovich’s “dysrationalia” sense of stupidity.