Rationality: From AI to Zombies

by Eliezer Yudkowsky

Your beliefs should be your best available estimate of the way things are; anything else is a lie.

in any information situation, there is always a best estimate. You are only entitled to your best honest effort to find that best estimate; anything else is a lie.

I’m not one of the smart kids like you; nay, one so lowly as myself can hope for no better lot.” This is social modesty, not humility. It has to do with regulating status in the tribe, rather than scientific process.

The problem is motivated skepticism a.k.a. disconfirmation bias—more heavily scrutinizing assertions that we don’t want to believe.

John Kenneth Galbraith said: “Faced with the choice of changing one’s mind and proving that there is no need to do so, almost everyone gets busy on the proof.”1 And the greater the inconvenience of changing one’s mind, the more effort people will expend on the proof.

“To be humble is to take specific actions in anticipation of your own errors. To confess your fallibility and then do nothing about it is not humble; it is boasting of your modesty.”

The best is the enemy of the good. If the goal is really to help people, then a superior alternative is cause for celebration—once we find this better strategy, we can help people more effectively. But if the goal is to justify a particular strategy by claiming that it helps people, a Third Alternative is an enemy argument, a competitor.

Beware when you find yourself arguing that a policy is defensible rather than optimal; or that it has some benefit compared to the null action, rather than the best benefit of any action.

To do better, ask yourself straight out: If I saw that there was a superior alternative to my current policy, would I be glad in the depths of my heart, or would I feel a tiny flash of reluctance before I let go? If the answers are “no” and “yes,” beware that you may not have searched for a Third Alternative.

Unsurprisingly, the human brain doesn’t do 64-bit floating-point arithmetic, and it can’t devalue the emotional force of a pleasant anticipation by a factor of 0.00000001 without dropping the line of reasoning entirely.

if you’re going to ignore an argument that says the likelihood is one over googol, why not also ignore an argument that says the likelihood is zero? I mean, as long as you’re ignoring the evidence anyway, why is it so much worse to ignore certain evidence than uncertain evidence?

Everything is shades of gray, but there are shades of gray so light as to be very nearly white, and shades of gray so dark as to be very nearly black. Or even if not, we can still compare shades, and say “it is darker” or “it is lighter.”

It’s a most peculiar psychology—this business of “Science is based on faith too, so there!” Typically this is said by people who claim that faith is a good thing. Then why do they say “Science is based on faith too!” in that angry-triumphal tone, rather than as a compliment? And a rather dangerous compliment to give, one would think, from their perspective. If science is based on “faith,” then science is of the same kind as religion—directly comparable. If science is a religion, it is the religion that heals the sick and reveals the secrets of the stars. It would make sense to say, “The priests of science can blatantly, publicly, verifiably walk on the Moon as a faith-based miracle, and your priests’ faith can’t do the same.” Are you sure you wish to go there, oh faithist? Perhaps, on further reflection, you would prefer to retract this whole business of “Science is a religion too!”

When people thought the earth was flat, they were wrong. When people thought the earth was spherical, they were wrong. But if you think that thinking the earth is spherical is just as wrong as thinking the earth is flat, then your view is wronger than both of them put together.

Here is someone who believes they have knowledge more reliable than science’s mere probabilistic guesses—such as the guess that the Moon will rise in its appointed place and phase tomorrow, just like it has every observed night since the invention of astronomical record-keeping, and just as predicted by physical theories whose previous predictions have been successfully confirmed to fourteen decimal places. And what is this knowledge that the unenlightened ones set above ours, and why? It’s probably some musty old scroll that has been contradicted eleventeen ways from Sunday, and from Monday, and from every day of the week. Yet this is more reliable than Science (they say) because it never admits to error, never changes its mind, no matter how often it is contradicted.

“The power of science comes from having the ability to change our minds and admit we’re wrong. If you’ve never admitted you’re wrong, it doesn’t mean you’ve made fewer mistakes.”

“Anyone can say they’re absolutely certain. It’s a bit harder to never, ever make any mistakes. Scientists understand the difference, so they don’t say they’re absolutely certain. That’s all. It doesn’t mean that they have any specific reason to doubt a theory—absolutely every scrap of evidence can be going the same way, all the stars and planets lined up like dominos in support of a single hypothesis, and the scientists still won’t say they’re absolutely sure, because they’ve just got higher standards. It doesn’t mean scientists are less entitled to certainty than, say, the politicians who always seem so sure of everything.”

“Scientists don’t use the phrase ‘not absolutely certain’ the way you’re used to from regular conversation. I mean, suppose you went to the doctor, and got a blood test, and the doctor came back and said, ‘We ran some tests, and it’s not absolutely certain that you’re not made out of cheese, and there’s a non-zero chance that twenty fairies made out of sentient chocolate are singing the “I love you” song from Barney inside your lower intestine.’ Run for the hills, your doctor needs a doctor. When a scientist says the same thing, it means that they think the probability is so tiny th...

“Would you be willing to change your mind about the things you call ‘certain’ if you saw enough evidence? I mean, suppose that God himself descended from the clouds and told you that your whole religion was true except for the Virgin Birth. If that would change your mind, you can’t say you’re absolutely certain of the Virgin Birth. For technical reasons of probability theory, if it’s theoretically possible for you to change your mind about something, it can’t have a probability exactly equal to one. The uncertainty might be smaller than a dust speck, but it has to be there. And if you wouldn’t change your mind ...

Reversed stupidity is not intelligence.

Let’s see, what else do they need to know? Well, there’s the entire rationalist culture which says that doubt, questioning, and confession of error are not terrible shameful things.

There’s the whole notion of gaining information by looking at things, rather than being proselytized. When you look at things harder, sometimes you find out that they’re different from what you thought they were at first glance; but it doesn’t mean that Nature lied to you, or that you should give up on seeing.

Then there’s the concept of a calibrated confidence—that “probability” isn’t the same concept as the little progress bar in your head that measures your emotional commitment to an idea. It’s more like a measure of how often, pragmatically, in real life, people in a certain state of belief say things that are actually true. If you take one hundred people and ask them each to make a statement...

the statements that people are really fanatic about are far less likely to be correct than statements like “the Sun is larger than the Moon” tha...

Once you realize you don’t need probabilities of 1.0 to get along in life, you’ll realize how absolutely ridiculous it is to think you could ever get to 1.0 with a human brain. A probability of 1.0 isn’t just certainty, it’s infinite certainty.

If what you believe doesn’t depend on what you see, you’ve been blinded as effectively as by poking out your eyeballs.

In the ancestral environment, politics was a matter of life and death. And sex, and wealth, and allies, and reputation . . .

Politics is an extension of war by other means. Arguments are soldiers. Once you know which side you’re on, you must support all arguments of that side, and attack all arguments that appear to favor the enemy side; otherwise it’s like stabbing your soldiers in the back—providing aid and comfort to the enemy.

If you allow shops that sell otherwise banned products, some poor, honest, poorly educated mother of five kids is going to buy something that kills her. This is a prediction about a factual consequence, and as a factual question it appears rather straightforward—a sane person should readily confess this to be true regardless of which stance they take on the policy issue. You may also think that making things illegal just makes them more expensive, that regulators will abuse their power, or that her individual freedom trumps your desire to meddle with her life. But, as a matter of simple fact, she’s still going to die.

Saying “People who buy dangerous products deserve to get hurt!” is not tough-minded. It is a way of refusing to live in an unfair universe. Real tough-mindedness is saying, “Yes, sulfuric acid is a horrible painful death, and no, that mother of five children didn’t deserve it, but we’re going to keep the shops open anyway because we did this cost-benefit calculation.” Can you imagine a politician saying that? Neither can I.

I don’t think that when someone makes a stupid choice and dies, this is a cause for celebration. I count it as a tragedy. It is not always helping people, to save them from the consequences of their own actions; but I draw a moral line at capital punishment. If you’re dead, you can’t learn from your mistakes.

We tend to see far too direct a correspondence between others’ actions and personalities. When we see someone else kick a vending machine for no visible reason, we assume they are “an angry person.” But when you yourself kick the vending machine, it’s because the bus was late, the train was early, your report is overdue, and now the damned vending machine has eaten your lunch money for the second day in a row. Surely, you think to yourself, anyone would kick the vending machine, in that situation.

To understand why people act the way they do, we must first realize that everyone sees themselves as behaving normally.

When someone actually offends us—commits an action of which we (rightly or wrongly) disapprove—then, I observe, the correspondence bias redoubles. There seems to be a very strong tendency to blame evil deeds on the Enemy’s mutant, evil disposition. Not as a moral point, but as a strict question of prior probability, we should ask what the Enemy might believe about their situation that would reduce the seeming bizarrity of their behavior.

maybe the fear is that understanding will lead to forgiveness. It’s easier to shoot down evil mutants. It is a more inspiring battle cry to scream, “Die, vicious scum!” instead of “Die, people who could have been just like me but grew up in a different environment!” You might feel guilty killing people who weren’t pure darkness.

When you accurately estimate the Enemy’s psychology—when you know what is really in the Enemy’s mind—that knowledge won’t feel like landing a delicious punch on the opposing side. It won’t give you a warm feeling of righteous indignation. It won’t make you feel good about yourself. If your estimate makes you feel unbearably sad, you may be seeing the world as it really is. More rarely, an accurate estimate may send shivers of serious horror down your spine, as when dealing with true psychopaths, or neurologically intact people with beliefs that have utterly destroyed their sanity (Scientologists or Jesus Campers).

“The world’s greatest fool may say the Sun is shining, but that doesn’t make it dark out.”2 If you knew someone who was wrong 99.99% of the time on yes-or-no questions, you could obtain 99.99% accuracy just by reversing their answers. They would need to do all the work of obtaining good evidence entangled with reality, and processing that evidence coherently, just to anticorrelate that reliably. They would have to be superintelligent to be that stupid. A car with a broken engine cannot drive backward at 200 mph, even if the engine is really really broken.

A good technical argument is one that eliminates reliance on the personal authority of the speaker.

If we know authority we are still interested in hearing the arguments; but if we know the arguments fully, we have very little left to learn from authority.

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.

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.”

Passive voice obscures reality.

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.

A writer knows that readers will not stop for a minute to think. A fictional experience is a continuous stream of first impressions.

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

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.

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.

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?

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.

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.