We mean:

1. Epistemic rationality: believing, and updating on evidence, so as to systematically improve the correspondence between your map and the territory.  The art of obtaining beliefs that correspond to reality as closely as possible.  This correspondence is commonly termed "truth" or "accuracy", and we're happy to call it that.
2. Instrumental rationality: achieving your values.  Not necessarily "your values" in the sense of being selfish values or unshared values: "your values" means anything you care about.  The art of choosing actions that steer the future toward outcomes ranked higher in your preferences.  On LW we sometimes refer to this as "winning".

If that seems like a perfectly good definition, you can stop reading here; otherwise continue.

This is an inclusive guide to the series of posts on quantum mechanics that began on April 9th, 2008, including the digressions into related topics (such as the difference between Science and Bayesianism) and some of the preliminary reading.

You may also be interested in one of the less inclusive post guides, such as:

• An Intuitive Explanation of Quantum Mechanics (just the science, for students confused by their physics textbooks)
• Quantum Physics Revealed As Non-Mysterious (quantum physics does not make the universe any more mysterious than it was previously)
• And the Winner is... Many-Worlds! (the many-worlds interpretation wins outright given the current state of evidence)
• Quantum Mechanics and Personal Identity (the ontology of quantum mechanics, in which there are no particles with individual identities, rules out theories of personal continuity that invoke "the same atoms" as a concept)

My current plan calls for the quantum physics series to eventually be turned into one or more e-books.

Followup to:  Anthropomorphic Optimism, Three Fallacies of Teleology

After spending a decade or two living inside a mind, you might think you knew a bit about how minds work, right?  That's what quite a few AGI wannabes (people who think they've got what it takes to program an Artificial General Intelligence) seem to have concluded.  This, unfortunately, is wrong.

Artificial Intelligence is fundamentally about reducing the mental to the non-mental.

You might want to contemplate that sentence for a while.  It's important.

Living inside a human mind doesn't teach you the art of reductionism, because nearly all of the work is carried out beneath your sight, by the opaque black boxes of the brain.  So far beneath your sight that there is no introspective sense that the black box is there - no internal sensory event marking that the work has been delegated.

Did Aristotle realize that when he talked about the telos, the final cause of events, that he was delegating predictive labor to his brain's complicated planning mechanisms - asking, "What would this object do, if it could make plans?"  I rather doubt it.  Aristotle thought the brain was an organ for cooling the blood - which he did think was important:  Humans, thanks to their larger brains, were more calm and contemplative.

So there's an AI design for you!  We just need to cool down the computer a lot, so it will be more calm and contemplative, and won't rush headlong into doing stupid things like modern computers.

Followup to:  Anthropomorphic Optimism, Superexponential Conceptspace, The Hidden Complexity of Wishes, Unnatural Categories

'We can design intelligent machines so their primary, innate emotion is unconditional love for all humans.  First we can build relatively simple machines that learn to recognize happiness and unhappiness in human facial expressions, human voices and human body language.  Then we can hard-wire the result of this learning as the innate emotional values of more complex intelligent machines, positively reinforced when we are happy and negatively reinforced when we are unhappy.'
        -- Bill Hibbard (2001), Super-intelligent machines.

That was published in a peer-reviewed journal, and the author later wrote a whole book about it, so this is not a strawman position I'm discussing here.

So... um... what could possibly go wrong...

When I mentioned (sec. 6) that Hibbard's AI ends up tiling the galaxy with tiny molecular smiley-faces, Hibbard wrote an indignant reply saying:

'When it is feasible to build a super-intelligence, it will be feasible to build hard-wired recognition of "human facial expressions, human voices and human body language" (to use the words of mine that you quote) that exceed the recognition accuracy of current humans such as you and me, and will certainly not be fooled by "tiny molecular pictures of smiley-faces." You should not assume such a poor implementation of my idea that it cannot make discriminations that are trivial to current humans.'

Related to: Why Real Men Wear Pink, That Other Kind of Status, Pretending to be Wise, The "Outside The Box" Box

WARNING: Beware of things that are fun to argue -- Eliezer Yudkowsky

Science has inexplicably failed to come up with a precise definition of "hipster", but from my limited understanding a hipster is a person who deliberately uses unpopular, obsolete, or obscure styles and preferences in an attempt to be "cooler" than the mainstream. But why would being deliberately uncool be cooler than being cool?

As previously discussed, in certain situations refusing to signal can be a sign of high status. Thorstein Veblen invented the term "conspicuous consumption" to refer to the showy spending habits of the nouveau riche, who unlike the established money of his day took great pains to signal their wealth by buying fast cars, expensive clothes, and shiny jewelery. Why was such flashiness common among new money but not old? Because the old money was so secure in their position that it never even occurred to them that they might be confused with poor people, whereas new money, with their lack of aristocratic breeding, worried they might be mistaken for poor people if they didn't make it blatantly obvious that they had expensive things.

The old money might have started off not buying flashy things for pragmatic reasons - they didn't need to, so why waste the money? But if F. Scott Fitzgerald is to be believed, the old money actively cultivated an air of superiority to the nouveau riche and their conspicuous consumption; not buying flashy objects becomes a matter of principle. This makes sense: the nouveau riche need to differentiate themselves from the poor, but the old money need to differentiate themselves from the nouveau riche.

This process is called countersignaling, and one can find its telltale patterns in many walks of life. Those who study human romantic attraction warn men not to "come on too strong", and this has similarities to the nouveau riche example. A total loser might come up to a woman without a hint of romance, promise her nothing, and demand sex. A more sophisticated man might buy roses for a woman, write her love poetry, hover on her every wish, et cetera; this signifies that he is not a total loser. But the most desirable men may deliberately avoid doing nice things for women in an attempt to signal they are so high status that they don't need to. The average man tries to differentiate himself from the total loser by being nice; the extremely attractive man tries to differentiate himself from the average man by not being especially nice.

In all three examples, people at the top of the pyramid end up displaying characteristics similar to those at the bottom. Hipsters deliberately wear the same clothes uncool people wear. Families with old money don't wear much more jewelry than the middle class. And very attractive men approach women with the same lack of subtlety a total loser would use.¹

If politics, philosophy, and religion are really about signaling, we should expect to find countersignaling there as well.

Followup to:  Disguised Queries, Superexponential Conceptspace

If a tree falls in the forest, and no one hears it, does it make a sound?

"Tell me why you want to know," says the rationalist, "and I'll tell you the answer."  If you want to know whether your seismograph, located nearby, will register an acoustic wave, then the experimental prediction is "Yes"; so, for seismographic purposes, the tree should be considered to make a sound.  If instead you're asking some question about firing patterns in a human auditory cortex - for whatever reason - then the answer is that no such patterns will be changed when the tree falls.

What is a poison?  Hemlock is a "poison"; so is cyanide; so is viper venom.  Carrots, water, and oxygen are "not poison".  But what determines this classification?  You would be hard pressed, just by looking at hemlock and cyanide and carrots and water, to tell what sort of difference is at work.  You would have to administer the substances to a human - preferably one signed up for cryonics - and see which ones proved fatal.  (And at that, the definition is still subtler than it appears: a ton of carrots, dropped on someone's head, will also prove fatal. You're really asking about fatality from metabolic disruption, after administering doses small enough to avoid mechanical damage and blockage, at room temperature, at low velocity.)

Where poison-ness is concerned, you are not classifying via a strictly local property of the substance.  You are asking about the consequence when a dose of that substance is applied to a human metabolism.  The local difference between a human who gasps and keels over, versus a human alive and healthy, is more compactly discriminated, than any local difference between poison and non-poison.

Followup to:  The Psychological Unity of Humankind

People ask me, "What will Artificial Intelligences be like?  What will they do?  Tell us your amazing story about the future."

And lo, I say unto them, "You have asked me a trick question."

ATP synthase is a molecular machine - one of three known occasions when evolution has invented the freely rotating wheel - which is essentially the same in animal mitochondria, plant chloroplasts, and bacteria.  ATP synthase has not changed significantly since the rise of eukaryotic life two billion years ago.  It's is something we all have in common -  thanks to the way that evolution strongly conserves certain genes; once many other genes depend on a gene, a mutation will tend to break all the dependencies.

Any two AI designs might be less similar to each other than you are to a petunia.

Followup to:  Righting a Wrong Question, Zombies! Zombies?, A Premature Word on AI, On Doing the Impossible

There is a subproblem of Friendly AI which is so scary that I usually don't talk about it, because very few would-be AI designers would react to it appropriately—that is, by saying, "Wow, that does sound like an interesting problem", instead of finding one of many subtle ways to scream and run away.

This is the problem that if you create an AI and tell it to model the world around it, it may form models of people that are people themselves.  Not necessarily the same person, but people nonetheless.

If you look up at the night sky, and see the tiny dots of light that move over days and weeks—planētoi, the Greeks called them, "wanderers"—and you try to predict the movements of those planet-dots as best you can...

Historically, humans went through a journey as long and as wandering as the planets themselves, to find an accurate model.  In the beginning, the models were things of cycles and epicycles, not much resembling the true Solar System.

But eventually we found laws of gravity, and finally built models—even if they were just on paper—that were extremely accurate so that Neptune could be deduced by looking at the unexplained perturbation of Uranus from its expected orbit.  This required moment-by-moment modeling of where a simplified version of Uranus would be, and the other known planets.  Simulation, not just abstraction.  Prediction through simplified-yet-still-detailed pointwise similarity.

Suppose you have an AI that is around human beings.  And like any Bayesian trying to explain its enivornment, the AI goes in quest of highly accurate models that predict what it sees of humans.

Models that predict/explain why people do the things they do, say the things they say, want the things they want, think the things they think, and even why people talk about "the mystery of subjective experience".

The model that most precisely predicts these facts, may well be a 'simulation' detailed enough to be a person in its own right.