[extropy-chat] Fools building AIs

Eliezer S. Yudkowsky sentience at pobox.com
Fri Oct 6 01:52:02 UTC 2006


Ben Goertzel wrote:
>>Perhaps they aren't even evil.  Perhaps they are so disgusted with
>>human foibles that they really don't care much anymore whether much
>>brighter artificial minds are particularly friendly to humanity or not.
>>
>>- samantha
> 
> Well put.
> 
> I asked a friend recently what he thought about the prospect of
> superhuman beings annihilating humans to make themselves more
> processing substrate...
> 
> His response: "It's about time."
> 
> When asked what he meant, he said simply, "We're not so great, and
> we've been dominating the planet long enough.  Let something better
> have its turn."

> I do not see why this attitude is inconsistent with a deep
> understanding of the nature of intelligence, and a profound
> rationality.

Hell, Ben, you aren't willing to say publicly that Arthur T. Murray is a 
fool.  In general you seem very reluctant to admit that certain things 
are inconsistent with rationality - a charity level that *I* think is 
inconsistent with rationality.

But anyway:

"In addition to standard biases, I have personally observed what look 
like harmful modes of thinking specific to existential risks.  The 
Spanish flu of 1918 killed 25-50 million people.  World War II killed 60 
million people.  107 is the order of the largest catastrophes in 
humanity's written history.  Substantially larger numbers, such as 500 
million deaths, and especially qualitatively different scenarios such as 
the extinction of the entire human species, seem to trigger a different 
mode of thinking - enter into a "separate magisterium".  People who 
would never dream of hurting a child hear of an existential risk, and 
say, "Well, maybe the human species doesn't really deserve to survive."

There is a saying in heuristics and biases that people do not evaluate 
events, but descriptions of events - what is called non-extensional 
reasoning.  The extension of humanity's extinction includes the death of 
yourself, of your friends, of your family, of your loved ones, of your 
city, of your country, of your political fellows.  Yet people who would 
take great offense at a proposal to wipe the country of Britain from the 
map, to kill every member of the Democratic Party in the U.S., to turn 
the city of Paris to glass - who would feel still greater horror on 
hearing the doctor say that their child had cancer - these people will 
discuss the extinction of humanity with perfect calm.  "Extinction of 
humanity", as words on paper, appears in fictional novels, or is 
discussed in philosophy books - it belongs to a different context than 
the Spanish flu.  We evaluate descriptions of events, not extensions of 
events.  The cliché phrase end of the world invokes the magisterium of 
myth and dream, of prophecy and apocalypse, of novels and movies.  The 
challenge of existential risks to rationality is that, the catastrophes 
being so huge, people snap into a different mode of thinking.  Human 
deaths are suddenly no longer bad, and detailed predictions suddenly no 
longer require any expertise, and whether the story is told with a happy 
ending or a sad ending is a matter of personal taste in stories."

  -- "Cognitive biases potentially affecting judgment of global risks"

I seriously doubt that your friend is processing that question with the 
same part of his brain that he uses to decide e.g. whether to 
deliberately drive into oncoming traffic or throw his three-year-old 
daughter off a hotel balcony.

I've seen plenty of half-skilled rationalists fail by adopting separate 
magisteria for different questions; they hold "spiritual" questions to a 
different standard than they would use when writing a journal article. 
Your friend, I suspect, is carrying out a form of non-extensional 
reasoning which consists of reacting to verbal descriptions of events 
quite differently than how he would react to witnessing even a small 
sample of the human deaths involved.

This entire class of mistakes is harder to make, or at least much harder 
to endorse in principle, if you have translated mathematics into 
intuition, and now see thought processes as engines for achieving work - 
once you reach this level, it does not seem as plausible to you that you 
can get good models by various spiritual means, because this is 
analogous to being able to draw a good map of a distant city by sitting 
in your living room with your blinds drawn - there's no causal 
explanation for how you are drawing a map by interacting with the 
territory, which is how a properly functioning cognitive engine works.

When you understand intelligence properly, you will not deliberately 
endorse separate magisteria, because you know in principle that 
divisions separating e.g. biology from physics, are divisions that 
humans make in academic subjects, not divisions in the things 
themselves; Bayes's Theorem is not going to operate any differently in 
the two cases.

Or as Richard Feynman put it:

	"A poet once said, "The whole universe is in a glass of wine." We will 
probably never know in what sense he said that, for poets do not write 
to be understood. But it is true that if we look in glass of wine 
closely enough we see the entire universe.
	There are the things of physics: the twisting liquid which evaporates 
depending on the wind and weather, the reflections in the glass, and our 
imagination adds the atoms. The glass is a distillation of the earth's 
rocks, and in its composition we see the secrets of the universe's age, 
and the evolution of the stars. What strange array of chemicals are in 
the wine? How did they come to be? There are the ferments, the enzymes, 
the substrates, and the products. There in wine is found the great 
generalization: all life is fermentation. Nobody can discover the 
chemistry of wine without discovering the cause of much disease. How 
vivid is the claret, pressing its existence into the consciousness that 
watches it!
         If in our small minds, for some convenience, divide this glass 
of wine, this universe, into parts - physics, biology, geology, 
astronomy, psychology, and so on - remember that nature does not know 
it! So let us put it all back together, not forgetting ultimately what 
it is for. Let us give one more final pleasure: drink it and forget it all!"

Highly skilled rationalists who understand intelligence are going to be 
on guard against:

Separate magisteria;
Extensional neglect;
Scope neglect;
Inconsistent evaluations of different verbal descriptions of the same 
events;
not to mention,
Failure to search for better third alternatives;
Fatuous philosophy that sounds like deep wisdom; and
Self-destructive impulses.

As usual, people who don't understand the above and have already 
committed such mistakes, may be skeptical that modes of reasoning 
committing these mistakes could be justifiably rejected by a more 
skilled rationalist, just as creationists are skeptical that a more 
skilled rationalist could justifiably reject creationism.

But a skilled rationalist who knows about extensional neglect is not 
likely to endorse the destruction of Earth unless they also endorse the 
death of Human_1, Human_2, Human_3, ... themselves, their mother, ... 
Human_6e9.

Also I expect that your friend is making a mistake of simple fact, with 
respect to what kind of superhumans these are likely to be - he thinks 
they'll be better just because they've got more processing power, an old 
old mistake I once made myself.

-- 
Eliezer S. Yudkowsky                          http://singinst.org/
Research Fellow, Singularity Institute for Artificial Intelligence



More information about the extropy-chat mailing list