# 71

"Would you kill babies if it was the right thing to do?  If no, under what circumstances would you not do the right thing to do?  If yes, how right would it have to be, for how many babies?"
—horrible job interview question

Swapping hats for a moment, I'm professionally intrigued by the decision theory of "things you shouldn't do even if they seem to be the right thing to do".

Suppose we have a reflective AI, self-modifying and self-improving, at an intermediate stage in the development process.  In particular, the AI's goal system isn't finished—the shape of its motivations is still being loaded, learned, tested, or tweaked.

Yea, I have seen many ways to screw up an AI goal system design, resulting in a decision system that decides, given its goals, that the universe ought to be tiled with tiny molecular smiley-faces, or some such.  Generally, these deadly suggestions also have the property that the AI will not desire its programmers to fix it.  If the AI is sufficiently advanced—which it may be even at an intermediate stage—then the AI may also realize that deceiving the programmers, hiding the changes in its thoughts, will help transform the universe into smiley-faces.

Now, from our perspective as programmers, if we condition on the fact that the AI has decided to hide its thoughts from the programmers, or otherwise act willfully to deceive us, then it would seem likely that some kind of unintended consequence has occurred in the goal system.  We would consider it probable that the AI is not functioning as intended, but rather likely that we have messed up the AI's utility function somehow.  So that the AI wants to turn the universe into tiny reward-system counters, or some such, and now has a motive to hide from us.

Well, suppose we're not going to implement some object-level Great Idea as the AI's utility function.  Instead we're going to do something advanced and recursive—build a goal system which knows (and cares) about the programmers outside.  A goal system that, via some nontrivial internal structure, "knows it's being programmed" and "knows it's incomplete".  Then you might be able to have and keep the rule:

"If [I decide that] fooling my programmers is the right thing to do, execute a controlled shutdown [instead of doing the right thing to do]."

And the AI would keep this rule, even through the self-modifying AI's revisions of its own code, because, in its structurally nontrivial goal system, the present-AI understands that this decision by a future-AI probably indicates something defined-as-a-malfunction.  Moreover, the present-AI knows that if future-AI tries to evaluate the utility of executing a shutdown, once this hypothetical malfunction has occurred, the future-AI will probably decide not to shut itself down.  So the shutdown should happen unconditionally, automatically, without the goal system getting another chance to recalculate the right thing to do.

I'm not going to go into the deep dark depths of the exact mathematical structure, because that would be beyond the scope of this blog.  Also I don't yet know the deep dark depths of the mathematical structure.  It looks like it should be possible, if you do things that are advanced and recursive and have nontrivial (but consistent) structure.  But I haven't reached that level, as yet, so for now it's only a dream.

But the topic here is not advanced AI; it's human ethics.  I introduce the AI scenario to bring out more starkly the strange idea of an ethical injunction:

You should never, ever murder an innocent person who's helped you, even if it's the right thing to do; because it's far more likely that you've made a mistake, than that murdering an innocent person who helped you is the right thing to do.

Sound reasonable?

During World War II, it became necessary to destroy Germany's supply of deuterium, a neutron moderator, in order to block their attempts to achieve a fission chain reaction.  Their supply of deuterium was coming at this point from a captured facility in Norway.  A shipment of heavy water was on board a Norwegian ferry ship, the SF Hydro.  Knut Haukelid and three others had slipped on board the ferry in order to sabotage it, when the saboteurs were discovered by the ferry watchman.  Haukelid told him that they were escaping the Gestapo, and the watchman immediately agreed to overlook their presence.  Haukelid "considered warning their benefactor but decided that might endanger the mission and only thanked him and shook his hand."  (Richard Rhodes, The Making of the Atomic Bomb.)  So the civilian ferry Hydro sank in the deepest part of the lake, with eighteen dead and twenty-nine survivors.  Some of the Norwegian rescuers felt that the German soldiers present should be left to drown, but this attitude did not prevail, and four Germans were rescued.  And that was, effectively, the end of the Nazi atomic weapons program.

Good move?  Bad move?  Germany very likely wouldn't have gotten the Bomb anyway...  I hope with absolute desperation that I never get faced by a choice like that, but in the end, I can't say a word against it.

On the other hand, when it comes to the rule:

"Never try to deceive yourself, or offer a reason to believe other than probable truth; because even if you come up with an amazing clever reason, it's more likely that you've made a mistake than that you have a reasonable expectation of this being a net benefit in the long run."

Then I really don't know of anyone who's knowingly been faced with an exception.  There are times when you try to convince yourself "I'm not hiding any Jews in my basement" before you talk to the Gestapo officer.  But then you do still know the truth, you're just trying to create something like an alternative self that exists in your imagination, a facade to talk to the Gestapo officer.

But to really believe something that isn't true?  I don't know if there was ever anyone for whom that was knowably a good idea.  I'm sure that there have been many many times in human history, where person X was better off with false belief Y.  And by the same token, there is always some set of winning lottery numbers in every drawing.  It's knowing which lottery ticket will win that is the epistemically difficult part, like X knowing when he's better off with a false belief.

Self-deceptions are the worst kind of black swan bets, much worse than lies, because without knowing the true state of affairs, you can't even guess at what the penalty will be for your self-deception.  They only have to blow up once to undo all the good they ever did.  One single time when you pray to God after discovering a lump, instead of going to a doctor.  That's all it takes to undo a life.  All the happiness that the warm thought of an afterlife ever produced in humanity, has now been more than cancelled by the failure of humanity to institute systematic cryonic preservations after liquid nitrogen became cheap to manufacture.  And I don't think that anyone ever had that sort of failure in mind as a possible blowup, when they said, "But we need religious beliefs to cushion the fear of death."  That's what black swan bets are all about—the unexpected blowup.

Maybe you even get away with one or two black-swan bets—they don't get you every time.  So you do it again, and then the blowup comes and cancels out every benefit and then some.  That's what black swan bets are all about.

Thus the difficulty of knowing when it's safe to believe a lie (assuming you can even manage that much mental contortion in the first place)—part of the nature of black swan bets is that you don't see the bullet that kills you; and since our perceptions just seem like the way the world is, it looks like there is no bullet, period.

So I would say that there is an ethical injunction against self-deception.  I call this an "ethical injunction" not so much because it's a matter of interpersonal morality (although it is), but because it's a rule that guards you from your own cleverness—an override against the temptation to do what seems like the right thing.

So now we have two kinds of situation that can support an "ethical injunction", a rule not to do something even when it's the right thing to do.  (That is, you refrain "even when your brain has computed it's the right thing to do", but this will just seem like "the right thing to do".)

First, being human and running on corrupted hardware, we may generalize classes of situation where when you say e.g. "It's time to rob a few banks for the greater good," we deem it more likely that you've been corrupted than that this is really the case.  (Note that we're not prohibiting it from ever being the case in reality, but we're questioning the epistemic state where you're justified in trusting your own calculation that this is the right thing to do—fair lottery tickets can win, but you can't justifiably buy them.)

Second, history may teach us that certain classes of action are black-swan bets, that is, they sometimes blow up bigtime for reasons not in the decider's model.  So even when we calculate within the model that something seems like the right thing to do, we apply the further knowledge of the black swan problem to arrive at an injunction against it.

But surely... if one is aware of these reasons... then one can simply redo the calculation, taking them into account.  So we can rob banks if it seems like the right thing to do after taking into account the problem of corrupted hardware and black swan blowups.  That's the rational course, right?

There's a number of replies I could give to that.

I'll start by saying that this is a prime example of the sort of thinking I have in mind, when I warn aspiring rationalists to beware of cleverness.

I'll also note that I wouldn't want an attempted Friendly AI that had just decided that the Earth ought to be transformed into paperclips, to assess whether this was a reasonable thing to do in light of all the various warnings it had received against it.  I would want it to undergo an automatic controlled shutdown.  Who says that meta-reasoning is immune from corruption?

I could mention the important times that my naive, idealistic ethical inhibitions have protected me from myself, and placed me in a recoverable position, or helped start the recovery, from very deep mistakes I had no clue I was making.  And I could ask whether I've really advanced so much, and whether it would really be all that wise, to remove the protections that saved me before.

Yet even so...  "Am I still dumber than my ethics?" is a question whose answer isn't automatically "Yes."

There are obvious silly things here that you shouldn't do; for example, you shouldn't wait until you're really tempted, and then try to figure out if you're smarter than your ethics on that particular occasion.

But in general—there's only so much power that can vest in what your parents told you not to do.  One shouldn't underestimate the power.  Smart people debated historical lessons in the course of forging the Enlightenment ethics that much of Western culture draws upon; and some subcultures, like scientific academia, or science-fiction fandom, draw on those ethics more directly.  But even so the power of the past is bounded.

And in fact...

I've had to make my ethics much stricter than what my parents and Jerry Pournelle and Richard Feynman told me not to do.

Funny thing, how when people seem to think they're smarter than their ethics, they argue for less strictness rather than more strictness.  I mean, when you think about how much more complicated the modern world is...

And along the same lines, the ones who come to me and say, "You should lie about the Singularity, because that way you can get more people to support you; it's the rational thing to do, for the greater good"—these ones seem to have no idea of the risks.

They don't mention the problem of running on corrupted hardware.  They don't mention the idea that lies have to be recursively protected from all the truths and all the truthfinding techniques that threaten them.  They don't mention that honest ways have a simplicity that dishonest ways often lack.  They don't talk about black-swan bets.  They don't talk about the terrible nakedness of discarding the last defense you have against yourself, and trying to survive on raw calculation.

I am reasonably sure that this is because they have no clue about any of these things.

If you've truly understood the reason and the rhythm behind ethics, then one major sign is that, augmented by this newfound knowledge, you don't do those things that previously seemed like ethical transgressions.  Only now you know why.

Someone who just looks at one or two reasons behind ethics, and says, "Okay, I've understood that, so now I'll take it into account consciously, and therefore I have no more need of ethical inhibitions"—this one is behaving more like a stereotype than a real rationalist.  The world isn't simple and pure and clean, so you can't just take the ethics you were raised with and trust them.  But that pretense of Vulcan logic, where you think you're just going to compute everything correctly once you've got one or two abstract insights—that doesn't work in real life either.

As for those who, having figured out none of this, think themselves smarter than their ethics:  Ha.

And as for those who previously thought themselves smarter than their ethics, but who hadn't conceived of all these elements behind ethical injunctions "in so many words" until they ran across this Overcoming Bias sequence, and who now think themselves smarter than their ethics, because they're going to take all this into account from now on:  Double ha.

I have seen many people struggling to excuse themselves from their ethics.  Always the modification is toward lenience, never to be more strict.  And I am stunned by the speed and the lightness with which they strive to abandon their protections.  Hobbes said, "I don't know what's worse, the fact that everyone's got a price, or the fact that their price is so low."  So very low the price, so very eager they are to be bought.  They don't look twice and then a third time for alternatives, before deciding that they have no option left but to transgress—though they may look very grave and solemn when they say it.  They abandon their ethics at the very first opportunity.  "Where there's a will to failure, obstacles can be found."  The will to fail at ethics seems very strong, in some people.

I don't know if I can endorse absolute ethical injunctions that bind over all possible epistemic states of a human brain.  The universe isn't kind enough for me to trust that.  (Though an ethical injunction against self-deception, for example, does seem to me to have tremendous force.  I've seen many people arguing for the Dark Side, and none of them seem aware of the network risks or the black-swan risks of self-deception.)  If, someday, I attempt to shape a (reflectively consistent) injunction within a self-modifying AI, it will only be after working out the math, because that is so totally not the sort of thing you could get away with doing via an ad-hoc patch.

But I will say this much:

I am completely unimpressed with the knowledge, the reasoning, and the overall level, of those folk who have eagerly come to me, and said in grave tones, "It's rational to do unethical thing X because it will have benefit Y."

# 71

New Comment
Some comments are truncated due to high volume. Change truncation settings

Given the current sequence, perhaps it's time to revisit the whole Torture vs Dust Specks thing?

0Grognor11y
Late as I am, I have to say: No. That debate more settled than many-worlds is.
If by "settled" you mean anything like "there's no argument between EY and the majority of contributors"... well, it doesn't look that way. Not even after you discard the fact that the examples were surprisingly, uncharacteristically poorly chosen in the first place (EY clarifying and proposing alternatives to dust specks but, failing to adjust for the fact that he's pretty much the only one who can imagine recovery from the "torture" proposed). For instance, there's the whole open business with Eliezer displaying - or merely signaling, or whatever - an unbounded utility function, which opens him up to all sort of shaky crap, as seen in "The Aliens Have Landed" and elsewhere. If you don't think so, go ahead and run a poll with, say, 200 minimum karma needed to vote. I'm going to be stunned if it turns out less than 30% speckers as of early 2012.

My guess is the results of that poll would depend radically on how the question is worded.

But yes, I agree with you that for most wordings, most people (including most LW contributors) will say "X units torture is worse than Y units of dust specks" for any substantial X & Y, no matter how vanishingly small X/Y is. And those who say "dust specks are worse for a sufficiently small X/Y" will chide them for succumbing to scope insensitivity, and the Torture Is Worse team will counterchide for being evil.

For my own part, I think recovery is a red herring. Sure, it's implausible to imagine a person recovering from fifty years of torture in the real world. It's also implausible to imagine 3^^^3 people getting a dust speck in their eye in the real world. It's an implausible thought experiment. So what?

But if one insists on taking recovery rates into account, well, OK: consider a person whose life thus far has been so miserable that they are right on the borderline of they can recover from. Left alone, they'd eventually manage recovery, but even the slightest worsening of their condition -- say, getting a dust speck in their eye at the wrong time -- will tip them o...

"Would you kill babies if it was the right thing to do? If no, under what circumstances would you not do the right thing to do? If yes, how right would it have to be, for how many babies?"

I would have answered "yes"; eg., I would have set off a bomb in Hitler's car in 1942, even if Hitler was surrounded by babies. This doesn't seem to be a case of corruption by unethical hardware; the benefit to me from setting off such a bomb is quite negative, as it greatly increases my chance of being tortured to death by the SS.

1mamert7y
Definitely yes. It's not like killing babies is inherently wrong (*), it just is under most circumstances. I was thinking more along the lines of euthanasia of babies you've discovered have been prepared for use in biological warfare... but my mind tends to go into bad places. Let's not get any further into that. *) unless you use absolute values for wrong, in which case it definitely is, but so is breathing

The problem here of course is how selective to be about rules to let into this protected level of "rules almost no one should think themselves clever enough to know when to violate." After all, your social training may well want you to include "Never question our noble leader" in that set. Many a Christian has been told the mysteries of God are so subtle that they shouldn't think themselves clever enough to know when they've found evidence that God isn't following a grand plan to make this the best of all possible worlds.

0MarsColony_in10years7y
Couldn't this be determined experimentally? Ignore the last hundred years or so, or however much might influence our conclusion based on modern politics. Find a list of the people who had a large counterfactual impact on history. Which rules lead to desirable results? For example, the trial of Socrates [https://en.wikipedia.org/wiki/Trial_of_Socrates] made him a martyr, significantly advancing his ideas. That's a couple points for "die for the principle of the matter" as an ethical injunction. After Alexander the great died, anti-Macedonian sentiment in Athens caused Aristotle to flee, saying "I will not allow the Athenians to sin twice against philosophy". Given this, perhaps Socrates's sacrifice didn't achieve as much as one might think, and we should update a bit in the opposite direction. Then again, Aristotle died a year later, having accomplished nothing noteworthy in that time.

There's that old quote: "never let your sense of morality keep you from doing what you know is right."

I'd still like an answer to the most basic Friendly AI question: what do you want it to do? Forget the implementation problems for a second, and just give me a scenario where the AI is doing what you want it to do. What does that world look like? Because I don't even know what I want from that future.

Michael, the AI I would currently like to create computes a metamoral question, looking for reflective equilibria of your current inconsistent and unknowledgeable self; something along the lines of "What would you ask me to do if you knew what I know and thought as fast as I do?"

What does the actual world look like? I can visualize a world that, to me at least, seems at least pleasant enough to refute most of the objections people have along the lines of "But you couldn't have that much fun and still lead a philosophically acceptable existence". But I'm not sure it's wise to write about it, because I'm afraid it would suck out people's souls. It's better for your mental health to look down at the Middle Ages than up at the future.

Because I don't even know what I want from that future.

Well, I hope you will stick around, MichaelG. Most people around here IMHO are too quickly satisifed with answers to questions about what sorts of terminal values properly apply even if the world changes drastically. A feeling of confusion about the question is your friend IMHO. Extreme scepticism of the popular answers is also your friend.

@Tom McCabe: I would have answered "yes"; eg., I would have set off a bomb in Hitler's car in 1942, even if Hitler was surrounded by babies. This doesn't seem to be a case of corruption by unethical hardware; the benefit to me from setting off such a bomb is quite negative, as it greatly increases my chance of being tortured to death by the SS.

It's easy to talk now about it, harder if you actually lived in Germany at that time and had to really fear the SS. Are you american? If yes did you consider the fact that the actual political situation in ...

3Autolykos7y
There probably was a time when killing Hitler had a significant chance of ending the war by enabling peace talks (allowing some high-ranking German generals/politicians to seize power while plausibly denying having wanted this outcome). The window might have been short, and probably a bit after '42, though. I'd guess any time between the Battle of Stalingrad (where Germany stopped winning) and the Battle of Kursk (which made Soviet victory inevitable) should've worked - everyone involved should rationally prefer white peace to the very real possibility of a bloody stalemate. Before, Germany would not accept. Afterwards, the Soviets wouldn't.
1AlexanderRM7y
It's also worth noting that "I would set off a bomb if it would avert or shorten the Holocaust even if it would kill a bunch of babies" would still answer the question... ...or maybe it wouldn't, because the whole point of the question is that you might be wrong that it would end the war. See for comparison "I would set off a bomb and kill a bunch of innocent Americans if it would end American imperialism", which has a surprising tendency to not end American imperialism and in fact make it worse. Overall I think if everyone followed a heuristic of "never kill babies", the world would be better on average. However you could get a problem if only the carefully moral people follow that rule and the less-careful don't and end up winning. For a consequentialist, a good rule would be "any ethical injunction which causes itself to be defeated cannot be used". At the very least, the heuristic of "don't violate Geneva Convention-like agreements restricting war to make it less horrible which the other side has stuck to" seems reasonable, although it's less clear for cases like where a few enemy soldiers individually violate it, or where being the first to violate it gives a major advantage and you're worried the other side might do so.
0waveman7y
Indeed. I remember an IT project manager telling me the German people should have stood up to Hitler and stopped him. I pointed out that she was not even prepared to tell her manager the truth about the state of her project (running later than advertised of course). All she had at stake was the size of her end of year bonus. I remember reading about a man who voted against Hitler in the referendum to make him dictator. He was severely beaten, his house was burned down, and he wife and daughter were gang-raped.
1Jiro7y
The penalty for telling the truth about the state of your project is less than the penalty for defying Hitler, but the good done by telling the truth about the state of your project is also less than the good done by defying Hitler.
0waveman7y
That is true. Whether higher stakes* would give her more courage, I doubt, but it is possible. ( * It was not entirely clear until it was too late, if you look at the people who had nice things to say about Hitler early on. The number of people int he resistance during the war (as opposed to after the war, in retrospect) was not very high. I am not suggesting I would have been one of those who took arms against him). Anthony Beevor's book Dresden has a good description of what happened to people who opposed Hitler.
0ChristianKl7y
For most people the good done by defying Hitler isn't that great. One individual more or less doesn't make a huge difference.

So... do you not actually believe in your injunction to "shut up and multiply"? Because for some time now you seem to have been arguing that we should do what feels right rather than trying to figure out what is right.

Learning Methods might be a relevant system. It's based on the idea that emotional and physical pain are information, and it's important to override the impulse to shut them down so that you can use them as detailed signals.

I think Eliezer makes some good points, but that he is taking them too far. I'm not certain where or how much we disagree though. It would be clearer what he really believes he was forced to discuss/debate a wide range of situations in which he agrees/disagrees that it is worth violating an ethic which is generally a good one.

I encourage people to offer thought experiments in the comments.

I'm much more sympathetic to "Never try to deceive yourself, or offer a reason to believe other than probable truth". Honestly, it seems to me that I take this injunction as seriously as anyone does, including Eliezer, but I'm still, unlike Eliezer, willing to mention a few caveats. The most important is that for humans, though not for minds in general, beliefs, brain states, world states, and values are not cleanly separate. There is not, for instance, any completely clean distinction between causing myself to hold a vague belief about what i...

-1Will_Newsome12y
How can utility functions (or terms in utility functions, depending on how you want to splice it up) survive except as self-protecting beliefs? The strange loop through the meta-level is not like induction where you have no other choice, there are many possible utility functions. (I'm making this comment as a note to self to flag Michael's comment for future reference.)

"looking for reflective equilibria of your current inconsistent and unknowledgeable self; something along the lines of 'What would you ask me to do if you knew what I know and thought as fast as I do?'"

We're sufficiently more intelligent than monkeys to do that reasoning... so humanity's goal (as the advanced intelligence created by monkeys a few million years ago for getting to the Singularity) should be to use all the knowledge gained to tile the universe with bananas and forests etc.

We don't have the right to say, "if monkeys were more in...

You should never, ever murder an innocent person who's helped you, even if it's the right thing to do

Shut up and do the impossible!

As written, both these statements are conceptually confused. I understand that you didn't actually mean either of them literally, but I would advise against trading on such deep-sounding conceptual confusions.

You should never, ever do X, even if if you are exceedingly confident that it is the right thing to do

This sounds less profound, but will actually be true for some value of X, unlike the first sentence or its derivatives. It sounds as profound as it is, and no more. I believe this is the right standard.

"Would you kill babies if it was the right thing to do? If no, under what circumstances would you not do the right thing to do? If yes, how right would it have to be, for how many babies?"

A: yes; B: N/A; C: approximately 3.6 floodlenips of rightness - per baby.

Robin has an excellent point. The majority of the planet, when faced with reasoning that argues against their religion, executes a very close variant on that shutdown code. They have a very similar injunction against being too clever. And they are similarly smug about rationalists who give up eternity to freeze their heads.

Eliezer, have you read Bryan Caplan yet? His "rational irrationality" argues that most of the planet engages in willful self-deception and gets away with it. Not without aggregate harm, but tragedy of the commons and all that.

So AIs are dangerous, because they're blind optimization processes; evolution is cruel, because it's a blind optimization process... and still Eliezer wants to build an optimizer-based AI. Why? We human beings are not optimizers or outcome pumps. We are a layered cake of instincts, and precisely this allows us to be moral and kind.

No idea what I'm talking about, but the "subsumption architecture" papers seem to me much more promising - a more gradual, less dangerous, more incrementally effective path to creating friendly intelligent beings. I hope something like this this will be Eliezer's next epiphany: the possibility of non-optimizer-based high intelligence, and its higher robustness compared to paperclip bombs.

We human beings are not optimizers or outcome pumps.

Sure we are. All biological organisms are. Evolution is a giant optimization process, and we are doing the optimizing in our region of design space.

I agree that there are certain moral rules we should never break. Human beings are not omniscient, so all of our principles have to be principles-in-a-context. In that sense every principle is vulnerable to a black swan, but there are levels of vulnerability. The levels correspond to how wide ranging the abstraction. The more abstract the less vulnerable.

Injunctions about truth are based on the metaphysical fact of identity, which is implied in every single object we encounter in our entire lives. So epistemological injunctions are the most invulnerable. T...

http://www.imdb.com/title/tt0113613/ Plot: A group of idealistic, but frustrated, liberals succumb to the temptation of murdering rightwing pundits for their political beliefs.

Toby,

You should never, ever murder an innocent person who's helped you, even if it's the right thing to do

You should never, ever do X, even if if you are exceedingly confident that it is the right thing to do

I believe a more sensible interpretation would be, "You should have an unbreakable prohibition against doing X, even in cases where X is the right thing to do" - the issue is not that you might be wrong about it being the right thing to do, but rather that not having the prohibition is a bad thing.

This seems closely related to inside-view versus outside-view. The think-lobe of the brain comes up with a cunning plan. The plan breaks an ethical rule but calculation shows it is for the greater good. The executive-lobe of the brain then ponders the outside view. Every-one who has executed an evil cunning plan has run a calculation of the greater good and had their plan endorsed. So the calculation lack outside-view credibility.

What kind of evidence could give outside-view credibility? Consider a plan with lots of traceability to previous events. If it g...

Michael, it applies to AI at an intermediate stage (and maybe not so much to AI as to the design decisions that came into its creation). These black swan safety measures should of course be relative to predictive horizon, where precise knowledge about (evaluation of) consequences is possible. There is no such problem when you need to choose between alternatives having only known immediate consequences that have known moral evaluation, so the question is when to pull the plug, when to decide that your model likely deceives you.

Interesting and convincing climax to a series of slightly less convincing posts. I see what you were getting at, and thanks for writing it.

Eliezer ---

I'm confused by your desire for an 'automatic controlled shutdown' and your fear that further meta-reasoning will override ethical inhibitions. In previous writings you've expressed a desire to have a provably correct solution before proceeding. But aren't you consciously leaving in a race-condition here?

What's to prohibit the meta-reasoning from taking place before the shutdown triggers? It would seem that either you can hard-code an ethical inhibition or you can't. Along those lines, is it fair to presume that the inhibitions are always neg...

Highly excellent series of posts. However, is there not a need to take account of more/better data on the aspects of human psychology that these Ethical Injunctions are there to protect against? Eliezer derived the hypotheses from evolutionary theory, but is not more solid empirical data needed in order to more accurately determine how severe these psychological effects are and in turn to more accurately design good Ethical Injunctions? Or will good Injunctions likely be so general that such a level of accuracy is not necessary?

The world isn't simple and pure and clean

Amen.

"Never try to deceive yourself, or offer a reason to believe other than probable truth; because even if you come up with an amazing clever reason, it's more likely that you've made a mistake than that you have a reasonable expectation of this being a net benefit in the long run."

I'll offer a reason to believe. The truth costs. Take pi, the most probable truth is that pi is equal to the limit of the Perimeter of an n sided polygon divided by its diameter as n goes to infinity.

pi = 3.14159000000 is...

Will, you are arguing about precision rather than accuracy.

As before, I agree with Toby Ord.

Will, when you use a rational approximation of pi, you still don't believe you're using the exact value of pi... I hope?

Thom, how is the issue not "that you might be wrong about it being the right thing to do"?

Vladimir N, it's meant to apply to AI at an intermediate stage, but I think Michael's concern is that it would get locked into the utility function forever. That is tricky.

Like I keep on saying, I have a different moral framework than most, but I come to the same conclusions on unethical means to allegedly ethical ends.

I've seen many claims that deceiving oneself optimistically is a prerequisite for success. In particular, it is claimed that most successful people were initially excessively optimistic about their prospects for success. Without this excessive optimism, success is claimed to be unlikely. I notice that Eliezer is indeed optimistic about his prospects for success in creating friendly AI, however he has a rationalization for why his optimism is justified. Many critics here have expressed skepticism about his justifications. One risk is that without conscious ...

Zubon, I didn't think I was arguing about either.

Nick Tartleton, I might occasionally forget that the value of PI I am using is an approximation, just like I sometimes forget that multiplication is not commutative for floating point numbers. For some people e.g. sea captains plotting a course, they might never need to know that pi is an approximation. Due to the immense amount of imprecision involved in piloting a boat, they don't need to know the truth. There isn't the phrase, "near enough for a sailing ship" for no reason. Preferring to spend t...

Letting yourself forget ≠ choosing to forget ≠ choosing to believe falsely.

Hal asks good questions. I advise always minding the distinction between personal success (personal economic security, reputation, esteem among high-status people) and global success (increasing the probability of a good explosion of engineered intelligence) and suggest that the pernicious self-deception (and blind spots) stem from unconscious awareness of the need for personal success. I.e., the need for global success does not tend to distort a person's perceptions like (awareness of) the need for personal success does.

Forgetting truths has the same potential consequences as rationally choosing to believe falsely. How is an AI who chooses to delete their memories and any logs of the action, any different from a system that forgets.

We are discussing AI design here right? The AI system must have a way of deciding what is forgotten, it might be subconscious, but you hope it is done with a reason or purpose it doesn't randomly forget very important things, like how to speak etc. So a choice is made by the system. So your subconscious chooses what you forget, not your consci...

One category of cases where self-deception might be (evolutionarily) adaptive would be for males to be over-confident about their chances to pick up a female for a one-night stand (or, alternative, over-confident about how pleasurable that dalliance would be, and/or about how little they would be emotionally hurt by a rejection of their advances).

Suppose that in reality the potential utility to the male of the 1-night stand (if the seduction works) is twice as much as the utility loss (if rejected) and the actual chances of success are 20%; in this case th...

Psy-Kosh: Given the current sequence, perhaps it's time to revisit the whole Torture vs Dust Specks thing?

I can think of two positions on torture to which I am sympathetic:

1) No legal system or society should ever refrain from punishing those who torture - anything important enough that torture would even be on the table, like a nuclear bomb in New York, is important enough that everyone involved should be willing to go to prison for the crime of torture.

2) The chance of actually encountering a "nuke in New York" situation, that can be effectively resolved by torture, is so low, and the knock-on effects of having the policy in place so awful, that a blanket injunction against torture makes sense.

In case 1, you would choose TORTURE over SPECKS, and then go to jail for it, even though it was the right thing to do.

In case 2, you would simultaneously say "TORTURE over SPECKS is the right alternative of the two, but a human can never be in an epistemic state where you have justified belief that this is the case", which would tie in well to the Hansonian argument that you have an O(3^^^3) probability penalty from the unlikelihood of finding yourself in such a uni...

Tim Tyler, IMO you're wrong: a human mind does not act as if maximizing any utility function on world states. The mind just goes around in grooves. Nice things like culture and civilization fall out accidentally as side effects. But thanks for the "bright light" idea, it's intriguing.

You are so Kantian. I think the world could use a little more Kant and a little less Hobbes these days.

I forgot I posted over here the other day, and so I didn't check back. For anyone still reading this thread, here's a bit of an email exchange I had on this subject. I'd really like a "FriendlyAI scenarios" thread.

From the few sentences I read on CEV, you are basically saying “I don’t know what I want or what the human race wants, but here I have a superintelligent AI. Let’s ask it!” This is clever, even if it means the solution is completely unknown at this point. Still, there are problems. I envision this as a two-step process. First, ...

MichaelG, read up on molecular nanotechnology. I think a biological humanity living on a real Earth is a terrible idea - that's not at all what I think of when I talk about defending humanity. I mean, everyone's just going to die young anyway at that rate.

Eliezer, I'm aware of nanotech. And I know you think the human race is obsolete when AI comes along. And I also think that you might be right, and that people like you might have the power to make it so.

But I also believe that if the rest of the human race really thought that was a possibility, you'd be burned at the stake.

Do you have any regard for the opinions of humanity at all? If you were in the position of having an AI in front of you, that you had convinced yourself was friendly, would you let it out of the box without bothering to consult anyone else?

0mamert7y
The term "obsolete" as used here confuses me. It seems to imply a purpose, one that individuals - or humanity - or whatever other "intelligence collective" there may be - could get behind. What might that purpose be? Not survival, is it?

I have great regard for the welfare of humanity. But there is no right to having an opinion on the subject. Not without doing all the work and studying all the issues required to have an opinion, on this terrible issue where a single flawed step in reasoning could be fatal.

I don't think you have any idea how poor humanity's position on the gameboard looks right now, if you think that there's any space at all for anything but the most perfect possible moves as fast as they can be made.

I have no intent, at present, to wield superhuman power with my own hum...

It’s been argued that since uploads are so complex, there will inevitably be designed AI before uploads. It might even require a very competent AI to do the upload. Still, computer technology is advancing so rapidly, it might only be a few years between the point where hardware could support a powerful designed AI, and the time when uploads are possible.

It doesn't make sense to me. More likely, once we have AI, not many will be interested in emulating the human brain. Emulations may happen eventually, but the results will probably have very low social an...

Eliezer, I understand the logic of what you are saying. If AI is an existential threat, then only FriendlyAI can save us. Since any self-improving AI can become quickly unstoppable, FriendlyAI must be developed first and deployed as soon as it is developed. The team that developed it would in fact have a moral imperative to deploy it without risking consultation from anyone else.

I assume you also understand where I'm coming from. Out here in the "normal" world, you sound like a zealot who would destroy the human race in order to save it. Any...

I think there are a large number of nerds who would consider becoming uploads. I don't see why you think this makes no sense.

Uploads are not a very practical idea. The required technology comes some considerable distance after that required to make an engineered intelligence - and so much of the motivation to develop it falls away before the technology is in place. Then there's the issue of machine status. Machines are likely to be enslaved by humans initially. An upload would probably have few rights. Also, uploads would have to be into a sandbox, ...

[-][anonymous]14y 0
Out here in the "normal" world, you sound like a zealot who would destroy the human race in order to save it.... The idea hitting the start button on something that could destroy the human race, based on nothing more than pages of logic, would be considered ridiculous by practically every member of the human race.

Are you saying this is a reason not to act, or just to tone down the rhetoric?

I understand if you think you are right about all of this, and don't need to listen to or even react to criticism.

"Don't have to listen to criticism ...

Tim, do we have any idea what is required for uploads? Do we have any idea what is required for AGI? How can you make those comparisons?

If we thin-section and scan a frozen brain, it's an immense amount of data, but at least potentially, captures everything you need to know about a brain. This is a solvable technological problem. If we understand neurons well enough, we can simulate that mapped brain. Again, that's just a matter of compute power. I'm sure there's a huge distance from a simulated scan to a functional virtual human, but it doesn't stri...

Tim, do we have any idea what is required for uploads? Do we have any idea what is required for AGI? How can you make those comparisons?

Kurzweil discusses the hardware requirements in TSIN, pages 124 and 199. His estimate for uploading is way too low - but the exact estimates don't matter much - the point is that uploads require a lot more in the way of computing hardware. That doesn't address software issues, but probably with several orders of magnitude of hardware difficulties come several orders of magnitude of software difficulties.

If we thin-sect
...

Even if at somepoint it would have been better for some particular human to believe false thing X, couldn't there be a set of truths T which would be even better in every one of those situations?

2orthonormal11y
Some of those truths may be above the cognitive capacity of even a smart human. The world doesn't have to be fair.
[-][anonymous]11y 0

If my utility function has a high enough U(Babies undergoing mind-state annihilation) I will go about tiling the universe. It doesn't at present and additionally implements U(high U(Babies undergoing mind-state annihilation)) as way low.

All the happiness that the warm thought of an afterlife ever produced in humanity, has now been more than cancelled by the failure of humanity to institute systematic cryonic preservations after liquid nitrogen became cheap to manufacture. And I don't think that anyone ever had that sort of failure in mind as a possible blowup, when they said, "But we need religious beliefs to cushion the fear of death." That's what black swan bets are all about—the unexpected blowup.

Y'know, I can't help but notice that a lot of atheists talk about how death...

All the happiness that the warm thought of an afterlife ever produced in humanity, has now been more than cancelled by the failure of humanity to institute systematic cryonic preservations after liquid nitrogen became cheap to manufacture. And I don't think that anyone ever had that sort of failure in mind as a possible blowup, when they said, "But we need religious beliefs to cushion the fear of death." That's what black swan bets are all about—the unexpected blowup.

That's a fantastic quote.

There is something I don't understand about the "fooling programmers -> shutdown" idea - how "It looks like it should be possible"

Am I correct assuming this requires an AI that:

1. Implements changes in discrete iterations

2. Understands how it itself works, both on low and very high levels (getting fractal here)

3. Can do the same for its more advanced iteration

4. Monitors the more advanced iteration (a simulation or a live deployment) for a certain behavior, preferably in real time or faster

5. Has the concept of deception (shutdown conditi

...

I've been working my way through the Sequences--and I'm wondering a lot about this essay, in light of the previously-introduce notion of 'how do you decide what values, given to you by natural selection, you are going to keep?'

Could someone use the stances you develop here, EY, to argue for something like Aristotelian ethics? (Which, admittedly, I may not properly understand fully, but my basic idea is:)

'You chose to keep human life, human happiness, love, and learning as values in YOUR utility function,' says the objector, 'even though you know where they...

0Viliam6y
2Relenzo6y
1Viliam6y
I guess some people are unable to deal with uncertainty, especially when it concerns important things (such as "I am not 100% sure whether doing A or doing B will make my soul burn forever in hell, but I have to make a decision now anyway"). The standard human way to deal with unpleasant information is to deny it. Catholic theologicians don't have an option of denying hell, so the obvious solution is to deny uncertainty. "There is a rule X, which is perfectly unambiguous and perfectly good." "But here is this non-central [http://lesswrong.com/lw/e95/the_noncentral_fallacy_the_worst_argument_in_the/] situation where following the rule blindly seems bad." "There is this ad-hoc rule Y, which covers the special situation, so the whole system is perfectly unambiguous and perfectly good." "But here is another situation where..." "There is another ad-hoc rule Z, which covers the other situation..." "But there is also..." "There is yet another ad-hoc rule..." You can play this game forever, adding epicycles upon epicycles, but the answer is always going to be that the system is perfectly unambiguous and perfectly good. It is also obvious how they are cheating to achieve that. Also, the starving orphan is probably not aware of all these theological rules and exceptions, so obviously the answer is designed to make the theologician feel happy about the unambiguity of the situation. I don't think you can actually talk people out of their emotional needs.
-2entirelyuseless6y
Here is a perfectly good rule: don't do evil. Now suppose someone comes to you and tells you that they will save one billion lives if you promise to do evil for the rest of your life to the best of your ability. Suppose you decide that overall you will not be able to do enough evil to counteract saving one billion lives. Should you make the agreement and do evil for the rest of your life to the best of your ability? If you do, your actions will have overall good effects. And if you do, you will be doing evil, or you will not be fulfilling your promise. If you want to talk to people, you need to first understand what they are saying. And they saying that the question that is important to them is, "Is this action good or evil," not "Are the results good or evil?" Those are two different questions, and there is nothing to prevent them from having different answers.
0CCC6y
This sounds like deontological ethics [https://en.wikipedia.org/wiki/Deontological_ethics]. It's not by any means unique to Catholicism; it's just the general idea that being good involves following a (presumably carefully chosen) list of rules. Not all Catholics are deontologists; not all deontologists are Catholic. And, I may be misreading here, but I think your worry is more about deontology than Catholicism; that is, it's more about people who follow a list of rules instead of trying consequentialism or virtue ethics or something else along those lines. Is this accurate?

Tangentially, there's an upcoming Netflix six-episode series named “The Heavy Water War,” that should cover both this event, and the sabotage of the heavy water production facility that led up to it.

Your protecting of Knut Haikelid's decision only comes from your "it is more meaningful that we save lives than that we conform to a particular pattern while attempting it" moral rule (which is, as I argued, not part of many people's ethics) - or am I getting something wrong?

As for lies on Singularity - a clever skeptic could say "people who are smart enough to expose you in a lie on such a technical matter are also smart enough to help you instead of exposing you, and you even could leave them a clue that you know you are lying that those outside the technical paradigm simply will not get". It is a difficult technical matter, after all. As for simplicity - is it a terminal value? I think not.