Moral Error and Moral Disagreement

Far more extreme, I would think, to say that zero out of 6.5 billion humans are stable psychopaths.

I wonder if the distinction between 1) something implementing the same dynamic as a typical human but mistaken about what it says and 2) something implementing a completely different dynamic and not mistaken about anything, is the same as the distinction people normally make between 1) immoral and 2) amoral.

Steven: quite possibly related. I don't think they're exactly the same (the classic comic book/high fantasy "I'm evil and I know it" villain fits A2, but I'd describe him as amoral), but it's an interesting parallel.

Eliezer: I'm coming more and more to the conclusion that our main area of disagreement is our willingness to believe that someone who disagrees with us really "embodies a different optimization process." There are infinitely many self-consistent belief systems and infinitely many internally consistent optimization processes; while I believe mine to be the best I've found, I remain aware that if I held any of the others I would believe exactly the same thing. And that I would have no way of convincing the anti-Occam intelligence that Occam's Razor was a good heuristic, or of convincing the psychopath who really doesn't care about other people that he 'ought' to. So I hesitate to say that I'm right in any objective sense, since I'm not sure exactly what standard I'm pointing to when I say 'objective.'

And I've had extended moral conversations with a few different people that led to us, eventually, concluding that our premises were so radically different that we really couldn't have a sensible moral conversation. (to wit: I think my highest goal in life is to make myself happy. Because I'm not a sociopath making myself happy tends to involve having friends and making them happy. But the ultimate goal is me. Makes it hard to talk to someone who actually believes in some form of altruism).

If a person's morality is not defined as what they believe about morals, I don't know how it can be considered to meaningfully entail any propositions at all. A General AI should be able to convince it just about anything, right?

Far more extreme, I would think, to say that zero out of 6.5 billion humans are stable psychopaths.

Heck, what about babies? What do they want, and would they be complicated enough to want anything different if they knew more and thought faster?

There are infinitely many self-consistent belief systems and infinitely many internally consistent optimization processes; while I believe mine to be the best I've found, I remain aware that if I held any of the others I would believe exactly the same thing.

You would not believe exactly the same thing. If you held one of the others, you would believe that your new system was frooter than any of the others, where "frooter" is not at all the same thing as "better". And you would be correct.

If a person's morality is not defined as what they believe about morals, I don't know how it can be considered to meaningfully entail any propositions at all. A General AI should be able to convince it just about anything, right?

If you make matters that complicated to begin with, i.e., we're not discussing metaethics for human usage anymore, then you should construe entailment / extrapolation / unfolding in more robust ways than "anything a superintelligence can convince you of". E.g. CEV describes a form of entailment.

As for what a person's morality is, surely you extrapolate it at least a little beyond their instantaneous beliefs. Would you agree that many people would morally disapprove of being shot by you, even if the actual thought has never crossed their mind and they don't know you exist?

I must be starting to get it. That unpacked in exactly the way I expected.

On the other hand, this:

If a person's morality is not defined as what they believe about morals, I don't know how it can be considered to meaningfully entail any propositions at all.

makes no sense to me at all.

I think my highest goal in life is to make myself happy. Because I'm not a sociopath making myself happy tends to involve having friends and making them happy. But the ultimate goal is me.

Sebastian Hagen:

My intuition is that a good deal of people would take the psychopath pill. At least if the social consequences were minimal, which is besides the point.

Frame it defensively rather than offensively and a whole heck of a lot of people would take that pill. Of course some of us would also take the pill that negates the effects of our friends taking the first pill, hehehe.

Weird, jsalvati is not my sock puppet, but the 11:16pm post above is mine.

Fixed. How very odd. (And for the record, jsalvati's IP is not HA's.)

"Perhaps Richard means that we could suppose that abortion is indeed prohibited by morality_Bob..."

That's right. (I didn't mean to suggest that there's never any disputing what someone's moral commitments are; just that this wasn't supposed to be in dispute in the particular case I was imagining.) I take it that Sally and Bob could disagree even so, and not merely be talking past each other, even if one or both of them was impervious to rational argument. It is at least a significant cost of your theory that it denies this datum. (It doesn't have to be 'irrefutable' to nonetheless be a hefty bullet to bite!)

I like your account of everyday moral disagreement, but would take it a step further: it is no mere accident that your Sally and Bob expect to be able to persuade the other. Rather, it is essential to the concept of morality that it involves shared standards common to all fully reasonable agents.

It's worth emphasizing, though, that humans are not fully reasonable. Some are even irrevocably unreasonable, incapable of rationally updating (some of) their beliefs. So while, I claim, we all aspire to the morality_Objective norms, I doubt there's any empirically specifiable procedure that could ensure our explicit affirmation of those norms (let alone their unfolded implications). Bob may stubbornly insist that abortion is wrong, and this may conflict with other claims he makes, but there's simply no way (short of brain surgery) to shake him from his illogic. What then? I say he's mistaken, even though he can't be brought to recognize this himself. It's not clear to me whether you can say this, since I'm not sure exactly what your 'extrapolation' procedure for defining morality_Bob is. But if it's based on any simple empirical facts about what Bob would believe if we told him various facts and arguments, then it doesn't look like you'll be able to correct for the moral errors that result from sheer irrationality, or imperviousness to argument.

Could you say a little more about exactly which empirical facts serve to define morality_Bob?

I do not eat steak, because I am uncertain of what my own morality outputs with respect to steak-eating. It seems reasonable to me to imagine that cows are capable of experiencing pain, of fearing death. Of being, and ceasing to be. If you are like the majority of human beings, you do eat steak. The propositions I have suggested do not seem reasonable to you.

Do you imagine that there are facts about the brains of cattle which we could both learn - facts drawn from fMRI scans, or from behavioral science experiments, perhaps - which would bring us into agreement on the issue?

Eliezer: for 'better' vs 'frooter,' of course you're right. I just would have phrased it differently; I've been known to claim that the word 'better' is completely meaningless unless you (are able to) follow it with "better at or for something." So of course, Jadagul_real would say that his worldview is better for fulfilling his values. And Jadagul_hypothetical would say that his worldview is better for achieving his values. And both would (potentially) be correct. (or potentially wrong. I never claimed to be infallible, either in reality or in hypothesis). But phrasing issues aside, I do believe that I think this happens more often than you think it happens.

Sebastian Hagen: That's actually a very good question. So a few answers. First is that I tend to go back and forth on whether by 'happiness' I mean something akin to "net stimulation of pleasure centers in brain," or to "achievement of total package of values" (at which point the statement nears tautology, but I think doesn't actually fall into it). But my moral code does include such statements as "you have no fundamental obligation to help other people." I help people because I like to. So I lean towards formulation 1; but I'm not altogether certain that's what I really mean.

Second is that your question, about the sociopath pill, is genuinely difficult for me. It reminds me of Nozick's experience machine thought experiment. But I know that I keep getting short-circuited by statements like, "but I'd be miserable if I were a sociopath," which is of course false by hypothesis. I think my final answer is that I'm such a social person and take such pleasure in people that were I to become a sociopath I would necessarily be someone else. That person wouldn't be me. And while I care about whether I'm happy, I don't know that I care about whether he is.

Of course, this all could be "I know the answer and now let me justify it." On the other hand, the point of the exercise is to figure out what my moral intuitions are...

Re: "We have nothing to argue about, we are only different optimization processes." That seems to apply in the case when a man wants to rescue copies of his genes from eternal oblivion - by convincing his mate not to abort his prospective offspring. Of course, not many would actually say that under those circumstances.

Eliezer: "But this would be an extreme position to take with respect to your fellow humans, and I recommend against doing so. Even a psychopath would still be in a common moral reference frame with you, if, fully informed, they would decide to take a pill that would make them non-psychopaths. If you told me that my ability to care about other people was neurologically damaged, and you offered me a pill to fix it, I would take it."

How sure are you that most human moral disagreements are attributable to

• lack of veridical information, or
• lack of ability/tools to work through that information, or
• defects? You talk freely about psychopaths and non-psychopaths as though these were distinct categories of non-defective and defective humans. I know you know this is not so. The arguments about psychological unity of humankind only extend so far. e.g., would you be prepared to tell a homosexual that, if they were fully informed, they would decide to take a pill to change their orientation? There are demonstrable differences where our fellow humans really are "different optimization processes". Why should we ignore the spread of differences in moral computations?

I've been enjoying your OB posts and your thought experiments are powerful, but I'm curious as to the empirical data that have led you to update your beliefs so strongly in favour of psychological unity and so strongly against differences in computation. Your arguments that mention psychopaths smack a little of a "no true Scotsman" definition of human morality.

Mike,

"I do not eat steak, because I am uncertain of what my own morality outputs with respect to steak-eating. It seems reasonable to me to imagine that cows are capable of experiencing pain, of fearing death. Of being, and ceasing to be. If you are like the majority of human beings, you do eat steak. The propositions I have suggested do not seem reasonable to you."

Accepting your propositions for the sake of argument, I still find that eating steak seems reasonable.

"Rather, it is essential to the concept of morality that it involves shared standards common to all fully reasonable agents."

Richard,

If you're going to define 'fully reasonable' to mean sharing your moral axioms, so that a superintelligent pencil maximizer with superhuman understanding of human ethics and philosophy is not a 'reasonable agent,' doesn't this just shift the problem a level? Your morality_objectivenorms is only common to all agents with full reasonableness_RichardChappell, and you don't seem to have any compelling reason for the latter (somewhat gerrymandered) account of reasonableness save that it's yours/your culture's/your species.'

Other moral issues where there are a gender differences include: "should prostitution be legalised" and "should there be tighter regulation of pornography".

Again, it seems that part of the effect is due to people's idea of what is right being influenced by their own personal role - i.e. the "different optimization processes" effect.

Gender is the most obvious source of such issues, but I'm sure you can find them in other areas of life. Race politics, for instance.

People in general do not want to be shot. The person doing the shooting, the lethal weapon being fired, the location in which the shooting occurs and the time of day are all pretty much irrelevant. You can ask people if they want to be shot and they'll say no, without even specifying those details. That seems a very different case from Bob, who is considering a moral proposition and outright rejecting it.

Given all of Bacon's idols of the Mind can you ever know definitely if there is an error in your own reasoning, let alone the other persons?

You cannot rely on your moral intuition, nor the cultural norms of your time, nor academic authority, nor your internal reasoning or ability to know the soundness of your argument.

Socialization, severe biases, faulty reasoning can all make you think you are ‘correct’, but can leave you with the incorrect impression of the ‘correctness’ of your thinking. & even if presented with all the correct or relevant information some people still make these errors, so if they can so could you.

Eliezer: "When a paperclip maximizer and a pencil maximizer do different things, they are not disagreeing about anything, they are just different optimization processes. You cannot detach should-ness from any specific criterion of should-ness and be left with a pure empty should-ness that the paperclip maximizer and pencil maximizer can be said to disagree about - unless you cover "disagreement" to include differences where two agents have nothing to say to each other.

But this would be an extreme position to take with respect to your fellow humans, and I recommend against doing so. Even a psychopath would still be in a common moral reference frame with you, if, fully informed, they would decide to take a pill that would make them non-psychopaths. If you told me that my ability to care about other people was neurologically damaged, and you offered me a pill to fix it, I would take it."

• no, you wouldn't. The only reason that you are now saying that you would take it is that you currently have the ability to care about other people. Surely this is obvious? Eliezer, you are ignoring your own advice and summoning a "ghost of perfect human unity" into every human mind, even that of a psychopath. Your ability to want to make yourself to care about other people only comes because you already care about other people.

I find your position somewhat outlandish: that every single moral disagreement between humans is simply there because the humans involved in it aren't fully informed, but that there is no "information" that I (or perhaps someone vastly more intelligent than me) could give to a paperclip maximizer that would persuade them that their ability to love human babies is damaged and they need to take a pill to fix it. (Hat tip to TGGP here) And this coming from the inventor of the AI-box thought experiment!

Let me spell it out. Every human mind comes with an evolved set of "yuck" factors (and their opposite, which I might call "yum" factors?). This is the "psychological unity of humankind". Unfortunately, these cover only those situations which we were likely to run into in our EEA. Abortion probably did not exist in our EEA: so people have to compare it to something that did. There are two ways to do this - either you think of it as being just like helping a fellow member of your tribe, and become pro-abortion, or you think of it as being infanticide and become anti abortion. Beyond these "yuck" factors, there is no further unity to the moral views of humankind.

In the modern world, people have to make moral choices using their general intelligence, because there aren't enough "yuck" and "yum" factors around to give guidance on every question. As such, we shouldn't expect much more moral agreement from humans than from rational (or approximately rational) AIs.

But in my opinion, there is a certain "psychological unity of approximately rational minds", and I think Eliezer is being irrational to deny this. Why he is overselling the extent to which humans agree, in flagrant contradiction with the facts, and underselling the extent to which all rational agents share common instrumental values, I do not know.

I should qualify this statement: "As such, we shouldn't expect much more moral agreement from humans than from rational (or approximately rational) AIs."

to instead read:

"As such, on ethical questions that had no precedent in our EEA, we shouldn't expect much more moral agreement from humans than from rational (or approximately rational) AIs, apart, of course, from the fact that most humans share a common set of cognitive biases"

one can see that this is true by looking at the vast disagreements between different moral philosophers consequentialists vs. deontological ethicists, or atheists vs. christians vs. muslims, or libertarians vs. liberals vs. communists.

You have been priming people to think in terms of functions. (Pure) Functions do not change. They map an input to an output, and can be substituted by a list, e.g. a function that tests for primality can can be performed by an (infinitely) long list.

You may want to describe impure functions for people without a functional programming background if you want to keep terminology like morality_john().

Virge's point seems particularly important, and hopefully Eliezer can address it.

I find Roko on-point. The psychological unity of humankind is important, but it can be over-stated. While human beings may occupy a very small area in the space of all possible minds, it is still an area and not a single point. When we shut up and multiply by sufficiently large numbers, very small differences in the starting point are very meaningful. If we are talking about a difference valued at 0.0000001% of a human life, and you extrapolate it over a billion lives, we are talking about life and death matters. Successful AI will affect more than a billion lives.

If you are the advocate of 3^^^3 specks, you must take seriously the notion that 0.0000001% differences in morality will be meaningful when multiplied over all minds into the indefinite future.

Virge:

How sure are you that most human moral disagreements are attributable to - lack of veridical information, or - lack of ability/tools to work through that information, or - defects? You talk freely about psychopaths and non-psychopaths as though these were distinct categories of non-defective and defective humans. I know you know this is not so. The arguments about psychological unity of humankind only extend so far. e.g., would you be prepared to tell a homosexual that, if they were fully informed, they would decide to take a pill to change their orientation?

I don't claim to be sure at all. It does seem to me that most modern humans are very much creatures of their own time; they don't consider that future moral progress could be as radical as the change between their own time and Archimedes's; they think of themselves as the wise, the educated, the modern, not as the savage barbarian children the Future will very likely regard us as. It also seems to me that people fail to systematically distinguish between terminal and instrumental disputes, and that they demonize their enemies (which is correspondence bias). The basic ev-bio necessity behind the psychological unity of human brains is not widely understood.

And even more importantly, the portion of our values that we regard as transpersonal, the portion we would intervene to enforce against others, is not all of our values; it's not going to include a taste for pepperoni pizza, or in my case, it's not going to include a notion of heterosexuality or homosexuality.

If there are distinct categories of human transpersonal values, I would expect them to look like "male and female babies", "male children", "male adults", "female children", "female adults", "neurological damage 1", "neurological damage 2", not "Muslims vs. Christians!"

Roko:

If you told me that my ability to care about other people was neurologically damaged, and you offered me a pill to fix it, I would take it. - no, you wouldn't. The only reason that you are now saying that you would take it is that you currently have the ability to care about other people.

I said "damaged" not "missing". The notion is that I am my current self, but one day you inform me that, relative to other humans, my ability to care about others is damaged. Do I want a pill to fix the damage, even though it will change my values? Yes, because I value humanity and want to stay with humanity; I don't want to be off in some lonely unoccupied volume of mindspace. This is one of the arguments that moves me.

(Albeit if the damage was in any way entwined with my ability to do Singularity work, I would delay taking the pill.)

Let me spell it out. Every human mind comes with an evolved set of "yuck" factors (and their opposite, which I might call "yum" factors?). This is the "psychological unity of humankind". Unfortunately, these cover only those situations which we were likely to run into in our EEA. Abortion probably did not exist in our EEA: so people have to compare it to something that did. There are two ways to do this - either you think of it as being just like helping a fellow member of your tribe, and become pro-abortion, or you think of it as being infanticide and become anti abortion. Beyond these "yuck" factors, there is no further unity to the moral views of humankind.

The question is how much of this disagreement would persist if the disputants had full veridical knowledge of everything that goes on inside the developing fetus and full veridical knowledge of a naturalistic universe. Given the same "yum" and "yuck" factors, why would they be differently targeted? If there are no interpersonally compelling reasons to target them one way or the other, how would a group of fully informed minds come to believe that this was a proper issue of transpersonal morality?

By the way, quite a number of hunter-gatherer tribes practice infanticide as a form of birth control.

Zubon:

If we are talking about a difference valued at 0.0000001% of a human life, and you extrapolate it over a billion lives, we are talking about life and death matters. Successful AI will affect more than a billion lives.

If I have a value judgment that would not be interpersonally compelling to a supermajority of humankind even if they were fully informed, then it is proper for me to personally fight for and advocate that value judgment, but not proper for me to preemptively build an AI that enforces that value judgment upon the rest of humanity. The notion of CEV reflects this statement of morality I have just made.

I must be missing something -- why would you advocate something that you know you can't justify to anyone else?

I said "damaged" not "missing". The notion is that I am my current self, but one day you inform me that, relative to other humans, my ability to care about others is damaged. Do I want a pill to fix the damage, even though it will change my values? Yes, because I value humanity and want to stay with humanity; I don't want to be off in some lonely unoccupied volume of mindspace. This is one of the arguments that moves me.

Does that work in the other direction? The notion is that you are your current self, but one day I inform you that, relative to other humans, your ability to care about others is damaged in the sense that it is hyperactive. Do you want a pill that will fix the damage and change your values so that you value humanity less (putting you in a less lonely volume of mindspace)?

(And if you do not think that there is a meaningful chance that you should value humanity less, doesn't that mean you are most likely undervaluing humanity right now, so you should update and start valuing humanity more? This is a general you, for everyone: if you do not think you should be a bit more sociopathic, what are the odds you have exactly the right amounts of empathy and altruism?)

Jadagul:

But my moral code does include such statements as "you have no fundamental obligation to help other people." I help people because I like to.

Roko:

In the modern world, people have to make moral choices using their general intelligence, because there aren't enough "yuck" and "yum" factors around to give guidance on every question. As such, we shouldn't expect much more moral agreement from humans than from rational (or approximately rational) AIs.

Eliezer Yudkowsky:

If I have a value judgment that would not be interpersonally compelling to a supermajority of humankind even if they were fully informed, then it is proper for me to personally fight for and advocate that value judgment, but not proper for me to preemptively build an AI that enforces that value judgment upon the rest of humanity.

Quick correction: s/abstract rational reasoning/abstract moral reasoning/

Will Pearson: Why not just treat them as pure functions in the State monad?

Re: If there are distinct categories of human transpersonal values, I would expect them to look like "male and female babies", "male children", "male adults", "female children", "female adults", "neurological damage 1", "neurological damage 2", not "Muslims vs. Christians!"

That seems like the position you would get if you thought that cultural evolution could not affect people's values.

Carl - "If you're going to define 'fully reasonable' to mean sharing your moral axioms, so that a superintelligent pencil maximizer with superhuman understanding of human ethics and philosophy is not a 'reasonable agent,' doesn't this just shift the problem a level? Your morality_objectivenorms is only common to all agents with full reasonableness_RichardChappell, and you don't seem to have any compelling reason for the latter (somewhat gerrymandered) account of reasonableness save that it's yours/your culture's/your species.'"

I don't mean to define 'fully reasonable' at all (though it is meant to be minimally ad hoc or gerrymandered). I take this normative notion as a conceptual primitive, and then hypothesize that it entails a certain set of moral norms. They're probably not even my norms (in any way Eliezer could accommodate), since I'm presumably not fully reasonable myself. But they're what I'm trying to aim for, even if I don't always grasp them correctly.

This may sound mysterious and troublingly ungrounded to you. Yet you use terms like 'superintelligent' and 'superhuman understanding', which are no less normative than my 'reasonable'. I think that reasonableness is a component of intelligence and (certainly) understanding, so I don't see how these terms could properly apply to a pencil maximizer. Maybe you simply mean that it is a pencil maximizer that is instrumentally rational and perfectly proficient at Bayesian updating. But that's not to say it's intelligent. It might, for example, be a counterinductivist (didn't someone mention anti-Occamists up-thread?), with completely wacky priors. I take it as a datum that this is simply unreasonable -- there are other norms, besides conditionalization and instrumental rationality, which govern 'intelligent' or good thinking.

So I say there are brute, unanalysable facts about what's reasonable. The buck's gotta stop somewhere. I don't see that any alternative theory does better than this one.

"If there are distinct categories of human transpersonal values, I would expect them to look like [...] 'male adults', [...] 'female adults', [...] not 'Muslims vs. Christians!'"

Really? In the ways that are truly important, don't you think you have more in common with Natasha Vita-More than Osama bin Laden?

ZM, he means after volition-extrapolating.

Steven, even so, I think the basic question stands. Why should cultural differences and within-sex individual differences wash out of the CEV?

Supposedly genetics allows for people of different ages or sexes to have different mental machinery, whereas individual genetic differences just represent low-complexity differences in tweaking. I'm not sure why that makes Eliezer's point though, if the aforementioned differences in tweaking mean different complex machinery gets activated. Cultural differences I'd expect to wash out just through people learning about different cultures that they could have grown up in.

Zubon: "if you do not think you should be a bit more sociopathic, what are the odds you have exactly the right amounts of empathy and altruism?"

• that was exactly what I was going to say ; - ) My personal "gut" feeling is that have exactly the right amount of empathy, no more, no less. Intellectually, I realize that this is means I have failed the reversal test, and that I am therefore probably suffering from status quo bias. (assuming, as I believe, that there is an objectively true ethics. If you're a moral relativist, you get a blank cheque for status quo bias in your ethical views)

Sebastian Hagen: "There might not be enough "yuck" and "yum" factors around to offer direct guidance on every question, but they're still the basis for abstract rational reasoning. Do you think "paperclip optimizer"-type AIs are impossible? If so, why? There's nothing incoherent about a "maximize the number of paperclips over time" optimization criterion; if anything, it's a lot simpler than those in use by humans.

• yes, that's true. As soon as I made that post I realized I had gone too far; let me restate a more reasonable position: any moral agreement or psychological unity that humankind has over and above the unity that all approximately rational minds have will stem from our evolved "yuck" and "yum" factors in our EEA.

As for the "rational economic agents" like the paperclip maximizer: yes, they do exist, but they, together with a wide class of rational agents (i.e. ones that are not utility maximizers) also have a certain axiological unity called universal instrumental values. I'm more interested in this "unity of agent kind".

One could summarize by saying:

Axiological agreement = (unity of agent kind) + (yuck and yum)

Personally I find it hard to really identify with my genes' desires. Perhaps one could consider this a character flaw, but I just cannot honestly make myself identify with these arbitrary choices.

Steven: "Cultural differences I'd expect to wash out just through people learning about different cultures that they could have grown up in."

I suspect a category error here hinging around personal identity. We say "if I had grown up in a different culture ..." when I think we mean "if the baby that grew into me had grown up in a different culture..." If the baby that grew into me had grown up in a radically different culture, I don't think ve'd be me in any meaningful sense, although of course there would be many similarities due to evo-psych and genetics. Whereas I would likely consider a hypothetical member of the opposite sex who shared my ideas and concerns to be me, even if ve was much better or worse than this me at mentally rotating 3D objects, or finding things in the refrigerator.

Re: Roko's "more reasonable position":

Human psychological unity, to the extent that it exists, includes brain speed, brain degree-of-parallelism, brain storage capacity, brain reliability - and other limitations that have little to do with human goals.

If you had a chance to take a pill which would cause you to stop caring about your friends by permanently maxing out that part of your hapiness function regardless of whether you had any friends, would you take it?

I'm not sure this proves anything. I'll take Jadagul's description as my own. I'm maximizing my happiness, but my non-sociopath status means that I like having friends/loved ones, so maximizing my own happiness entails caring about them to some degree or another. Under my existing moral code I wouldn't take the pill, but that's because it will in the future entail behavior that I would currently, as I am, find obnoxious.

In theory, taking the pill will allow me to be happier by obviating the need to worry about anybody else (along with the resources that entails.) But you can't get there from here. I already know what the pill will make me later, and the prospect of taking it makes me unhappy now. Taking the pill would be a viable option only if the behavior the pill would induce could somehow be made acceptable to current, non-sociopath me.

I, too, wonder if the "psychological unity of humankind" has been a bit overstated. All [insert brand and model here] computers have identical hardware, but you can install different software on them. We're running different

Consider the case of a "something maximizer". It's given an object, and then maximizes the number of copies of that object.

You give one something maximizer a paperclip, and it becomes a paperclip maximizer. You give another a pencil, and that one becomes a pencil maximizer.

There's no particular reason to expect the paperclip maximizer and the pencil maximizer to agree on values, even though they are both something maximizers, implemented on identical hardware. The extrapolated volition of a something-maximizer is not well-defined.

There are probably blank spaces in human Eliezer::morality that are written on by experience, and such writing may well be irrevocable, or mostly irrevocable. If humans' terminal values are, in fact, contingent on experiences, then you could have two people disagreeing on the same level that the two something maximizers do.

As a practical matter, people generally do seem to have similar sets of terminal values, but different people rank the values differently. Consider the case of "honor". Is it better to die with honor or to live on in disgrace? People raised in different cultures will give different answers to this question.

Eliezer: "The basic ev-bio necessity behind the psychological unity of human brains is not widely understood."

I agree. And I think you've over-emphasized the unity and ignored evidence of diversity, explaining it away as defects.

Eliezer: "And even more importantly, the portion of our values that we regard as transpersonal, the portion we would intervene to enforce against others, is not all of our values; it's not going to include a taste for pepperoni pizza, or in my case, it's not going to include a notion of heterosexuality or homosexuality."

I think I failed to make my point clearly on the idea of a sexual orientation pill. I didn't want to present homosexuality as a moral issue for your judgment, but as an example of the psychological non-unity of human brains. Many people have made the mistake of assuming that heterosexuality is "normal" and that homosexuals need re-education or "fixing" (defect removal). I hold that sexuality is distributed over a spectrum. The modes of that distribution represent heterosexual males and females--an evolutionary stable pattern. The other regions of that distribution remain non-zero despite selection pressure.

Clearly we do not have a psychological unity of human sexual preference. People with various levels of homosexual preference are not merely defective or badly educated/informed.

Sexuality is a complex feature arising in a complex brain. Because of the required mutual compatability of brain-construction genetics, we can be sure that we all have extremely similar machinery, but our sexual dimorphism requires that a single set of genes can code flexibly for either male or female. Since that flexibility doesn't implement a pure binary male/female switch, we find various in-between states in both physical and mental machinery. The selection pressure from sexual dimorphism means we should expect far more non-unity of sexual preference than in other areas of our psychology.

But the fact that our genes can code for that level of flexibility, yet still remain biologically compatible, tells us that there are likely to be many other computations that could exhibit a superficial unity, but with a broad spread. The spread of propensities to submit to authority and override empathy observed in the Stanford Prison experiment gives good reason to question the supposed unity. (Yes I know you could shoehorn that diversity into your model as a effect of lack of moral training.)

Now let's reconsider psychopathy or the broader diagnosis of antisocial personality disorder. What should we do with those humans whose combination of narcissism and poor social cognition is beyond some particular limit? Lock them up, or elect them to govern? From my limited understanding of the subject, it seems that the "condition" is considered untreatable.

It's an easy path to stick to the psychological unity of humans and declare those in the tails of the distribution to be defective. But is it statistically justified? Does your unity model actually fit the data or just give a better model than the tabula rasa model that Tooby and Cosmides reacted against?

That's why the idea of some idealised human moral computation, that everyone would agree to if they knew enough and weren't defective, seems like question begging. That's why I was asking for the empirical data that have led you to update your beliefs. Then I could update mine from them and maybe we'd be in agreement.

I'm open to the idea that we can identify some best-fit human morality--a compromise that minimizes the distance/disagreement to our population of (veridically informed) humans. That seems to me to be the best we can do.

virge makes a very good point here. The human mind is probably rather flexible in terms of it's ethical views; I suspect that Eli is overplaying our psychological unity.

I think that views are being attributed to me that I do not possess - perhaps on the Gricean notion that if someone attacks me for holding these views, I ought to hold them; but on a blog like this one, that leaves you prey to everyone else's misunderstanding.

I do not assert that all humans end up in the same moral frame of reference (with regard to any particular extrapolation method). I do think that psychological unity is typically underestimated, and I have a hard time taking modern culture at face value (we're the ancient Greeks, guys, not a finished product) - read Tooby and Cosmides's "The Psychological Foundations of Culture" to get a picture of where I'm coming from.

But if you read "Coherent Extrapolated Volition" you'll see that it's specifically designed to handle, among other problems, the problem of, "What if we don't all want the same thing?" What then can an AI programmer do that does not constitute being a jerk? That was my attempt to answer.

Michael Vassar has tried to convince me that I should be more worried about a majority of humanity being "selfish bastards" as defined in CEV. I have a couple of thoughts on this problem, may post on them later.

"Being a jerk" here means "being a jerk according to other people's notion of morality, but not according to my own notion of morality", right?

I sort of take offense to "we're the ancient Greeks"; I make sure to disagree with Western morality whenever it's wrong, and I have no reason to believe the resulting distribution of errors is biased toward agreement with Western morality. If you meant to say "most of them are the ancient Greeks", then sure.

On second thought I suppose it could mean "being a jerk according to 'ethics'", where "ethics" is conceived not as something intrinsically moral but as a practical way for agents with different moralities to coordinate on a mutually acceptable solution.

The notion is that I am my current self, but one day you inform me that, relative to other humans, my ability to care about others is damaged. Do I want a pill to fix the damage, even though it will change my values? Yes, because I value humanity and want to stay with humanity; I don't want to be off in some lonely unoccupied volume of mindspace. This is one of the arguments that moves me.

Eliezer, relative to other humans, your ability to believe in a personal creative deity is damaged.

Do you want a pill to help you be religious?

Virge: The argument for psychological unity is that, as a sexually reproducing species, it is almost impossible for one gene to rise in relative frequency if the genes it depends on are not already nearly universal. So the all the diversity within any species at any given time consists of only one-step changes; no complex adaptations. The one exception of course is that males can have complex adaptations that females lack, and vice versa.

So, with respect to your specific examples:

Homosexuals: sexual preference certainly is a complex adaptation, but obviously one that differs between males and females. Homosexuals just got the wrong sexual preference for their equipment. And it doesn't do any good to say that they aren't defective. They aren't defective from a human, moral point of view, but that's not the point. From evolutions view, there's hardly anything more defective, except perhaps a fox that voluntarily restrains it's own breeding.

Stanford Prison Experiment, Psychopaths: I'm not sure if I see where the complex adaptation is here. Some people have more empathy, some less. Even if the difference is supposed to be genetic, there seem to be a lot of these flexible parameters in our genome. Empathy-level could be like skin-color, height, hairiness, etc. We all have the machinery to compute empathy (we all have the same complex adaptation), but it's used more often, or carries more influence in some people and less in others. Those that totally lack empathy are like albinos. They have the genes that are supposed to code for empathy, but they're broken.

Of course you are right that empirical data on this question is needed. But absent that, we have what looks like a strong theoretical argument for psycological unity.

Eli: "I do not assert that all humans end up in the same moral frame of reference (with regard to any particular extrapolation method). I do think that psychological unity is typically underestimated,"

- right, thanks for the clarification.

"But if you read "Coherent Extrapolated Volition" you'll see that it's specifically designed to handle, among other problems, the problem of, "What if we don't all want the same thing?" What then can an AI programmer do that does not constitute being a jerk? That was my attempt to answer."

- this is where I think I disagree with you somewhat. Your notion of what constitutes a "jerk" thing to do differs from my notion of what constitutes a jerk thing to do. I would not extrapolate the volitions of people whose volitions I deem to be particularly dangerous, in fact I would probably only extrapolate the volition of a small subset (perhaps 1 thousand - 1 million) people whose outward philosophical stances on life were at least fairly similar to mine. I would consider it a jerk-like thing to extrapolate, with equal weight, the volitions of every human on the planet, including all the religious fundamentalists, etc. In any case, the problem for you is that if you and I disagree on exactly whose volitions should be taken into account in the CEV algorithm, how exactly do we settle our dispute? You can't appeal to the psychological unity of humankind, for I am human and I disagree with you. You're an antirealist, so there's no objective fact of the matter either.

Or are you a closet realist? Is there some objective notion of "non-jerkness" that transcends the views of any particular human?

As a realist, I don't have this problem. I think I have found objective criteria upon which to judge the question.

Roko: I think Eliezer has explicitly stated that he is a realist.

Larry D'Anna: "And it doesn't do any good to say that they aren't defective. They aren't defective from a human, moral point of view, but that's not the point. From evolutions view, there's hardly anything more defective, except perhaps a fox that voluntarily restrains it's own breeding."

Why is it "not the point"? In this discussion we are talking about differences in moral computation as implemented within individual humans. That the blind idiot's global optimization strategy defines homosexuality as a defect is of no relevance.

Larry D'Anna: "I'm not sure if I see where the complex adaptation is here. Some people have more empathy, some less. Even if the difference is supposed to be genetic, there seem to be a lot of these flexible parameters in our genome."

I wasn't claiming a complex adaptation. I was claiming "other computations that could exhibit a superficial unity, but with a broad spread."

I think we are already in substantial agreement, and having seen Eliezer's last comment, I see that much of what I've been rambling on about comes from reading more than was warranted into the last paragraphs of his blog entry.

Roko:

I would not extrapolate the volitions of people whose volitions I deem to be particularly dangerous, in fact I would probably only extrapolate the volition of a small subset (perhaps 1 thousand - 1 million) people whose outward philosophical stances on life were at least fairly similar to mine.

Then you are far too confident in your own wisdom. The overall FAI strategy has to be one that would have turned out okay if Archimedes of Syracuse had been able to build an FAI, because when you zoom out to the billion-year view, we may not be all that much wiser than they.

I'm sure that Archimedes of Syracuse thought that Syracuse had lots of incredibly important philosophical and cultural differences with the Romans who were attacking his city.

Had it fallen to Archimedes to build an AI, he might well have been tempted to believe that the whole fate of humanity would depend on whether the extrapolated volition of Syracuse or of Rome came to rule the world - due to all those incredibly important philosophical differences.

Without looking in Wikipedia, can you remember what any of those philosophical differences were?

And you are separated from Archimedes by nothing more than a handful of centuries.

Just to check, surely you're not saying an extrapolated version of Archimedes and a thousand people who agreed with him wouldn't have turned out OK?

It seems to me that we have some quite strong evidence against rotten bastards theory in that intelligent and well-informed people IRL seem to converge away from bastardly beliefs. Still, rotten bastards theory seems worth thinking about for negative-utilitarian reasons.

The basic ev-bio necessity behind the psychological unity of human brains is not widely understood.

"Necessity" may be over-stating it. Humans are not very diverse, due to recent genetic bottlenecks. We do have enormous psychological differences between us - due to neotony-induced developmental plasticity - and because there are many ways to break a human. We haven't yet lived in the human hive long enough for the developmental plasticity to result in clearly-discrete queen/worker/warrior castes, with associated mental adaptations, though.

Go back in time, and often proto-humanity was divided into multiple tribes: the neanderthals, the cro-magnons, etc - with consequently reduced psychological unity. Travel and the modern gene pool expansion and stirring has obliterated the competeting tribes.

Had it fallen to Archimedes to build an AI, he might well have been tempted to believe that the whole fate of humanity would depend on whether the extrapolated volition of Syracuse or of Rome came to rule the world

I doubt there would have been much controversy. The fate of humanity is bound to be obliteration by far more advanced technology. The idea that our crappy evolved slug bodies, with their sluggish meat brains might go the distance would have seemed pretty ridiculous, even back then.

@Eliezer: "I'm sure that Archimedes of Syracuse thought that Syracuse had lots of incredibly important philosophical and cultural differences with the Romans who were attacking his city. Had it fallen to Archimedes to build an AI, he might well have been tempted to believe that the whole fate of humanity would depend on whether the extrapolated volition of Syracuse or of Rome came to rule the world - due to all those incredibly important philosophical differences."

- I don't see how adding the romans to the CEV algorithm would have made much of a difference either way. If Archimedes had chosen himself and a few thousand people who he deemed to be "wise", I suspect things would have gone somewhat better than if he had decided, on grounds of "non-jerkness", to extrapolate the volition of the whole of humanity at that time, including all the barbarians, hunter gatherers, cannibal pygmies, etc.

Why can we expect this to generalize? Well, people who design AIs self-select for intelligence. People who design AIs with friendliness in mind self-select for intelligence, caution etc.

Virge: Why is it "not the point"? In this discussion we are talking about differences in moral computation as implemented within individual humans. That the blind idiot's global optimization strategy defines homosexuality as a defect is of no relevance.

well because we're trying to characterize the sort of psychological diversity that can exist within our species. And this psychological unity argument is saying "we're all the same, except for a mix of one-step changes". This means that any complex adaptation in any human is in almost all humans. The exceptions being: sexual dimorphism, and the fact that certain individuals are "defective", in the sense that one of their complex adaptations is broken. So if you're arguing against this position and saying: look at homosexuals, they are different but not broken, then you aren't talking about the same kind of "broken". I'm not arguing that we should make base any moral judgment on evolution's silly ideas of what's broken. I'm just arguing that homosexuals don't serve as a counterexample to the idea of psychological unity.

Virge: I wasn't claiming a complex adaptation. I was claiming "other computations that could exhibit a superficial unity, but with a broad spread."

I think you're right here. But hopefully the spread is not so much that we could not come to agree if we "knew more, thought faster, were more the people we wished we were, and had grown up farther together."

An example that gives me hope that this could be true is Vengeance. We seem to be born with a terminal value saying that it is good to see our enemies suffer. In terms of explicit moral argument, if not in deeds, we have mostly come to agree that it is wrong to take vengeance; even though some of us came from cultures that once reveled in it; even though some of us may be more naturally inclined towards it.

When you do Bayesian updates, the specific values of your initial priors become less important as you gather more evidence. The evidence piles up exponentially, and you need exponentially bad priors to keep the wrong answer in the face of it. Perhaps our moral debates are similar. Perhaps the "broad spread" is not so great that we cannot come to agree, if we consider enough evidence, if we hear enough arguments. Psychological unity does not prove that this is so, but without psychological unity, there would be no reason to hope it is possible.

Many people seem to have set their priors to 1 on several facts. I suspect even MiniLuv would have a hard time getting these guys to believe that Christianity is false.

In other words:

Bob: "Abortion is wrong."

Sally: "Do you think that this is something of which most humans ought to be persuadable?"

Bob: "Yes, I do. Do you think abortion is right?"

Sally: "Yes, I do. And I don't think that's because I'm a psychopath by common human standards. I think most humans would come to agree with me, if they knew the facts I knew, and heard the same moral arguments I've heard."

Bob and Sally are wrong. Well, half-wrong, anyway. A human's beliefs depend on the order in which he hears arguments. If I info-dumped all my experiences into the Pope's mind, and vice-versa, he'd still be a Christian and I'd still be an atheist.

I do not think that rational arguments and evidence are sufficient to convince people to change a sufficiently stubborn belief.

Eliezer, you've used your AI-box experiment as an example that people can be persuaded. If you had the Pope in a holodeck that you completely controlled, do you think you could convince him that Jesus was never resurrected? I really doubt it.

Doug raises another good point. Related to what I said earlier, I think people really do functionally have prior probability=1 on some propositions. Or act as if they do. If "The Bible is the inerrant word of God" is a core part of your worldview, it is literally impossible for me to convince you this is false, because you use this belief to interpret any facts I present to you. Eliezer has commented before that you can rationalize just about anything; if "God exists" or "The Flying Spaghetti Monster exists" or "reincarnation exists" is part of the machinery you use to interpret your experience, in a deep enough way, your experiences can't disprove it.

If you had the Pope in a holodeck that you completely controlled, do you think you could convince him that Jesus was never resurrected?

Oh hell yeah. Then again, I'd also go for it if you offered me 24 hours. Then again, the Pope almost certainly already believes that Jesus was never resurrected "except in our hearts" or some such, which makes the job much harder.

If the Pope knows that he's in a holodeck, and that you are controlling it, would that change your answer?

The argument for psychological unity is that, as a sexually reproducing species, it is almost impossible for one gene to rise in relative frequency if the genes it depends on are not already nearly universal. So the all the diversity within any species at any given time consists of only one-step changes; no complex adaptations. The one exception of course is that males can have complex adaptations that females lack, and vice versa.

That argument is not right - as fig wasps demonstrate. Organisms can exhibit developmental plasticity, and show different traits under different circumstances. Humans are a good example of this: we show remarkable developmental plasticity due to neoteny. E.g. the phenotypes of the jockey and the sumo wrestler are remarkably different. The jockey is continuously on calorie restriction - and so exhibits a radically different gene expression profile in almost every tissue.

Doug S: "A human's beliefs depend on the order in which he hears arguments."

- indeed. Anyone who has spent any time arguing with Christians should know this. And the effect is auto-catalytic - our beliefs about both facts and values tend to self-reinforce; c.f. "affective death spirals".

As I have claimed earlier in the comments, many issues in the modern world are not issues that our in-built evolutionary urges or "yuck factors" can advise us on directly. So human beliefs on issues such as which politics is best, whether to be a bioluddite or a technoprogressive, whether and which religion to believe in, whether men and women should be given equal rights, etc, etc are decided by our developmental plasticity as Tim Tyler has described above.

The state of human belief and value is a mess, mostly based on irrationalities and self-sustaining cognitive biases which Eliezer has painstakingly pointed out on this blog. Hardly what I would call "psychological unity". Yes, there is some unity: everyone favors their friends and family over strangers. Everyone has the same sexuality(ies). Everyone prefers pleasure over pain. But on important non-EEA questions, there is widespread and deep disagreement.

The CEV algorithm, as I currently understand it, would attempt to rectify this by taking the beliefs of every human, with equal weight, and editing incorrect factual beliefs. I am not convinced that I would like the output of such an algorithm.

Eliezer: The overall FAI strategy has to be one that would have turned out okay if Archimedes of Syracuse had been able to build an FAI.

I'd feel a lot safer if you'd extend this back at least to the infanticidal hunter-gatherers, and preferably to apes fighting around the 2001 monolith.

Recovering, if I write CEV then it ought to work on hunter-gatherers, but the hunter-gatherers could not plausible have understood the concepts involved in CEV (whereas I might be willing to try to explain it to Archimedes, if not any other Syracusans). So "think of a strategy such that it would work for hunter-gatherers" fails here; I can't visualize that counterfactual unless the hunter-gatherers have the concept of math.

The apes fighting around the monolith are outside my moral reference frame and a CEV focused on them would produce different results.

Roko, it doesn't just edit incorrect factual beliefs, there's also the "what if we thought faster, were smarter, were more like the people we wished we were", etc.

Steven: "what if we thought faster, were smarter, were more like the people we wished we were"

- yes, I'm aware of this, but the first two act in essentially the same way - they cause simulees to more quickly come to factually correct beliefs, and the last is just a "consistent under reflection" condition.

These conditions make little difference to my concern: the algorithm will end up mixing my values (which I like) with values I hate (religious dogma, sharia law, Christian fundamentalism, the naturalistic fallacy/bioluddism ... ), where my beliefs recieve a very small weighting, and those that I dislike receive a very large weighting.

If you think an IQ-200 extreme-polymath pope who pondered all current and future arguments for atheism would still remain a Christian, then maybe.

Steven: If you think an IQ-200 extreme-polymath pope who pondered all current and future arguments for atheism would still remain a Christian, then maybe.

Unfortunately, I know from personal experience that there are people who are more intelligent than I am who have been "hooked" by religious memes. I know of several Cambridge mathematicians who are currently at PhD level, one of them in mathematical logic, who are members of this evangelical Christian organization. One in particular is extremely bright: triple first, British mathematics Olympiad, can grasp abstract mathematical concepts twice as fast as I can. When you question these kinds of people, you don't get anywhere, I've tried it. They just keep coming up with ever more bizzare (but not quite logically contradictory) positions, up to and including abandonment of Occam's razor, re-defining words in the ethical vocabulary, doubting the entire scientific method, etc. I'm sure many people here have had similar experiences. What is to say that the CEV of (all of) humanity won't go like this?

If there are smart Christians out there, then where are their works?

The nearest I thing I ever saw was probably Philip Johnson - and he's not that smart.

Time - Philip Johnson is not just a Christian but a creationist. Do you mean, "if there are smart creationists out there..."? I don't really pay much attention to the religious beliefs of the smartest mathematicians and scientists and I'm not especially keen on looking into it now, but I would be surprised if all top scientists without exception were atheists. This page seems to suggest that many of the best scientists are something other than atheist, many of those Christian.

PhD in mathematical logic != extreme polymath. I guess Dyson and Tipler come closest to refuting my position, but I wouldn't expect their beliefs to remain constant under a few thousand years of pondering the overcoming bias archives, say.

You can bring a brain to data, but you can't make it think.

Things like an IQ of 200 indicate that a person has certain cognitive strengths. They DO NOT indicate that those strengths will be utilized. Someone who is not concerned about being dishonest with themselves can self-convince of whatever they please.

At this point, there are no rational grounds for a person to accept the truth claims of, say, the various Christian doctrinal groups. A person who accepts them regardless has already decided to suspend rationality - unless a desire for honesty greater than their desire to continue to believe can be induced in them, they will never be reasoned out of their convinctions. Such induction is impossible in most people and is highly problematic in the remaining few.

Having the capacity to do a thing isn't enough - you need also the motivation to do it. Lacking that motivation, potential becomes irrelevant.

What I mean is, if there are smart Christians out there, why can't they put together a coherent argument favouring Christianity?

I mean, is this really the best they can do?

@Tim Tyler

"a coherent argument favouring Christianity"

Catholic people believe that they have such a thing, resting on strong philosophical definitions of ontology and truth. Traditionally I think that if one was truly interested in hearing a coherent argument for Christian belief, the Jesuit order specialized in teaching and expounding the philosophy. Short a long session with a Jesuit, you might consult the Catholic Encyclopedia for Christian arguments.

While perhaps you will ultimately agree that their system is coherent, that is, "marked by an orderly, logical, and aesthetically consistent relation of parts," I doubt you will cotton to their first principles.

I do agree with Collins in your Time link on one point and one point alone: sincere discussion is probably the best way for honest minds. Otherwise, he's not my demitasse of anything.

Caledonian and Tim Tyler: there are lots of coherent defenses of Christianity. It's just that many of them rest on statements like, "if Occam's Razor comes into conflict with Revealed Truth, we must privilege the latter over the former." This isn't incoherent; it's just wrong. At least from our perspective. Which is the point I've been trying to make. They'd say the same thing about us.

Roko: I sent you an email.

Well, it is not logically necessary that we have a genuine disagreement. We might be mistaken in believing ourselves to mean the same thing by the words right and wrong, since neither of us can introspectively report our own moral reference frames or unfold them fully."

I think the idea of associating the meaning of a word with a detailed theory of fine-grained set of criteria, allowing you to apply the term in all cases, has disadvantages.

Newtonian theory has a different set of fine grained criteria about gravity than relativistic theory. If we take those criteria as define the meaning of gravity, then they must be talking about different things. If we take that as the end of the story, then there is no way we can make sense of their being contrasting theories, or of one theory superseding another. The one is a theory of Newton-gravity, the other of Einstein-gravity. If we take them as both being theories of some more vaguely and coarsely defined notion gravity, we can explain their disagreement and differing success. And we don't have to give up on Einstein-gravity and Newton-gravity.

You cannot have a disagreement about which algorithm should direct your actions, without first having the same meaning of should - and no matter how you try to phrase this in terms of "what ought to direct your actions" or "right actions" or "correct heaps of pebbles", in the end you will be left with the empirical fact that it is possible to construct minds directed by any coherent utility function.

I don't see the point of this comment. No-one holds that the constraint that makes some sets of values genuinely moral is the same as the constrain that makes them implementable.

When a paperclip maximizer and a pencil maximizer do different things, they are not disagreeing about anything, they are just different optimization processes.

That are both in the superclass of optimisation processes. Why should they not both be in the class of genuinely moral optimisation processes?

You cannot detach should-ness from any specific criterion of should-ness and be left with a pure empty should-ness that the paperclip maximizer and pencil maximizer can be said to disagree about - unless you cover "disagreement" to include differences where two agents have nothing to say to each other.

Meta ethics can supply a meaning of should/ought without specifying anything specific. For instance, if you ought to maximise happiness, that doesn't specify any action without further information about what leads to happiness.