Less Wrong is a community blog devoted to refining the art of human rationality. Please visit our About page for more information.
A few months ago, my friend said the following thing to me: “After seeing Divergent, I finally understand virtue ethics. The main character is a cross between Aristotle and you.”
That was an impossible-to-resist pitch, and I saw the movie. The thing that resonated most with me–also the thing that my friend thought I had in common with the main character–was the idea that you could make a particular decision, and set yourself down a particular course of action, in order to make yourself become a particular kind of person. Tris didn’t join the Dauntless cast because she thought they were doing the most good in society, or because she thought her comparative advantage to do good lay there–she chose it because they were brave, and she wasn’t, yet, and she wanted to be. Bravery was a virtue that she thought she ought to have. If the graph of her motivations even went any deeper, the only node beyond ‘become brave’ was ‘become good.’
(Tris did have a concept of some future world-outcomes being better than others, and wanting to have an effect on the world. But that wasn't the causal reason why she chose Dauntless; as far as I can tell, it was unrelated.)
My twelve-year-old self had a similar attitude. I read a lot of fiction, and stories had heroes, and I wanted to be like them–and that meant acquiring the right skills and the right traits. I knew I was terrible at reacting under pressure–that in the case of an earthquake or other natural disaster, I would freeze up and not be useful at all. Being good at reacting under pressure was an important trait for a hero to have. I could be sad that I didn’t have it, or I could decide to acquire it by doing the things that scared me over and over and over again. So that someday, when the world tried to throw bad things at my friends and family, I’d be ready.
You could call that an awfully passive way to look at things. It reveals a deep-seated belief that I’m not in control, that the world is big and complicated and beyond my ability to understand and predict, much less steer–that I am not the locus of control. But this way of thinking is an algorithm. It will almost always spit out an answer, when otherwise I might get stuck in the complexity and unpredictability of trying to make a particular outcome happen.
I find the different houses of the HPMOR universe to be a very compelling metaphor. It’s not because they suggest actions to take; instead, they suggest virtues to focus on, so that when a particular situation comes up, you can act ‘in character.’ Courage and bravery for Gryffindor, for example. It also suggests the idea that different people can focus on different virtues–diversity is a useful thing to have in the world. (I'm probably mangling the concept of virtue ethics here, not having any background in philosophy, but it's the closest term for the thing I mean.)
I’ve thought a lot about the virtue of loyalty. In the past, loyalty has kept me with jobs and friends that, from an objective perspective, might not seem like the optimal things to spend my time on. But the costs of quitting and finding a new job, or cutting off friendships, wouldn’t just have been about direct consequences in the world, like needing to spend a bunch of time handing out resumes or having an unpleasant conversation. There would also be a shift within myself, a weakening in the drive towards loyalty. It wasn’t that I thought everyone ought to be extremely loyal–it’s a virtue with obvious downsides and failure modes. But it was a virtue that I wanted, partly because it seemed undervalued.
By calling myself a ‘loyal person’, I can aim myself in a particular direction without having to understand all the subcomponents of the world. More importantly, I can make decisions even when I’m rushed, or tired, or under cognitive strain that makes it hard to calculate through all of the consequences of a particular action.
The Less Wrong/CFAR/rationalist community puts a lot of emphasis on a different way of trying to be a hero–where you start from a terminal goal, like “saving the world”, and break it into subgoals, and do whatever it takes to accomplish it. In the past I’ve thought of myself as being mostly consequentialist, in terms of morality, and this is a very consequentialist way to think about being a good person. And it doesn't feel like it would work.
There are some bad reasons why it might feel wrong–i.e. that it feels arrogant to think you can accomplish something that big–but I think the main reason is that it feels fake. There is strong social pressure in the CFAR/Less Wrong community to claim that you have terminal goals, that you’re working towards something big. My System 2 understands terminal goals and consequentialism, as a thing that other people do–I could talk about my terminal goals, and get the points, and fit in, but I’d be lying about my thoughts. My model of my mind would be incorrect, and that would have consequences on, for example, whether my plans actually worked.
Practicing the art of rationality
Recently, Anna Salamon brought up a question with the other CFAR staff: “What is the thing that’s wrong with your own practice of the art of rationality?” The terminal goals thing was what I thought of immediately–namely, the conversations I've had over the past two years, where other rationalists have asked me "so what are your terminal goals/values?" and I've stammered something and then gone to hide in a corner and try to come up with some.
In Alicorn’s Luminosity, Bella says about her thoughts that “they were liable to morph into versions of themselves that were more idealized, more consistent - and not what they were originally, and therefore false. Or they'd be forgotten altogether, which was even worse (those thoughts were mine, and I wanted them).”
I want to know true things about myself. I also want to impress my friends by having the traits that they think are cool, but not at the price of faking it–my brain screams that pretending to be something other than what you are isn’t virtuous. When my immediate response to someone asking me about my terminal goals is “but brains don’t work that way!” it may not be a true statement about all brains, but it’s a true statement about my brain. My motivational system is wired in a certain way. I could think it was broken; I could let my friends convince me that I needed to change, and try to shoehorn my brain into a different shape; or I could accept that it works, that I get things done and people find me useful to have around and this is how I am. For now. I'm not going to rule out future attempts to hack my brain, because Growth Mindset, and maybe some other reasons will convince me that it's important enough, but if I do it, it'll be on my terms. Other people are welcome to have their terminal goals and existential struggles. I’m okay the way I am–I have an algorithm to follow.
Why write this post?
It would be an awfully surprising coincidence if mine was the only brain that worked this way. I’m not a special snowflake. And other people who interact with the Less Wrong community might not deal with it the way I do. They might try to twist their brains into the ‘right’ shape, and break their motivational system. Or they might decide that rationality is stupid and walk away.
When someone complains that utilitarianism1 leads to the dust speck paradox or the trolley-car problem, I tell them that's a feature, not a bug. I'm not ready to say that respecting the utility monster is also a feature of utilitarianism, but it is what most people everywhere have always done. A model that doesn't allow for utility monsters can't model human behavior, and certainly shouldn't provoke indignant responses from philosophers who keep right on respecting their own utility monsters.
There have been some posts about animals lately, for instance here and here. While normative assumptions about the treatment of nonhumans played an important role in the articles and were debated at length in the comment sections, I was missing a concise summary of these arguments. This post from over a year ago comes closest to what I have in mind, but I want to focus on some of the issues in more detail.
A while back, I read the following comment in a LessWrong discussion on uploads:
I do not at all understand this PETA-like obsession with ethical treatment of bits.
Aside from (carbon-based) humans, which other beings deserve moral consideration? Nonhuman animals? Intelligent aliens? Uploads? Nothing else?
This article is intended to shed light on these questions; it is however not the intent of this post to advocate a specific ethical framework. Instead, I'll try to show that some ethical principles held by a lot of people are inconsistent with some of their other attitudes -- an argument that doesn't rely on ethics being universal or objective.
More precisely, I will develop the arguments behind anti-speciesism (and the rejection of analogous forms of discrimination, such as discrimination against uploads) to point out common inconsistencies in some people's values. This will also provide an illustrative example of how coherentist ethical reasoning can be applied to shared intuitions. If there are no shared intuitions, ethical discourse will likely be unfruitful, so it is likely that not everyone will draw the same conclusions from the arguments here.
What Is Speciesism?
Speciesism, a term popularized (but not coined) by the philosopher Peter Singer, is meant to be analogous to sexism or racism. It refers to a discriminatory attitude against a being where less ethical consideration i.e. caring less about a being's welfare or interests is given solely because of the "wrong" species membership. The "solely" here is crucial, and it's misunderstood often enough to warrant the redundant emphasis.
For instance, it is not speciesist to deny pigs the right to vote, just like it is not sexist to deny men the right to have an abortion performed on their body. Treating beings of different species differently is not speciesist if there are relevant criteria for doing so.
Singer summarized his case against speciesism in this essay. The argument that does most of the work is often referred to as the argument from marginal cases. A perhaps less anthropocentric, more fitting name would be argument from species overlap, as some philosophers (e.g. Oscar Horta) have pointed out.
The argument boils down to the question of choosing relevant criteria for moral concern. What properties do human beings possess that makes us think that it is wrong to torture them? Or to kill them? (Note that these are two different questions.) The argument from species overlap points out that all the typical or plausible suggestions for relevant criteria apply equally to dogs, pigs or chickens as they do to human infants or late-stage Alzheimer patients. Therefore, giving less ethical consideration to the former would be based merely on species membership, which is just as arbitrary as choosing race or sex as relevant criterion (further justification for that claim follows below).
Here are some examples for commonly suggested criteria. Those who want may pause at this point and think about the criteria they consult for whether it is wrong to inflict suffering on a being (and separately, those that are relevant for the wrongness of killing).
The suggestions are:
A: Capacity for moral reasoning
B: Being able to reciprocate
C: (Human-like) intelligence
E: Future-related preferences; future plans
E': Preferences / interests (in general)
F: Sentience (capacity for suffering and happiness)
G: Life / biological complexity
H: What I care about / feel sympathy or loyalty towards
The argument from species overlap points out that not all humans are equal. The sentiment behind "all humans are equal" is not that they are literally equal, but that equal interests/capacities deserve equal consideration. None of the above criteria except (in some empirical cases) H imply that human infants or late stage demented people should be given more ethical consideration than cows, pigs or chickens.
While H is an unlikely criterion for direct ethical consideration (it could justify genocide in specific circumstances!), it is an important indirect factor. Most humans have much more empathy for fellow humans than for nonhuman animals. While this is not a criterion for giving humans more ethical consideration per se, it is nevertheless a factor that strongly influences ethical decision-making in real-life.
However, such factors can't apply for ethical reasoning at a theoretical/normative level, where all the relevant variables are looked at in isolation in order to come up with a consistent ethical framework that covers all possible cases.
If there were no intrinsic reasons for giving moral consideration to babies, then a society in which some babies were (factory-)farmed would be totally fine as long as the people are okay with it. If we consider this implication to be unacceptable, then the same must apply for the situations nonhuman animals find themselves in on farms.
Side note: The question whether killing a given being is wrong, and if so, "why" and "how wrong exactly", is complex and outside the scope of this article. Instead of on killing, the focus will be on suffering, and by suffering I mean something like wanting to get out of one's current conscious state, or wanting to change some aspect about it. The empirical issue of which beings are capable of suffering is a different matter that I will (only briefly) discuss below. So in this context, giving a being moral consideration means that we don't want it to suffer, leaving open the question whether killing it painlessly is bad/neutral/good or prohibited/permissible/obligatory.
The main conclusion so far is that if we care about all the suffering of members of the human species, and if we reject question-begging reasoning that could also be used to justify racism or other forms of discrimination, then we must also care fully about suffering happening in nonhuman animals. This would imply that x amount of suffering is just as bad, i.e. that we care about it just as much, in nonhuman animals as in humans, or in aliens or in uploads. (Though admittedly the latter wouldn't be anti-speciesist but rather anti-"substratist", or anti-"fleshist".)
The claim is that there is no way to block this conclusion without:
1. using reasoning that could analogically be used to justify racism or sexism
2. using reasoning that allows for hypothetical circumstances where it would be okay (or even called for) to torture babies in cases where utilitarian calculations prohibit it.
I've tried and have asked others to try -- without success.
Caring about suffering
I have not given a reason why torturing babies or racism is bad or wrong. I'm hoping that the vast majority of people will share that intuition/value of mine, that they want to be the sort of person who would have been amongst those challenging racist or sexist prejudices, had they lived in the past.
Some might be willing to bite the bullet at this point, trusting some strongly held ethical principle of theirs (e.g. A, B, C, D, or E above), to the conclusion of excluding humans who lack certain cognitive capacities from moral concern. One could point out that people's empathy and indirect considerations about human rights, societal stability and so on, will ensure that this "loophole" in such an ethical view almost certainly remains without consequences for beings with human DNA. It is a convenient Schelling point after all to care about all humans (or at least all humans outside their mother's womb). However, I don't see why absurd conclusions that will likely remain hypothetical would be significantly less bad than other absurd conclusions. Their mere possibility undermines the whole foundation one's decisional algorithm is grounded in. (Compare hypothetical problems for specific decision theories.)
Furthermore, while D and E seem plausible candidates for reasons against killing a being with these properties (E is in fact Peter Singer's view on the matter), none of the criteria from A to E seem relevant to suffering, to whether a being can be harmed or benefitted. The case for these being bottom-up morally relevant criteria for the relevance of suffering (or happiness) is very weak, to say the least.
Maybe that's the speciesist's central confusion, that the rationality/sapience of a being is somehow relevant for whether its suffering matters morally. Clearly, for us ourselves, this does not seem to be the case. If I was told that some evil scientist would first operate on my brain to (temporarily) lower my IQ and cognitive abilities, and then torture me afterwards, it is not like I will be less afraid of the torture or care less about averting it!
Those who do consider biting the bullet should ask themselves whether they would have defended that view in all contexts, or whether they might be driven towards such a conclusion by a self-serving bias. There seems to be a strange and sudden increase in the frequency of people who are willing to claim that there is nothing intrinsically wrong with torturing babies when the subject is animal rights, or more specifically, the steak they intend to have for dinner.
It is an entirely different matter if people genuinely think that animals or human infants or late-stage demented people are not sentient. To be clear about what is meant by sentience:
A sentient being is one for whom "it feels like something to be that being".
I find it highly implausible that only self-aware or "sapient" beings are sentient, but if true, this would constitute a compelling reason against caring for at least most nonhuman animals, for the same reason that it would pointless to care about pebbles for the pebbles' sake. If all nonhumans truly weren't sentient, then obviously singling out humans for the sphere of moral concern would not be speciesist.
What irritates me, however, is that anyone advocating such a view should, it seems to me, still have to factor in a significant probability of being wrong, given that both philosophy of mind and the neuroscience that goes with it are hard and, as far as I'm aware, not quite settled yet. The issue matters because of the huge numbers of nonhuman animals at stake and because of the terrible conditions these beings live in.
I rarely see this uncertainty acknowledged. If we imagine the torture-scenario outlined above, how confident would we really be that the torture "won't matter" if our own advanced cognitive capacities are temporarily suspended?
Why species membership really is an absurd criterion
In the beginning of the article, I wrote that I'd get back to this for those not convinced. Some readers may still feel that there is something special about being a member of the human species. Some may be tempted to think about the concept of "species" as if it were a fundamental concept, a Platonic form.
The following likely isn't news to most of the LW audience, but it is worth spelling it out anyway: There exists a continuum of "species" in thing-space as well as in the actual evolutionary timescale. The species boundaries seem obvious just because the intermediates kept evolving or went extinct. And even if that were not the case, we could imagine it. The theoretical possibility is enough to make the philosophical case, even though psychologically, actualities are more convincing.
We can imagine a continuous line-up of ancestors, always daughter and mother, from modern humans back to the common ancestor of humans and, say, cows, and then forward in time again to modern cows. How would we then divide this line up into distinct species? Morally significant lines would have to be drawn between mother and daughter, but that seems absurd! There are several different definitions of "species" used in biology. A common criterion -- for sexually reproducing organisms anyway -- is whether groups of beings (of different sex) can have fertile offspring together. If so, they belong to the same species.
That is a rather odd way of determining whether one cares about the suffering of some hominid creature in the line-up of ancestors -- why should that for instance be relevant in regard to determining whether some instance of suffering matters to us?
Moreover, is that really the terminal value of people who claim they only care about humans, or could it be that they would, upon reflection, revoke such statements?
And what about transhumanism? I remember that a couple of years ago, I thought I had found a decisive argument against human enhancement. I thought it would likely lead to speciation, and somehow the thought of that directly implied that posthumans would treat the remaining humans badly, and so the whole thing became immoral in my mind. Obviously this is absurd; there is nothing wrong with speciation per se, and if posthumans will be anti-speciesist, then the remaining humans would have nothing to fear! But given the speciesism in today's society, it is all too understandable that people would be concerned about this. If we imagine the huge extent to which a posthuman, or not to mention a strong AI, would be superior compared to current humans, isn't that a bit like comparing chickens to us?
A last possible objection I can think of: Suppose one held the belief that group averages are what matters, and that all members of the human species deserve equal protection because of the group average for a criterion that is considered relevant and that would, without the group average rule, deny moral consideration to some sentient humans.
This defense too doesn't work. Aside from seeming suspiciously arbitrary, such a view would imply absurd conclusions. A thought experiment for illustration: A pig with a macro-mutation is born, she develops child-like intelligence and the ability to speak. Do we refuse to allow her to live unharmed -- or even let her go to school -- simply because she belongs to a group (defined presumably by snout shape, or DNA, or whatever the criteria for "pigness" are) with an average that is too low?
Or imagine you are the head of an architecture bureau and looking to hire a new aspiring architect. Is tossing out an application written by a brilliant woman going to increase the expected success of your firm, assuming that women are, on average, less skilled at spatial imagination than men? Surely not!
Moreover, taking group averages as our ethical criterion requires us to first define the relevant groups. Why even take species-groups instead of groups defined by skin color, weight or height? Why single out one property and not others?
Our speciesism is an anthropocentric bias without any reasonable foundation. It would be completely arbitrary to give special consideration to a being simply because of its species membership. Doing so would lead to a number of implications that most people clearly reject. A strong case can be made that suffering is bad in virtue of being suffering, regardless of where it happens. If the suffering or deaths of nonhuman animals deserve no ethical consideration, then human beings with the same relevant properties (of which all plausible ones seem to come down to having similar levels of awareness) deserve no intrinsic ethical consideration either, barring speciesism.
Assuming that we would feel uncomfortable giving justifications or criteria for our scope of ethical concern that can analogously be used to defend racism or sexism, those not willing to bite the bullet about torturing babies are forced by considerations of consistency to care about animal suffering just as much as they care about human suffering.
Such a view leaves room for probabilistic discounting in cases where we are empirically uncertain whether beings are capable of suffering, but we should be on the lookout for biases in our assessments.
Edit: As Carl Shulman has pointed out, discounting may also apply for "intensity of sentience", because it seems at least plausible that shrimps (for instance), if they are sentient, can experience less suffering than e.g. a whale.
For the first time in history, it has become possible for a limited group of a few thousand people to threaten the absolute destruction of millions.
-- Norbert Wiener (1956), Moral Reflections of a Mathematician.
Today, the general attitude towards scientific discovery is that scientists are not themselves responsible for how their work is used. For someone who is interested in science for its own sake, or even for someone who mostly considers research to be a way to pay the bills, this is a tempting attitude. It would be easy to only focus on one’s work, and leave it up to others to decide what to do with it.
But this is not necessarily the attitude that we should encourage. As technology becomes more powerful, it also becomes more dangerous. Throughout history, many scientists and inventors have recognized this, and taken different kinds of action to help ensure that their work will have beneficial consequences. Here are some of them.
This post is not arguing that any specific approach for taking responsibility for one's actions is the correct one. Some researchers hid their work, others refocused on other fields, still others began active campaigns to change the way their work was being used. It is up to the reader to decide which of these approaches were successful and worth emulating, and which ones were not.
… I do not publish nor divulge [methods of building submarines] by reason of the evil nature of men who would use them as means of destruction at the bottom of the sea, by sending ships to the bottom, and sinking them together with the men in them.
People did not always think that the benefits of freely disseminating knowledge outweighed the harms. O.T. Benfey, writing in a 1956 issue of the Bulletin of the Atomic Scientists, cites F.S. Taylor’s book on early alchemists:
Alchemy was certainly intended to be useful .... But [the alchemist] never proposes the public use of such things, the disclosing of his knowledge for the benefit of man. …. Any disclosure of the alchemical secret was felt to be profoundly wrong, and likely to bring immediate punishment from on high. The reason generally given for such secrecy was the probable abuse by wicked men of the power that the alchemical would give …. The alchemists, indeed, felt a strong moral responsibility that is not always acknowledged by the scientists of today.
With the Renaissance, science began to be viewed as public property, but many scientists remained cautious about the way in which their work might be used. Although he held the office of military engineer, Leonardo da Vinci (1452-1519) drew a distinction between offensive and defensive warfare, and emphasized the role of good defenses in protecting people’s liberty from tyrants. He described war as ‘bestialissima pazzia’ (most bestial madness), and wrote that ‘it is an infinitely atrocious thing to take away the life of a man’. One of the clearest examples of his reluctance to unleash dangerous inventions was his refusal to publish the details of his plans for submarines.
Later Renaissance thinkers continued to be concerned with the potential uses of their discoveries. John Napier (1550-1617), the inventor of logarithms, also experimented with a new form of artillery. Upon seeing its destructive power, he decided to keep its details a secret, and even spoke from his deathbed against the creation of new kinds of weapons.
But only concealing one discovery pales in comparison to the likes of Robert Boyle (1627-1691). A pioneer of physics and chemistry and possibly the most famous for describing and publishing Boyle’s law, he sought to make humanity better off, taking an interest in things such as improved agricultural methods as well as better medicine. In his studies, he also discovered knowledge and made inventions related to a variety of potentially harmful subjects, including poisons, invisible ink, counterfeit money, explosives, and kinetic weaponry. These ‘my love of Mankind has oblig’d me to conceal, even from my nearest Friends’.
Nick_Beckstead asked me to link to posts I referred to in this comment. I should put up or shut up, so here's an attempt to give an organized overview of them.
Since I wrote these, LukeProg has begun tackling some related issues. He has accomplished the seemingly-impossible task of writing many long, substantive posts none of which I recall disagreeing with. And I have, irrationally, not read most of his posts. So he may have dealt with more of these same issues.
I think that I only raised Holden's "objection 2" in comments, which I couldn't easily dig up; and in a critique of a book chapter, which I emailed to LukeProg and did not post to LessWrong. So I'm only going to talk about "Objection 1: It seems to me that any AGI that was set to maximize a "Friendly" utility function would be extraordinarily dangerous." I've arranged my previous posts and comments on this point into categories. (Much of what I've said on the topic has been in comments on LessWrong and Overcoming Bias, and in email lists including SL4, and isn't here.)
The concept of "human values" cannot be defined in the way that FAI presupposes
Human errors, human values: Suppose all humans shared an identical set of values, preferences, and biases. We cannot retain human values without retaining human errors, because there is no principled distinction between them.
A comment on this post: There are at least three distinct levels of human values: The values an evolutionary agent holds that maximize their reproductive fitness, the values a society holds that maximizes its fitness, and the values a rational optimizer holds who has chosen to maximize social utility. They often conflict. Which of them are the real human values?
Values vs. parameters: Eliezer has suggested using human values, but without time discounting (= changing the time-discounting parameter). CEV presupposes that we can abstract human values and apply them in a different situation that has different parameters. But the parameters are values. There is no distinction between parameters and values.
A comment on "Incremental progress and the valley": The "values" that our brains try to maximize in the short run are designed to maximize different values for our bodies in the long run. Which are human values: The motivations we feel, or the effects they have in the long term? LukeProg's post Do Humans Want Things? makes a related point.
Group selection update: The reason I harp on group selection, besides my outrage at the way it's been treated for the past 50 years, is that group selection implies that some human values evolved at the group level, not at the level of the individual. This means that increasing the rationality of individuals may enable people to act more effectively in their own interests, rather than in the group's interest, and thus diminish the degree to which humans embody human values. Identifying the values embodied in individual humans - supposing we could do so - would still not arrive at human values. Transferring human values to a post-human world, which might contain groups at many different levels of a hierarchy, would be problematic.
I wanted to write about my opinion that human values can't be divided into final values and instrumental values, the way discussion of FAI presumes they can. This is an idea that comes from mathematics, symbolic logic, and classical AI. A symbolic approach would probably make proving safety easier. But human brains don't work that way. You can and do change your values over time, because you don't really have terminal values.
Strictly speaking, it is impossible for an agent whose goals are all indexical goals describing states involving itself to have preferences about a situation in which it does not exist. Those of you who are operating under the assumption that we are maximizing a utility function with evolved terminal goals, should I think admit these terminal goals all involve either ourselves, or our genes. If they involve ourselves, then utility functions based on these goals cannot even be computed once we die. If they involve our genes, they they are goals that our bodies are pursuing, that we call errors, not goals, when we the conscious agent inside our bodies evaluate them. In either case, there is no logical reason for us to wish to maximize some utility function based on these after our own deaths. Any action I wish to take regarding the distant future necessarily presupposes that the entire SIAI approach to goals is wrong.
My view, under which it does make sense for me to say I have preferences about the distant future, is that my mind has learned "values" that are not symbols, but analog numbers distributed among neurons. As described in "Only humans can have human values", these values do not exist in a hierarchy with some at the bottom and some on the top, but in a recurrent network which does not have a top or a bottom, because the different parts of the network developed simultaneously. These values therefore can't be categorized into instrumental or terminal. They can include very abstract values that don't need to refer specifically to me, because other values elsewhere in the network do refer to me, and this will ensure that actions I finally execute incorporating those values are also influenced by my other values that do talk about me.
Even if human values existed, it would be pointless to preserve them
- The only preferences that can be unambiguously determined are the preferences a person (mind+body) implements, which are not always the preferences expressed by their beliefs.
- If you extract a set of consciously-believed propositions from an existing agent, then build a new agent to use those propositions in a different environment, with an "improved" logic, you can't claim that it has the same values, since it will behave differently.
- Values exist in a network of other values. A key ethical question is to what degree values are referential (meaning they can be tested against something outside that network); or non-referential (and hence relative).
- Supposing that values are referential helps only by telling you to ignore human values.
- You cannot resolve the problem by combining information from different behaviors, because the needed information is missing.
- Today's ethical disagreements are largely the result of attempting to extrapolate ancestral human values into a changing world.
- The future will thus be ethically contentious even if we accurately characterize and agree on present human values, because these values will fail to address the new important problems.
Human values differ as much as values can differ: There are two fundamentally different categories of values:
- Non-positional, mutually-satisfiable values (physical luxury, for instance)
- Positional, zero-sum social values, such as wanting to be the alpha male or the homecoming queen
All mutually-satisfiable values have more in common with each other than they do with any non-mutually-satisfiable values, because mutually-satisfiable values are compatible with social harmony and non-problematic utility maximization, while non- mutually-satisfiable values require eternal conflict. If you find an alien life form from a distant galaxy with non-positional values, it would be easier to integrate those values into a human culture with only human non-positional values, than to integrate already-existing positional human values into that culture.
It appears that some humans have mainly the one type, while other humans have mainly the other type. So talking about trying to preserve human values is pointless - the values held by different humans have already passed the most-important point of divergence.
Enforcing human values would be harmful
The human problem: This argues that the qualia and values we have now are only the beginning of those that could evolve in the universe, and that ensuring that we maximize human values - or any existing value set - from now on, will stop this process in its tracks, and prevent anything better from ever evolving. This is the most-important objection of all.
Re-reading this, I see that the critical paragraph is painfully obscure, as if written by Kant; but it summarizes the argument: "Once the initial symbol set has been chosen, the semantics must be set in stone for the judging function to be "safe" for preserving value; this means that any new symbols must be defined completely in terms of already-existing symbols. Because fine-grained sensory information has been lost, new developments in consciousness might not be detectable in the symbolic representation after the abstraction process. If they are detectable via statistical correlations between existing concepts, they will be difficult to reify parsimoniously as a composite of existing symbols. Not using a theory of phenomenology means that no effort is being made to look for such new developments, making their detection and reification even more unlikely. And an evaluation based on already-developed values and qualia means that even if they could be found, new ones would not improve the score. Competition for high scores on the existing function, plus lack of selection for components orthogonal to that function, will ensure that no such new developments last."
Averaging value systems is worse than choosing one: This describes a neural-network that encodes preferences, and takes some input pattern and computes a new pattern that optimizes these preferences. Such a system is taken as analogous for a value system and an ethical system to attain those values. I then define a measure for the internal conflict produced by a set of values, and show that a system built by averaging together the parameters from many different systems will have higher internal conflict than any of the systems that were averaged together to produce it. The point is that the CEV plan of "averaging together" human values will result in a set of values that is worse (more self-contradictory) than any of the value systems it was derived from.
A point I may not have made in these posts, but made in comments, is that the majority of humans today think that women should not have full rights, homosexuals should be killed or at least severely persecuted, and nerds should be given wedgies. These are not incompletely-extrapolated values that will change with more information; they are values. Opponents of gay marriage make it clear that they do not object to gay marriage based on a long-range utilitarian calculation; they directly value not allowing gays to marry. Many human values horrify most people on this list, so they shouldn't be trying to preserve them.
In poetic terms, our coherent extrapolated volition is our wish if we knew more, thought faster, were more the people we wished we were, had grown up farther together; where the extrapolation converges rather than diverges, where our wishes cohere rather than interfere; extrapolated as we wish that extrapolated, interpreted as we wish that interpreted.
— Eliezer Yudkowsky, May 2004, Coherent Extrapolated Volition
Foragers versus industry era folks
Consider the difference between a hunter-gatherer, who cares about his hunting success and to become the new tribal chief, and a modern computer scientist who wants to determine if a “sufficiently large randomized Conway board could turn out to converge to a barren ‘all off’ state.”
The utility of the success in hunting down animals and proving abstract conjectures about cellular automata is largely determined by factors such as your education, culture and environmental circumstances. The same forager who cared to kill a lot of animals, to get the best ladies in its clan, might have under different circumstances turned out to be a vegetarian mathematician solely caring about his understanding of the nature of reality. Both sets of values are to some extent mutually exclusive or at least disjoint. Yet both sets of values are what the person wants, given the circumstances. Change the circumstances dramatically and you change the persons values.
What do you really want?
You might conclude that what the hunter-gatherer really wants is to solve abstract mathematical problems, he just doesn’t know it. But there is no set of values that a person “really” wants. Humans are largely defined by the circumstances they reside in.
- If you already knew a movie, you wouldn’t watch it.
- To be able to get your meat from the supermarket changes the value of hunting.
If “we knew more, thought faster, were more the people we wished we were, and had grown up closer together” then we would stop to desire what we learnt, wish to think even faster, become even different people and get bored of and rise up from the people similar to us.
A singleton is an attractor
Much of our values and goals, what we want, are culturally induced or the result of our ignorance. Reduce our ignorance and you change our values. One trivial example is our intellectual curiosity. If we don’t need to figure out what we want on our own, our curiosity is impaired.
A singleton won’t extrapolate human volition but implement an artificial set values as a result of abstract high-order contemplations about rational conduct.
With knowledge comes responsibility, with wisdom comes sorrow
Knowledge changes and introduces terminal goals. The toolkit that is called ‘rationality’, the rules and heuristics developed to help us to achieve our terminal goals are also altering and deleting them. A stone age hunter-gatherer seems to possess very different values than we do. Learning about rationality and various ethical theories such as Utilitarianism would alter those values considerably.
Rationality was meant to help us achieve our goals, e.g. become a better hunter. Rationality was designed to tell us what we ought to do (instrumental goals) to achieve what we want to do (terminal goals). Yet what actually happens is that we are told, that we will learn, what we ought to want.
If an agent becomes more knowledgeable and smarter then this does not leave its goal-reward-system intact if it is not especially designed to be stable. An agent who originally wanted to become a better hunter and feed his tribe would end up wanting to eliminate poverty in Obscureistan. The question is, how much of this new “wanting” is the result of using rationality to achieve terminal goals and how much is a side-effect of using rationality, how much is left of the original values versus the values induced by a feedback loop between the toolkit and its user?
Take for example an agent that is facing the Prisoner’s dilemma. Such an agent might originally tend to cooperate and only after learning about game theory decide to defect and gain a greater payoff. Was it rational for the agent to learn about game theory, in the sense that it helped the agent to achieve its goal or in the sense that it deleted one of its goals in exchange for a allegedly more “valuable” goal?
Beware rationality as a purpose in and of itself
It seems to me that becoming more knowledgeable and smarter is gradually altering our utility functions. But what is it that we are approaching if the extrapolation of our volition becomes a purpose in and of itself? Extrapolating our coherent volition will distort or alter what we really value by installing a new cognitive toolkit designed to achieve an equilibrium between us and other agents with the same toolkit.
Would a singleton be a tool that we can use to get what we want or would the tool use us to do what it does, would we be modeled or would it create models, would we be extrapolating our volition or rather follow our extrapolations?
(This post is a write-up of a previous comment designated to receive feedback from a larger audience.)
Most people believe the way to lose weight is through willpower. My successful experience losing weight is that this is not the case. You will lose weight if you want to, meaning you effectively believe0 that the utility you will gain from losing weight, even time-discounted, will outweigh the utility from yummy food now. In LW terms, you will lose weight if your utility function tells you to. This is the basis of cognitive behavioral therapy (the effective kind of therapy), which tries to change peoples' behavior by examining their beliefs and changing their thinking habits.
Similarly, most people believe behaving ethically is a matter of willpower; and I believe this even less. Your ethics is part of your utility function. Acting morally is, technically, a choice; but not the difficult kind that holds up a stop sign and says "Choose wisely!" We notice difficult moral choices more than easy moral choices; but most moral choices are easy, like choosing a ten dollar bill over a five. Immorality is not a continual temptation we must resist; it's just a kind of stupidity.
This post can be summarized as:
- Each normal human has an instinctive personal morality.
- This morality consists of inputs into that human's decision-making system. There is no need to propose separate moral and selfish decision-making systems.
- Acknowledging that all decisions are made by a single decision-making system, and that the moral elements enter it in the same manner as other preferences, results in many changes to how we encourage social behavior.
Here is a simple method for resolving some arguments about free will. Not for resolving the question, mind you. Just the arguments.
One group of people doesn't want to give people any credit for anything they do. All good deeds are ultimately done for "selfish" reasons, where even having a goal of helping other people counts as selfish. The quote from Lukeprog's recent article is a perfect example:
No one deserves thanks from another about something he has done for him or goodness he has done. He is either willing to get a reward from God, therefore he wanted to serve himself. Or he wanted to get a reward from people, therefore he has done that to get profit for himself. Or to be mentioned and praised by people, therefore, it is also for himself. Or due to his mercy and tenderheartedness, so he has simply done that goodness to pacify these feelings and treat himself.
- Mohammed Ibn Al-Jahm Al-Barmaki
Another group of people doesn't want to blame people for anything they do. Criminals sometimes had criminal parents - crime was in their environment and in their genes. Or, to take a different variety of this attitude, cultural beliefs that seem horrible to us are always justifiable within their own cultural context.
The funny thing is that these are different groups. Both assert that people should not be given credit, or else blame, for their actions, beyond the degree of free will that they had. Yet you rarely find the same person who will not give people credit for their good deeds unwilling to blame them for their bad deeds, or vice-versa.
When you find yourself in an argument that appears to be about free will, but is really about credit or blame, ask the person to agree that the matter applies equally to good deeds and bad deeds - however they define those terms. This may make them lose interest in the argument - because it no longer does what they want it to do.
ETA: As stated below, criticizing beliefs is trivial in principle, either they were arrived at with an approximation to Bayes' rule starting with a reasonable prior and then updated with actual observations, or they weren't. Subsequent conversation made it clear that criticizing behavior is also trivial in principle, since someone is either taking the action that they believe will best suit their preferences, or not. Finally, criticizing preferences became trivial too -- the relevant question is "Does/will agent X behave as though they have preferences Y", and that's a belief, so go back to Bayes' rule and a reasonable prior. So the entire issue that this post was meant to solve has evaporated, in my opinion. Here's the original article, in case anyone is still interested:
Pancritical rationalism is a fundamental value in Extropianism that has only been mentioned in passing on LessWrong. I think it deserves more attention here. It's an approach to epistemology, that is, the question of "How do we know what we know?", that avoids the contradictions inherent in some of the alternative approaches.
The fundamental source document for it is William Bartley's Retreat to Commitment. He describes three approaches to epistemology, along with the dissatisfying aspects of the other two:
- Nihilism. Nothing matters, so it doesn't matter what you believe. This path is self-consistent, but it gives no guidance.
- Justificationlism. Your belief is justified because it is a consequence of other beliefs. This path is self-contradictory. Eventually you'll go in circles trying to justify the other beliefs, or you'll find beliefs you can't jutify. Justificationalism itself cannot be justified.
- Pancritical rationalism. You have taken the available criticisms for the belief into account and still feel comfortable with the belief. This path gives guidance about what to believe, although it does not uniquely determine one's beliefs. Pancritical rationalism can be criticized, so it is self-consistent in that sense.
Read on for a discussion about emotional consequences and extending this to include preferences and behaviors as well as beliefs.
"General Thud! General Thud! Wake up! The aliens have landed. We must surrender!" General Thud's assistant Fred turned on the lights and opened the curtains to help Thud wake up and confront the situation. Thud was groggy because he had stayed up late supervising an ultimately successful mission carried out by remotely piloted vehicles in some small country on the other side of the world. Thud mumbled, "Aliens? How many? Where are they? What are they doing?" General Thud looked out the window, expecting to see giant tripods walking around and destroying buildings with death rays. He saw his lawn, a bright blue sky, and hummingbirds hovering near his bird feeder.
View more: Next