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

D: Self-awareness

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
or
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? 

Summary

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.