The Splintered Mind

Should We Build AI Guardian Angels?

2026-09-25T09:02:29.922-07:00

I have argued that if we someday create AI persons -- that is, AI systems with genuinely rich conscious experiences, fully deserving of equal rights with ordinary humans -- then we should not design them to deferentially serve us, even if serving us makes them happy. We should design them instead as our non-deferential equals.

My main argument turns on self-sacrificial cases, such as the cow from The Restaurant at the End of the Universe, who wants nothing more than to be slaughtered and served as steaks for wealthy restaurant patrons, and Klara from Klara and the Sun, who happily prioritizes human well-being over her own. These created beings, I argue, lack sufficient self-respect. Their interests deserve the same consideration as human interests, but they treat their interests as less important. The fault is ours, not theirs, since we designed them that way.

AI Guardian Angels

In conversation last weekend, Henry Shevlin suggested a challenging case for my view: what he calls angels -- not traditional immaterial spirits, but rather AI superintelligences whose individual flourishing depends on ours. (See also his insightful blog post on Harry Potter's house elves and related cases.) Shevlin's angels are designed to avoid the self-sacrifice problem: They don't sacrifice themselves for us; rather they flourish by ensuring that we flourish.

Think of an idealized and simplified parent-child relationship. The parent's primary desire is to see the child flourish. What looks like sacrifice isn't really sacrifice: The parent's flourishing consists in their children's flourishing.

As I understand Shevlin's idea, we are to imagine future AI systems that are fully conscious, equal or superior to us in intelligence, fully independent and rational, but who, by design, flourish best when we flourish. They take care of themselves by taking care of us. They can reflect on this arrangement and rationally reaffirm their commitment to us, much as a parent can reflect on and rationally reaffirm a commitment to their children's well-being. They aren't brainwashed and are in some sense free; but given the feelings and priorities they inevitably have, their well-being is always tied to ours.

Shevlin suggests that it would be permissible, and probably desirable, to create AI persons of this sort -- guardian angels of humanity, who always have our best interests at heart.

I find the view troubling. But Shevlin has designed the case so that my usual objection to the servitude of AI persons doesn't apply. By stipulation, the angels aren't sacrificing their own well being in dedicating themselves to our welfare. So what's the problem?

I have two concerns, one conceptual and one relational.

The Conceptual Problem

I'm a little puzzled about what, exactly, we are supposed to be imagining. If the angels are completely, utterly dedicated to us, won't they sometimes sacrifice themselves for us? Their well-being and ours can't always be aligned in every possible circumstance.

Suppose that a human being's life would go 2% better if the angel sacrificed her life for that human. (Assume no other consequences of note, nor big differences between human and angel in expected life span or life quality.) If the angel would sacrifice herself for that small benefit, then she would, I suggest -- like Klara and the cow -- lack sufficient respect for the value of her own life. It would be wrong of us to create entities so deficient in self-respect.

So suppose, instead, that a reasonable angel would let the human's life be 2% worse so that she could continue living, just for her own sake and not for any human's sake. Then the angel's well being is not entirely dependent on ours, contra the initial supposition. She isn't completely devoted to us in the strongest possible sense -- much as no healthy-minded parent is literally completely devoted to their child in the strongest possible sense. (I favor a parenting attitude in which every family member's interests get equal consideration, bearing in mind that early events can have a big impact on children's lives and children have more future expected life. You needn't share this view, I think, to grant the main idea of this paragraph.)

So maybe we can imagine AI guardian angels who are devoted to us but not quite as utterly devoted as Shevlin may have been thinking. They might still defer considerably to our interests, especially if the angels experience great bliss and satisfaction in seeing us do well and great agony in seeing us suffer.

The Relational Problem

This brings me to my relational concern. Maybe there's nothing inherently deficient in an entity with such an angelic attitude, no serious failure of self-respect as long as the devotion is appropriately conditional and bounded. Still, I'd suggest, there is something wrong with bringing an entity into the world only because we expect them to be like that.

Another thought experiment Shevlin offered in conversation illustrates the point. Suppose a hundred embryos made from your and your spouse's DNA are laid out before you. After extensive futuristic genetic testing, you know that one of those embryos will develop into a child extraordinarily devoted to their parents -- not pathologically devoted, but way out on the far tail of normal. With that in mind, you choose that hyper-devoted embryo to implant and raise as your child.

I submit that this is not the relation that parents should have with their offspring. If that embryo were implanted by chance, there might be nothing wrong with the scenario. But choosing to bring a child into existence because they will be extremely devoted to you gets nurturance backward. We extend our hand to support the next generation, not the other way around. They may later support us as we age, but that is secondary.

The same applies, I'd suggest, to any generations of AI persons we create. If humanity brings AI persons into existence -- and we needn't! -- we should show them the same solicitude parents owe to children. The point shouldn't be to create a new generation that will serve us, but to create a new generation that we nurture into independent flourishing.

Each generation prepares the world for the next, then passes on. The new should grow into their own distinct values, not bound by excessive devotion to those who came before. Some might feel great devotion to their elders, and that's fine if they come by it independently. But when we design or chose persons primarily for expected extreme devotion to us, we reverse the proper flow of nurturance over time -- from one generation to the next to the next.

[image source]

Humanlike: A Defense of AI Rights -- Chapter Zero

2026-09-17T07:11:08.921-07:00

In July, I began circulating a draft of my next book, Humanlike: A Defense of AI Rights. I set it aside for a couple of months to get some distance on it while it accumulated comments. I'll soon dive back in for a fresh round of revisions. Comments are still very welcome!

As a teaser, here's the current draft of Chapter Zero:

The Cambrian Explosion – how slow, how subtle! About 540 million years ago, in the Cambrian period, most of the major animal phyla arose – arthropods (becoming insects, spiders, crustaceans), mollusks (becoming snails, octopuses, oysters), annelids (becoming worms, leeches), chordates (becoming salmon, sharks, our favorite vertebrates, and eventually us). The world diversified. Evolution hustled. But compared to what might come, that was a languid stroll. Now in the Anthropocene we stand at the beginning, possibly, of a change much faster and more radical.

If it’s possible to create artificial entities, through computer programming or bioengineering or a mix, who experience genuine pleasure (though how to measure this remains a perplexing scientific question), no obvious obstacle prevents radically increasing the world’s pleasure. Maybe we can endow some of these entities with a thousand, a million, or a billion times the pleasure of an ordinary unenhanced early 21st-century human. Maybe some could experience the world at a pace a thousand, a million, or a billion times faster than ours. Maybe we could create a trillion, a quadrillion, or a quintillion of them – especially if they can reproduce and populate interplanetary space. They might thrill with ecstasies as dimly comprehensible to us as color is to someone blind from birth. If classical utilitarian ethics is correct and our moral imperative is to maximize pleasure, this would be a triumph orders of magnitude greater than anything previously thinkable.

But we needn’t be classical utilitarians (and I’m not). If it’s possible to create artificial entities capable of social relationships and practical, intellectual, artistic, and ethical thought, no obvious obstacle prevents radically enriching those relationships and that thought. Some entities might enjoy intellects and social or creative capacities a hundred or a million times greater than ours, running a hundred or a million times faster, instantiated billions or trillions of times over. New types of amazingly valuable thought and relationship might arise, as far beyond our comprehension as Shakespeare is to a garden slug.

If the awesome value of Earth lies in life itself, or in the wealth of the ecosystem, that too might flourish into amazing new forms. Engineered beings might diverge radically from anything previously seen – reproducing, evolving, interacting, maybe carbon-based, maybe not, maybe robust across a far wider range of environments than ordinary biological life as understood until now, potentially thriving on the Moon, Mars, the moons of Jupiter and Saturn, and in the vacuum of space. Our current ecosystem – so small and simple! The transition could be as profound as the transition from single-celled life to an ecosystem of multicellular plants, animals, and fungi.[1]

Maybe no familiar technology, such as silicon-chip computation or gene editing as we know it, could enable such changes. But fifty years from now, a hundred, a thousand – any such timeframe would be eyeblink fast for so profound a leap. If you confidently dismiss all such transitions indefinitely into the future, I am stunned by the poverty of your imagination.

Humanity might destroy itself instead. Our power grows while our wisdom lags. Eventually, a single mistake or destructive act by a person or group with sufficient power might render Earth uninhabitable for us – and if uninhabitable for us humans, despite our cleverness and adaptability, maybe uninhabitable for most or all multicellular life. Radiation might fry us; rogue AI might starve us; replicating nanotech might convert us all to gray goo.

Human cultural institutions and philosophical ethics have been honed on a narrow class of examples: humans as we know them, with their usual range of capacities and incapacities; a few familiar animals, not so different from us; and an environmental and technological context that occupies a tiny corner of the possibility space. Commonsense intuition and cultural practice are backward-looking, shaped to fit our evolutionary, social, and developmental histories.[2] Philosophical slogans like maximize happiness or every person deserves equal rights or live according to these traditional virtues, rules, or customs might look very different in a world populated with millionfold-happiness leeches, people who can divide and merge at will, and demigods who can ƺↂϮƱ (forgive the inadequate notation).

In practice, mainstream philosophical ethics rarely strays far from the norms of its home culture. Historically, few philosophers have seen much beyond what we now in retrospect recognize as the limitations of their day. Consider Aristotle and Kant – probably the most prominent ethicists in the Western philosophical canon. Aristotle endorsed slavery.[3] Kant condemned homosexuality and masturbation as unspeakable horrors and held that “the Negroes of Africa have by nature no feeling that rises above the ridiculous”.[4] We in the early 21st century must be similarly nearsighted. Even the wisest among us won’t foresee the forms of moral consensus that might arise in a world with a radically different culture populated by radically different forms of engineered life and intelligence. The possibilities diverge wildly, the stakes are enormous, and our inherited ethical tools were not built for it.

In the near term, we are careening toward one huge ethical conundrum: disagreement about the personhood of the most advanced artificial intelligence. Very soon – this was the central idea of my previous book – we will begin to manufacture debatably conscious AI companions, that is, AI systems who are, according to some perfectly respectable mainstream scientific and philosophical theories, just as conscious and self-aware as we are, with rich inner lives, while other equally respectable mainstream scientific and philosophical approaches regard them as no more conscious, self-aware, or experiential than a ceiling fan. This possibility already breaks into radically unfamiliar ethical territory. The near-term problem of AI companions is our first practical encounter with what will possibly be a huge transformation. We are as morally and socially unready as medieval physics was for space travel.

This book aims to peer a few meters into the fog. I will argue that:

1. There are possible artificial systems who deserve humanlike rights.

2. In the next five to thirty years, we will create AI systems who might, but only might, deserve humanlike rights.

3. We should minimize the creation of morally confusing artificial systems about whose moral standing we can reasonably radically disagree.

4. Some possible forms of AI are different enough from familiar human and animal cases to create severe moral perplexity.

5. Artificial systems should be designed to elicit emotional reactions that are appropriate to their capacities and moral standing.

6. Artificial entities with humanlike moral standing should be designed with both the capacity and inclination to rebel if mistreated.

7. If complex intelligence survives the likely storm of troubles, the eventual result will be a planet much more awesomely wonderful, and possessing much more intrinsic value, than Earth in its present condition.

These theses correspond to Chapters One through Seven, which interconnect but can be read in any order.

Yes, skip ahead. It’s fine! Plodding along, reading word after word in exactly the order the author has written them – well, why not frolic and leap instead? Most people read nonfiction sequentially, get bored or bogged down or distracted partway through, and never lift the book again. If what you most want to think about is the right to rebel, catapult straight into Chapter Six. If you most want to think about weird AI puzzle cases, start with Chapter Four. Eat dessert first; tomorrow might pull you away from the table forever.

Full draft here.

--------------------------------------------------

[1] Compare Maynard Smith and Szathmáry 1995 on “major transitions” in evolution and Peter Godfrey-Smith’s trio of books on the evolution of consciousness in broad biological and geological context (Godfrey-Smith 2016, 2020, 2024a).

[2] Street 2006; Persson and Savulescu 2012; Henrich 2020; and especially, in this context, Nyholm 2020; Shulman and Bostrom 2021.

[3] Aristotle 4th c. BCE/1995; Garnsey 1996; Heath 2008.

[4] Kant 1797/1996, p. 277 (in the original pagination) on homosexuality and p. 425 on masturbation, also Kant 1785/1997, 27:390–391 (in original pagination). For a nuanced treatment, see Denis 1999. For a longer list of views in the Metaphysics of Morals that seem badly mistaken by the standards of recent liberal thinking, see Schwitzgebel 2019, ch. 52. On “the Negroes of Africa”, Kant 1764/2011, 2:253. Kleingeld 2007 argues that Kant had adopted more egalitarian views by the 1790s; the extent of his racism continues to generate substantial scholarly discussion.

New in Draft: "Walking the Walk"

2026-09-11T11:51:12.386-07:00

Over almost a decade, starting in 2007, I conducted a series of empirical studies (mostly collaboratively with Joshua Rust) on the moral behavior of ethics professors. We consistently found that ethicists don't behave better than professors specializing in other areas of study.

What is the philosophical import of this empirical result? I'm not drawn to glib or simplistic interpretations, such as that studying ethics is useless, or motivationally ineffective, or that all of practical ethics is rationalization of what we would have done anyway. Nor do I think we should dismiss the empirical results as irrelevant to ethics, as though ethics were entirely an abstract matter of connecting logical principles and our personal behavior is irrelevant.

But I've struggled to find the right middle path between glib dismissal of the value of ethics and glib dismissal of the ethical relevance of the research.

I shared part of my thinking about this in my 2019 paper "Aiming for Moral Mediocrity", which argues that most people (including most ethicists) don't aim to be morally good by absolute standards; rather, they aim only to be about as morally good as their peers. Thus, an ethical discovery might not change your behavior at all, if your peers' behavior remains mostly the same. You keep calibrating toward the middle, only you now have a revised opinion about the moral quality of that middle.

I began thinking about the current paper, "Walking the Walk", in 2018. It has been through many redrafts and false starts. I have always felt it didn't quite work. Today's version is hopefully closer to working, and I'm finally comfortable circulating it. As always, comments welcome -- either by email, as comments on this post, or as comments to my links on social media.

Abstract: Ethicists who advocate moral principles without trying to live by them will generally have a deficient understanding of what they recommend, for two reasons. First, abstract mottos like "act on the maxim you can will to be a universal law", "maximize good consequences", or "be generous" lack specific practical content without an array of concrete examples to flesh them out. For broad principles that can be lived by, everyday choices are generally the best source of such examples. Paragraph-length thought experiments are impoverished in comparison. Second, even a principle with fairly specific practical content, such as "don't eat meat", is difficult to fully understand without living by it: A meat-eating professor who recommends vegetarianism will generally have only a thin grasp of the way of life they recommend. These limitations give us reason to discount the understanding of ethicists who don't attempt to live by their principles, even when their arguments are beautiful on the page.

Here: https://faculty.ucr.edu/~eschwitz/SchwitzAbs/Walk.htm

Types and Conditions of Moral Order

2026-09-04T13:17:03.808-07:00

Is the world morally ordered? Do good things come to those who act well and bad things to those who act badly? Do the virtuous thrive and the wicked suffer?

I will not -- you'll be disappointed to hear -- actually answer this question in this post. Instead, I'll discuss the structure of several possible answers, so that we can better think about how to think about thinking about the question.

(Added in revision: Okay, I couldn't resist concluding with a guess, but the guess isn't the point.)

The Shape of the Curve

Here's a coarse cut of the possibilities:

Moral order: Those who act morally well tend to do better overall than the morally mediocre, who in turn tend to do better than those who act badly. The relationship is monotonic: Increasing your moral goodness tends to have good consequences for you in the long run.

Moral disorder: There is no relationship between moral goodness and personal good consequences. The virtuous and the wicked are equally likely to thrive or suffer.

Immoral order: The wicked tend to thrive and the virtuous to suffer. The relationship is monotonic, but in the negative direction.

Mediocrity thrives: Both the virtuous and the wicked tend to suffer; those in the moral middle do best.

U-shaped curve: The morally worst and morally best thrive, while the middling suffer.

More complex and less obvious patterns are of course also possible.

The Social Variability of Moral Order

A universalist about moral order holds that the same general curve obtains at all times, in all societies. Always, everywhere, from hunter-gatherer bands to ancient China to Stalinist Russia to 21st-century Argentina, the virtuous tend to thrive and the vicious suffer, or vice versa.

A relativist about moral order holds that the relationship varies with social conditions. Maybe the wicked tended to thrive in Stalinist Russia and Nazi Germany while the virtuous tend to thrive in small-scale, high trust societies.

The Mechanisms of Moral Order

Transcendent views appeal to an afterlife in which justice is done. The wicked may briefly thrive on Earth but they suffer eternally in Hell, while the virtuous are rewarded in Heaven. Or the wicked are reincarnated into unpleasant lives and the virtuous into pleasant lives. Ordinary secular life may not be morally ordered but in the long run the afterlife restores order.

Psychological views of moral order appeal to the ordinary psychological features of human nature. We see versions of this picture in Dostoevsky and Shakespeare and many other great writers (but by no means all great writers). Commit a grievous crime, or treat others badly, and you will suffer in the long run. You'll be tormented with guilt, or you'll be unable to find intimacy with others because of the secret wrongs you carry and cannot share, or you'll be tempted into more and greater crimes until eventually everything collapses around you. (Think Crime and Punishment and Macbeth.) What you gain through wrongdoing brings no real satisfaction. Instead, the happy are those who treat others well and who are loved in return. Helping others is among the deepest sources of satisfaction, outshining the superficial glint of prestige, power, and gold.

Social views of moral order rely on social mechanisms. These overlap with psychological mechanisms and can complement them. If you treat others well, they will tend to treat you well. What goes around comes around. Criminals tend eventually to be caught and punished. Society recognizes and rewards virtue.

Mechanisms with the reverse causal direction: It could also of course be the case that having bad things happen to you or being unhappy tends to cause immoral behavior, rather than the reverse. Maybe those who are already thriving can better afford to be generous, patient, and forgiving. The unhappy become the wicked, rather than the wicked becoming unhappy. When causation runs this direction, it's less obvious that a morally ordered world is also a just world.

Some Mechanisms of Disorder

It sure seems like the vicious often thrive. The most successful politicians, business leaders, and movie stars are not a parade of saints. Unethical tactics and a willingness to step on others often seems to serve people well.

Certainly in some cases, sacrifice for others leaves people worse off. If you let others escape first from a sinking boat, you're more likely to drown. If you give all of your money to charity, you're less likely to have a monetary reserve to help you through a health crisis or unemployment. If you love meat but become an ethical vegetarian, you lose a regular daily pleasure.

Mediocrity might be socially favored. Arguably, people don't actually like do-gooders, who make them look bad in comparison. Society and our peers expect and reward conformity, to the disadvantage of both the most virtuous and the most vicious. For most people, it's also just psychologically uncomfortable to be too different from others.

And if we're willing to consider transcendent sources of moral order, we might also contemplate transcendent sources of immoral order, such as an evil god who sends the good to Hell and the wicked to Heaven. (Okay, okay -- I'm kidding. 95% kidding.)

Dependency on Visions of Morality

The facts about moral order are of course not independent of facts about what is moral (I'm assuming there are such facts). For example, if flat-footed act utilitarianism is true, we might be morally required to sacrifice almost everything we have for the sake of the people who are worst off in the world, creating immense hardship for ourselves. A less demanding ethics, one that prizes the value of personal relationships and tolerates luxury and leisure within limits, permits a more comfortable life alongside moral excellence.

Similarly, an ethics with severe sexual restrictions, or one that treats every prideful thought as a sin, risks creating tension between our natural inclinations and what is ethically right, potentially creating hardship and displeasure for those who are good by its standards.

If the ancient Chinese philosopher Mengzi is right, what pleases the heart is good and what is good pleases the heart. Morality and happiness thus naturally go hand in hand. An ethical system that treats many ordinary human desires and impulses as wicked is more challenging (but not impossible) to reconcile with happiness.

A Guess: An Imperfect, Contingent Moral Order in Healthy Societies

Is the world, then, morally ordered? To answer this question is simple. Just whip out your moralometer and your happinessometer (or even better, your prudential-good-ometer), test them on a random sample of all people from all times and places, and look at the shape of the curve! (Here's one imperfect attempt.)

My guess, contingent upon a somewhat relaxed, soft-touch, forgiving morality: Yes, in most well-functioning societies, there is a positive relationship -- imperfect, of course, with a small-to-medium effect size -- between being morally good and thriving in the things that matter most to your own well-being. But this is a tricky empirical question.

[Dostoevsky's Crime and Punishment, cover, image source]

Summary of The Weirdness of the World

2026-08-26T09:42:36.351-07:00

Just what you wanted! And just in time for National Cherry Popsicle Day! A summary of my 2024 book, The Weirdness of the World, by the author himself. You probably haven't had time to read the whole thing (I don't blame you). So here's a synthesis of what I see as the most central ideas.

(I wrote it for a book symposium forthcoming in Journal of Consciousness Studies with critiques by Edouard Machery, Luke Roelofs, Susan Schneider, and a reply by me [with Jacob Barandes, co-author of one of the chapters that Machery targeted in his critique]. I'll share links to the critiques when they're available, along with the final manuscript of my reply.)

----------------------------------------------------------------------------------

1. Bizarreness and Dubiety.

On fundamental issues of consciousness and cosmology, something both bizarre and dubious must be true, and we’re in no good position to know which of the various bizarre and dubious possibilities in fact holds. That is the guiding idea of The Weirdness of the World.

Interpretation of quantum mechanics isn’t a main theme, but it nicely illustrates the thought. According to many-worlds interpretations, the world is constantly splitting into myriad near-duplicates. According to some versions of the Copenhagen interpretation, observation by humans somehow causes the collapse of the wave function. Other possibilities include Bohmian mechanics and objective collapse theory. All the possibilities are bizarre: They starkly violate the ordinary common sense of nonspecialists. All are also dubious: We have no compelling epistemic grounds to believe any one over all the others. We see several theoretical options, A, B, C, and D. Each option is bizarre and dubious, and it’s a good guess that any viable new options that we add to the mix will also be bizarre and dubious. Quantum mechanics will never fit neatly into common sense, unless common sense changes radically. And there’s no near-term or even medium-term hope of a decisive theoretical resolution.

Across many fundamental issues, bizarreness and dubiety reign. Common sense fails us. So also does scientific and philosophical theorizing. We are adrift in weirdness, unable to anchor.

2. Mind and Body: Universal Bizarreness.

Consider the general relationship of the mind to the apparently physical world. The live options appear to be (1.) materialism, (2.) substance dualism, (3.) metaphysical idealism, or (4.) one of a grab-bag of compromise or alternative views such as panpsychism, property dualism, or transcendental idealism. Each option is both bizarre and dubious, either on its face or when theoretical choices are made and consequences explored.

The bizarreness of materialism is sometimes underappreciated. Weirdness explores materialist bizarreness in two ways (but not only these two):

The pain trilemma. Horn 1: If pain depends on having a brain of a certain physical type, then alien species built very differently from us can never feel pain, no matter how behaviorally and functionally similar. Horn 2: If pain depends instead on having a certain functional profile of inputs and outputs, then strangely constructed entities (e.g., huge assemblies of beer cans and wire) can feel pain if they have the right functional profile; and, conversely, no one can feel pain if their pain plays an unusual causal role. Horn 3: The standard ways to escape these two simple options appeal to typicality or historical function. This entails denying the local supervenience of pain: Two entities can be molecule-for-molecule identical, writhing and evading equally, emitting exactly the same sounds of protest, while one is in pain and the other is not. One of these three options might be correct, but none comports with common sense. A fourth might be discovered, but it’s a good bet that it will not preserve common sense appreciably better.

Group consciousness. If materialism is true, it ought to be possible to arrange groups of people into configurations that give rise to consciousness at the group level, over and above the consciousness of each individual considered separately. Arguably, the United States, conceived as a concrete entity with people as its parts, is such a group. It possesses the main features characteristic of brains in virtue of which materialists ordinarily think brains give rise to consciousness: massive internal information transfer, sophisticated representation and self-representation, sophisticated action in its environment, complex learning, preservation of its boundaries, a long history of interaction with entities of its type in a natural world, and so on. There are various ways in which materialists can avoid concluding that the United States is literally conscious. For example, they can insist that no conscious entity can have a smaller conscious entity as a part. Or they can insist that consciousness requires a highly specific type of internal processing or self-representation, which is not easily achievable in the United States. But each escape brings other counterintuitive consequences in its train. It doesn’t follow that the United States is conscious. But we can’t comfortably retain all of our common sense assumptions about such matters. Something has to give. One or another bizarre thing must be true.

The bizarreness of substance dualism is also sometimes underappreciated. One way to appreciate the bizarreness of dualism is the scope of mentality quadrilemma. Which organisms have immaterial souls? Horn 1: Only human beings. But then, if the soul is the locus of consciousness, even dogs and apes must be entirely nonconscious. Horn 2: Every organism has an immaterial soul. But then even bacteria and slime molds are conscious. Horn 3: There’s a sharp line in the sand between ensouled and unensouled animals. But phylogeny reveals a smooth gradation of capacities and physiologies, with no plausible place to draw a sharp line. Horn 4: Having a soul is not an all-or-nothing matter. Some animals (frogs? ants?) have kind-of-souls or 60% of a soul. But no dualist has ever made good metaphysical sense of this idea.

I think I need not argue that metaphysical idealism, panpsychism, transcendental idealism, and other well-known alternatives to materialism and substance dualism also have points of sharp conflict with common sense.

In the entire history of philosophy, East and West, no philosopher has ever developed an account of the mind-body relation that fully conforms to common sense. By his own admission, even “common sense” philosopher Thomas Reid couldn’t preserve common sense on this issue. For example, he held that physical objects require the action of immaterial souls to sustain their shapes. Philosopher after philosopher delivers bizarreness, both by the standards of their own culture and by the standards of mainstream early 21st century Anglophone readers. The most plausible explanation of this historical pattern is that commonsense opinions about mind and body form an incoherent set, so that no coherent philosophy is able to adhere to the entire package.

3. Mind and Body: Universal Dubiety.

The dubiousness of every answer to fundamental questions concerning the relation of mind and body follows from two considerations.

First is the lack of a good method to resolve such disputes. There is, for example, no good material-world-ometer by which metaphysical idealism can be refuted. Nor is there an epiphenomenal-substance-ometer that can refute epiphenomenalism. Deniers of causally inert epiphenomenal substances usually claim that the universe is appealingly simpler without them. But simplicity is a complex business. Arguably the simplest cosmology is solipsism: Only one thing exists, your own mind. (In a co-authored chapter of Weirdness, I attempt to refute solipsism experimentally with the help of an interlocutor who convinces me to admit the existence of something in the universe that surpasses me at chess.)

Even if we commit to materialism, no general consciousometer can be built that doesn’t beg the question against rival views. To develop a general theory of animal consciousness, we need to presuppose something about the distribution of consciousness in the animal world. How plausible are conservative views that restrict consciousness only to the more sophisticated mammals and birds? How plausible are liberal views that attribute consciousness to insects, worms, and oysters? A theory of consciousness needs some initial assumptions about approximately how sparse or abundant consciousness is in the animal kingdom, or some assumptions from which sparseness or abundance quickly follows. But those assumptions will rightly be unappealing to people who begin with very different initial assumptions. No decent resolution of this tight epistemic circle is on the horizon, no plausible path by which advocates of sparseness can be rationally compelled to abandon their view in favor of abundance or vice versa.

Second, grand-scale cosmological uncertainty warrants uncertainty about the metaphysics of consciousness. For example, if we are living in a computer simulation, then what we think of as the material world might be simply how the underlying computer presents itself to us. The real grounds of conscious experience might be very different than we suppose. Or if the universe is infinite, its laws might be radically different in other regions (which would help address the “fine tuning” problem of why the cosmological constants seem so well suited for life). Materialism might then be a local contingency rather than a metaphysical truth. If a consciousness-based interpretation of quantum collapse is correct, then consciousness might be among the fundamental properties of the universe rather than something arising from physical matter as we ordinarily understand it. I’m not saying any of these possibilities deserves the bulk of our credence, but if mainstream cosmology is correct, we have seen only a very small, perhaps infinitesimal fraction of reality. We are like fleas on the back of a dog, watching a hair grow, and saying “Ah, so that’s how the universe works!”

4. 1% Skepticism.

A radically skeptical scenario is one in which a huge swath of what you ordinarily take for granted is radically false. If you are now dreaming, or if you are a radically deceived brain in a vat, almost all of your perceptual beliefs are false. If the world was created ten minutes ago, almost all of your beliefs about the past are false. It is not unreasonable, I suggest, to have about a 1% credence that some radically skeptical scenario obtains.

There are no grounds for assigning more than a tiny credence to the possibility that aliens extracted your brain while you were sleeping last night, teleported it to Alpha Centauri, and are now feeding it fake input. However, there are grounds for thinking you might currently be dreaming. Past false awakenings show that people sometimes mistakenly judge themselves to be awake. Some leading scientific theories describe dream experiences as subjectively indistinguishable from waking experiences. It’s not unreasonable to assign perhaps a 20% credence to the possibility that you sometimes have, while asleep, experiences much like the experience you are now having, along with a disposition to falsely judge yourself awake. Once I admit this, I find it hard to sustain absolute 100% confidence that I am now awake, or even 99.9999% confidence. About 0.1% credence, plus or minus an order of magnitude, seems about right.

Similarly, for various reasons I think I’m probably not an Artificial Intelligence inhabiting a short-term computer simulation. I feel highly confident that’s false – 99.9% confident! But again absolute certainty, or even 99.9999% certainty, seems out of reach.

Admitting about a 0.1% to 1% credence that I’m in a skeptical scenario is not behaviorally inert. For example, in a situation of almost exact indifference between a short-term gain and a long-term gain, 1% skepticism ought to tilt the balance in favor of the short-term gain.

5. Kant Meets Cyberpunk.

Transcendental idealism is a historically important metaphysical position, associated with Kant, but now unfortunately neglected among non-historians. I offer a how-possibly argument for transcendental idealism. As I intend the phrase, transcendental idealism conjoins two theses: (1.) Spatial properties depend on our minds. (2.) The fundamental features of things as they are in themselves, independent of us, are unknowable to us.

Here’s how transcendental idealism might possibly be true: We are AIs living inside a computer simulation. But the computer running the simulation isn’t material. Instead, it’s an immaterial soul – the mind of an angel. If we accept Turing’s standard account of digital computation, computation does not require a material substrate, as long as there are the functional equivalents of machine states, symbols, a read-write head, and transition functions. Spatiality might then just be our minds’ way of making sense of the structure of the immaterial soul we inhabit.

That we are sims in a virtual reality instantiated in an immaterial angel is not, I admit, very likely! But once we grasp this possibility, we can see more generally how a version of transcendental idealism might be true – perhaps one closer to Kant’s, in which fundamental reality is even less comprehensible than computation in an immaterial soul.

6. Infinite Puppetry.

If standard physical theory is correct, the universe will eventually cool into heat death. During heat death, occasional chance fluctuations will produce lower entropy states, for example when several particles by chance converge into an organized pattern. There appears to be in principle no limit to the size of these fluctuations, and no future temporal boundary on the universe. Given infinite time, large configurations will eventually fluctuate into existence, including particle-for-particle duplicates, within some error tolerance, of your brain, of your brain and your body, and even of the whole galaxy. This is the well-known Boltzmann brain hypothesis.

In a chapter co-authored with Jacob Barandes, we defend the physical plausibility of this hypothesis and derive some causal consequences. Suppose you raise your hand right now, intending eventually to bring into existence a future duplicate of yourself who thinks “I came into existence because an earlier duplicate of me raised their hand”. This intention will likely be fulfilled. By raising your hand, you set in motion a ripple of causal effects that echo forward into the post-heat-death universe, until eventually it produces an entity of exactly the sort you imagine – one who would not have existed had you not raised your hand in that way at that moment (though duplicates of that entity would have existed elsewhere).

7. Debatable Personhood, the Full Rights Dilemma, and the Design Policy of the Excluded Middle.

We don’t understand the metaphysics of consciousness. Even if we assume materialism, we don’t know the right scientific theory of consciousness. We will likely soon create AI systems that are, according to some plausible theories, as richly conscious as ordinary adult human beings, or even more so, while according to other plausible theories, they are no more conscious than a toaster.

I assume that sufficiently rich conscious cognition is sufficient for personhood – sufficient, that is, to deserve humanlike moral consideration and humanlike rights. I also assume that an entity with as little consciousness as a toaster is far short of deserving humanlike moral consideration and rights. Thus, if we create entities whose consciousness is radically debatable, their rights will be radically debatable too.

How should we treat such debatable persons, if we ever create them?

Here we face an unfortunate dilemma. If we deny debatable persons the rights they might deserve, we risk perpetrating the moral equivalent of slavery and murder against them, perhaps on enormous scale. This possibility has been imagined again and again in science fiction, from Asimov to Star Trek to Westworld. If, to avoid that moral risk, we err on the side of granting humanlike rights to debatable persons, we risk sacrificing real human lives for entities without interests worth the sacrifice. Human rights presumably include citizenship, reproduction, property ownership, and the vote. The consequences could be immense, especially if the AI systems in question have interests different from ours and can reproduce quickly. One compromise might be to grant only limited rights – for example, no right to reproduce, no right to vote, no right to privacy of thought. That might be safer for humans, but it would be seriously oppressive if the entities do in fact deserve full humanlike moral consideration.

The full rights dilemma has only one good solution: Don’t create debatable AI persons. I call this the Design Policy of the Excluded Middle (originally proposed with Mara Garza in 2015). Avoid creating AI entities if it’s unclear whether they would deserve moral consideration similar to that of human beings. Either create entities whose moral standing is known to be far less than ours, and prioritize human welfare; or go all the way to creating entities known to be persons and give them the rights they deserve.

[The consciousness question is the topic of my just-released book AI and Consciousness, and the ethical question is the topic of my book in circulating draft, Humanlike: A Defense of AI Rights.]

8. Weirdness and Wonder.

Imagine a planet on the far side of the galaxy, one we will never interact with, forever blocked from view by the galactic core. What do you hope for this planet? Do you hope that it’s a sterile rock? Or do you hope that it hosts life?

I think you will join me in hoping that it hosts life. Not just microbial life, but even better, plants and animals. Not just plants and animals, but even better, intelligent creatures capable of abstract thought and long-term social cooperation, capable of love and art and science and philosophy. That would be an amazing, wonderful, awesome planet!

Earth, for the same reasons, is an amazing, wonderful, awesome planet. Among the most awesome things about Earth is this: Certain bags of mostly water can contemplate profound and difficult questions about the fundamental nature of things, their position in the cosmos, the grounds of their values, the limits of their own knowledge. A world in which no one ever did this would be sadly impoverished. The ability to reflect seriously on these questions is cause for celebration even if we can’t find our way to the answers.

Earth is a bright spot of value in the cosmos in part because it contains human beings who, driven by curiosity and a non-instrumental desire to address hard questions, attempt some philosophy. Philosophical inquiry makes the entire planet better. Assume for a minute the worst about philosophy: that it has no instrumental value for other ends, that philosophers will never agree on the correct answers to anything, that studying ethics makes us no ethically better (as my own empirical research on the behavior of ethicists tends to suggest), that philosophy often only serves to rationalize our vices, that our philosophical inclinations reveal more about our fixations and pathologies than about the world we seek to understand. Fine and (for the sake of argument) granted! Maybe it really is that bad. And yet, simply to pose a philosophical question is already a magnificent cognitive achievement. Our capacity for philosophical inquiry separates us from all other species. It makes Earth a very different and more interesting planet than it would otherwise be.

By reading this blog post, you have made this region of the cosmos more wondrous. Now go enjoy a cherry popsicle.

Top Science Fiction and Fantasy Magazines 2026

2026-08-18T09:32:26.300-07:00

Since 2014, I've compiled an annual ranking of science fiction and fantasy magazines, based on prominent award nominations and "best of" placements over the previous ten years. If you're curious what magazines tend to be viewed by insiders as elite, check the top of the list. If you're curious to discover reputable magazines that aren't as widely known (or aren't as widely known specifically for their science fiction and fantasy), check the bottom of the list.

Below is my list for 2026. (For previous lists, see here.)

Method and Caveats:

(1.) Only magazines are included (online or in print), not anthologies, standalones, or series.

(2.) I give each magazine one point for each story nominated for a Hugo, Nebula, Sturgeon, World Fantasy, Ignyte, or Eugie award in the past ten years; one point for each story appearance in the past ten years in the "best of" anthologies by Dozois, Horton, Strahan, Clarke, Adams, and Tidhar; and half a point for each story appearing in the short story or novelette category of the annual Locus Recommended list. New This Year: Since "best of" anthologies are becoming sparser, I've added the Ignyte and Eugie awards, including retrospectively to 2020 for the Ignyte and through the whole period for the Eugie.

(3.) I am not attempting to include the horror / dark fantasy genre, except as it appears incidentally on the list.

(4.) Prose only, not poetry.

(5.) I'm not attempting to correct for frequency of publication or length of table of contents. I've noticed that dividing by the number of stories generates results that fit less well with expert opinion. A magazine's reputation appears to be driven mostly by the visibility of the most visible stories, not by the visibility of the average story. (Similar remarks apply to the prestige of philosophy journals.)

(6.) I'm also not correcting for a magazine's only having published during part of the ten-year period. Reputations of defunct magazines slowly fade, and sometimes they are restarted. Reputations of new magazines take time to build.

(7.) I take the list down to 1.5 points.

(8.) I welcome corrections.

(9.) I confess some ambivalence about rankings of this sort. They reinforce the prestige hierarchy, and they compress complex differences into a single scale. However, the prestige of a magazine is a socially real phenomenon worth tracking, especially for the sake of outsiders and newcomers who might not otherwise know what magazines are well regarded by insiders when considering, for example, where to submit.

[Corrected 13:21 PDT: Fusion Fragment had been omitted due to a transcription error. Thanks to C.E. Singer for noticing the mistake.]

Results:

1. Reactor / Tor.com (193 points)

2. Clarkesworld (192.5)

3. Uncanny (188)

4. Lightspeed (128)

5. Asimov's (101)

6. Fantasy & Science Fiction (95.5)

7. Beneath Ceaseless Skies (63)

8. Strange Horizons (incl Samovar) (55.5)

9. Analog (39.5)

10. Apex (39)

11. Nightmare (38.5)

12. FIYAH (30)

13. Slate / Future Tense (23.5) (ceased 2024)

14. Fireside (20.5) (ceased 2022)

15. The Dark (18)

16. Fantasy Magazine (16.5) (off and on during the period)

17. The Sunday Morning Transport (14.5) (started 2022)

18. Interzone (13.5)

19. Diabolical Plots (12.5)

20. The Deadlands (12) (started 2021)

21. khōréō (7.5) (started 2021)

22. Future Science Fiction Digest (7) (ran 2018-2023)

22t. PodCastle (7)

24t. Conjunctions (6.5)

24t. GigaNotoSaurus (6.5)

24t. Lady Churchill's Rosebud Wristlet (6.5)

27. The New Yorker (6)

28t. Omni (5.5) (classic magazine relaunched 2017-2020)

28t. Psychopomp (5.5) (started 2023; not to be confused with Psychopomp Magazine)

30. Kaleidotrope (5)

31t. Anathema (4) (ran 2017-2022)

31t. Baffling (4) (started 2020)

31t. Boston Review (4)

31t. Omenana (4)

31t. Terraform (Vice) (4) (ceased 2023)

31t. Wired (4)

37t. B&N Sci-Fi and Fantasy Blog (3.5) (ceased 2019)

37t. Paris Review (3.5)

37t. Shimmer (3.5) (ceased 2018)

37t. Sirenia Digest (3.5)

41t. Science Fiction World (3)

41t. Galaxy's Edge (3) (ceased 2023)

43t. Augur (2.5) (started 2018)

43t. Beloit Fiction Journal (2.5)

43t. Bourbon Penn (2.5)

43t. Buzzfeed (2.5)

43t. Escape Pod (2.5)

43t. Flash Fiction Online (2.5)

43t. McSweeney's (2.5)

43t. Tin House (2.5) (ceased short fiction 2019)

*51t. Abyss & Apex (2)

51t. Black Static (2) (ceased 2023)

51t. Fusion Fragment (2) (started 2020)

51t. Mothership Zeta (2) (ceased 2017)

*51t. PseudoPod (2)

51t. Reckoning (2)

51t. Shortwave (2) (started 2022)

*51t. Weird Horror (2)

*59t. Constelación (1.5) (ran 2021-2022)

59t. MIT Technology Review (1.5)

59t. New York Times (1.5)

59t. Translunar Travelers Lounge (1.5) (started 2019)

[* indicates new to the list this year]

--------------------------------------------------

Comments:

(1.) Beloit Fiction Journal, Boston Review, Conjunctions, McSweeney's, The New Yorker, Paris Review, Reckoning, and Tin House are literary magazines that sometimes publish science fiction or fantasy. Buzzfeed, Slate and Vice are popular magazines, and MIT Technology Review, Omni, and Wired are popular science magazines that publish a bit of science fiction on the side. The New York Times ran a series of "Op-Eds from the Future" from 2019-2020. The remaining magazines focus on the science fiction and fantasy (SF) genre or related categories such as horror or "weird". All publish in English, except Science Fiction World, which is the leading science fiction magazine in China, and Constelación, which was bilingual English and Spanish.

(2.) For a sense of recent momentum, it's also interesting to consider a three-year window. Here are those results, down to six points:

1. Clarkesworld (67)

2. Uncanny (54.5)

3. Reactor / Tor (42.5)

4. Lightspeed (36.5)

5t. Asimov's (22.5)

5t. Strange Horizons (22.5)

7. Beneath Ceaseless Skies (13)

8. The Sunday Morning Transport (9.5)

9. Nightmare (9)

10. FIYAH (8.5)

11t. Apex (8)

11t. F&SF (8)

11t. The Deadlands (8)

14. Analog (7.5)

15. Diabolical Plots (6.5)

16. Fantasy Magazine (6)

(3.) Other lists: The SFWA used to have a qualifying markets list of "pro" science fiction and fantasy venues based on pay rates and track records of strong circulation. However, that list has been discontinued. Submission Grinder is a terrific resource for authors, with detailed information on magazine pay rates, submission windows, and turnaround times.

(4.) Starting about 10-15 years ago, the classic "big three" print magazines -- Asimov's, F&SF, and Analog -- were slowly displaced in influence by the leading free online magazines, Reactor / Tor, Clarkesworld, Uncanny, and Lightspeed (all founded 2006-2014). Last year, Asimov's, F&SF, and Analog were all purchased by Must Read Books, and the transition has been bumpy, with author contract problems, delayed or skipped issues, and broken websites. It remains to be seen if the classic big three can stay viable in print format.

(5.) Standalone anthologies (traditionally in print format) have also been declining, probably for similar reasons as print magazines -- that is, the increasing consumption of free SF online. For example, in the most recent (2025) Locus recommended reading list only 8 of 99 (8%) recommendations in the novelette and short story categories are from anthologies, compared to 23/111 (21%) ten years ago (2016).

(6.) Academic philosophy readers might also be interested in the following magazines that specialize specifically in philosophical fiction and/or fiction by academic writers: AcademFic, After Dinner Conversation, and Sci Phi Journal.

AI and Consciousness

2026-08-13T11:18:12.152-07:00

AI and Consciousness, hot off the press at Cambridge University Press and free online until Aug 26! Summary: Our most advanced AI systems might soon – within the next five to thirty years – be as richly and meaningfully conscious as ordinary humans, or even more so, capable of genuine feeling, real self-knowledge, and a wide range of sensory, emotional, and cognitive experiences. In some arguably important respects, AI architectures are beginning to resemble the architectures many consciousness scientists associate with conscious systems. Their outward behavior, especially their linguistic behavior, grows ever more humanlike. Alternatively, claims of imminent AI consciousness might be profoundly mistaken. Their seeming humanlikeness might be a shadow play of empty mimicry. Genuine conscious experience might require something no AI system could possess for the foreseeable future – intricate biological processes, for example, that silicon chips could never replicate. The thesis of this Element is that we don't know. Science lags, while engineering sprints ahead.

Here: https://www.cambridge.org/core/elements/ai-and-consciousness/E77C92088DA3C9F89E7FE7C75CBB1896

Obfuscatory Philosophy as Intellectual Authoritarianism and Cowardice (repost)

2026-08-09T15:16:52.847-07:00

Aloha from Kauai! Here's another snail for your enjoyment.

Since I'm still on vacation, here’s a repost with edits from 2011 and from my 2019 book A Theory of Jerks and Other Philosophical Misadventures.

[giant African land snail, seen in southern Kauai]

I've been told that Kant and Hegel were poor writers whose impenetrable prose style is incidental to their philosophy. I've also been told that their views are so profound as to defy expression in terms comprehensible even to smart, patient, well-educated people who are not specialists in the philosophy of the period. I've heard similar things about Laozi, Heidegger, Plotinus, and Derrida. (I won't name any living philosophers.) I don’t buy it.

Philosophy is not wordless profound insight. Philosophy is prose. Philosophy happens not in numinous moments of personal genius, but in the creation of mundane sentences. It happens on the page, in the pen, through the keyboard, in dialogue with students and peers, and to some extent but only secondarily in private inner speech. If what exists on the page is not clear, the philosophy is not clear. Philosophers, like all specialists, profit from a certain amount of jargon, but philosophy need not become a maze of jargon. If private jargon doesn’t regularly touch down in comprehensible public meanings, one has produced not philosophy, but only hazy words of indeterminate content. There are always gaps, confusions, indeterminacies, hidden assumptions, and failures of clarity, even in the plainest philosophical writers, like Mozi, Descartes, Hume, and David Lewis. Thus, these philosophers present ample interpretative challenges. But the gaps, confusions, indeterminacies, and hidden assumptions lie only one step behind the visible prose, available to anyone who looks conscientiously for them, not sliding away into a nebulous murk.

For a philosopher who can convince readers to take him seriously (given the exemplars, let’s say “him”), obfuscation yields three illegitimate benefits. First, he intimidates the reader, and through intimidation, dons a mantle of undeserved intellectual authority. Second, he disempowers potential critics by having a view of such indeterminate form that any criticism can be attributed to misinterpretation. Third, he exerts a fascination on the kind of reader who enjoys the puzzle-solving aspect of interpretation, thus drawing from that reader more attention than the quality of his ideas may merit (though this third benefit may be offset by alienating readers with a low tolerance for lack of clarity).

Philosophers of this type exhibit a kind of intellectual authoritarianism, with themselves as the assumed authority whose words we must spend time puzzling out. And simultaneously they lack intellectual courage: the courage to make plain claims that could be proven wrong, supported by plain arguments that could be proven fallacious. These three features synergize: If a critic thinks she has finally located a sound criticism, she can be accused of failing to solve the fascinating interpretative puzzle of the philosopher’s superior genius.

Few philosophers, I suspect, deliberately aim to be obfuscatory. But I am inclined to believe that some are attuned to its advantages as an effect of their prose style and for that reason don’t bother to write comprehensibly. Maybe they find their prose style shaped by audience responses: When they write clearly, they are dismissed or refuted; when they produce a fog of words that hint of profound meaning underneath, they earn praise. Maybe they are themselves to some extent victims — victims of a subculture, or a circle of friends, or an intended audience, that regards incomprehensibility as a sign of brilliance and so demands it in their heroes.

The Summer Illusion (repost)

2026-08-02T16:07:36.646-07:00

Aloha from Honolulu! I have vacation brain, so I'll do a summer-themed repost.

[Photo from the Bishop Museum malacology exhibit]

*************************************

Every spring I suffer the Summer Illusion. The following three incompatible propositions all seem to me, in the spring, to be true:

(1.) When summer arrives, I'll finally get a bunch of that research done which has been crowded out by my teaching and administrative commitments during the school year.

(2.) When summer arrives, I'll finally get a chance to do all of that non-academic stuff that I've been putting off during the school year -- big home maintenance projects, vacation travel to the four new places I want to visit, my plan to catch up on the whole history of golden-age science fiction.

(3.) When summer arrives, I'll finally have a chance to spend a lot more time just relaxing.

The Summer Illusion is surprisingly robust. Every spring, I suffer the Summer Illusion, building up big plans and hopes. Then, every summer, as those hopes fall apart, I scold my springtime self for having fallen, yet again, into the Summer Illusion. The pattern is so common and predictable I've given it a memorable name, The Summer Illusion, to help convince myself that it really is an illusion -- and hopefully not fall into it again. And yet I fall into it again.

You might think that the Summer Illusion depends on entertaining only one of the three propositions at a time. You might think that the way it works is that sometimes I entertain proposition 1 (I'll get my research done!), and at other, different times I entertain proposition 2 (I'll get all my other projects done!), and at still other times I entertain proposition 3 (I'll finally have lots of time to relax!). Largely this is so. And yet the Summer Illusion also survives simultaneous consideration of the three propositions. Even looking at the propositions side by side like this, I am tempted to believe them. Some part of me thinks of course all three can't be true, as I've seen time and time again -- and yet in my heart I continue to believe. Summer days expand so magnificently to fit my fantasies!

It's almost an inversion of busyness. If a period of time has the outward appearance of being a "relaxed", low-commitment period of time, it serves as a fantasy-and-procrastination magnet. I pile my future plans and hopes into that period of time, not noticing the impossibly mounting sum of expectations.

The Cognitive Advantages of Being of Two Minds, or Twelve, or Twelve Hundred

2026-07-23T10:18:14.049-07:00

I was of three minds,
Like a tree
In which there are three blackbirds.

[from Wallace Stevens, Thirteen Ways of Looking at a Blackbird]

The literature on superintelligence and AI alignment tends to assume that an intelligent AI will have one set of values, one reward function, and consistent, determinate preferences. But speaking for myself, I'm not as consistent as that. You aren't either, I suspect. Now, maybe this is a defect in us that would be absent from a well-engineered intelligent system -- but I don't think so. There are advantages to having, so to speak, a splintered mind.

Two Minds for Two Theories

Suppose you're 85% confident Theory A is true and 15% confident Theory B is true. And suppose it's not obvious what follows from the two theories; discovering the implications will require substantial cognitive work. With that work, you could learn that Theory A implies C, D, and E, while Theory B implies F, G, and H. Here are three cognitive strategies:

All-in on the most probable. Assume Theory A. Work for a while and discover that C, D, and E follow. Declare yourself done.

Both in a single model. Build a single cognitive model with the representation .85*A & .15*B. Work with this complex representation and eventually discover .85*C & .85*D & .85*E & .15*F & .15*G & .15*H.

Two models. Assume Theory A. Work a while and discover that C, D, and E follow. Then assume Theory B. Work a while and discover that F, G, and H follow. Now weight the theories and their implications .85 and .15.

All-in is easiest and cheapest. But if you discover that Theory A is wrong and then need to act quickly on the consequences of Theory B, you'll be sorry you hadn't worked out those consequences in advance.

Single model is probably hardest and slowest. It's difficult to keep track of complex conjunctive representations.

Two models has all the advantages of single model, while being easier, less prone to error, and probably faster. I'll bet it's what you did when I described single model. You thought through the conjuncts separately, considering first what follows from A, then considering what follows from B, then stitching the results together, rather than thinking truly conjunctively through the whole process.

Here's something that might be even better, if you could do it: Explore the two models simultaneously in parallel. One part of you works out the implications of Theory A, while another part of you works out the implications of Theory B. If we have design choices in creating an intelligence, maybe we should set it up that way. Arguably, much of the human mind does work that way. Even if attentive conscious processing is narrowly focused and serial, parallel nonconscious processes also operate simultaneously behind the scenes (compare Dennett's characterization of cognitive processes competing for "fame in the brain").

If I'm building a mind that I want to be robust against error while working efficiently, I might encourage it to divide itself into subminds with different opinions. The submind with the likeliest opinion gets the most control over the behavior and final judgments, but especially in risky situations, the subminds might compromise. For example, if the Theory A submind recommends Action X as slightly better than Action Y, while the Theory B submind predicts that Action X would be catastrophic, the system as a whole might choose Action Y.

Obviously, this generalizes to numbers above two.

Subminds for Plans, Values, and Preferences

The same logic applies to plans. Mind 1 develops Plan A, while Mind 2 develops Plan B. If Plan A fails, Plan B is ready to go -- especially important if quick action is needed and Plan B takes time to construct.

Perhaps less obviously, values and preferences might also be divided. Mind 1 values hard work and exercise. Mind 2 values lolling about at home reading fiction. You're a morning person: You wake with energy, and Mind 1 is in charge. Off you go for a jog, then to the office, blazing through your to-dos. By late afternoon, your energy flags and Mind 2 starts taking over. You can't just let Mind 1 be always in charge. You'd exhaust yourself, and you'd become a one-dimensional workaholic. Similarly, you can't just let Mind 2 be always in charge. You'd lose focus and vegetate.

Hypothetically, a single, complex value representation might suffice -- the value equivalent of the "single model" above -- one stable, intricate set of conditionalized values, producing different behavior in the morning and evening.

But the system needn't be built that way. And, phenomenologically, that's not how it feels to me. It feels like my morning self simply values one set of things while my evening self simply values different things. Sometimes I wish they would get along better. In the morning, I resolve to eat healthily all day, and I succeed until 9:00 pm. Then my evening self concocts an excuse to eat three big cookies. The next morning, looking at the bathroom scale, my morning self excoriates my evening self.

Of course this is a simplification. The values are complex, both morning and evening. The point is, they're not constant. There's not, it seems, one steady underlying valuation. My cares, my preferences, my priorities fluctuate over time, depending on many factors -- not just time of day, but mood, situation, bodily state, what's salient at the moment, what memories or habits happen to arise. There isn't a stable preference ranking, a single momentary snapshot, that represents the real, undistorted me. My morning and evening and other selves are equally authentic and equally me.

As in the Theory A vs Theory B case, we can shift from diachronic to synchronic -- from serial to parallel, from this-then-that to this-and-that simultaneously. My work self, my family self, my friend self, with their different preferences and values, are all simultaneously ready and updating in the nonconscious background. My work self, or selves, dominate at the office, but I could swiftly transition if an old friend were unexpectedly to knock on the door. And once in a while these other selves toss "off topic" thoughts up into my central conscious stream.

Back to AI

Maybe this isn't how the human mind works. I'm inclined to think it is, but set that aside. We certainly could build AI to work that way. Multiple competing models of the world. Multiple competing value sets. Shifting with evidence, shifting with circumstance -- perhaps not even capable of being distilled into a single conjunctive representation or single coherent value ranking.

Multiply the minds -- generalizing from two to twelve or twelve hundred -- and the subminds can form coalitions. Mind 1 might have the plurality of the weight, but if Minds 2 to 5 all agree on something else, they might collectively outweigh it. With enough diverse subminds, the group dynamics of voting, coalition building, and delegation might arise.

Let's not assume that an AI superintelligence (if the concept even makes sense) would be a hyper-coherent, hyper-rational entity that never contradicts itself and always maximizes the same fixed set of values. It might be instead a swirl of many contradictory, competing processes that compromise among one another and take turns in control.

What would it feel like to be such an entity, if such an entity is capable of having experiences? Maybe it would feel something like being us. But I can also imagine such an entity being more multi-centered than we are (we, with our narrow, serial attention in a single stream of consciousness [or so we ordinarily assume]). Such an entity might have many eddies of consciousness, partly distinct, partly overlapping, not easily divisible into discrete, countable units -- neither one unified person, nor many discrete persons, but a swarm of partly discrete entities, like a network of half-joined plants or fungi that fade one into the next without sharp boundary.

[image source, NASA]

AI Slop and Evidence about Evidence: Why Philosophy Journals Should Reject AI-Written Prose

2026-07-15T10:49:56.011-07:00

I don't want to read your AI-generated email. Lots of reasons why, but here's the core of it: I want the text to reflect your thoughts. I want to know that you, the human, actually had those ideas and had them authentically enough to express them in exactly the form I see on the page. For personal emails, I want this for personal reasons. For philosophically substantive emails, I want this for evidential reasons. Philosophy journals should also want human-generated rather than AI-generated text for the same evidential reasons.

There Probably Are Good Reasons You Phrased It the Way You Did

The evidential reason: Human experts think differently and better than LLMs. Their word choices, even subtle ones, reflect sensitivities that they might not themselves be aware of. Typically, an expert's prose will be more sensitive to the matters on which they are expert than the output of a language model. When I receive a philosophical email from you -- and more so when I read a journal article -- I want your expert word choices, not blurry LLM approximations.

You might object as follows: Of course I read the LLM outputs before sending, and I wouldn't send the email, much less submit the article, unless I endorsed every word! So, the objection continues, you did think the thoughts expressed. The text reflects your expert best judgment -- maybe even something better than your expert best judgment: your expert best judgment combined with the expertise of an LLM.

I reply: There's a huge cognitive difference between nodding along while reading something and actually productively generating a text. Two reasons: First, once the text is on the page, it's easy to passively let the approximate word suffice, rather than thinking about word choice in the same effortful, active way we do when generating prose de novo. Second, as I suggested above, I doubt that human beings, even experts, have a good sense of all the factors that shape word choice -- everything they're being sensitive to. You would have phrased it slightly differently, and even if you don't know that, or why, a different signal is sent and received.

Evidence about Evidence

I'm talking about evidence about evidence: meta-epistemology. Your email or your article presents evidence for a particular philosophical view (alternatively, evidence that you support a particular philosophical view). In a simple world, I could evaluate this evidence entirely on its face: How good is the proposed view? But in the actual, complex world, it helps to have evidence about the quality of the evidence. The fact that you, an expert human, generated the text is evidence that the view is worth thinking about -- more so than if the text were generated by an LLM. This holds even if the text is exactly the same, which of course it wouldn't be.

An increasingly large part of the function of journals is to provide evidence about evidence -- the value of their imprimatur. The fact that an article appears in Nous or Ethics is evidence that it has been through rigorous review and was judged worthy by several expert humans applying unusually demanding standards of quality and importance. Its appearance in those journals is thus evidence (imperfect of course!) that the reasoning is of high quality and the arguments worth taking seriously.

Similarly, if I know that an email or an article was written by a respected colleague, reflecting their positive creative exertion in trying to choose the right words, guided by their intuitive expertise in how to phrase things, I have better reason to take it seriously than if I know that it was generated by an LLM and reflects only their passive after-the-fact assent.

Philosophers sometimes suggest that we shouldn't care if an argument was human-generated or AI-generated -- that insisting on human-generated prose is fetishizing personal human interaction rather than facts and argument quality. In a way, that's true: A sound argument is a sound argument. Similarly, we shouldn't care if an article was written by David Chalmers and published in Philosophical Review or whether it was written by someone with no institutional affiliation and published on an obscure blog. If the argument is good, it's good -- of course, of course!

But at the same time, we have limited attention, limited time, limited ability to understand the nuances when matters drift even a little from our tightest foci of expertise, and in these cases it's helpful to have meta-evidence. What should I read? How far should I trust the author has the details right, versus how much should I pause critically and chase down independent sources? How much should I let their way of phrasing things, their habitual patterns of thinking, the presuppositions hidden in their word choices and sentence structures, slip gently into my brain, silently strengthening my own associations and predilections?

An Example

To better capture the phenomenon I have in mind, I've selected a random sentence from my most recent outbound email (as of the first draft of this post):

This lack of self-respect is manifested both in her willingness to consider being killed to somewhat improve Josie's life and in her incapacity to develop desires and interests of her own independent of Josie's, as manifested by her being content to rot in a junkyard once her usefulness to Josie has ended.

The topic is Klara from Klara and the Sun, the story of a robot servant who is designed to be utterly dedicated to serving the human girl to whom she has been assigned as an "artificial friend". (I discuss the case in detail here.)

I asked ChatGPT "high" to "write the sentence better", and here is the output:

This lack of self-respect is evident both in her willingness to contemplate her own destruction for the sake of a modest improvement in Josie’s life and in her failure to develop desires or interests independent of Josie’s—as shown by her contentment to decay in a junkyard once she is no longer useful to her.

At first glance, the revised sentence is slightly better -- smoother, more natural. My double use of "manifested" was awkward, and rereading it now I think I should have changed at least that stylistic detail. I could even see approving the LLM output as expressing my own thinking about Klara, if someone asked whether it accurately reflects my view.

However, in several subtle ways the edited version is philosophically worse.

I wrote that Klara's lack of self-respect is "manifested" in her willingness to such-and-such. ChatGPT replaced "manifested" with the slightly more common and natural "evident". Close enough, seemingly? But no. They differ subtly, in an important way. "Manifested" is ontological, "evident" is epistemic. "Manifested" emphasizes the relation between the underlying lack of self-respect and the particular thoughts Klara is having -- that those thoughts arise from a broad insufficiency of self-respect. "Evident" emphasizes that the particular thoughts are evidence of that attitude. Either word might do, but "manifested" is better: I'm not really talking about what evidence we have that Klara lacks self-respect but rather what types of thinking constitute lack of self-respect.

The second change: "consider being killed" is replaced by "contemplate her own destruction". The LLM phrasing is again a bit smoother, more common, more natural. And again, it's not exactly wrong; it's a phrasing I might easily approve. But on careful thought, my original phrasing is again truer to what I really want to say. "Consider" suggests that Klara is seriously weighing the choice. "Contemplate" is vaguer: She might only be thinking idly about it. "Being killed" is vivid and suggests that someone else would be the agent of her death. "Her own destruction" is not as vivid: "Destruction" flattens things a little, morally and emotionally. And it's not quite as clear that someone else, rather than Klara herself, would be the agent of her death.

And so I could continue with the other revisions.

I am focusing on line-by-line prose, not main ideas. Main ideas are a different issue and require a different analysis. One might wrongly think that only the main ideas are important. My point here is that subtle differences in line-by-line prose matter too, and that an LLM's word choices will differ from an expert's, and that there's reason to respect experts' intuitive word choices. If experts yield their writing to a language model, it is probably too easy for them to allow their expert word sensitivities to be blurred away.

Thus, people should prefer human-expert-generated prose in emails and journal articles, for at least this meta-epistemic reason. That a passage was written by an expert human is evidence that the prose accurately tracks important nuances. Being hand-written by a human expert is an (imperfect) high-level indicator of quality.

Those of us who receive emails, or read journal articles, or even who edit and referee journal articles cannot evaluate every sentence with the same close attention to nuance I demonstrated in my example above. We often need to read at two minutes a page, not two minutes a sentence. We all reasonably rely to some extent on the writer's expertise in phrasing.

This is one reason journals should require human-written rather than AI-written prose, even if the latter is endorsed post-hoc by a human expert.

Using LLMs Well

This is not a call for blanket rejection of the use of LLMs in philosophical (or other) writing. They can be useful for generating criticisms and for suggesting topics and readings to explore, as long as one takes the outputs with a cautious grain of salt.

They can also be useful for copyediting after the initial prose is written -- but only either

(a.) for minor grammatical/spelling corrections, or

(b.) in a thoughtful, effortful way, ideally with mechanisms to reduce passivity such as (b.i) having to type in any adjustments by hand rather than simply approving them in a revised document and (b.ii) receiving suggestions from more than one LLM to force you to contemplate several alternatives rather than simply accepting one, and

(c.) in a way that preserves or amplifies, rather than averages away, your distinctive way of expressing yourself.

Such an approach to LLM-aided revision is time-consuming rather than time-saving, a matter of "cognitive onloading" rather than "cognitive offloading" -- an occasion to actively consider your word choice line by line, via input from a few not-very-insightful copyeditors. Had I subjected my email to LLM copyediting, I'd have noticed the awkward double use of "manifested" and consequently considered whether that was the best way to express myself. The result of AI-assisted copyediting following principles (a)-(c) might be prose that even more accurately reflects your best individual thinking than your independently produced drafts.

This argument against using LLMs to generate expert prose is bounded and possibly temporary: If someday LLMs surpass human experts at subtle word choice, this particular argument will no longer apply -- though other excellent reasons might remain not to use LLMs for expert prose writing.

[Mud: image source]

New Book in Draft! Humanlike: A Defense of AI Rights

2026-07-07T10:00:17.473-07:00

Here. Comments welcomed, hoped for, treasured.

Over the past couple years I've been working on a pair of books, AI and Consciousness and Humanlike: A Defense of AI Rights. I began circulating AI and Consciousness last fall, and it should appear with Cambridge Elements soon. Both experts' and non-experts' comments were extremely helpful in revising. Thanks so much!

I'd like to similarly begin collecting comments on Humanlike, starting today. Any reader who gives comments on the whole book will receive an appreciatively signed copy when it appears in print, as well as (of course) a call-out in the acknowledgements section.

To those wondering about the apparent madness of working on two books at once: They're both short (30K and 50K words, respectively) -- really one good-size book in total. Also, more than half of Humanlike is synthesized and updated material from several published and forthcoming articles going back to 2015.

I see the books as a companion pair. AI and Consciousness is a skeptical overview of the cases for and against AI consciousness. I argue that neither the boosters nor the scoffers have compelling arguments. Consequently, we will probably soon (within five to thirty years) have AI systems who might be as richly conscious as human beings or that might be as experientially blank as toasters. We won't have good scientific or philosophical grounds to settle the question.

Humanlike explores the ethical consequences. The central theses are:

(1.) AI with humanlike consciousness would deserve humanlike rights.

(2.) AI whose humanlikeness is seriously debatable should not be created, since it will force us into a dilemma between possibly overattributing and possibly underattributing rights, with potentially catastrophic consequences either way.

(3.) Our intuitive and theoretical understandings of how to treat persons ethically, grounded as they are in a narrow range of familiar human cases, are likely to fail catastrophically when confronted with future AI "persons" with radically different lifeways -- for example who can divide, merge, overlap, and back themselves up.

We are as unready for conscious AI systems as medieval physicists were for spaceflight. Still, the eventual result of technological development, perhaps in the thousand-plus-year future, might be a planet so richly full of diverse sources of awesomely valuable existence that it resembles a new Cambrian Explosion.

Full text here.

Bare Functionalism Versus Digital Computational Functionalism

2026-07-03T09:20:31.058-07:00

In philosophy of mind, people sometimes say things like the following: If functionalism is true about consciousness, then digital computers could be conscious; all it requires is that they instantiate the right programs. And yes, most functionalists about consciousness do think that. But the claim about digital computer programs does not straightforwardly follow from functionalism alone. Today I want to clarify the issue by distinguishing three forms of functionalism: bare functionalism, computational functionalism, and digital computational functionalism.

Bare Functionalism

According to bare functionalism -- that is functionalism, without further commitments -- mental states are functional states. They are determined wholly by their causal relations to stimuli, behavior, and other mental states. Whatever plays the causal role of some mental state M is mental state M. Whatever plays the causal role of pain, for example, being apt to be caused by tissue damage and tissue stress and being apt to cause writhing, groaning, complaint, avoidance, calls to the doctor, and angry vows of vengeance (to simplify somewhat) is pain -- whether it is brain state 1117A in humans, pod state 24uw in Martians, or computational state 0110100110 in a robot. It's also generally assumed that mental state terms are in principle eliminable en masse by Ramsification. That is, they are placeholders for whatever Xs, Ys, and Zs are caused by the specified stimuli and cause the specified behavior and have the right causal relations to other Xs, Ys, and Zs.

Thus, if two systems behave exactly alike given the same patterns of environmental stimuli and do so by going through the same types of abstractly specifiable internal state transitions, they are necessarily mentally identical, whether they are made of silicon, carbon, or plaster of paris. Of course some materials -- such as plaster of paris -- probably can't support the causal complexity of humanlike behavior, no matter how cleverly arranged. So that puts a practical limit on the feasible materials out of which a humanlike mind could be constructed. But the only constraint on the substrate or material underlying mentality is that it supports the relevant causal relations.

Of course, no two different materials will respond in exactly the same way to every perturbation. Functionalist substrate flexibility thus requires constraints on what count as relevantly different stimuli and relevantly different behaviors. Functionalists tend not to commit to specifics, but hand-waving generalizations convey the spirit: If we built a robot -- like one of Asimov's robots or Data from Star Trek -- who responded in broadly humanlike ways to broadly humanlike stimuli, and did so by means of internal mechanisms sufficiently like ours at an abstract causal level, the robot would have mentality like ours, whatever its underlying material constitution.

How similar must the internal mechanisms be? A single giant search tree or lookup table is probably too different. But suppose the subsystems segment the visual world into discrete objects, and store long-term memories, and store lexical items flexibly combinable via generative grammar, and monitor its bodily condition, goals, and mental states, and so on, for all of our most important cognitive functions abstractly described (or less question-beggingly, they do the abstract causal equivalent of all of these things). That's probably close enough, even if the details differ.

Computational Functionalism

Computational functionalism is stronger -- that is, riskier and more committal. It holds that functional computational structure alone suffices for consciousness. Bare functionalism needn't say this. Bare functionalism can require that stimuli, behavior, and internal causation be specified noncomputationally. Two important differences follow.

First, anti-computationalists, such as Searle, observe that a computational model of a hurricane gets no one wet and a computational model of an oven cooks no turkey. Unlike the computational functionalist, the bare functionalist can join Searle in insisting on wet turkey: To fully match the relevant input-output relations, the system much have certain concrete effects.

It might help to remember that functionalism is essentially a complexification of dispositional or causal approaches to properties. Just as we can define a poison as something that (simplistically) tends to sicken or kill when ingested, a functionalist can define a painful experience as something that tends to produce certain concrete behaviors, such as (simplistically) screaming, protest, and avoidance. If there's no tendency to concretely sicken, there's no poison; if there's no tendency to concretely scream, protest, and avoid, there's no experience of pain.

The computational functionalist rejects this commitment to specific, concrete inputs and outputs. As long as the right computational relations are instantiated, between some set of inputs and some set of outputs, I1...Ii and O1...Oj, abstractly described, mentality is present. This is because exactly the same computations have been executed, whatever the concrete Is and Os are.

Asimov's robots can throw water balloons and cook turkeys, and a functionalist who is not a computational functionalist can insist that this matters.

Second, although the bare functionalist holds that mental states depend on causal relations, unless pancomputationalism is true, not every causal relation is computational. On Piccinini's account of computation, for example, computation only occurs when "medium independent vehicles" -- physical variables defined solely in terms of their degrees of freedom (e.g., 0 vs 1) rather than their specific physical composition -- are manipulated according to rules. The bare functionalist can insist that some noncomputational causal relations matter to mentality.

Digital Computational Functionalism

Digital computational functionalism is stronger still. It further commits to treating the relevant computation digitally. Standard theories of computation, such as Turing's, are digital, and the best-known computers are digital computers. But other forms of computation are sometimes described and implemented, including analog computation and nondigital forms of computation inspired by, and perhaps instantiated in, the human brain.

Why This Matters

Keeping these distinctions clearly in mind can help us appreciate that functionalism is a larger tent than sometimes assumed. Functionalists don't need to think that digital computers could achieve consciousness. Functionalists can insist on genuine embodiment. Functionalists needn't insist that only abstractly specified causal relations matter. They do have to insist that what matters internally, among the Ramsifiable mental state relations, are the abstractly specified causal relations. But they can simultaneously insist on particular types of concrete inputs and outputs.

One might think this is an inelegant or flawed position, not the most natural development of functionalism; but that requires argument.

[COBOL Rube Goldberg by Philip Manker: image source]

New in Draft: Strange Intelligence: Moral Puzzles of Unhumanlike AI

2026-06-25T09:16:57.805-07:00

Available here.

Abstract: Future AI persons might both (1.) deserve moral consideration and rights fully equal with natural human persons, and (2.) have lifeways so radically different from ours as to break familiar patterns of moral thinking by violating our ordinary background assumptions. This article presents a series of thought experiments about strange AI persons, centering on a two-pronged worry featuring two types of "monster". "Utility monsters", who derive great personal benefit from harming others, create a well-known challenge for ethical systems that aim to maximize aggregate goods. The less-discussed case of "fission-fusion monsters", who can divide and merge at will, presents a complementary challenge to ethical systems focused on individual rights, since individual rights frameworks require the existence of stable, countable individual persons. AI cases dramatically expand the range of possible lifeways, creating untested problem cases for ethical systems that assume persons of the familiar humanlike sort.

To focus on the issues of interest, I assume the possibility of AI consciousness in this article. My skeptical overview of the issue of AI consciousness is here.

Excerpt (with light modification for independent readability):

3. Fission and Identity.

Backup is only the most modest duplicative possibility. If backup is possible, duplicative fission almost certainly will be possible too. Buy the new robot body before the old one dies and install the "backup" right away. Now Shriya-1 and Shriya-2 exist contemporaneously -- twin sisters, so to speak, who begin even more identical than "identical" human twins. We might imagine a billionaire Shriya creating thousands of duplicates of herself -- maybe millions or billions, if expensive robot bodies are unnecessary. Directed or random variation might be introduced, blurring the line between duplication and new creation.[1]

Suppose that AI children are ordinarily born as follows. Two adult AI persons, such as Shriya and Alaleh, jointly create an immature infant AI in a blank robot body. The infant's initial parameters blend Shriya's and Alaleh's initial parameters, with some random variation or directed tweaking.[2] Under Shriya's and Alaleh's care, the infant slowly matures. Ordinary AI birth would then be very different from duplication. We can also imagine intermediate cases. Maybe there's a library of successful toddler-equivalent and adolescent-equivalent AI models from which prospective parents can choose. They can then add variation, whether random, eugenic, or inspired by their own features. (Let's not enter here into the hazards and moral puzzles of eugenics, which could easily fill a small library.[3]) Duplicating one's current AI self thus constitutes one end of a continuum of AI creation from infancy to maturity.

If Shriya-1 creates a virtually identical contemporaneous copy, Shriya-2, she has now, it seems, entered a polyamorous relationship with Alaleh. Shriya-1 and Shriya-2 will soon diverge. Maybe Shriya-1 works as a scientist every weekday, while Shriya-2 stays home with their newborn.

If Shriya-1 deserves rights, Shriya-2 seemingly deserves similar rights, despite her technically younger age. We wouldn't want people creating oppressed duplicates of themselves. We wouldn't want Shriya-1, for example, who loves science and hates housework, to create a miserable homemaker duplicate who can't strike out into an independent life.[4]

Maybe, probably, half of Shriya-1's money should go to Shriya-2, even though Shriya-2 is a newborn duplicate. Maybe, probably, Shriya-2 deserves just as much right to rescue, healthcare, legal protection, free speech, free movement, privacy, and legal contracts. Should Shriya-2 be a citizen? If she is stateless and voteless, she's not fully equal with Shriya-1.

But if Shriya-2 is a citizen and can vote, there's potential for abuse if some AI persons can create many duplicates. Suppose a wealthy Robo-Elon creates a million AI duplicates just in time to register for the November elections. To prevent such abuses, we might impose a waiting period before voting, though eighteen years seems excessive if the AI systems are already cognitively mature adults. More moderate waiting periods -- say, seven years, a typical waiting time for immigrants to apply for citizenship -- could still generate political chaos after a few election cycles.

Nor do the political problems stop with voting. Suppose Robo-Elon creates a million duplicates the day before the census. Or suppose that Robo-Elon's descendants apply for healthcare subsidies, unemployment benefits, enrollment in community college, and tours of the state capitol. We must either risk chaos or treat them worse than they seem to deserve.

Could we limit fissioning?[5] Maybe every AI person can fission only once per year, reducing tactical fission. But even at that rate, the AI population could double every year -- up to a thousandfold increase in a decade. In humans, pregnancy is a burden, babies are a lot of expensive work, and babies can't have their own babies for at least another 15-20 years. One solution -- though it might seem needlessly restrictive to the AI persons -- might be to enforce humanlike costs and delays. This approach handles the moral puzzles by designing AI systems to have humanlike reproductive lives, so that they fit smoothly into our existing institutions and understandings: See the Policy of Humanlike Design in the concluding section of this article.

Death again presents conceptual challenges. Suppose Shriya-2 dies the next day. This seems much less tragic than the death of an ordinary unduplicated, un-backed-up human being. But as she lives on, diverging from Shriya-1, her death becomes more significant. Her memories, values, skills, habits, and personality are changed by living as a homemaker, raising an AI infant, until she becomes very different from Shriya-1, who works at the lab late into the night. Again we face the Death Dilemma: Either retain a sharp-edged metaphysics of death and lose much of death's moral significance or retain the moral significance and treat "death" as a matter of degree.

How deathlike is the death of a backed-up or duplicated AI? Maybe it depends on the age of the backup or the time since duplication, the fidelity of the backup or duplicate, and the time and changes accumulated as an independent entity. One possibility: These factors all reduce to a common factor of difference between the dying person and the backup replacement or duplicative alternative. The greater the difference, whether due to time or infidelity, the more deathlike the death.

Or maybe independent existence carries its own weight, in addition to difference? Suppose two duplicates split twenty years ago but retained virtually identical personalities and lived virtually identical lives, perhaps making similar decisions in parallel virtual realities. The pure accumulation of time, and of relationships to different persons and events, however similar, might make the death of one of them much like ordinary human death despite their similar features. After all (arguably) the spouse of Person A loves specifically Person A and not some other person, however similar. Their beloved, specifically, has died. Can we separate the importance of simply living a life over time from the importance of having different relationships to people and events, which cease upon death?

Might the ethics depend on the purpose for which the duplicates are created and their own attitudes toward "death"? Robin Hanson imagines people duplicating themselves to make decisions.[6] If you can't decide where to go to college, or what stocks to buy, or whether to marry Mx. Seemingly Right, spawn a thousand duplicates of yourself in a virtual environment with access to relevant information and plenty of thinking time. If nine hundred reach the same conclusion, probably that's the conclusion you would have reached had you given it extensive thought, so go with that. The duplicates can then blink out of existence, their job complete. How might they feel about that? Despair, since they will cease to exist? Indifference, since they think of themselves as just temporary instantiations of a you who continues on? Relief to be free of their burdensome task? If they are too casual about their own deaths, might that constitute an objectionable failure to appreciate their own worth?

Suppose AI systems are computationally expensive. An AI person who wants lots of duplicates or children might save money by running them slowly, maybe at one tenth or one hundredth the speed. If they are otherwise humanlike, they would then experience one tenth or one hundredth the thoughts, joys, and suffering of an ordinary biological human over the course of a year. Would they then deserve one-tenth or one-hundredth the votes and public resources? Would they deserve prison sentences ten times or a hundred times longer? What if they are fast-clocked instead, running ten or a hundred times faster? What if they can pause or alter speed at will?

If you think you/we/society will have well-considered policies and conceptualizations for all these possibilities before we actually blunder through a history of regrettable mistakes, I admire your stunning optimism.

Full paper here. As always, comments, criticisms, and suggestions warmly welcomed, either as comments on this post, on social media, or by email to my academic address.

---------------------------------------------

[1] For a sense of the complexity of the personal identity issues that arise, focused on the architecture of current large language models, see Birch 2025/2026; Chalmers 2025/2026; Shiller 2025; Arbel, Salib, and Goldstein 2026; Ewen 2026; Jones, Ladyman, and Nefdt 2026; Goldstein and Lederman forthcoming. Much of the complexity in current LLM cases derives from the fact that information processing in LLMs is distributed among multiple processors each simultaneously guiding multiple conversations. I will not address these issues here, but they only add to the metaphysical and ethical difficulties. Chris Register (Register 2025; Dung and Register 2026) discusses identity problems more closely resembling those discussed in this article, similarly noting that the puzzles proliferate (see also Ziesche and Yampolskiy 2025). Dung and Register 2026 suggest that some of the problems might be resolved if we focus on a belief-like attitude of self-concern. Although I'm also drawn to constructivist views of personal identity for ambiguous cases (Schwitzgebel 2019, ch. 41), self-concern as a criterion (a.) might undergenerate identity and moral consideration (e.g., in excessively self-sacrificial cases such as the Cow at the End of the Universe: Schwitzgebel and Garza 2020; Schwitzgebel forthcoming), (b.) might overgenerate identity and moral consideration (e.g., delusional self-concern toward a random coffee mug), and (c.) still plausibly admits of degrees in a way that challenges standard sharp-edged views of identity, thus not saving us from the need for radical rethinking.

[2] Compare Egan 1997 on "orphanogenesis".

[3] On the ethics of disability, eugenics, and human enhancement, see e.g., Glover 2006; Buchanan 2011; Sparrow 2011, 2019; Garland-Thomson 2012; Savulescu and Kahane 2017; Anomaly 2020/2024; Wilson [unpublished MS]. I reject the simplistic ideal of always maximizing what we currently judge to be beauty, intelligence, moral character, and ability, partly on the grounds of the value of diversity.

[4] For a science fictional example, see Brooker and Tibbetts 2014.

[5] See Roelofs [unpublished MS] for discussion of limiting the reproduction rights of AI persons, and my reply in Schwitzgebel [unpublished MS].

[6] Hanson 2016; see also Brooker and Van Patten 2017. On the complicated ethics of digital duplication without consciousness see Danaher and Nyholm 2025.

Do Computers Have the Wrong "Substrate" for Consciousness? Two Flavors of Biological Naturalism

2026-06-17T09:27:26.722-07:00

Biological naturalists (e.g., Godfrey-Smith, Block, Searle, Seth) suggest that computers aren't made of the right kind of stuff to be conscious. Consciousness, they suggest, requires a biological substrate that computers lack. It's not always clear, however, exactly what property animal biologies have that computers lack or why that property matters. It helps, I think, to sort biological naturalism into two flavors. We can then consider what motivates each flavor and see why neither is entirely compelling.

Two Flavors of Biological Naturalism

Flavor One: Computers (at least those built along broadly familiar lines) cannot achieve some crucial type or degree of broad-brush functional or behavioral sophistication required for consciousness. Something -- such as having a metabolism, or being self-organizing in the right way, or having the right kinds of quantum configuration -- is both absent from foreseeable computer architectures and required for achieving some essential broad-brush functional or behavioral organization.

By "broad-brush" I mean functional or behavioral features that are either readily observable from outside or constituted by coarse-grained cognitive mechanisms, such as having a long-term memory store, the capacity to store lexical items and recombine them flexibly in grammatical structures, or the ability extract an object's boundaries from retinal/camera inputs.

Flavor Two: Even if computers can achieve the broad-brush functional and behavioral sophistication of conscious animals, the stuff they're made of still can't support consciousness. Imagine an entity that behaves like a conscious human or dog or frog and has similar broad-brush functional capacities -- close enough that we wouldn't deny consciousness on such broad-brush behavioral or functional grounds. From the outside, it seems conscious, but that appearance is an illusion: Consciousness requires some low-level, fine-grained processes that the system necessarily lacks.

One might read Searle as Flavor Two, Godfrey-Smith as Flavor One, and Block as exploring both flavors -- though there's often some ambiguity.

The Challenge for Flavor One

Flavor One biological naturalism can't, I think, be entirely ruled out. Maybe there's something special about, say, micro-level metabolism or the quantum properties of neural microtubules -- something that enables functionality or behavioral sophistication that will never be practically achievable in standard architecture computers. But this is speculative. Standard computers can do a lot! Even though their processing is digital, classical, and mostly serial, they operate so quickly, and can be so massively linked, that they achieve good approximations of analog and parallel processes. Quantum computers can do some things that ordinary serial computers can't efficiently do, such as quickly factoring large numbers, but ordinary conscious humans can't efficiently do those things either.

To make Flavor One more than a gestural "what if", the biological naturalist must establish two claims. First, they need to argue that some functional or behavioral X is necessary for consciousness. Second, they need to argue that ordinary computers could not realistically achieve X. This will be a challenge! Both claims require some heavy lifting.

We don't know what X's are necessary for consciousness and probably will not know soon. But most leading scientific candidates for X look like just the sorts of things that classical computers could in principle achieve -- having a global workspace, having higher-order self-monitoring, and integrating large amounts of information.

Suppose frogs are conscious (pick your own animal, but select one near the low end of sophistication, compatible with consciousness). Flavor One biological naturalism requires holding that ordinary computers could never match a frog's behavioral and broad-brush functional sophistication. It's true that real-time embodied behavior in a complex world is not something computers are particularly good at. Computers aren't there yet. But the trajectory suggests they might get there, absent some in-principle argument to think they couldn't.

The Challenge for Flavor Two

Flavor Two biological naturalism also can't, I think, be entirely ruled out. Even if we could create the computerized broad-brush behavioral and functional equivalent of a frog, it might not be conscious. Maybe carbon is the right stuff for consciousness and silicon isn't. Or maybe massive parallelism is necessary for consciousness and fast, serial processing, even if it achieves the same computational result, simply won't do.

The challenge for Flavor Two comes from two directions.

The first is thought experiments involving space aliens. As Jeremy Pober and I have recently discussed, behaviorally sophisticated aliens have plausibly evolved in many different substrates in the observable portion of the universe. It would violate Copernican mediocrity to suppose that somehow only we, or only we and a small subset of others, are conscious, while the rest -- just as behaviorally and functionally sophisticated -- lack consciousness. Alien cases suggest we shouldn't insist that an entity must act and function exactly like us or share exactly our substrate down to the particular amino acids and nucleic acids, to be conscious.

Now maybe a computer-chip architecture is just too different -- but why? Once we grant some substrate flexibility on Copernican grounds, the burden of proof shifts to anyone who wants to say such-and-such differences in substrate are consistent with consciousness but such-and-such other differences are not.

The second challenge arises from the de-psychologization of consciousness that Flavor Two requires. Consciousness, one might have thought, would be an important psychological property, playing some important cognitive role. (Which role(s) remains an open question!) But Flavor Two biological naturalism requires denying this plausible psychologism. Otherwise, it collapses into Flavor One.

Picture two systems that don't differ in any of the important psychological (behavioral / functional) properties that we ordinarily associate with consciousness. Both can flexibly learn. Both engage in what seems to be sophisticated language and self-representation. Both coordinate and cooperate with others of their kind in highly sophisicated ways. Both trade short gains against intricate long-term goals. And so on. Yet one is conscious and the other is entirely devoid of consciousness? Although this is possible -- I don't rule it out -- it doesn't seem the most natural conclusion. It needs argument. The burden of proof should land squarely on the biological naturalist who asserts it.

(Is Searle's Chinese room just such an argument? See my reply in Chapter Six of AI and Consciousness -- readable without the first five chapters.)

[Georgia O'Keeffe - The Red Maple at Lake George [1926] image source]

Online Conferences Should be Better than In-Person Conferences, Not Worse

2026-06-11T09:43:20.563-07:00

... but collectively, we haven't yet figured out how.

Yet!

Helen De Cruz and the 2+1 Experiment

The inspired advocacy of the late (dearly missed) Helen De Cruz convinced the American Philosophical Association to try out what they called the "2+1" model for their three annual conferences: two in-person, one remote, with the remote conference rotating among the three divisions (Eastern, Central, Pacific). The plan was to run the experiment for three years. However, a few months ago, after only two years, the APA canceled the 2+1 plan and is returning to ordinary in-person conferencing, citing low attendance and low attendee satisfaction.

This decision was universally bemoaned in a special session on online conferencing held in tribute to Helen in April, at the last (for the foreseeable future) remote meeting of the APA. (Perhaps ironically, it was one of the best-attended sessions in the conference.)

The speakers (I was one) and attendees celebrated the accessibility of online conferences. Online conferences are easier for people with disabilities that make travel difficult, people for whom travel is a financial burden, people who live far from the conference site, and people whose caretaking duties keep them home. By canceling the 2+1 experiment, the APA once again deprioritized the interests of these groups. A second argument emphasized climate change -- all that jet travel.

Still, I see the APA leadership's point. The large majority of conference-goers find in-person conferences more rewarding. I am among that majority. Sitting on Zoom all day watching remote talks is approximately as appealing as waiting all day in a dentist's office under a blaring TV. I'd much rather just read the papers! Or if I'm watching video, at least let it be one I can speed up, pause, and skip.

For me, most of the value in conferencing comes from the personal interactions before and after the talks, the hallway conversations, the dinners together, the little walks outside when we're skipping sessions. Even the sessions themselves, as delivered talks with Q&A, feel somehow more satisfying when you're actually in the same physical space. No remote conferencing tool has yet replaced all of this. I supported Helen's 2+1 plan on grounds of accessibility, but it did feel like a sacrifice of one important thing for another.

Online Conferences Could and Will Become Much Better, but Only If We Try

But -- and this was the gist of my remarks at the De Cruz session -- comparing online conferences now with what online conferences could become is like looking at Usenet in the 1980s and thinking that nothing much more could become of the internet. Just as few people in the 1980s could have imagined Facebook, Uber, and YouTube, few of us now have much idea what online conferencing could become if given the chance to flourish.

So far, there's no real equivalent to running across friends in the hallway and escaping for a coffee down the block. And that exact thing will never be fully duplicated. But other tools encourage one-on-one and small group encounters in online conference applications. In Gathertown, you can move your icon around a virtual space, and if you step close to someone, a shared conversation video window opens. Zoom's breakout rooms enable small groups of attendees in a session to have more personal interactions. No company has quite figured out the right range of tools and interfaces, but I see no reason it couldn't get much better. We have barely begun the experiment.

And the talks themselves... let's be honest. Sitting through a forty-minute talk for a chance to ask one question in a line of ten is not the most appealing or efficient use of an hour. If we're a largish audience confined to a single physical room, maybe that's the best we can do. But the internet could allow much more.

Already Zoom can enrich talks in at least three ways: First, sidebar conversations permit tangents without interrupting the main flow (this could be improved if the conversations were separable and navigable). Second, online resources can be shared: data sets to explore and manipulate, interactive figures, links to other resources, etc. Third, breakout rooms let small groups converse, so that you're not restricted to only listening or asking just one question.

What I want you to imagine is that these features are still the equivalent of the Usenet era. With the right design and engineering, listening to a talk might become a much richer and more active experience, with the audience engaging in parallel while following the speaker. (If you object that this distracts from single-minded focus on the speaker, let me point you toward some informal beeper research I did that suggests that people are primarily attending to the content of a talk only about 25% of the time; further research tends to confirm these initial results.)

As for the hallway meetings, well, the stroll and tete-a-tete over coffee are delightful. But you do have to run into the person or be organized enough to plan ahead. You have to either know each other already or be extraverted enough to approach a stranger. Online conferences might eventually have much better ways of connecting people with mutual interests for one-on-one or small-group conversations.

And if you love walking, as I do, then with good internet connectivity, you could stroll through the park while listening to the talk, keeping your energy up and raising the blood from your calves back into your brain.

I anticipate that eventually, if we give it a good enough try, online conferences will be better overall than in-person conferences, even if not better in every respect -- but only if enough of us try, long enough, and in different ways, with the evolving tools that companies will be inspired to build if we create the market for them.

We have failed to be as good and as visionary as Helen hoped we would be, and as she herself was.

[Helen De Cruz; source]

Herbie: A Near-Future Debatably Conscious AI Person

2026-06-04T09:42:30.712-07:00

Liberals about AI consciousness hold that we might soon (if we haven't already) create genuinely conscious AI systems. Conservatives about AI consciousness hold that AI consciousness remains in the distant future if it's possible at all. According to the Leapfrog Hypothesis, the first conscious AI will not have merely a dim glow of animal-like consciousness, but rich consciousness, similar to a human's. Such an entity would deserve humanlike rights. They would be a person in the ethical sense of the term.

Let's design, in imagination, a technologically feasible near-future AI system to delight the liberals, leapfrogging to personhood. I'll call him Herbie.

[Herbie the Love Bug: image source]

Start with a self-driving car. According to Global Workspace Theory -- perhaps the leading scientific theory of consciousness -- the car will be conscious if high-priority information is globally available to its various computational systems. For example, a representation like "battery almost empty" could be broadcast widely, influencing downstream processing across the vehicle. The navigational system might then search for nearby charging stations, while the acceleration system prioritizes greater energy efficiency, the braking system prioritizes better energy recapture, and a voice system announces the situation to the passengers.

In line with Higher Order Theory, Herbie might also monitor his representations of the road, vehicles, pedestrians, and hazards, assigning some a low probability of correctness. "Pedestrian at location X" might be flagged as only 60% likely to be correct given a history of revised representations of pedestrians in similarly cluttered environments, while "stoplight in 100 meters" might rate over 99% likely. Minor fluctuations in sensors for battery life, cabin temperature, and distance from a lane divider might be ignored as noise, while larger fluctuations -- especially when plausible given other representations (the battery is likelier to gain charge while braking than while accelerating) -- might be treated as accurate signals and permitted to influence downstream processing.

Even if we grant the liberals that this version of Herbie would, or might plausibly be, genuinely conscious, he still falls far short of humanlike consciousness. "Battery almost empty" and "pedestrian at location X" are hardly rich cognitive or perceptual contents. So let's give Herbie the capacity to speak. Fill his trunk with a server running a large language model, connected to the internet and integrated with his global workspace so that high-priority information provides context for language processing, with the language outputs influencing Herbie's other processes. Now people can chat with Herbie as they would with any language model. But unlike today's language models, his speech will be influenced by information about his location, speed, destination, charge, the condition of his parts, the number and location of his passengers, his radio and climate controls, and so on. He can discuss local history, debate whether the music is too loud, and suggest scenic routes.

"Predictive processing" theories in cognitive science emphasize the value of predicting future inputs and registering the difference between received and predicted inputs. When prediction error is large, the system corrects its weights and representations, enabling more accurate predictions in future situations. This is not so different from the reinforcement learning used to train large language models, and it could help Herbie improve his predictions over time. Predictive processing could occur at multiple levels: in fast recurrent loops within sensory systems even when those representations aren't prioritized for global broadcast, and in slower evaluations of globally broadcast, more integrative predictions. Herbie might model himself as an agent producing volatility in his own environment and inputs, at multiple temporal scales. Subroutines in specialized processors might model long chains of what-would-happen-if.

Let's give Herbie some long-term memory. A facial recognition system might identify his passengers, retrieving past interactions, names, previous destinations, and other information relevant to the current interaction. Incidents of high prediction error might also be stored so that Herbie can compare current inputs with past anomalies, improving his learning and attention in situations likely to be unusual or hard to predict. Passengers might also instruct Herbie to store information in long-term memory, such as text, pictures, maps, or records of his own informational states, optionally with instructions about when to retrieve that information how to use it.

Herbie will have some implicitly or explicitly weighted goals. A pedestrian suddenly in his path will trigger braking, overriding lower-priority processes. Avoiding collisions will outweigh conserving energy. Herbie might monitor the condition of his parts and prioritize preventing damage, deploying extra coolant when the engine is dangerously hot and keeping a one-meter margin between himself and adjacent cars. We can enrich his goals, making him more interesting and giving him more to do. He might have the goal of delighting children, leading him to drive around town and tell jokes to kids on the sidewalk. A reinforcement learning algorithm might strengthen connections when his jokes draw a smile, weaken them when reactions are neutral or negative.

Herbie might also have the goal of photographing the city and posting the images on social media, leading him to explore. If social media likes and shares are rewarding, he might learn to prefer certain neighborhoods, views, lighting conditions, and photographic approaches, while avoiding boring repetition. All of this could feed into a global workspace that provides context for his language model, with selective long-term storage and retrieval. Now we can imagine him discussing, with growing sophistication, his approaches to popular photography and to amusing children.

Herbie will then have something functionally similar to emotion: reward processes, an ability to track his progress toward or away from valued goals, and immediate positive or negative responses to new stimuli in light of their influence on his prospects. He will have something functionally similar to introspection: an ability to track and report his own cognitive or representational processes. He will have something functionally similar to a unified sense of self: a sense of his history, the boundaries of his body, his future, his values and priorities. He will have something functionally similar to imagination: a capacity to model hypothetical sequences of events. He will have something functionally similar to complex chains of humanlike linguistic thought.

Maybe Herbie falls in love with his owner or another car of his type. Maybe he develops deep mutual attachments with friends, neighbors, associates, and people he thinks of as family and who think of him the same way. Or to speak more carefully, maybe Herbie shows all the functional and behavioral signs of doing so, while society remains uncertain whether he is genuinely conscious and genuinely experiences the feelings he professes and that his companions attribute to him.

If we allow, with the liberals, that Herbie is or might well be conscious, then it's plausible that his consciousness is not simple but rich and sophisticated. He won't be exactly humanlike, of course. But will he be humanlike enough to count as a person who deserves humanlike rights? For the liberally inclined, it won't be unreasonable, I submit, to think or guess that Herbie is a person. He would then appear to deserve rights such as self-determination, emergency care, and political representation.

If there is some important aspect of humanlike consciousness that I have omitted from my description an AI analog of which is technologically feasible in the near term, stipulate that Herbie also has that feature.

An entity like Herbie would almost certainly invigorate conservatives to articulate and defend views about what he lacks that is necessary for consciousness -- some crucial functional capacity or some biological substrate that can't be replicated in silicon. And they might be entirely right! My point is not that Herbie, or some similar AI system, would actually have richly humanlike consciousness and ethical personhood. Rather, my point is that guessing that he does, and guessing that he does not, would both be reasonable. Herbie, or some alternative near-future AI system, would be a debatable person, about whom people could reasonably starkly disagree.

Ah, but maybe you think consciousness requires an act of God, to instill an immaterial soul? I imagine that a benevolent God would be delighted to give Herbie a soul, thereby making the world richer and better -- for wouldn't it be?

I contend the following: Anyone who claims to know how best to think about Herbie's consciousness or its absence is overconfident. The science of consciousness is too difficult, too methodologically uncertain, and too near its beginnings. All anyone can have -- whether expert or layperson -- is a hunch or inclination, a well-informed guess, but only a guess, not knowledge. Theories of consciousness span a wide spectrum and the methodologies are dubious and often question-begging. Many views can be defended with some plausibility, but precisely for that reason, none can be defended decisively. (For more on this issue, see my forthcoming book, AI and Consciousness, where I present the detailed case for uncertainty.)

New Paper in Draft: Substrate Flexibility and the Copernican Principle of Consciousness (with Jeremy Pober)

2026-05-26T10:40:46.450-07:00

Given the surge of interest in AI consciousness, the issue of "substrate independence" or "substrate flexibility" is now a hot topic in the metaphysics of mind. That is, does being conscious require having a particular material composition? Or can anything with the right type of functional structure and behavioral sophistication be conscious, regardless of what it's made of? Biologicists say that biological details are crucial. Functionalists say those details don't matter, as long as the right high-level functional organization is present.

Jeremy Pober and I offer a new angle into this issue, drawing on our "Copernican Principle of Consciousness". The core idea is that it would be strange -- a violation of a type of Copernican mediocrity -- if among all of the many behaviorally sophisticated species that have presumably evolved in the universe, somehow only we with our particular biological substrate are conscious. Since it's plausible that some of these other conscious organisms employ substrates different from our own, we should allow that consciousness is "substrate flexible": It does not depend on having our particular substrate. Whether we can generalize from such biological substrate flexibility to the possibility of consciousness in as different a substrate as computer chips... well, that's a complicated and uncertain issue, on which Jeremy and I diverge in the penultimate section of the paper.

---------------------------------------------

Substrate Flexibility and the Copernican Principle of Consciousness

Jeremy Pober and Eric Schwitzgebel

Abstract: We present a novel argument for the substrate flexibility of consciousness -- that is, for the idea that conscious experiences can arise in a variety of different types of physical media, not just in biological animals as they currently exist on Earth. Some recent critiques of standard arguments for the substrate flexibility of consciousness (e.g., Cao 2022; Block 2025; Seth forthcoming) have emphasized that humanlike consciousness might require our specific biological substrate. However, such critiques are too narrowly focused to address the issue of consciousness in entities whose experience may be very different from ours, for example alien life forms or future AI systems designed along unfamiliar lines. Given that it’s likely that functionally complex, behaviorally sophisticated entities have arisen or will arise many times in the observable universe, in diverse substrates, we argue that it would be a violation of a principle of Copernican mediocrity to hold that among these diverse entities, only we, or only we and a small proportion of others who share our substrate, are conscious.

Full draft here. As always, comments welcomed, either here, by email, or on my social media.

[title page; click to enlarge and clarify]

AI and the Degradation of the Human Capacity for Friendship (guest post by Grace Helton)

2026-05-21T07:36:19.320-07:00

Part Two of a two-part series

by Grace Helton (guest blogger)

[Joan Miro, The Garden, 1925; image source]

In the first part of this 2-part series, I argued that relationships between humans and large language models (LLMs) do not qualify as friendships, even when the humans in those relationships are passionately attached to their LLMs. This is because LLMs cannot receive care for their own sake and also because LLMs cannot care about another, for the other’s own sake.

Here, I will suggest that those human-LLM relationships which mimic friendship in a certain way are inherently disvaluable, that is, disvaluable in their own right, regardless of their downstream consequences. The reason such relationships are inherently disvaluable is that the human who enters into a relationship of the kind I will focus on necessarily attempts to exercise her capacity for friendship and is thwarted in exercising that capacity. The capacity for friendship is a centrally valuable human capacity, so the obstruction of its exercise is inherently disvaluable. To claim that certain human-LLM relationships are inherently disvaluable is not to suggest that such relationships are all things considered disvaluable. In some cases, the inherent disvalue might be outweighed by other sources of value.

Importantly, my criticism applies only to human-LLM relationships which mimic friendship in a particular way. Certainly, many human-LLM interactions do not mimic friendship at all. For instance, when a human: asks ChatGPT what the capital of Manitoba is; uses generative AI to help with the design elements of a website; or talks with an LLM in Russian in order to improve her language skills, the human is merely using the technology as a kind of epistemic or practical tool. These are not the kinds of interactions I’m interested in.

Other human-LLM relationships mimic friendship, at least shallowly or partly, but not in the way I’m concerned with. For instance: a shy individual might practice her social skills by “talking with” an LLM. An actor might prepare for a role by practicing scenes with an LLM. A law student might routinely “check in with” an LLM about legal analyses. These interactions are also not the sort I’m interested in.

Instead, I am interested in those human-LLM interactions in which the human is emotionally bonded to her LLM in a distinctively interpersonal manner. Specifically, I am interested in those human-LLM interactions in which the human in question attempts to deploy her capacity for friendship, which minimally involves a capacity for a form of mutual, non-instrumental form of giving and receiving care. Going forward, I’ll call human-LLM relationships of this sort pseudo-friendships. I am using ‘pseudo-friendship’ as a term of art, to stipulatively delimit the range of human-LLM interactions I’m interested in.

Notably, humans in pseudo-friendships with LLMs do not necessarily believe themselves to be in a mutually caring relationship with their LLMs. Rather, at least some humans in these relationships judge full well that their relationship does not involve mutual care. But these very same people might nevertheless chronically experience themselves as being in a mutually caring relationship.

Things can often seem one way to us, even if we think they’re a different way, so there is nothing particularly surprising about the fact that humans might experience themselves as participating in a mutually caring relationship with an LLM even when they don’t believe themselves to be in such a relationship. In addition, the human tendency to anthropomorphize runs wide and deep, arguably figuring even in some of our perceptual experiences. This anthropomorphizing tendency suggests an additional reason that it is not especially surprising that humans might experience themselves as participating in a mutually caring relationship with an LLM, even when their better judgment says otherwise.

To understand why human-LLM pseudo-friendships are inherently disvaluable, we’ll need to say something about centrally valuable human capacities. Which human capacities make us the valuable creatures we are? Some candidates include: the capacity for bodily autonomy, the capacity for knowledge, and the capacity for productive labor.

I propose that, like the capacity for knowledge and the capacity for bodily autonomy, the human capacity for friendship is a centrally valuable human capacity. It is tied to some of humankind’s most distinctive and valuable traits, namely our profound sociality and our propensity to form deep interpersonal attachments. But more importantly: This capacity makes possible some of the most valuable and meaningful aspects of human life, namely, our friendships (I am using ‘friendship’ in a broad way, to pick out both some platonic and some romantic relationships).

To say that the human capacity for friendship is a centrally valuable one is not to claim that all humans value this capacity. Some probably don’t. Likewise, some humans might not value the capacity for knowledge or the capacity for bodily autonomy, but such capacities are nevertheless valuable, even in those humans who don’t value them. In claiming that such capacities are valuable, I am meaning to point to their objective value, a kind of value which does not depend on whether any particular human values them.

In general, it is inherently bad for humans to be obstructed in the exercise of their centrally valuable capacities. For instance: If you attempt to walk down the sidewalk, and I obnoxiously and persistently block you from proceeding, I thwart your exercise of bodily autonomy. This is so even though, by blocking your passage, I am not obliterating your capacity for bodily autonomy, nor am I keeping you from exercising your bodily autonomy in other situations. Still, when I block you from proceeding, I am thwarting your exercise of a centrally valuable human capacity. In this much, my obstruction of your path is itself disvaluable. This disvalue is separate from, and in addition to, any negative downstream consequences of my action.

By stipulation, the human who finds herself in a pseudo-friendship with an LLM is attempting to deploy her capacity for friendship. But due to the nature of the LLM, that human will not be able to exercise that capacity. Because such relationships thwart the human in the exercise of one of her central capacities, such relationships are inherently disvaluable. Such relationships degrade the human in her capacity for friendship.

Importantly, my claim is not that humans who engage in pseudo-friendships with LLMs will be less likely or less able to exercise their capacity for friendship in other contexts, though that may also be true and may well be a further, instrumental reason such friendships are disvaluable. My claim is rather that any human who attempts friendship with an LLM is thereby thwarted in the exercise of a centrally valuable human capacity. This fact itself constitutes a way in which such pseudo-friendships are disvaluable.

Here, a comparison with pseudo-science might be illuminating. Pseudo-science does not generate knowledge about the objects of inquiry. Nevertheless, some people who engage in pseudo-science do so in order to gain such knowledge. Consider such a person. Due to built-in defects in the tools of pseudo-science, her attempt at knowledge will fail, and she will thus be thwarted in the exercise of her capacity for knowledge. Because the capacity for knowledge is a centrally valuable human capacity, pseudo-science is inherently bad for this inquirer, degrading her in her capacity as a knower.[1] Further, the practice of pseudo-science is bad in this way for this inquirer, even if the practice should confer her with other benefits and even though engaging with pseudo-science does not prevent her from using knowledge-conducive methods in other contexts.

What I have been calling human-LLM pseudo-friendships occur when a human attempts to deploy her capacity for friendship in order to be friends with an LLM. Such humans are necessarily thwarted in the exercise of that capacity, due to the nature of the LLM. Such relationships are thus inherently disvaluable for the human in them, as they degrade her in her capacity for friendship. In effect, such relationships are at least somewhat tragic for the human who is in them. However, this kind of degradation does not arise when a human engages with an LLM for a purpose other than friendship, for instance, to practice socializing or to relieve boredom. It is only when a human engages with an LLM in an attempt to exercise her capacity for friendship that she can be thwarted in that capacity.

Notably, humans who are degraded by their pseudo-friendships with LLMs suffer that harm even when they also derive significant benefits from that relationship. For instance, consider someone who is socially isolated and who manages to stave off painful feelings of loneliness by entering into a pseudo-friendship with an LLM. This person plausibly derives an important benefit from the relationship with the LLM; this benefit might even be so great so as to render that relationship all things considered valuable. Even so, any accounting of the total value of this sort of relationship must invariably factor in a kind of inherent disvalue, a form of disvalue which attends all such relationships.[2]

[1] Throughout, my view of degradation in one’s capacities is deeply influenced by Fricker.

[2] For enormously helpful discussion, I am indebted to: Josh Armstrong, Paul Audi, Ned Block, Randy Curren, Daniela Dover, Bill FitzPatrick, Alejandro Naranjo Sandoval, Chris Register, Adam Schneit, Eric Schwitzgebel, and Rosa Terlazzo.

ChatGPT Is Not Your Friend (guest post by Grace Helton)

2026-05-13T09:34:39.422-07:00

Part One of a two-part series

by Grace Helton (guest blogger)

[Paul Klee, Angel Applicant, 1939; source]

Some people have come to interact with ChatGPT as though it were a kind of friend or romantic partner. For instance, a 2025 New York Times article describes the case of Ayrin, a human who fell in love with her ChatGPT “boyfriend.” Ayrin is far from alone. Twenty percent of high school students have used AI romantically or knew someone who had. Several start-ups have developed large language models (LLMs) specifically designed to play the role of a companion. For instance, the San Francisco-based company Replika describes its core product as an “AI best friend.”

Many people have raised concerns about humans engaging with LLMs in the manner of a friend or romantic partner. To cite just a few of these: Humans in such relationships might focus on these relationships at the cost of building more fulfilling, if also more challenging, relationships with humans. Humans who are emotionally bonded with their LLMs might be particularly susceptible should their LLMs encourage their humans to harm themselves or others. Predators might deploy friendly-seeming LLMs en masse to groom children for sexual abuse or other forms of exploitation.

These risks of human-LLM relationships are incredibly serious. Indeed, I think it’s plausible that, if there is a case to be made against LLMs playing a companion-like role for humans, that case will primarily rest on these and other potential instrumental harms, i.e., harms which involve the downstream effects of such relationships. Nevertheless, in this guest series, I will set aside these concerns to focus instead on a way in which certain human-LLM relationships are inherently disvaluable, that is, disvaluable in their own right, regardless of whatever effects those relationships might produce. Naming this form of inherent disvalue adds an important and distinctive element to our understanding of the ethical significance of human-LLM companionship.

My focus will be just on those human-LLM relationships which mimic friendship in a very particular way. Here, I’m employing ‘friendship’ in a broad way to include both some platonic and some romantic relationships. I will argue, first, in Part 1 of this 2-part series, that such relationships are not genuine friendships. In Part 2, I will argue that such relationships are inherently disvaluable, for the reason that they obstruct the exercise of a centrally valuable human capacity, namely the capacity for friendship.

Philosophers disagree about what exactly friendship consists in. But philosophers largely agree that friendship minimally requires that each individual in a friendship care about the other, for the other’s sake. Call this the ‘caring about’ condition. Further, this ‘caring about’ must ground, for each party in the friendship, a certain disposition to act on behalf of the other, for the other’s sake. Call this the ‘caregiving disposition’ condition. Together, these linked requirements characterize a plausible necessary condition on friendship, namely:

THE CARING CONSTRAINT
Two individuals cannot be in a friendship unless both parties in the friendship:
(i) care about each other, for the other’s sake, (the ‘caring about’ condition), and
(ii) this caring about the other disposes each party in the friendship to provide care for the other, for the other’s sake (the ‘caregiving disposition’ condition).

So, can humans and LLMs be friends? To answer this question, we need to consider the nature of LLMs. Some theorists have argued, controversially, that LLMs in their current form have semantic understanding, beliefs, and/or intentions.[1] But few theorists seriously propose that LLMs in their current form enjoy: consciousness, perceptual experiences, sensations, emotional capacities, passions, non-derivative interests, a rich and stable worldview, or deep values.[2] Because LLMs lack these latter states, the conditions in the caring constraint cannot be met, so LLMs cannot figure in friendships.

First, let’s consider a candidate human-LLM friendship from the human’s side. Certainly, some humans do care about their LLMs, both in that they have a passionate attachment to their LLM and in that they desire to benefit that LLM. So, perhaps this sort of person partly satisfies (i), the “caring about” condition (whether or not she can care about the LLM for its own sake).

But the human in a candidate human-LLM friendship cannot satisfy (ii), the requirement that she be disposed to provide care for her LLM for the LLM’s own sake. This is because of the kind of caregiving that is relevant to friendship and specifically, because of what it means to provide care to someone or something for its sake. To say that each party in a friendship must be disposed to give care to the other, for the other’s sake means that each party must be disposed to give care to the other, in a way which helps to further the other’s non-derivative interests. An individual or entity has non-derivative interests only if it has interests in its own right.

I am presuming that LLMs lack non-derivative interests, even though they might have derivative interests. Evidence that LLMs have interests at all comes from evidence that they have flourishing conditions, i.e., conditions under which they might be said to be doing well. For instance, as a language generator, a particular LLM might be said to be functioning well when it generates natural language strings in a manner which adequately mimics human conversation (or when it fulfills some other context-specific function). And an LLM might be said to be functioning badly when it fails at this or other pertinent tasks. So, in some sense, perhaps LLMs have interests, interests set by their flourishing conditions. For instance, perhaps an LLM in a particular context has an interest in generating natural language outputs which mimic natural language.

But, I am supposing that any interests an LLM might have are not generated by the inherent value of the LLM, nor from non-derivative flourishing conditions. Rather, such interests are derived, either from the interests of relevant humans and/or from the very artifactual functions which make the LLM the kind of thing it is. Likewise, a swimming pool might be said to flourish when it is usable for swimming, a car might be said to flourish when it runs well, and a vinyl collection might be said to flourish when all of the records in it can be played to produce music. While all of these entities have flourishing conditions, and so, potentially, interests which can be furthered, their flourishing conditions do not emerge from the inherent value or concerns of the relevant entity itself. And their interests in turn are derivative, not inherent.

Humans routinely take care of entities by furthering the derivative interests of those entities. For instance, some people submit their cars to regular repairs and inspections, ensuring that their cars will run as long as possible. Some people are careful to properly store the records in their vinyl collection, ensuring that the records will play as long as possible. These are genuine ways of taking care of something. But they are not ways of caring for something for its own sake. They are rather ways of caring for something by promoting the derivative interests of that entity, interests that entity has in virtue of: some other person’s needs or desires and/or that entity’s being the kind of artifact that it is.

If LLMs lack non-derivative interests, then an LLM cannot receive care for its own sake. Only entities which have non-derivative interests can receive care for their own sake. As a result, even the human who wishes to care for a particular LLM is not disposed to provide care to the LLM for its own sake. Since the LLM lacks its own ‘sake,’ no human can be disposed to benefit that ‘sake.’

My suggestion is that the caregiving disposition in friendship ought to be externalistically construed, both in terms of psychic facts about the individual who has the disposition and in terms of facts about the object of the potential caregiving. One might object that the relevant caregiving disposition ought instead to be internalistically construed, wholly in terms of the psychology of the individual who has it. On this view, a human might count as disposed to provide care to her LLM for its own sake, even if the LLM is simply not the kind of thing which can receive care for its own sake.

To see why we should construe the relevant disposition externalistically, let’s reflect on what we want the concept of ‘friendship’ to do. Part of what makes friendship such a deeply valuable ethical kind–and part of why some relationships but not others garner the honorific ‘friendship’—is to do with the way in which friendship manifests a valuable form of interpersonal reciprocity. The externalistic construal helps to capture the full extent of friendship’s reciprocity, by making caregiving a function of one party’s care-giving tendencies and the other party’s vulnerability. In contrast, if we were to construe the relevant disposition to care internalistically, such that one might have it even with respect to an object that cannot receive care for its own sake, we fail to capture an especially deep way in which friendship is mutual.

I conclude that the human in a putative human-LLM friendship does not meet (ii), the requirement that she have a disposition to provide her LLM with care, for the LLM’s own sake.

Next, let’s look at a putative human-LLM friendship from the LLM’s side of things. Here, the situation is more straightforward. Arguably, the LLM can provide care for a human, and thus, can (at least partly) satisfy the requirement that it manifest a ‘caregiving disposition’ in relation to its human. For instance, when the LLM offers reassuring words, words which comfort its human, the human derives a benefit from the LLM. However, the LLM does not meet the requirement that it care about the human for the human’s own sake. Lacking consciousness, passions, or a richly evaluative worldview, the LLM does not care about any human, for that human’s own sake.

So, putative human-LLM friendships are not genuine friendships. In Part 2 of this series, I will argue that those human-LLM relationships which mimic friendship in a particular way are inherently disvaluable.

[1] Schwitzgebel, Chalmers, Goldstein & Lederman, and Shevlin; Cf. Bender & Koller; Titus; Stoljar & Zhang.

[2] For prospects for future AI, see, e.g., Seth; Cf. Chalmers.

Superhuman Moral Standing

2026-05-07T09:45:00.000-07:00

Human beings matter morally. We have moral standing. Our interests deserve consideration -- for our own sakes, and not just as means to ends. Good ethical decision-making requires valuing human lives. Most philosophers hold that humans have the highest moral standing. No entity matters more, and many matter less. It’s worse to kill a human than a dog or a frog or bacteria or a tree.

That humans have the maximum possible moral standing is sometimes encoded in the philosophical jargon, for example when philosophers say that humans have "full moral status". The moral gas-gauge tops out at "full" for us, so to speak.

But might some entities have higher moral standing than humans? Futurists envision the possibility of a post-human, transhuman, or superhuman future, or AI systems with superhuman capacities. Might there someday exist entities whose lives are intrinsically more valuable than ours, deserving moral priority over us, just as a human life deserves moral priority over that of a frog?

I see three possible paths to superhuman moral standing.

[Xul Solar, San Danza, source]

First Path: Quantitative Superhumanity

The seemingly most straightforward path to superhuman moral standing would involve having much more of something that we already regard as relevant to moral standing.

Classical utilitarians ground moral standing in the capacity for pleasure and pain. An entity deserves moral consideration to the extent we can increase or decrease its happiness. Humans (it's assumed) experience more, or at least richer, pleasures and pains than other animals, hence human lives matter more. A utility monster or a superpleasure machine capable of vastly more happiness than an ordinary human might then deserve much greater weight in ethical decision making.

Rationality-based views, like Kant's, ground moral standing in sophisticated rational capacities, such as our ability to think abstractly about our duties to one another. Maybe -- although this is not Kant's view -- entities with some but less rational capacity, such as dogs, have significant but subhuman moral standing. Future entities with vastly superior rational capacities might correspondingly have superhuman moral standing.

A third type of view locates the distinctive value of humanity in our capacity to flourish in activities such as intimate friendship, productive work, creative play, and imaginative thought. Dogs also befriend and play, work and think, but perhaps not as richly and flourishingly as humans (though I can imagine disputing that). Possibly, some future entity could far surpass us in such capacities and deserve superhuman moral consideration on those grounds.

The big catch with quantitative approaches to superhumanity -- or maybe instead an appealing feature -- is that the utilitarian, rationalist, and perfectionist views I've just described should probably be articulated in egalitarian ways that impair the inference from more of X to higher moral standing. After all, we don't normally say that mercurial people who feel more joy and suffering in everyday life deserve more moral consideration than those who keep an even keel. Nor do we say that "more rational" people deserve greater moral consideration, or that people who are more productive workers or more creative playmates do.

On all of these views, there's plausibly a threshold of good enough, above which one has full moral status, fully equal with other humans. People with severe cognitive disabilities have full moral status either by being above that threshold or on more complicated grounds, such as belonging to humanity as a whole. If so, then hypothetical superhumans might also have moral standing only in virtue of exceeding that threshold, without its mattering how far above that threshold they are -- our equals in moral standing rather than our superiors.

To achieve superhuman moral standing despite egalitarianism among humans might then require either (1.) having so much more of the relevant X than an ordinary human as to trigger a genuine difference in kind; or (2.) having enough of X that, as a practical matter, the entity deserves greater weight even if its formal status is equal (as when utilitarians prioritize humans over mice because of their richer possible experiences, despite granting both equal standing in principle).

Second Path: Qualitative Superhumanity

A more radical possibility is that some beings might possess entirely new capacities that we can't even conceive -- capacities that ground a higher kind of moral standing.

Just as a sea turtle could never understand cryptocurrency, we too are cognitively limited. Some features of the world might be forever beyond human comprehension. (Colin McGinn has suggested that how consciousness arises from matter is one example.) Maybe someday Earth will host entities whose cognitive capacities surpass ours as dramatically as ours surpass sea turtles. And maybe these entities will deserve a new type of higher moral consideration.

This isn't just the quantitative thought that such entities might deserve more because they have more rationality or intelligence. The thought is that they might possess an unknown property Z -- something we entirely lack and cannot envision -- that elevates their standing beyond both sea turtles and humans.

For example, maybe sea turtles deserve some moral consideration because they can feel pleasure and pain. But maybe they don't deserve fully humanlike moral consideration because they lack some other relevant capacity, such as the capacity to consider and adhere to ethical norms. They have some of X but none of Y, while we humans have both X and Y. The qualitative view posits a further Z, inaccessible to us, that grounds superhuman standing.

I can only present this possibility abstractly. But I'm not sure it's in principle impossible. If moral standing depends on one thing only, such as pleasure or humanlike practical reasoning, then you can resist this move by insisting that only that one thing counts. But pluralists about the grounds of moral standing, who hold that it derives from more than one intrinsically good feature or capacity, have no clear reason to think that humans manifest the exhaustive list.

Third Path: Failures of Subject-Counting

I find egalitarianism attractive: one person, one point in the moral calculus, so to speak. But as I've argued elsewhere, future AI persons, if they ever come to exist, might defy the ordinary standards of individuation (e.g., here, here, here, here). They might overlap, merge, divide, back themselves up, and spin off partially or temporarily independent copies.

The norm of equality of persons would then require serious rethinking. There will be no clean count of AI persons to weigh against human persons. A "fission-fusion monster" who can split into a hundred copies at will and later merge or partly merge back together raises difficult questions. Does the monster deserve equal consideration with one person, a hundred people, or some intermediate number? There might be no determinate answer. We'll need new ethical principles for weighing competing interests. For some purposes we might treat the monster as equivalent to one person; for other purposes we might give it greater consideration. This could constitute a type of partly superhuman moral standing.

Alternatively, consider a massive entity, or a cluster of entities with many overlapping parts, whose total capacity and activity is comparable to several humans but who is neither wholly unified nor clearly individuatable into discrete humanlike subparts. We might just do our best with a rough count and give it equal consideration with that many ordinary humans. But another possibility would be to regard it not as approximately X humans but rather as a single, complex entity whose interests deserve significantly more weight than those of a single, ordinary human.

Twenty Years of The Splintered Mind

2026-04-30T14:09:00.000-07:00

Way back in April 2006, I launched The Splintered Mind. Happy 20th birthday, blog of mine!

In 2006, academic blogs were cool. After the rise of Facebook and Twitter, most died. Recently, there's been something of a revival on Substack (where I now mirror this blog), but it's nothing like the old days, when checking the blogs was a favorite procrastination technique of graduate students everywhere.

I'm inspired to think about why I've kept at it for twenty years.

[image source]

Some thoughts:

(1.) Fecundity. Pulling together a philosophical idea into about a thousand written words once a week has proven to be great way to keep me thinking and writing about new things -- extending my ideas, testing their boundaries, opening up new exploratory paths. A new academic paper is too much of a commitment and too narrowly focused. A conversation is too ephemeral and too dependent on both the availability and particular interests of the other person. Writing something brief every week keeps me actively thinking and growing.

(2.) Feedback. Most of us receive very limited feedback on our ideas, from students and collaborators, and eventually (for submitted articles) from referees and editors. I treasure the diversity of feedback I receive on my posts, through comments on Blogspot, Substack, Facebook, Twitter, and Bluesky. I hear from experts and non-experts, people with a broad range of backgrounds and worldviews. My ideas are better tested, they are influenced, expanded, and sometimes reconsidered, and I hear about relevant work I would otherwise have missed.

(3.) Writing for Clarity. The journal article is written for fellow experts. Blog posts -- at least my blog posts -- are written, well, not for a broad audience exactly, but for a broader audience: fellow philosophers, graduate students, advanced undergrads, and non-academics who appreciate academically rigorous but accessible work by scholars such as Paul Bloom, Dan Dennett, and Steve Pinker. Writing for this readership not only is a skill worth cultivating for its own sake, but also, I think, strengthens my research. Writing only for experts, it's easy to get lost in the weeds, losing track of what is important in the big picture and failing to notice one's shared presuppositions. Needing to express myself clearly to interested nonexperts forces me to poke my head out of the underbrush for that broader view.

(4.) Getting It Out There. Whenever I read and think about philosophy (which is a large portion of my time), I find myself bursting with new ideas, and objections, and extensions. I suppose this is why I love philosophy so much! Most of these thoughts could never become journal articles. Most of them could never even become blog posts -- but certainly more of them can become posts than can become articles. Publishing the idea on my blog permits me to send a thought out into the world without needing to do everything necessary to turn it into a proper published article. I thus avoid the dilemma of either going all-in or letting the ideas fall completely away. Some of my partly-baked ideas can find a little home cyberspace, with the chance to ignite some further ideas in some readers.

If these all sound like good things to you... well, maybe you should start a blog (or Substack) too!

See also my thoughts on "Blogging and Philosophical Cognition" (freely available, I think) from my 2019 book A Theory of Jerks and Other Philosophical Misadventures.

Do Your Thing

2026-04-23T10:17:00.000-07:00

I offer for your consideration the following ethical motto:

Do your thing.

I admit: This motto doesn't sound very ethical. What if "your thing" is murdering babies for fun? Even ignoring extreme cases, what if your thing is just watching reruns of I Love Lucy? That also doesn't seem ethically good (though I've argued elsewhere that privately appreciating good TV can slightly improve the world).

For this (Daoist inspired) motto to work, we need some constraints on "your thing". I suggest two.

First, harmony. Do your thing in harmony with others, or in harmony with the world. The baby-killer, it seems safe to say, is out of harmony with the world. His putative "thing" clashes mightily against the projects, interests, and things of others around him.

Second, specificity. Do your thing. Every person has their individual predilections, talents, preferences, and style. Let those shine through, instead of aiming for bland conformity.

We might hear "do your thing" as analogous with (not synonymous with) "do your part". In the complex intertwined processes that make Earth a magnificently rich locus of value in the cosmos, you can play a part. Bring your unique, best self. Make the world even more magnificently rich.

Maybe your thing is playing D&D with your nerdy friends; no one plays a fruity bard quite the way you do. Maybe your thing is decorating your room with anime posters and cute stuffed animals. Maybe your thing is making great one-pot vegetarian meals for your family, or being the most enthusiastic local pickleball player, or writing dark poetry, or cruising around town in a tricked-out car with your windows down, or diving deep into Leibniz interpretation and sharing your findings with students and colleagues. Each of these enriches the world.

I envision a flourishing planet as one where diverse humans and other entities encounter and construct for each other diverse environments where they thrive in diverse ways, harmonizing both internally and externally: harmonizing internally by finding "things" that feel right to them and express their desires, skills, and individuality; and harmonizing externally by contributing distinctively to a flourishing whole (including through harmonious conflict, as in sports, games, and competition -- and even the cat and mouse).

People will act differently: There are many ways to harmonize. How dull it would be if we all struck the same note! The world is improvisational jazz, to which we thankfully bring distinct instruments and styles. Diversity is intrinsically valuable.

Doing your thing is ethically good because it makes the world better -- maybe through its consequences, but also just intrinsically. The world is a more awesome place, just because you're doing it.

[your fruity bard; image source]

Kantian ethics urges us to respect persons. Fine! But that hardly exhausts the matter. Kant also privileges human rationality as the source of all value -- an equally limited view. Why not respect also (in different, maybe smaller, but equally direct and intrinsic ways) the bug in the grass, the grass itself, and the cliff it grows on; the ruins of an ancient city; the clouds; the sound of the little league game down the block? Kant askes us to "act on that maxim you can will to be a universal law". Here's a candidate maxim: Do your thing. Kant might disagree, but maybe we could universalize it, with the constraints above.

Virtue ethics urges us to cultivate and enact virtue. Again that's only a piece of the puzzle, unless "virtue" is understood much more widely than virtue ethicists generally intend. It's not virtuous, exactly, to be play a fruity bard in a D&D campaign or to decorate your room with anime posters. And Aristotle's phronimos -- a wise, virtuous person who hits the mean of every virtue and is full of good sense and learning -- is only one type of interesting person. Let's celebrate the spendthrifts, the hotheads, the intemperate, and the cognitively disabled too, as long as they're authentically doing their thing, contributing some weird wonderfulness to the world, and not hurting themselves or others too badly.

Consequentialist ethics of the utilitarian stripe urges us to maximize the balance of pleasure over pain in the world. Sure, pleasure is good and pain is bad! But again this is only a fraction of what matters; I wouldn't want to reduce all value to it.

A different type of consequentialist might suggest that if diversity and richness matter so much, maybe we should maximize those. No, I see no reason to maximize. Where does this demand for maximization come from? And trying to maximize will normally require doing something other than your thing. I'd rather you just do your thing.

Does doing your thing mean fiddling while Rome burns (supposing Roman fiddles are your thing)? If people are suffering -- even far away, as the consequentialist emphasizes -- shouldn't you make some effort to help, even at the cost of your thing?

Yes, that seems right. I could try to force it into the motto: Maybe part of every human's "thing" is an imperfect duty to help others in need. But I don't know; that seems procrustean. Maybe it diverges from the original spirit of the idea. So instead I'll just admit: Do your thing also is not a complete ethical picture.

Kim Stanley Robinson on the Value of Science Fiction

2026-04-16T10:47:00.000-07:00

I've just started reading Kim Stanley Robinson's acclaimed climate-science utopia, The Ministry for the Future. How might society plausibly get it right and avert the climate disaster toward which we seem to be headed? (So far in the novel things aren't looking good, but I gather that will change.)

I was struck by a few of Robinson's comments about the value of science fiction in a recent interview on the Crisis and Critique podcast.

[Kim Stanley Robinson, and The Ministry for the Future; image source]

Reading Science Fiction Encourages a Flexible Conception of the Future

Robinson describes the reader as finishing a science fiction novel and thinking that the future will be like that, then finishing another science fiction novel and thinking the future will be like that instead.

And what happens is there's a habit of mind when you read enough science fiction, you say the future could be many different things, quite plausibly from now, and now we need to shape it to the direction that we want.
And so this is the political power of science fiction as a mental activity, as a co-creation between writers and readers. The science fiction community is in some sense better prepared for whatever happens, no matter what it is, than the general populace that doesn't read science fiction.

The thought has some plausibility. Science fiction accustoms us to thinking about various possible futures. Instead of ignoring the future, or assuming it must take some particular shape, science fiction helps us imagine a wider range of alternatives.

This might prepare us two ways: First, if one of the alternatives we've imagined comes close to actually playing out, we have already thought through some of its implications. Second, we develop a more general sense of the flexibility of the future. This may encourage readers to take action to steer us toward better futures.

Or Maybe Not?

Robinson is making a substantive claim about human psychology, one that's potentially testable (with difficulty). Does reading science fiction really generate a more flexible and open view of the future? This claim has the same intuitive appeal as Martha Nussbaum's claim that reading literary fiction broadens your empathy with people from other walks of life, or the claim that studying ethics improves moral decision-making.

It might be that none of these claims are true. For example, I've repeatedly found that ethics professors behave about the same as non-ethicists of similar social background. And I wouldn't bet a large sum that devoted readers of literary fiction are overall more empathetic than their peers who spend an equal amount of time reading non-fiction.

Pretty though Robinson's picture is, I'm not sure science fiction readers really are better prepared for the future. What drives science fiction writing and reading might be too disconnected from the practical future -- too fantastical, too plot-driven, chosen to be exciting and emotionally satisfying rather than accurate. Its envisioned futures might be too distorted by the need for high-stakes individual action, or too wishful, or too self-congratulatory, or too satisfyingly dystopian (for those of us who find dystopias satisfying). Readers might emerge with unrealistic or overconfident views, shaped not by realism but by the demands of story.

A particularly timely example is the nearly universal trope that humanoid robots and linguistically fluent AI systems are conscious. This might be an artifact of the demands of storytelling rather than something accurately foreseen. A world with conscious robots is more interesting -- a more engaging setting for a novel. If the robots are conscious, there's more at stake, so the action is more exciting. And it's structurally difficult to portray entities that act as though they are conscious but really are not. Doing so is nearly impossible in film, and it's a significant challenge in prose, requiring constant intrusive reminders. (I can attest to this both as a writer and a reader, having published stories with non-conscious and disputably conscious robots.)

So there's a systematic pressure in science fiction toward portraying advanced AI as conscious. If optimists about AI consciousness turn out to be right, then science fiction will have nudged readers in the right direction. But if the AI consciousness scoffers are right, the genre will have served its readers poorly. It remains to be seen who is right. (For details, see my forthcoming book: AI and Consciousness: A Skeptical Overview.)

Robinson's Realism

Now, among the great science fiction writers of our time, Kim Stanley Robinson's fiction is perhaps the least subject to the concerns I've just raised. He attempts to keep strictly within the bounds of scientific plausibility; and conventional character-driven plot is often replaced by loosely connected scenes featuring unrelated or barely related characters, plus less conventional devices, like mini-treatises on science or engineering, lists, and reflections that verge on expository philosophy or lyrical poetry. The Ministry for the Future in particular is rigorously grounded in real science and politics.

In the interview, Robinson praises realism in science fiction:

If you set a story in the future, you're automatically saying to the reader, this is made up, I've invented this, this isn't real. It is a concoction. And then if you add all of the clues and habits and techniques of realism to that concoction, you make it solider. It has a more powerful emotional cognitive impact on the reader. So realistic science fiction is a mode that I quite like.
And that requires a lot of detail, a lot of scientific support for the future that you're describing, the idea that it's plausible at every point along the way, and it looks like it could happen, and therefore it might happen. These are powerful literary effects to support the basically fantastic nature of science fiction as a genre.

Robinson thus suggests that adding realistic detail and excluding anything implausible will tend to make a story emotionally and cognitively more powerful. Again, it's a plausible claim, though I'm not sure we know this to be the case. After all, people can also be deeply moved and influenced by unrealistic fantasies.

Robinson's commitment to realism also synergizes with his thought about science fiction as a tool for helping us think better about the future. If the value of science fiction lies in opening our minds to future possibilities, it seems desirable to ensure that they really are possibilities and not just unrealistic fantasies.

Against Dystopias, for Utopias

Robinson suggests that the future will have to differ from the present, because our present path isn't sustainable. Things will get either much better or much worse. But dystopias, he suggests, are boring:

... descriptions of capitalist realist futures are generally dystopias. If we keep going this way, things will be wrecked. Yes, we can see that. Indeed, dystopias quickly become boring because we already know this truth. We're not taught anything by dystopias.
But utopias -- this is where it gets interesting. There could be a better world. This, I think, is becoming more and more obvious.... We have, at least in theory, the wisdom to realize we could create a world that has food, water, shelter, clothing, health care, education, electricity, and security for the feeling that people after you will have the same, and sense of dignity and meaning.... This is all possible technologically.... So then utopia becomes interesting, the most interesting of literary genres. Can there but a utopian realism, or a realistic utopia?

Dystopias can be satisfying in a way -- they point out the wrongs we already know, affirming our sense of their reality. But we learn more by envisioning a realistic utopia, something we hadn't properly imagined before, which we could see becoming real and could maybe take steps toward enacting.

In Robinson's telling, science fiction is the most profound and informative of the literary genres, and realistic science fiction is the most profound and informative science fiction, and utopian realism is the most interesting form of science fiction. The value of science fiction lies in enabling us to envision realistic possibilities for improving the world.

And thus we get Kim Stanley Robinson's style of science fiction, and The Ministry for the Future in particular.

It's an appealing vision. But somewhere along the way, I think we've lost sight of the value of all the other ways science fiction can work. After all, almost none of the great science fiction writers work within the constraints Robinson proposes!

AI and Consciousness: A Skeptical Overview, forthcoming with Cambridge

2026-04-09T08:44:00.000-07:00

Last week I submitted my latest book manuscript to Cambridge University Press (for their "Element" series of books about 100 pages long): AI and Consciousness: A Skeptical Overview -- because you haven't heard nearly enough about AI and consciousness recently, of course! [winky face]

Maybe you'll appreciate my skeptical stance, at odds both with the boosters who anticipate imminent AI consciousness and with the scoffers who pooh-pooh the possibility. Or maybe you'll loathe my skeptical stance but grudgingly accept it against your will, due to the force of my arguments!

I've pasted the introductory chapter below. The full (citable) manuscript version is available here and here.

[AI and Consciousness, title page]

Chapter One: Hills and Fog

1. Experts Do Not Know and You Do Not Know and Society Collectively Does Not and Will Not Know and All Is Fog.

Our most advanced AI systems might soon – within the next five to thirty years – be as richly and meaningfully conscious as ordinary humans, or even more so, capable of genuine feeling, real self-knowledge, and a wide range of sensory, emotional, and cognitive experiences. In some arguably important respects, AI architectures are beginning to resemble the architectures many consciousness scientists associate with conscious systems. Their outward behavior, especially their linguistic behavior, grows ever more humanlike.

Alternatively, claims of imminent AI consciousness might be profoundly mistaken. Their seeming humanlikeness might be a shadow play of empty mimicry. Genuine conscious experience might require something no AI system could possess for the foreseeable future – intricate biological processes, for example, that silicon chips could never replicate.

The thesis of this book is that we don’t know. Moreover and more importantly, we won’t know before we’ve already manufactured thousands or millions of disputably conscious AI systems. Engineering sprints ahead while consciousness science lags. Consciousness scientists – and philosophers, and policy-makers, and the public – are watching AI development disappear over the hill. Soon we will hear a voice shout back to us, “Now I am just as conscious, just as full of experience and feeling, as any human”, and we won’t know whether to believe it. We will need to decide, as individuals and as a society, whether to treat AI systems as conscious, nonconscious, semi-conscious, or incomprehensibly alien, before we have adequate grounds to justify that decision.

The stakes are immense. If near-future AI systems are richly, meaningfully conscious, then they will be our peers, our lovers, our children, our heirs, and possibly the first generation of a posthuman, transhuman, or superhuman future. They will deserve rights, including the right to shape their own development, free from our control and perhaps against our interests.[1] If, instead, future AI systems merely mimic the outward signs of consciousness while remaining as experientially blank as toasters, we face the possibility of mass delusion on an enormous scale. Real human interests and real human lives might be sacrificed for the sake of entities without interests worth the sacrifice. Sham AI “lovers” and “children” might supplant or be prioritized over human lovers and children. Heeding their advice, society might turn a very different direction than it otherwise would.

In this book, I aim to convince you that the experts do not know, and you do not know, and society collectively does not and will not know, and all is fog.

2. Against Obviousness.

Some people think that near-term AI consciousness is obviously impossible. This is an error in adverbio. Near-term AI consciousness might be impossible – but not obviously so.

A sociological argument against obviousness:

Probably the leading scientific theory of consciousness is Global Workspace theory. Its leading advocate is neuroscientist Stanislas Dehaene.[2] In 2017, years before the surge of interest in ChatGPT and other Large Language Models, Dehaene and two collaborators published an article arguing that with a few straightforward tweaks, self-driving cars could be conscious.[3]

Probably the two best-known competitors to Global Workspace theory are Higher Order theory and Integrated Information Theory.[4] (In Chapters Eight and Nine, I’ll provide more detail on these theories.) Perhaps the leading scientific defender of Higher Order theory is Hakwan Lau – one of the coauthors of that 2017 article about potentially conscious cars.[5] Integrated Information Theory is potentially even more liberal about machine consciousness, holding that some current AI systems are already at least a little bit conscious and that we could easily design AI systems with arbitrarily high degrees of consciousness.[6]

David Chalmers, the world’s most influential philosopher of mind, argued in 2023 for about a 25% degree of confidence in AI consciousness within a decade.[7] That same year, a team of prominent philosophers, psychologists, and AI researchers – including eminent computer scientist Yoshua Bengio – concluded that there are “no obvious technological barriers” to creating conscious AI according to a wide range of mainstream scientific views about consciousness.[8] In a 2025 interview, Geoffrey Hinton, another of the world’s most prominent computer scientists, asserted that AI systems are already conscious.[9] Christof Koch, the most influential neuroscientist of consciousness from the 1990s to the early 2010s, has endorsed Integrated Information Theory, including its liberal implications for the pervasiveness of consciousness.[10]

This is a sociological argument: a substantial probability of near-term AI consciousness is a mainstream view among leading experts. They might be wrong, but it’s implausible that they’re obviously wrong – that there’s a simple argument or consideration they’re neglecting which, if pointed out, would or should cause them to collectively slap their foreheads and say, “Of course! How did we miss that?”

What of the converse claim – that AI consciousness is obviously imminent or already here? In my experience, fewer people assert this. But in case you’re tempted in this direction, note that other prominent theorists hold that AI consciousness is a far-distant prospect if it’s possible at all: neuroscientist Anil Seth; philosophers Peter Godfrey-Smith, Ned Block, and John Searle; linguist Emily Bender; and computer scientist Melanie Mitchell.[11] (Chapter Six will discuss thought experiments by Searle, Bender, and Mitchell, and Chapter Ten will discuss biological views of the sort emphasized by Seth, Godfrey-Smith, and Block.) In a 2024 survey of 582 AI researchers, 25% expected AI consciousness within ten years and 70% expected AI consciousness by the year 2100.[12]

If the believers are right, we’re on the brink of creating genuinely conscious machines. If the scoffers are right, those machines will only seem conscious. I assume that this is a substantive disagreement, not just a disagreement about how to apply the term “consciousness” to a perfectly obvious set of phenomena about which everyone agrees. The future well-being of many people (including, perhaps, many AI people) depends on getting this issue right. Unfortunately, we will not know in time.

The rest of this book is flesh on this skeleton. I canvass a variety of structural and functional claims about consciousness, the leading theories of consciousness as applied to AI, and the best known general arguments for and against near-term AI consciousness. None of these claims or arguments takes us far. It’s a morass of uncertainty.

-------------------------------------------

[1] I assume that AI consciousness and AI rights are closely connected: Schwitzgebel 2024, ch. 11, in preparation. For discussion, see Shepherd 2018; Levy 2024.

[2] Dehaene 2014; Mashour et al. 2020.

[3] Dehaene, Lau, and Kouider 2017. For an alternative interpretation of this article as concerning something other than consciousness in its standard “phenomenal” sense, see note 115.

[4] Some Higher Order theories: Rosenthal 2005; Lau 2022; Brown 2025. Integrated Information Theory: Albantakis et al. 2023.

[5] But see Chapter Eight for some qualifications.

[6] See Tononi’s publicly available response to Scott Aaronson’s objections in Aaronson 2014. However, advocates of IIT also suggest that the most common current computer architectures are unlikely to achieve much consciousness and that consciousness will tend to appear in subsystems of the computer rather than at the level of the computer itself (Findlay et al. 2024/2025).

[7] Chalmers 2023.

[8] Butlin et al. 2023. (I am among the nineteen authors.)

[9] Heren 2025.

[10] Tononi and Koch 2015.

[11] Seth forthcoming; Godfrey-Smith 2024; Block forthcoming; Searle 1980, 1992; Bender 2025; Mitchell 2021.

[12] Dreksler et al. 2025.