Here Joscha Bach discusses consciousness, it’s relationship to qualia and whether an AI or a utility maximizer would do with it.
What is consciousness? “I think under certain circumstances being conscious is an important part of a mind; it’s a model of a model of a model basically. What it means is our mind (our new cortex) produces this dream that we take to be the world based on the sensory data – so it’s basically a hallucination that predicts what next hits your retina – that’s the world. Out there, we don’t know what this is.. The universe is some kind of weird pattern generator with some quantum properties. And this pattern generator throws patterns at us, and we try to find regularity in them – and the hidden layers of this neural network amount to latent variables that are colors people sounds ideas and so on.. And this is the world that we subjectively inhabit – that’s the world that we find meaningful.”
… “I find theories [about consciousness] that make you feel good very suspicious. If there is something that is like my preferred outcome for emotional reasons, I should be realising that I have a confirmation bias towards this – and that truth is a very brutal vector”..
OUTLINE: 0:07 Consciousness and it’s importance 0:47 Phenomenal content 1:43 Consciousness and attention 2:30 When AI becomes conscious 2:57 Mary’s Room – the Knowledge Argument, art, science & understanding 4:07 What is understanding? What is truth? 4:49 What interests an artist? Art as a communicative exercise 5:48 Thomas Nagel: What is it like to be a bat? 6:19 Feel good theories 7:01 Raw feels or no? Why did nature endow us with raw feels? 8:29 What is qualia, and is it important? 9:49 Insight addiction & the aesthetics of information 10:52 Would a utility maximizer care about qualia?
BIO: Joscha Bach, Ph.D. is an AI researcher who worked and published about cognitive architectures, mental representation, emotion, social modeling, and multi-agent systems. He earned his Ph.D. in cognitive science from the University of Osnabrück, Germany, and has built computational models of motivated decision making, perception, categorization, and concept-formation. He is especially interested in the philosophy of AI and in the augmentation of the human mind.
Joscha has taught computer science, AI, and cognitive science at the Humboldt-University of Berlin and the Institute for Cognitive Science at Osnabrück. His book “Principles of Synthetic Intelligence” (Oxford University Press) is available on amazon.
There is a really interesting Aeon article on what bad science, and how it fails.
What is Bad Science? According to Imre Lakatosh, science degenerates unless it is both theoretically and experimentally progressive. Can Lakatosh’s ‘scientific programme’ approach, which incorporates merits of both Khunian and Popperian ideas, help solve this problem?
Is our current research tradition adequate and effective enough to solve seemingly intractable scientific problems in a timely manner (i.e. in foundational theoretical physics or climate science)? Ideas are cheap, but backing them up with sound hypotheses (main and auxiliary) predicting novel stuff and experimental evidence aimed at confirming this stuff _is expensive_ given time/resource constraints means that among other things an ideal experimental progressiveness is sometimes not achievable.
A scientific programme is considered ‘degenerating’ if: 1) it’s theoretically degenerating because it doesn’t predict novel facts (it just accommodates existing facts); no new forecasts OR 2) it’s experimentally degenerating because none of the predicted novel facts can be tested (i.e. string theory)
Lakatosh’s ideas (that good science is both theoretically and experimentally progressive) may serve as groundwork for further maturing what it means to ‘do science’ where an existing dominant programme is no longer able to respond to accumulating anomalies – which was the reason why Kuhn wrote about changing scientific paradigms – but unlike Kuhn, Lakatos believes that a ‘gestalt-switch’ or scientific revolution should be driven by rationality rather than mob psychology. Though a scientific programme which looks like it is degenerating may be just around the corner from a breakthrough…
For anyone seeking an unambiguously definitive demarcation criterion, this is a death-knell. On the one hand, scientists doggedly pursuing a degenerating research programme are guilty of an irrational commitment to bad science. But, on the other hand, these same scientists can legitimately argue that they’re behaving quite rationally, as their research programme ‘might still be true’, and salvation might lie just around the next corner (which, in the string theory programme, is typically represented by the particle collider that has yet to be built). Lakatos’s methodology doesn’t explicitly negate this argument, and there is likely no rationale that can.
Lakatos argued that it is up to individual scientists (or their institutions) to exercise some intellectual honesty, to own up to their own degenerating programmes’ shortcomings (or, at least, not ‘deny its poor public record’) and accept that they can’t rationally continue to flog a horse that appears, to all intents and purposes, to be quite dead. He accepted that: ‘It is perfectly rational to play a risky game: what is irrational is to deceive oneself about the risk.’ He was also pretty clear on the consequences for those indulging in such self-deception: ‘Editors of scientific journals should refuse to publish their papers … Research foundations, too, should refuse money.’
“In short, data is not knowledge; knowledge is not comprehension; comprehension is not wisdom”
The standard account of understanding has been, since Aristotle, knowledge of the causes of an event or effect. However, this account fails in cases where the subject understood is not causal. In this paper I offer an account of understanding as pattern recognition in large sets of data without the presumption that the patterns indicate causal chains.
All nervous systems by nature desire to process information. Consequently, entities with nervous systems tend to find information everywhere, and on the principle that if some is good a lot is better, we have come up with “Big Data”, which is often suggested as the solution to the problems of one science or another, although it is unclear exactly what counts as big data and how it is supposed to do this. In this paper I will argue (i) that understanding does not and cannot come from larger and higher dimensionality data sets, but from structure in the data that can be literally comprehended; and (ii) that big data multiplies uncertainties unless it can be summarized. In short, data is not knowledge; knowledge is not comprehension; comprehension is not wisdom.
Reason was interviewed at the Undoing Aging conference in Berlin 2019 by Adam Ford – focusing on philosophy of anti-aging, ethics, research & advocacy. Here is the audio!
And the video:
Topics include philosophical reasons to support anti-aging, high impact research (senolytics etc), convincing existence proofs that further research is worth doing, how AI can help and how human research (bench-work) isn’t being replaced by AI atm or in the foreseeable future, suffering mitigation and cause prioritization in Effective Altruism – how the EA movement sees anti-aging and why it should advocate for it, population effects (financial & public health) of an aging population and the ethics of solving aging as a problem…and more.
Reason is the founder and primary blogger at FightAging.org
Adam: What is emotional valence (as opposed to valence in chemistry)?
Mike: Put simply, emotional valence is how pleasant or unpleasant something is. A somewhat weird fact about our universe is that some conscious experiences do seem to feel better than others.
Adam: What makes things feel the way they do? What makes some things feel better than others?
Mike: This sounds like it should be a simple question, but neuroscience just don’t know. It knows a lot of random facts about what kinds of experiences, and what kinds of brain activation patterns, feel good, and which feel bad, but it doesn’t have anything close to a general theory here.
..the way affective neuroscience talks about this puzzle sometimes sort of covers this mystery up, without solving it.
And the way affective neuroscience talks about this puzzle sometimes sort of covers this mystery up, without solving it. For instance, we know that certain regions of the brain, like the nucleus accumbens and ventral pallidum, seem to be important for pleasure, so we call them “pleasure centers”. But we don’t know what makes something a pleasure center. We don’t even know how common painkillers like acetaminophen (paracetamol) work! Which is kind of surprising.
In contrast, the hypothesis about valence I put forth in Principia Qualia would explain pleasure centers and acetaminophen and many other things in a unified, simple way.
Adam: How does the hypothesis about valence work?
Mike: My core hypothesis is that symmetry in the mathematical representation of an experience corresponds to how pleasant or unpleasant that experience is. I see this as an identity relationship which is ‘True with a capital T’, not merely a correlation. (Credit also goes to Andres Gomez Emilsson & Randal Koene for helping explore this idea.)
What makes this hypothesis interesting is that (1) On a theoretical level, it could unify all existing valence research, from Berridge’s work on hedonic hotspots, to Friston & Seth’s work on predictive coding, to Schmidhuber’s idea of a compression drive;
(2) It could finally explain how the brain’s so-called “pleasure centers” work– they function to tune the brain toward more symmetrical states!
(3) It implies lots and lots of weird, bold, *testable* hypotheses. For instance, we know that painkillers like acetaminophen, and anti-depressants like SSRIs, actually blunt both negative *and* positive affect, but we’ve never figured out how. Perhaps they do so by introducing a certain type of stochastic noise into acute & long-term activity patterns, respectively, which disrupts both symmetry (pleasure) and anti-symmetry (pain).
Adam: What kinds of tests would validate or dis-confirm your hypothesis? How could it be falsified and/or justified by weight of induction?
Mike: So this depends on the details of how activity in the brain generates the mind. But I offer some falsifiable predictions in PQ (Principia Qualia):
If we control for degree of consciousness, more pleasant brain states should be more compressible;
Direct, low-power stimulation (TMS) in harmonious patterns (e.g. 2hz+4hz+6hz+8hz…160hz) should feel remarkably more pleasant than stimulation with similar-yet-dissonant patterns (2.01hz+3.99hz+6.15hz…).
Those are some ‘obvious’ ways to test this. But my hypothesis also implies odd things such as that chronic tinnitus (ringing in the ears) should product affective blunting (lessened ability to feel strong valence).
Mike Johnson: Put simply, valence research is important because valence is important. David Chalmers famously coined “The Hard Problem of Consciousness”, or why we’re conscious at all, and “The Easy Problem of Consciousness”, or how the brain processes information. I think valence research should be called “The Important Problem of Consciousness”. When you’re in a conscious moment, the most important thing to you is how pleasant or unpleasant it feels.
That’s the philosophical angle. We can also take the moral perspective, and add up all the human and non-human animal suffering in the world. If we knew what suffering was, we could presumably use this knowledge to more effectively reduce it and make the world a kinder place.
We can also take the economic perspective, and add up all the person-years, capacity to contribute, and quality of life lost to Depression and chronic pain. A good theory of valence should allow us to create much better treatments for these things. And probably make some money while doing it.
Finally, a question I’ve been wondering for a while now is whether having a good theory of qualia could help with AI safety and existential risk. I think it probably can, by helping us see and avoid certain failure-modes.
Adam: How can understanding valence could help make future AIs safer? (How to help define how the AI should approach making us happy?, and in terms of a reinforcement mechanism for AI?)
Mike: Last year, I noted a few ways a better understanding of valence could help make future AIs safer on my blog. I’d point out a few notions in particular though:
If we understand how to measure valence, we could use this as part of a “sanity check” for AI behavior. If some proposed action would cause lots of suffering, maybe the AI shouldn’t do it.
Understanding consciousness & valence seem important for treating an AI humanely. We don’t want to inadvertently torture AIs- but how would we know?
Understanding consciousness & valence seems critically important for “raising the sanity waterline” on metaphysics. Right now, you can ask 10 AGI researchers about what consciousness is, or what has consciousness, or what level of abstraction to define value, and you’ll get at least 10 different answers. This is absolutely a recipe for trouble. But I think this is an avoidable mess if we get serious about understanding this stuff.
Adam: Why the information theoretical approach?
Mike: The way I would put it, there are two kinds of knowledge about valence: (1) how pain & pleasure work in the human brain, and (2) universal principles which apply to all conscious systems, whether they’re humans, dogs, dinosaurs, aliens, or conscious AIs.
It’s counter-intuitive, but I think these more general principles might be a lot easier to figure out than the human-specific stuff. Brains are complicated, but it could be that the laws of the universe, or regularities, which govern consciousness are pretty simple. That’s certainly been the case when we look at physics. For instance, my iPhone’s processor is super-complicated, but it runs on electricity, which itself actually obeys very simple & elegant laws.
Elsewhere I’ve argued that:
>Anything piped through the complexity of the brain will look complex, regardless of how simple or complex it starts out as. Similarly, anything will look irreducibly complex if we’re looking at it from the wrong level of abstraction.
Adam: What do you think of Thomas A. Bass’s view of ITheory – he thinks that (at least in many cases) it has not been easy to turn data into knowledge. That there is a pathological attraction to information which is making us ‘sick’ – he calls it Information Pathology. If his view offers any useful insights to you concerning avoiding ‘Information Pathology’ – what would they be?
Mike: Right, I would agree with Bass that we’re swimming in neuroscience data, but it’s not magically turning into knowledge. There was a recent paper called “Could a neuroscientist understand a microprocessor?” which asked if the standard suite of neuroscience methods could successfully reverse-engineer the 6502 microprocessor used in the Atari 2600 and NES. This should be easier than reverse-engineering a brain, since it’s a lot smaller and simpler, and since they were analyzing it in software they had all the data they could ever ask for, but it turned out that the methods they were using couldn’t cut it. Which really begs the question of whether these methods can make progress on reverse-engineering actual brains. As the paper puts it, neuroscience thinks it’s data-limited, but it’s actually theory-limited.
The first takeaway from this is that even in the age of “big data” we still need theories, not just data. We still need people trying to guess Nature’s structure and figuring out what data to even gather. Relatedly, I would say that in our age of “Big Science” relatively few people are willing or able to be sufficiently bold to tackle these big questions. Academic promotions & grants don’t particularly reward risk-taking.
Adam: Information Theory frameworks – what is your “Eight Problems” framework and how does it contrast with Giulio Tononi’s Integrated Information Theory (IIT)? How might IIT help address valence in a principled manner? What is lacking IIT – and how does your ‘Eight Problems’ framework address this?
Mike: IIT is great, but it’s incomplete. I think of it as *half* a theory of consciousness. My “Eight Problems for a new science of consciousness” framework describes what a “full stack” approach would look like, what IIT will have to do in order to become a full theory.
The biggest two problems IIT faces is that (1) it’s not compatible with physics, so we can’t actually apply it to any real physical systems, and (2) it says almost nothing about what its output means. Both of these are big problems! But IIT is also the best and only game in town in terms of quantitative theories of consciousness.
Principia Qualia aims to help fix IIT, and also to build a bridge between IIT and valence research. If IIT is right, and we can quantify conscious experiences, then how pleasant or unpleasant this experience is should be encoded into its corresponding mathematical object.
Adam: What are the three principles for a mathematical derivation of valence?
Mike: First, a few words about the larger context. Probably the most important question in consciousness research is whether consciousness is real, like an electromagnetic field is real, or an inherently complex, irreducible linguistic artifact, like “justice” or “life”. If consciousness is real, then there’s interesting stuff to discover about it, like there was interesting stuff to discover about quantum mechanics and gravity. But if consciousness isn’t real, then any attempt to ‘discover’ knowledge about it will fail, just like attempts to draw a crisp definition for ‘life’ (elan vital) failed.
If consciousness is real, then there’s a hidden cache of predictive knowledge waiting to be discovered. If consciousness isn’t real, then the harder we try to find patterns, the more elusive they’ll be- basically, we’ll just be talking in circles. David Chalmers refers to a similar distinction with his “Type-A vs Type-B Materialism”.
I’m a strong believer in consciousness realism, as are my research collaborators. The cool thing here is, if we assume that consciousness is real, a lot of things follow from this– like my “Eight Problems” framework. Throw in a couple more fairly modest assumptions, and we can start building a real science of qualia.
Anyway, the formal principles are the following:
Consciousness can be quantified. (More formally, that for any conscious experience, there exists a mathematical object isomorphic to it.)
There is some order, some rhyme & reason & elegance, to consciousness. (More formally, the state space of consciousness has a rich set of mathematical structures.)
Valence is real. (More formally, valence is an ordered property of conscious systems.)
Basically, they combine to say: this thing we call ‘valence’ could have a relatively simple mathematical representation. Figuring out valence might not take an AGI several million years. Instead, it could be almost embarrassingly easy.
Adam: Does Qualia Structuralism, Valence Structuralism and Valence Realism relate to the philosophy of physics principles of realism and structuralism? If so, is there an equivalent ontic Qualia Structuralism and Valence Structuralism?….
Mike: “Structuralism” is many things to many contexts. I use it in a specifically mathematical way, to denote that the state space of qualia quite likely embodies many mathematical structures, or properties (such as being a metric space).
Re: your question about ontics, I tend to take the empirical route and evaluate claims based on their predictions whenever possible. I don’t think predictions change if we assume realism vs structuralism in physics, so maybe it doesn’t matter. But I can get back to you on this. 🙂
Adam: What about the Qualia Research Institute I’ve also recently heard about :D! It seems both you (Mike) and Andrés Gómez Emilson are doing some interesting work there
Mike: We know very little about consciousness. This is a problem, for various and increasing reasons– it’s upstream of a lot of futurist-related topics.
But nobody seems to know quite where to start unraveling this mystery. The way we talk about consciousness is stuck in “alchemy mode”– we catch glimpses of interesting patterns, but it’s unclear how to systematize this into a unified framework. How to turn ‘consciousness alchemy’ into ‘consciousness chemistry’, so to speak.
Qualia Research Institute is a research collective which is working on building a new “science of qualia”. Basically, we think our “full-stack” approach cuts through all the confusion around this topic and can generate hypotheses which are novel, falsifiable, and useful.
Right now, we’re small (myself, Andres, and a few others behind the scenes) but I’m proud of what we’ve accomplished so far, and we’ve got more exciting things in the pipeline. 🙂
Mike Johnson is a philosopher living in the Bay Area, writing about mind, complexity theory, and formalization. He is Co-founder of the Qualia Research Institute. Much of Mike’s research and writings can be found at the Open Theory website. ‘Principia Qualia’ is Mike’s magnum opus – a blueprint for building a new Science of Qualia. Click here for the full version, or here for an executive summary. If you like Mike’s work, consider helping fund it at Patreon.
Materialism was a pre-socratic view that for something to be real it has to be matter – physical stuff made of atoms (which at the time were considered hard like billiard balls – fundametal parts of reality). The reason these days the term physicalism is used is because it can describe things that aren’t matter – like forces, or aren’t observable matter – like dark matter, or energy or fields, or spacetime etc.. Physicalism is the idea that all that exist can be described in the language of some ‘ideal’ physics – we may never know what this ideal physics is, though people think that it is something close to our current physics (as we can make very accurate predictions with our current physics).
If magic, telepathy or angels were real, there would be a physics that could describe them – they’d have patterns and properties that would be describable and explainable. A physicist would likely think that even the mind operates according to physical rules. Being a physicalist according to John means you think everything is governed by rules, physical rules – and that there is an ideal language that can be used to describe all this.
Note John is also a deontologist. Perhaps there should exist an ideal language that can fully describe ethics – does this mean that ideally there is no need for utilitarianism? I’ll leave that question for another post.
Here are some blog posts about physicalism by John Wilkins:
Is physicalism an impoverished metaphysics?
Every so often, we read about some philosopher or other form of public intellectual who makes the claim that a physicalist ontology – a world view in which only things that can be described in terms of physics are said to exist – is impoverished. That is, there are things whereof science cannot know, &c. A recent example is that made by Thomas Nagel [nicely eviscerated here by the physicist Sean Carroll], whose fame in philosophy rests with an influential 1974 paper that there is something like being a bat that no amount of physics, physiology or other objective science could account for.
Recent, Nagel has argued that the evolutionary view called (historically misleadingly) neo-Darwinism, is “almost certainly” false. One of the reasons is that “materialism” (which Nagel should know is an antiquated world view replaced by physicalism defined above; there are many non-material things in physics, not least fields of various kinds) does not permit a full account of consciousness; the subjective facts of being a particular individual organism. Another is that the chance that life would emerge from a lifeless universe is staggeringly unlikely. How this is calculated is somewhat mysterious, given that at best we only have (dare I say it?) subjective estimates anyway, but there it is.
But Nagel is not alone. Various nonreligious (apparently) thinkers have made similar assertions, although some, like Frank Jackson, who proposed the Knowledge Argument, have since backed down. What is it that physicalism must account for that these disputants and objectors say it cannot?
It almost entirely consists of consciousness, intentions, intelligence or some similar mental property which is entirely inexplicable by “reductionist” physicalism. [Reductionism is a term of abuse that means – so far as I can tell – solely that the person who makes such an accusation does not like the thing or persons being accused.] And that raises our question: is physicalism lacking something?
In my last post I argued that physicalism cannot be rejected simply because people assert there are nonphysical objects which are beyond specification. Some are, however, specifiable, and one commentator has identified the obvious ones: abstract objects like the rules of chess or numbers. I have dealt with these before in my “Pizza reductionism” post, which I invite you to go read.
Done? OK, then; let us proceed.
It is often asserted that there are obviously things that are not physical, such as ideas, numbers, concepts, etc., quite apart from qualia, I once sat with a distinguished philosopher, who I respect greatly and so shall not name, when he asserted that we can construct natural classifications because we can deal first with the natural numbers. I asked him “In what sense are numbers natural objects?”, meaning, why should we think numbers are entities in the natural world. He admitted that the question had not occurred to him (I doubt that – he is rather smart), but that it was simply an axiom of his philosophy. I do not think such abstract objects are natural.
This applies to anything that is “informational”, including all semantic entities like meanings, symbols, lexical objects, and so on. They only “exist” as functional modalities in our thoughts and language. I have also argued this before: information does not “exist”; it is a function of how we process signals. Mathematics is not a domain, it is a language, and the reason it works is because the bits that seriously do not work are not explored far[*] – not all of it has to work in a physical or natural sense, but much of it has to, or else it becomes a simple game that we would not play so much.
So the question of the incoherence of physicalism is based on the assumption (which runs contrary to physicalism, and is thus question begging) that abstract objects are natural things. I don’t believe they are, and I certainly do not think that a thought, or concept, for example, which can be had by many minds and is therefore supposed to be located in none of them (and thus transcendental), really is nonphysical. That is another case of nouning language. The thought “that is red” exists, for a physicalist, in all the heads that meet the functional social criteria for ascriptions of red. It exists nowhere else – it just is all those cognitive and social behaviours in biological heads…
In philosophy, physicalism is the ontological thesis that “everything is physical”, that there is “nothing over and above” the physical, or that everything supervenes on the physical. Physicalism is a form of ontological monism—a “one substance” view of the nature of reality as opposed to a “two-substance” (dualism) or “many-substance” (pluralism) view. Both the definition of physical and the meaning of physicalism have been debated. Physicalism is closely related to materialism. Physicalism grew out of materialism with the success of the physical sciences in explaining observed phenomena. The terms are often used interchangeably, although they are sometimes distinguished, for example on the basis of physics describing more than just matter (including energy and physical law). Common arguments against physicalism include both the philosophical zombie argument and the multiple observers argument, that the existence of a physical being may imply zero or more distinct conscious entities. “When I lost my belief in religion I had to decide what I needed to accept as a bare minimum. I decided that I needed to believe in the physical world. I never found the slightest reason to accept the existence of anything else. To this day I am a physicalist only because I never found the need to be anything else. The principle of parsimony suggests that one should not believe in more than one needs to. Even if it does make you feel comfortable.”
What’s the relationship between valence research and AI ethics?
Hedonic valence is a measure of the quality of our felt sense of experience, the intrinsic goodness (positive valence) or averseness (negative valence) of an event, object, or situation. It is an important aspect of conscious experience; always present in our waking lives. If we seek to understand ourselves, it makes sense to seek to understand how valence works – how to measure it and test for it.
Also, might there be a relationship to the AI safety/friendliness problem? In this interview, we cover a lot of things, not least .. THE SINGULARITY (of course) & the importance of Valence Research to AI Friendliness Research (as detailed here). Will thinking machines require experience with valence to understand it’s importance?
Here we cover some general questions about Mike Johnson’s views on recent advances in science and technology & what he sees as being the most impactful, what world views are ready to be retired, his views on XRisk and on AI Safety – especially related to value theory.
Adam Ford: Welcome Mike Johnson, many thanks for doing this interview. Can we start with your background?
Mike Johnson
Mike Johnson: My formal background is in epistemology and philosophy of science: what do we know & how do we know it, what separates good theories from bad ones, and so on. Prior to researching qualia, I did work in information security, algorithmic trading, and human augmentation research.
Adam: What is the most exciting / interesting recent (scientific/engineering) news? Why is it important to you?
Mike: CRISPR is definitely up there! In a few short years precision genetic engineering has gone from a pipe dream to reality. The problem is that we’re like the proverbial dog that caught up to the car it was chasing: what do we do now? Increasingly, we can change our genome, but we have no idea how we should change our genome, and the public discussion about this seems very muddled. The same could be said about breakthroughs in AI.
Adam: What are the most important discoveries/inventions over the last 500 years?
Mike: Tough question. Darwin’s theory of Natural Selection, Newton’s theory of gravity, Faraday & Maxwell’s theory of electricity, and the many discoveries of modern physics would all make the cut. Perhaps also the germ theory of disease. In general what makes discoveries & inventions important is when they lead to a productive new way of looking at the world.
Adam: What philosophical/scientific ideas are ready to be retired? What theories of valence are ready to be relegated to the dustbin of history? (Why are they still in currency? Why are they in need of being thrown away or revised?)
Mike: I think that 99% of the time when someone uses the term “pleasure neurochemicals” or “hedonic brain regions” it obscures more than it explains. We know that opioids & activity in the nucleus accumbens are correlated with pleasure– but we don’t know why, we don’t know the causal mechanism. So it can be useful shorthand to call these things “pleasure neurochemicals” and whatnot, but every single time anyone does that, there should be a footnote that we fundamentally don’t know the causal story here, and this abstraction may ‘leak’ in unexpected ways.
Adam: What have you changed your mind about?
Mike: Whether pushing toward the Singularity is unequivocally a good idea. I read Kurzweil’s The Singularity is Near back in 2005 and loved it- it made me realize that all my life I’d been a transhumanist and didn’t know it. But twelve years later, I’m a lot less optimistic about Kurzweil’s rosy vision. Value is fragile, and there are a lot more ways that things could go wrong, than ways things could go well.
Adam: I remember reading Eliezer’s writings on ‘The Fragility of Value’, it’s quite interesting and worth consideration – the idea that if we don’t get AI’s value system exactly right, then it would be like pulling a random mind out of mindspace – most likely inimicable to human interests. The writing did seem quite abstract, and it would be nice to see a formal model or something concrete to show this would be the case. I’d really like to know how and why value is as fragile as Eliezer seems to make out. Is there any convincing crisply defined model supporting this thesis?
Mike: Whether the ‘Complexity of Value Thesis’ is correct is super important. Essentially, the idea is that we can think of what humans find valuable as a tiny location in a very large, very high-dimensional space– let’s say 1000 dimensions for the sake of argument. Under this framework, value is very fragile; if we move a little bit in any one of these 1000 dimensions, we leave this special zone and get a future that doesn’t match our preferences, desires, and goals. In a word, we get something worthless (to us). This is perhaps most succinctly put by Eliezer in “Value is fragile”:
“If you loose the grip of human morals and metamorals – the result is not mysterious and alien and beautiful by the standards of human value. It is moral noise, a universe tiled with paperclips. To change away from human morals in the direction of improvement rather than entropy, requires a criterion of improvement; and that criterion would be physically represented in our brains, and our brains alone. … You want a wonderful and mysterious universe? That’s your value. … Valuable things appear because a goal system that values them takes action to create them. … if our values that prefer it are physically obliterated – or even disturbed in the wrong dimension. Then there is nothing left in the universe that works to make the universe valuable.”
If this frame is right, then it’s going to be really really really hard to get AGI right, because one wrong step in programming will make the AGI depart from human values, and “there will be nothing left to want to bring it back.” Eliezer, and I think most of the AI safety community assumes this.
But– and I want to shout this from the rooftops– the complexity of value thesis is just a thesis! Nobody knows if it’s true. An alternative here would be, instead of trying to look at value in terms of goals and preferences, we look at it in terms of properties of phenomenological experience. This leads to what I call the Unity of Value Thesis, where all the different manifestations of valuable things end up as special cases of a more general, unifying principle (emotional valence). What we know from neuroscience seems to support this: Berridge and Kringelbach write about how “The available evidence suggests that brain mechanisms involved in fundamental pleasures (food and sexual pleasures) overlap with those for higher-order pleasures (for example, monetary, artistic, musical, altruistic, and transcendent pleasures).” My colleague Andres Gomez Emilsson writes about this in The Tyranny of the Intentional Object. Anyway, if this is right, then the AI safety community could approach the Value Problem and Value Loading Problem much differently.
Adam: I’m also interested in the nature of possible attractors that agents might ‘extropically’ gravitate towards (like a thirst for useful and interesting novelty, generative and non-regressive, that might not neatly fit categorically under ‘happiness’) – I’m not wholly convinced that they exist, but if one leans away from moral relativism, it makes sense that a superintelligence may be able to discover or extrapolate facts from all physical systems in the universe, not just humans, to determine valuable futures and avoid malignant failure modes (Coherent Extrapolated Value if you will). Being strongly locked into optimizing human values may be a non-malignant failure mode.
Mike: What you write reminds me of Schmidhuber’s notion of a ‘compression drive’: we’re drawn to interesting things because getting exposed to them helps build our ‘compression library’ and lets us predict the world better. But this feels like an instrumental goal, sort of a “Basic AI Drives” sort of thing. Would definitely agree that there’s a danger of getting locked into a good-yet-not-great local optima if we hard optimize on current human values.
Probably the danger is larger than that too– as Eric Schwitzgebel notes,
“Common sense is incoherent in matters of metaphysics. There’s no way to develop an ambitious, broad-ranging, self- consistent metaphysical system without doing serious violence to common sense somewhere. It’s just impossible. Since common sense is an inconsistent system, you can’t respect it all. Every metaphysician will have to violate it somewhere.”
If we lock in human values based on common sense, we’re basically committing to following an inconsistent formal system. I don’t think most people realize how badly that will fail.
Adam: What invention or idea will change everything?
Mike: A device that allows people to explore the space of all possible qualia in a systematic way. Right now, we do a lot of weird things to experience interesting qualia: we drink fermented liquids, smoke various plant extracts, strap ourselves into rollercoasters, and parachute out of plans, and so on, to give just a few examples. But these are very haphazard ways to experience new qualia! When we’re able to ‘domesticate’ and ‘technologize’ qualia, like we’ve done with electricity, we’ll be living in a new (and, I think, incredibly exciting) world.
Adam: What are you most concerned about? What ought we be worrying about?
Mike: I’m worried that society’s ability to coordinate on hard things seems to be breaking down, and about AI safety. Similarly, I’m also worried about what Eliezer Yudkowsky calls ‘Moore’s Law of Mad Science’, that steady technological progress means that ‘every eighteen months the minimum IQ necessary to destroy the world drops by one point’. But I think some very smart people are worrying about these things, and are trying to address them.
In contrast, almost no one is worrying that we don’t have good theories of qualia & valence. And I think we really, really ought to, because they’re upstream of a lot of important things, and right now they’re “unknown unknowns”- we don’t know what we don’t know about them.
One failure case that I worry about is that we could trade away what makes life worth living in return for some minor competitive advantage. As Bostrom notes in Superintelligence,
“When it becomes possible to build architectures that could not be implemented well on biological neural networks, new design space opens up; and the global optima in this extended space need not resemble familiar types of mentality. Human-like cognitive organizations would then lack a niche in a competitive post-transition economy or ecosystem. We could thus imagine, as an extreme case, a technologically highly advanced society, containing many complex structures, some of them far more intricate and intelligent than anything that exists on the planet today – a society which nevertheless lacks any type of being that is conscious or whose welfare has moral significance. In a sense, this would be an uninhabited society. It would be a society of economic miracles and technological awesomeness, with nobody there to benefit. A Disneyland with no children.”
Nick Bostrom
Now, if we don’t know how qualia works, I think this is the default case. Our future could easily be a technological wonderland, but with very little subjective experience. “A Disneyland with no children,” as Bostrom quips.
Adam: How would you describe your ethical views? What are your thoughts on the relative importance of happiness vs. suffering? Do things besides valence have intrinsic moral importance?
Mike: Good question. First, I’d just like to comment that Principia Qualia is a descriptive document; it doesn’t make any normative claims.
I think the core question in ethics is whether there are elegant ethical principles to be discovered, or not. Whether we can find some sort of simple description or efficient compression scheme for ethics, or if ethics is irreducibly complex & inconsistent.
The most efficient compression scheme I can find for ethics, that seems to explain very much with very little, and besides that seems intuitively plausible, is the following:
Strictly speaking, conscious experience is necessary for intrinsic moral significance. I.e., I care about what happens to dogs, because I think they’re conscious; I don’t care about what happens to paperclips, because I don’t think they are.
Some conscious experiences do feel better than others, and all else being equal, pleasant experiences have more value than unpleasant experiences.
Beyond this, though, I think things get very speculative. Is valence the only thing that has intrinsic moral importance? I don’t know. On one hand, this sounds like a bad moral theory, one which is low-status, has lots of failure-modes, and doesn’t match all our intuitions. On the other hand, all other systematic approaches seem even worse. And if we can explain the value of most things in terms of valence, then Occam’s Razor suggests that we should put extra effort into explaining everything in those terms, since it’d be a lot more elegant. So– I don’t know that valence is the arbiter of all value, and I think we should be actively looking for other options, but I am open to it. That said I strongly believe that we should avoid premature optimization, and we should prioritize figuring out the details of consciousness & valence (i.e. we should prioritize research over advocacy).
Re: the relative importance of happiness vs suffering, it’s hard to say much at this point, but I’d expect that if we can move valence research to a more formal basis, there will be an implicit answer to this embedded in the mathematics.
Perhaps the clearest and most important ethical view I have is that ethics must ultimately “compile” to physics. What we value and what we disvalue must ultimately cash out in terms of particle arrangements & dynamics, because these are the only things we can actually change. And so if people are doing ethics without caring about making their theories cash out in physical terms, they’re not actually doing ethics- they’re doing art, or social signaling, or something which can serve as the inspiration for a future ethics.
Perhaps the clearest and most important ethical view I have is that ethics must ultimately “compile” to physics. What we value and what we disvalue must ultimately cash out in terms of particle arrangements & dynamics, because these are the only things we can actually change.
The analogy I’d offer here is that we can think about our universe as a computer, and ethics as choosing a program to run on this computer. Unfortunately, most ethicists aren’t writing machine-code, or even thinking about things in ways that could be easily translated to machine-code. Instead, they’re writing poetry about the sorts of programs that might be nice to run. But you can’t compile poetry to machine-code! So I hope the field of ethics becomes more physics-savvy and quantitative (although I’m not optimistic this will happen quickly).
Eliezer Yudkowsky refers to something similar with his notions of “AI grade philosophy”, “compilable philosophy”, and “computable ethics”, though I don’t think he quite goes far enough (i.e., all the way to physics).
Adam: What excites you? What do you think we have reason to be optimistic about?
Mike: The potential of qualia research to actually make peoples’ lives better in concrete, meaningful ways. Medicine’s approach to pain management and treatment of affective disorders are stuck in the dark ages because we don’t know what pain is. We don’t know why some mental states hurt. If we can figure that out, we can almost immediately help a lot of people, and probably unlock a surprising amount of human potential as well. What does the world look like with sane, scientific, effective treatments for pain & depression & akrasia? I think it’ll look amazing.
Adam: If you were to take a stab at forecasting the Intelligence Explosion – in what timeframe do you think it might happen (confidence intervals allowed)?
Mike: I don’t see any intractable technical hurdles to an Intelligence Explosion: the general attitude in AI circles seems to be that progress is actually happening a lot more quickly than expected, and that getting to human-level AGI is less a matter of finding some fundamental breakthrough, and more a matter of refining and connecting all the stuff we already know how to do.
The real unknown, I think, is the socio-political side of things. AI research depends on a stable, prosperous society able to support it and willing to ‘roll the dice’ on a good outcome, and peering into the future, I’m not sure we can take this as a given. My predictions for an Intelligence Explosion:
Between ~2035-2045 if we just extrapolate research trends within the current system;
Between ~2080-2100 if major socio-political disruptions happen but we stabilize without too much collateral damage (e.g., non-nuclear war, drawn-out social conflict);
If it doesn’t happen by 2100, it probably implies a fundamental shift in our ability or desire to create an Intelligence Explosion, and so it might take hundreds of years (or never happen).
If a tree falls in the forest and no one is around to hear it, does it make a sound? It would be unfortunate if a whole lot of awesome stuff were to happen with no one around to experience it. <!–If a rainbow appears in a universe, and there is no one around to experience it, is it beautiful?–>
Mike Johnson is a philosopher living in the Bay Area, writing about mind, complexity theory, and formalization. He is Co-founder of the Qualia Research Institute. Much of Mike’s research and writings can be found at the Open Theory website. ‘Principia Qualia’ is Mike’s magnum opus – a blueprint for building a new Science of Qualia. Click here for the full version, or here for an executive summary. If you like Mike’s work, consider helping fund it at Patreon.
In this interview with Christof Koch, he shares some deeply felt ideas about the urgency of reducing suffering (with some caveats), his experience with mindfulness – explaining what it was like to visit the Dali Lama for a week, as well as a heart felt experience of his family dog ‘Nosey’ dying in his arms, and how that moved him to become a vegetarian. He also discusses the bias of human exceptionalism, the horrors of factory farming of non-human animals, as well as a consequentialist view on animal testing. Christof Koch is an American neuroscientist best known for his work on the neural bases of consciousness.
An online panel focusing on reducing suffering & paradise engineering through the lens of science.
Panelists: Andrés Gómez Emilsson, David Pearce, Brian Tomasik and Mike Johnson
Note, consider skipping to to 10:19 to bypass some audio problems in the beginning!!
Topics
Andrés Gómez Emilsson: Qualia computing (how to use consciousness for information processing, and why that has ethical implications)
How do we know consciousness is causally efficacious? Because we are conscious and evolution can only recruit systems/properties when they do something (and they do it better than the available alternatives).
What is consciousness’ purpose on animals? (Information processing).
What is consciousness’ comparative advantage? (Phenomenal binding).
Why does this matter for suffering reduction? Suffering has functional properties that play a role in the inclusive fitness of organisms. If we figure out exactly what role they play (by reverse-engineering the computational properties of consciousness), we can substitute them by equally (or better) functioning non-conscious or positive hedonic-tone analogues.
What is the focus of Qualia Computing? (it focuses on basic fundamental questions and simple experimental paradigms to get at them (e.g. computational properties of visual qualia via psychedelic psychophysics)).
Brian Tomasik:
Space colonization “Colonization of space seems likely to increase suffering by creating (literally) astronomically more minds than exist on Earth, so we should push for policies that would make a colonization wave more humane, such as not propagating wild-animal suffering to other planets or in virtual worlds.”
AGI safety “It looks likely that artificial general intelligence (AGI) will be developed in the coming decades or centuries, and its initial conditions and control structures may make an enormous impact to the dynamics, values, and character of life in the cosmos.”,
Animals and insects “Because most wild animals die, often painfully, shortly after birth, it’s plausible that suffering dominates happiness in nature. This is especially plausible if we extend moral considerations to smaller creatures like the ~1019 insects on Earth, whose collective neural mass outweighs that of humanity by several orders of magnitude.”
Mike Johnson:
If we successfully “reverse-engineer” the patterns for pain and pleasure, what does ‘responsible disclosure’ look like? Potential benefits and potential for abuse both seem significant.
If we agree that valence is a pattern in a dataset, what’s a good approach to defining the dataset, and what’s a good heuristic for finding the pattern?
What order of magnitude is the theoretical potential of mood enhancement? E.g., 2x vs 10x vs 10^10x
What are your expectations of the distribution of suffering in the world? What proportion happens in nature vs within the boundaries of civilization? What are counter-intuitive sources of suffering? Do we know about ~90% of suffering on the earth, or ~.001%?
Why is it such an exciting time round about now to be doing valence research? Are we at a sweet spot in history with this regard? What is hindering valence research? (examples of muddled thinking, cultural barriers etc?)
How do we use the available science to improve the QALY? GiveDirectly has used change in cortisol levels to measure effectiveness, and the EU (what’s EU stand for?) evidently does something similar involving cattle. It seems like a lot of the pieces for a more biologically-grounded QALY- and maybe a SQALY (Species and Quality-Adjusted Life-Year)- are available, someone just needs to put them together. I suspect this one of the lowest-hanging highest-leverage research fruits.
David Pearce: The ultimate scope of our moral responsibilities. Assume for a moment that our main or overriding goal should be to minimise and ideally abolish involuntary suffering. I typically assume that (a) only biological minds suffer and (b) we are probably alone within our cosmological horizon. If so, then our responsibility is “only” to phase out the biology of involuntary suffering here on Earth and make sure it doesn’t spread or propagate outside our solar system. But Brian, for instance, has quite a different metaphysics of mind, most famously that digital characters in video games can suffer (now only a little – but in future perhaps a lot). The ramifications here for abolitionist bioethics are far-reaching.
Other: – Valence research, Qualia computing (how to use consciousness for information processing, and why that has ethical implications), animal suffering, insect suffering, developing an ethical Nozick’s Experience Machine, long term paradise engineering, complexity and valence – Effective Altruism/Cause prioritization and suffering reduction – People’s practical recommendations for the best projects that suffering reducers can work on (including where to donate, what research topics to prioritize, what messages to spread). – So cause prioritization applied directly to the abolition of suffering? – what are the best projects people can work on to reduce suffering? and what to work on first? (including where to donate, what research topics to prioritize, what messages to spread) – If we successfully “reverse-engineer” the patterns for pain and pleasure, what does ‘responsible disclosure’ look like? Potential benefits and potential for abuse both seem significant – If we agree that valence is a pattern in a dataset, what’s a good approach to defining the dataset, and what’s a good heuristic for finding the pattern? – What order of magnitude is the theoretical potential of mood enhancement? E.g., 2x vs 10x vs 10^10x
Speciesism. When is it ethically acceptable to harm another sentient being? On some fairly modest(1) assumptions, to harm or kill someone simply on the grounds they belong to a different gender, sexual orientation or ethnic group is unjustified. Such distinctions are real but ethically irrelevant. On the other hand, species membership is normally reckoned an ethically relevant criterion. Fundamental to our conceptual scheme is the pre-Darwinian distinction between “humans” and “animals”. In law, nonhuman animals share with inanimate objects the status of property. As property, nonhuman animals can be bought, sold, killed or otherwise harmed as humans see fit. In consequence, humans treat nonhuman animals in ways that would earn a life-time prison sentence without parole if our victims were human. From an evolutionary perspective, this contrast in status isn’t surprising. In our ancestral environment of adaptedness, the human capacity to hunt, kill and exploit sentient beings of other species was fitness-enhancing(2). Our moral intuitions have been shaped accordingly. Yet can we ethically justify such behaviour today?
Naively, one reason for disregarding the interests of nonhumans is the dimmer-switch model of consciousness. Humans matter more than nonhuman animals because (most) humans are more intelligent. Intuitively, more intelligent beings are more conscious than less intelligent beings; consciousness is the touchstone of moral status.
The problem with the dimmer-switch model is that it’s empirically unsupported, among vertebrates with central nervous systems at least. Microelectrode studies of the brains of awake human subjects suggest that the most intense forms of experience, for example agony, terror and orgasmic bliss, are mediated by the limbic system, not the prefrontal cortex. Our core emotions are evolutionarily ancient and strongly conserved. Humans share the anatomical and molecular substrates of our core emotions with the nonhuman animals whom we factory-farm and kill. By contrast, distinctively human cognitive capacities such as generative syntax, or the ability to do higher mathematics, are either phenomenologically subtle or impenetrable to introspection. To be sure, genetic and epigenetic differences exist between, say, a pig and a human being that explain our adult behavioural differences, e.g. the allele of the FOXP2(1) gene implicated in the human capacity for recursive syntax. Such mutations have little to do with raw sentience(1).
Antispeciesism. So what is the alternative to traditional anthropocentric ethics? Antispeciesism is not the claim that “All Animals Are Equal”, or that all species are of equal value, or that a human or a pig is equivalent to a mosquito. Rather the antispeciesist claims that, other things being equal, conscious beings of equivalent sentience deserve equal care and respect. A pig, for example, is of comparable sentience to a prelinguistic human toddler. As it happens, a pig is of comparable (or superior) intelligence to a toddler as well(5). However, such cognitive prowess is ethically incidental. If ethical status is a function of sentience, then to factory-farm and slaughter a pig is as ethically abhorrent as to factory-farm and slaughter a human baby. To exploit one and nurture the other expresses an irrational but genetically adaptive prejudice.
On the face of it, this antispeciesist claim isn’t just wrong-headed; it’s absurd. Philosopher Jonathan Haidt speaks of “moral dumfounding”(6), where we just know something is wrong but can’t articulate precisely why. Haidt offers the example of consensual incest between an adult brother and sister who use birth control. For evolutionary reasons, we “just know” such an incestuous relationship is immoral. In the case of any comparisons of pigs with human infants and toddlers, we “just know” at some deep level that any alleged equivalence in status is unfounded. After all, if there were no ethically relevant distinction between a pig and a toddler, or between a battery-farmed chicken and a human infant, then the daily behaviour of ordinary meat-eating humans would be sociopathic – which is crazy. In fact, unless the psychiatrists’ bible, Diagnostic and Statistical Manual of Mental Disorders, is modified explicitly to exclude behaviour towards nonhumans, most of us do risk satisfying its diagnostic criteria for the disorder. Even so, humans often conceive of ourselves as animal lovers. Despite the horrors of factory-farming, most consumers of meat and animal products are clearly not sociopaths in the normal usage of the term; most factory-farm managers are not wantonly cruel; and the majority of slaughterhouse workers are not sadists who delight in suffering. Serial killers of nonhuman animals are just ordinary men doing a distasteful job – “obeying orders” – on pain of losing their livelihoods.
Should we expect anything different? Jewish political theorist Hannah Arendt spoke famously of the “banality of evil”(7). If twenty-first century humans are collectively doing something posthuman superintelligence will reckon monstrous, akin to the [human] Holocaust or Atlantic slave trade, then it’s easy to assume our moral intuitions would disclose this to us. Our intuitions don’t disclose anything of the kind; so we sleep easy. But both natural selection and the historical record offer powerful reasons for doubting the trustworthiness of our naive moral intuitions. So the possibility that human civilisation might be founded upon some monstrous evil should be taken seriously – even if the possibility seems transparently absurd at the time.
One possible speciesist response is to raise the question of “potential”. Even if a pig is as sentient as a human toddler, there is a fundamental distinction between human toddlers and pigs. Only a toddler has the potential to mature into a rational adult human being.
The problem with this response is that it contradicts our treatment of humans who lack “potential”. Thus we recognise that a toddler with a progressive disorder who will never live to celebrate his third birthday deserves at least as much love, care and respect as his normally developing peers – not to be packed off to a factory-farm on the grounds it’s a shame to let good food go to waste. We recognise a similar duty of care for mentally handicapped adult humans and cognitively frail old people. For sure, historical exceptions exist to this perceived duty of care for vulnerable humans, e.g. the Nazi “euthanasia” program, with its eugenicist conception of “life unworthy of life”. But by common consent, we value young children and cognitively challenged adults for who they are, not simply for who they may – or may not – one day become. On occasion, there may controversially be instrumental reasons for allocating more care and resources to a potential genius or exceptionally gifted child than to a normal human. Yet disproportionate intraspecies resource allocation may be justified, not because high IQ humans are more sentient, but because of the anticipated benefits to society as a whole.
Practical Implications. 1. Invitrotarianism. The greatest source of severe, chronic and readily avoidable suffering in the world today is man-made: factory farming. Humans currently slaughter over fifty billion sentient beings each year. One implication of an antispeciesist ethic is that factory farms should be shut and their surviving victims rehabilitated.
In common with most ethical revolutions in history, the prospect of humanity switching to a cruelty-free diet initially strikes most practically-minded folk as utopian dreaming. “Realists” certainly have plenty of hard evidence to bolster their case. As English essayist William Hazlitt observed, “The least pain in our little finger gives us more concern and uneasiness than the destruction of millions of our fellow-beings.” Without the aid of twenty-first century technology, the mass slaughter and abuse of our fellow animals might continue indefinitely. Yet tissue science technology promises to allow consumers to become moral agents without the slightest hint of personal inconvenience. Lab-grown in vitro meat produced in cell culture rather than a live animal has long been a staple of science fiction. But global veganism – or its ethical invitrotarian equivalent – is no longer a futuristic fantasy. Rapid advances in tissue engineering mean that in vitro meat will shortly be developed and commercialised. Today’s experimental cultured mincemeat can be supplanted by mass-manufactured gourmet steaks for the consumer market. Perhaps critically for its rapid public acceptance, in vitro meat does not need to be genetically modified – thereby spiking the guns of techno-luddites who might otherwise worry about “FrankenBurgers”. Indeed, cultured meat products will be more “natural” in some ways than their antibiotic-laced counterparts derived from factory-farmed animals.
Momentum for commercialisation is growing. Non-profit research organisations like New Harvest(8), working to develop alternatives to conventionally-produced meat, have been joined by hard-headed businessmen. Visionary entrepreneur and Stanford academic Peter Thiel has just funnelled $350,000 into Modern Meadow, a start-up that aims to combine 3D printing with in vitro meat cultivation. Within the next decade or so, gourmet steaks could be printed out from biological materials. In principle, the technology should be scalable.
Tragically, billions of nonhuman animals will grievously suffer and die this century at human hands before the dietary transition is complete. Humans are not obligate carnivores; eating meat and animal products is a lifestyle choice. “But I like the taste!” is not a morally compelling argument. Vegans and animal advocates ask whether we are ethically entitled to wait on a technological fix? The antispeciesist answer is clear: no.
2. Compassionate Biology. If and when humans stop systematically harming other sentient beings, will our ethical duties to members of other species have been discharged? Not if the same ethical considerations as apply to members of other human races or age-groups apply also to members of other species of equivalent sentience. Thus if famine breaks out in sub-Saharan Africa and young human children are starving, then we recognise we have a duty to send aid; or better still, to take proactive measures to ensure famines do not arise in the first instance, i.e. to provide not just food aid but family planning. So why not assist, say, starving free-living elephants? Until recently, no comparable interventions were feasible for members of other species. The technical challenges were insurmountable. Not least, the absence of cross-species fertility control technologies would have often made bad problems worse. Yet thanks to the exponential growth of computer power, every cubic metre of the planet will shortly be computationally accessible to micro-management, surveillance and control. Harnessed to biotechnology, nanotechnology and robotics, such tools confer unprecedented power over Nature. With unbridled power comes complicity. Ethically speaking, how many of the traditional cruelties of the living world do we wish to perpetuate? Orthodox conservation biologists argue we should not “interfere”: humans can’t “police” Nature. Antispeciesists disagree. Advocates of compassionate biology argue that humans and nonhumans alike should not be parasitised, starved, disembowelled, asphyxiated, or eaten alive.
As always, bioconservatives insist such miseries are “natural”; status quo bias runs deep. “Custom will reconcile people to any atrocity”, observed George Bernard Shaw. Snuff movies in the guise of Nature documentaries are quite popular on Youtube, a counterpoint to the Disneyfied wildlife shows aired on mainstream TV. Moreover even sympathetic critics of compassionate biology might respond that helping free-living members of other species is prohibitively expensive. An adequate welfare safety-net scarcely exists for humans in many parts of the world. So how can we contemplate its extension to nonhumans – even just to large-brained, long-lived vertebrates in our Nature reserves? Provision of comprehensive healthcare for all free-living elephants(10), for example, might cost between two or three billion dollars annually. Compassionate stewardship of the living world would be technically daunting too, entailing ecosystem management, cross-species fertility control via immunocontraception, veterinary care, emergency famine-relief, GPS tracking and monitoring, and ultimately phasing out or genetically “reprogramming”(11) carnivorous predators. The notional bill could approach the world’s 1.7 trillion-dollar annual arms budget. But irrespective of cost or timescale, if we are to be consistently non-speciesist, then decisions about resource allocation should be based not on species membership, but directly or indirectly on sentience. An elephant, for example, is at least as sentient as a human toddler. If it is ethically obligatory to help sick or starving children, then it’s ethically obligatory to help sick or starving elephants – not just via crisis interventions but via long-term healthcare support.
A traditional conservation biologist might respond that elephants helped by humans are no longer truly wild. Yet on such a criterion, clothes-wearing humans or beneficiaries of food aid and family planning aren’t “wild” humans either. Why should this matter? “Free-living” and “wild” are conceptually distinct. To assume that the civilising process should be confined to our own species is mere speciesist prejudice. Humans, transhumans and posthumans must choose what forms of sentience we want to preserve and create on Earth and beyond. Humans already massively intervene in Nature, whether though habitat destruction, captive breeding programs for big cats, “rewilding”, etc. So the question is not whether humans should “interfere”, but rather what ethical principles should govern our interventions(12).
Speciesism and Superintelligence. Why should transhumanists care about the suffering of nonhuman animals? This is not a “feel-good” issue. One reason we should care cuts to the heart of the future of life in the universe. Transhumanists differ over whether our posthuman successors will most likely be nonbiological artificial superintelligence; or cyborgs who effectively merge with our hyperintelligent machines; or our own recursively self-improving biological descendents who modify their own genetic source code and bootstrap their way to full-spectrum superintelligence(13). Regardless of the dominant lifeform of the posthuman era, biological humans have a vested interest in the behaviour of intellectually advanced beings towards cognitively humble creatures – if we survive at all. Compared to posthuman superintelligence, archaic humans may be no smarter than pigs or chickens – or perhaps worms. This does not augur well for Homo sapiens. Western-educated humans tend to view Jains as faintly ridiculous for practising ahimsa, or harmlessness, sweeping the ground in front of them to avoid inadvertently treading on insects. How quixotic! Yet the fate of sentient but cognitively humble lifeforms in relation to vastly superior intelligence is precisely the issue at stake as we confront the prospect of posthuman superintelligence. How can we ensure a Jain-like concern for comparatively simple-minded creatures such as ourselves? Why should superintelligences care any more than humans about the well-being of their intellectual inferiors? Might distinctively human-friendly superintelligence turn out to be as intellectually-incoherent as, say, Aryan-friendly superintelligence? If human primitives are to prove worthy of conservation, how can we implement technologies of impartial friendliness towards other sentients? And if posthumans do care, how do we know that a truly benevolent superintelligence wouldn’t turn Darwinian life into utilitronium with a communal hug?
Viewed in such a light, biological humanity’s prospects in a future world of superintelligence might seem dire. However, this worry expresses a one-dimensional conception of general intelligence. No doubt the nature of mature superintelligence is humanly unknowable. But presumably full-spectrum(14) superintelligence entails, at the very least, a capacity to investigate, understand and manipulate both the formal and the subjective properties of mind. Modern science aspires to an idealised “view from nowhere”(15), an impartial, God-like understanding of the natural universe, stripped of any bias in perspective and expressed in the language of mathematical physics. By the same token, a God-like superintelligence must also be endowed with the capacity impartially to grasp all possible first-person perspectives – not a partial and primitive Machiavellian cunning of the kind adaptive on the African savannah, but an unimaginably radical expansion of our own fitfully growing circle of empathy.
What such superhuman perspective-taking ability might entail is unclear. We are familiar with people who display abnormally advanced forms of “mind-blind”(16), autistic intelligence in higher mathematics and theoretical physics. Less well known are hyper-empathisers who display unusually sophisticated social intelligence. Perhaps the most advanced naturally occurring hyper-empathisers exhibit mirror-touch synaesthesia(17). A mirror-touch synaesthete cannot be unfriendly towards you because she feels your pain and pleasure as if it were her own. In principle, such unusual perspective-taking capacity could be generalised and extended with reciprocal neuroscanning technology and telemetry into a kind of naturalised telepathy, both between and within species. Interpersonal and cross-species mind-reading could in theory break down hitherto invincible barriers of ignorance between different skull-bound subjects of experience, thereby eroding the anthropocentric, ethnocentric and egocentric bias that has plagued life on Earth to date. Today, the intelligence-testing community tends to treat facility at empathetic understanding as if it were a mere personality variable, or at best some sort of second-rate cognition for people who can’t do IQ tests. But “mind-reading” can be a highly sophisticated, cognitively demanding ability. Compare, say, the sixth-order intentionality manifested by Shakespeare. Thus we shouldn’t conceive superintelligence as akin to God imagined by someone with autistic spectrum disorder. Rather full-spectrum superintelligence entails a God’s-eye capacity to understand the rich multi-faceted first-person perspectives of diverse lifeforms whose mind-spaces humans would find incomprehensibly alien.
An obvious objection arises. Just because ultra-intelligent posthumans may be capable of displaying empathetic superintelligence, how do we know such intelligence will be exercised? The short answer is that we don’t: by analogy, today’s mirror-touch synaesthetes might one day neurosurgically opt to become mind-blind. But then equally we don’t know whether posthumans will renounce their advanced logico-mathematical prowess in favour of the functional equivalent of wireheading. If they do so, then they won’t be superintelligent. The existence of diverse first-person perspectives is a fundamental feature of the natural world, as fundamental as the second law of thermodynamics or the Higgs boson. To be ignorant of fundamental features of the world is to be an idiot savant: a super-Watson(18) perhaps, but not a superintelligence(19).
High-Tech Jainism? Jules Renard once remarked, “I don’t know if God exists, but it would be better for His reputation if He didn’t.” God’s conspicuous absence from the natural world needn’t deter us from asking what an omniscient, omnipotent, all-merciful deity would want humans to do with our imminent God-like powers. For we’re on the brink of a momentous evolutionary transition in the history of life on Earth. Physicist Freeman Dyson predicts we’ll soon “be writing genomes as fluently as Blake and Byron wrote verses”(20). The ethical risks and opportunities for apprentice deities are huge.
On the one hand, Karl Popper warns, “Those who promise us paradise on earth never produced anything but a hell”(21). Twentieth-century history bears out such pessimism. Yet for billions of sentient beings from less powerful species, existing life on Earth is hell. They end their miserable lives on our dinner plates: “for the animals it is an eternal Treblinka”, writes Jewish Nobel laureate Isaac Bashevis Singer(22).
In a more utopian vein, some utterly sublime scenarios are technically feasible later this century and beyond. It’s not clear whether experience below Sidgwick’s(23) “hedonic zero” has any long-term future. Thanks to molecular neuroscience, mastery of the brain’s reward circuitry could make everyday life wonderful beyond the bounds of normal human experience. There is no technical reason why the pitiless Darwinian struggle of the past half billion years can’t be replaced by an earthly paradise for all creatures great and small. Genetic engineering could allow “the lion to lie down with the lamb.” Enhancement technologies could transform killer apes into saintly smart angels. Biotechnology could abolish suffering throughout the living world. Artificial intelligence could secure the well-being of all sentience in our forward light-cone. Our quasi-immortal descendants may be animated by gradients of intelligent bliss orders of magnitude richer than anything physiologically feasible today.
Such fantastical-sounding scenarios may never come to pass. Yet if so, this won’t be because the technical challenges prove too daunting, but because intelligent agents choose to forgo the molecular keys to paradise for something else. Critically, the substrates of bliss don’t need to be species-specific or rationed. Transhumanists believe the well-being of all sentience(24) is the bedrock of any civilisation worthy of the name.
Also see this related interview with David Pearce on ‘Antispecism & Compassionate Stewardship’:
* * *
NOTES
1. How modest? A venerable tradition in philosophical meta-ethics is anti-realism. The meta-ethical anti-realist proposes that claims such as it’s wrong to rape women, kill Jews, torture babies (etc) lack truth value – or are simply false. (cf. JL Mackie, Ethics: Inventing Right and Wrong, Viking Press, 1977.) Here I shall assume that, for reasons we simply don’t understand, the pain-pleasure axis discloses the world’s inbuilt metric of (dis)value. Meta-ethical anti-realists may instead wish to interpret this critique of speciesism merely as casting doubt on its internal coherence rather than a substantive claim that a non-speciesist ethic is objectively true.
2. Extreme violence towards members of other tribes and races can be fitness-enhancing too. See, e.g. Richard Wrangham & Dale Peterson, Demonic Males: Apes and the Origins of Human Violence, Houghton Mifflin, 1997.
3. Fisher SE, Scharff C (2009). “FOXP2 as a molecular window into speech and language”. Trends Genet. 25 (4): 166–77. doi:10.1016/j.tig.2009.03.002. PMID 19304338.
4. Interpersonal and interspecies comparisons of sentience are of course fraught with problems. Comparative studies of how hard a human or nonhuman animal will work to avoid or obtain a particular stimulus give one crude behavioural indication. Yet we can go right down to the genetic and molecular level, e.g. interspecies comparisons of SCN9A genotype. (cf. http://www.pnas.org/? content/early/2010/02/23/?0913181107.full.pdf) We know that in humans the SCN9A gene modulates pain-sensitivity. Some alleles of SCN9A give rise to hypoalgesia, others alleles to hyperalgesia. Nonsense mutations yield congenital insensitivity to pain. So we could systematically compare the SCN9A gene and its homologues in nonhuman animals. Neocortical chauvinists will still be sceptical of non-mammalian sentience, pointing to the extensive role of cortical processing in higher vertebrates. But recall how neuroscanning techniques reveal that during orgasm, for example, much of the neocortex effectively shuts down. Intensity of experience is scarcely diminished.
5. Held S, Mendl M, Devereux C, and Byrne RW. 2001. “Studies in social cognition: from primates to pigs”. Animal Welfare 10:S209-17.
6. Jonathan Haidt, The Righteous Mind: Why Good People Are Divided by Politics and Religion, Pantheon Books, 2012.
7. Hannah Arendt, Eichmann in Jerusalem: A Report on the Banality of Evil, Viking Press, 1963.
12. The scholarly literature on the problem of wild animal suffering is still sparse. But perhaps see Arne Naess, “Should We Try To Relieve Clear Cases of Suffering in Nature?”, published in The Selected Works of Arne Naess, Springer, 2005; Oscar Horta, “The Ethics of the Ecology of Fear against the Nonspeciesist Paradigm: A Shift in the Aims of Intervention in Nature”, Between the Species, Issue X, August 2010. http://digitalcommons.calpoly.edu/bts/vol13/iss10/10/ ; Brian Tomasik, “The Importance of Wild-Animal Suffering”, http://www.utilitarian-essays.com/suffering-nature.html ; and the first print-published plea for phasing out carnivorism in Nature, Jeff McMahan’s “The Meat Eaters”, The New York Times. September 19, 2010. http://opinionator.blogs.nytimes.com/2010/09/19/the-meat-eaters/
13. Singularity Hypotheses, A Scientific and Philosophical Assessment, Eden, A.H.; Moor, J.H.; Søraker, J.H.; Steinhart, E. (Eds.) Spinger 2013. http://singularityhypothesis.blogspot.co.uk/p/table-of-contents.html
14. David Pearce, The Biointelligence Explosion. (preprint), 2012. https://www.biointelligence-explosion.com.
15. Thomas Nagel, The View From Nowhere , OUP, 1989.
16. Simon Baron-Cohen (2009). “Autism: the empathizing–systemizing (E-S) theory” (PDF). Ann N Y Acad Sci 1156: 68–80. doi:10.1111/j.1749-6632.2009.04467.x. PMID 19338503.
17. Banissy, M. J. & Ward, J. (2007). Mirror-touch synesthesia is linked with empathy. Nature Neurosci. doi: 10.1038/nn1926.
18. Stephen Baker. Final Jeopardy: Man vs. Machine and the Quest to Know Everything. Houghton Mifflin Harcourt. 2011.
19. Orthogonality or convergence? For an alternative to the convergence thesis, see Nick Bostrom, “The Superintelligent Will: Motivation and Instrumental Rationality in Advanced Artificial Agents”, 2012, http://www.nickbostrom.com/superintelligentwill.pdf; and Eliezer Yudkowsky, Carl Shulman, Anna Salamon, Rolf Nelson, Steven Kaas, Steve Rayhawk, Zack Davis, and Tom McCabe. “Reducing Long-Term Catastrophic Risks from Artificial Intelligence”, 2010. http://singularity.org/files/ReducingRisks.pdf
20. Freeman Dyson, “When Science & Poetry Were Friends”, New York Review of Books, August 13, 2009.
21. As quoted in Jon Winokur, In Passing: Condolences and Complaints on Death, Dying, and Related Disappointments, Sasquatch Books, 2005.
22. Isaac Bashevis Singer, The Letter Writer, 1964.
23. Henry Sidgwick, The Methods of Ethics. London, 1874, 7th ed. 1907.
24. The Transhumanist Declaration (1998, 2009). http://humanityplus.org/philosophy/transhumanist-declaration/
Joscha Bach, Ph.D. is an AI researcher who worked and published about cognitive architectures, mental representation, emotion, social modeling, and multi-agent systems. He earned his Ph.D. in cognitive science from the University of Osnabrück, Germany, and has built computational models of motivated decision making, perception, categorization, and concept-formation. He is especially interested in the philosophy of AI and in the augmentation of the human mind.
That’s the philosophical angle. We can also take the moral perspective, and add up all the human and non-human animal suffering in the world. If we knew what suffering was, we could presumably use this knowledge to more effectively reduce it and make the world a kinder place.
Adam: How can understanding valence could help make future AIs safer? (How to help define how the AI should approach making us happy?, and in terms of a reinforcement mechanism for AI?)
Note John is also a deontologist. Perhaps there should exist an ideal language that can fully describe ethics – does this mean that ideally there is no need for utilitarianism? I’ll leave that question for another post.
In this 
Christof Koch is the President and Chief Scientific Officer of the 
