7 Recent Videos: Cognitive Sovereignty, Phenomenology of Scent, Solution to the Problem of Other Minds, Novel Qualia Research Methods, Higher Dimensions, Solution to the Binding Problem, and Qualia Computing

[Context: 4th in a series of 7-video packages. See the previous three packages: 1st2nd, and 3rd]

Genuinely new thoughts are actually very rare. Why is that? And how can we incentivize the good side of smart people to focus their energies on having genuinely new thoughts for the benefit of all? In order to create the conditions for that we need to strike the right balance between many complementary forces.

I offer a new ideal we call “Cognitive Sovereignty”. This ideal consists of three principles working together in synergy: (1) Freedom of Thought and Feeling, (2) Idea Ownership, and (3) Information Responsibility.

(1) Freedom of Thought and Feeling is the cultivation of a child-like wonder and positive attitude towards the ideas of one another. A “Yes And” approach to idea sharing.

As QRI advisors Anders Amelin and Margareta “Maggie” Wassinge write on the topic:

“On the topic of liberty of mind, we may reflect that inhibitory mechanisms are typically strong within groups of people. As is the case within minds of individuals. In minds it’s this tip of the iceberg which gets rendered as qualia and is the end result of unexperienced hierarchies of powerfully constraining filters. It’s really practical for life forms to function this way and for teams made up of life forms to function similarly, but for making grand improvements to the very foundations of life itself, you need maximum creativity instead of the default self-organizing consensus emergence.

“There is creativity-limiting pressure to conform to ‘correctness’ everywhere. Paradigmatic correctness in science, corporate correctness in business, social correctness, political correctness, and so on. As antidotes to chaos these can serve a purpose but for exceptional intellectual work to blossom they are quite counterproductive. There is something to be said for Elon Musk’s assertion that ‘excellence is the only passing grade’.

“The difference to the future wellbeing of sentient entities between the QRI becoming something pretty much overall OK-ish, and the QRI becoming something of great excellence, is probably bigger than between the corresponding outcomes for Tesla Motors.

“The creativity of the team is down to this exact thing: The qualia computing of the gut feeling getting to enjoy a haven of liberty all too rare elsewhere.”

On (2) we can say that to “be the adult in the room” is also equally important. As Michael Johnson puts it, “it’s important to keep track of the metadata of ideas.” One cannot incentivize smart people to share ideas if they don’t feel like others will recognize who came up with them. While not everyone pays close attention to who says what in conversation, we think that a reasonable level of attention on this is necessary to align incentives. Obviously too much emphasis on Idea Ownership can be stifling and generate excessive overhead. So having open conversations about (failed) attribution while assuming the best from others is also a key practice to make Idea Ownership good for everyone.

And finally, (3) is the principle of “Information Responsibility”. This is the “wise old person” energy and attitude that deeply cares about the effects that information has on the world. Simple heuristics like “information wants to be free” and the ideal of a fully “open science” are pleasant to think about, but in practice they may lead to disasters on a grand scale. From gain of function research in virology to analysis of water pipes in cities, cutting-edge research can at times encounter novel ways of causing great harm. It’s imperative that one resists the urge to share them with the world for the sake of signaling how smart one is (which is the default path for the vast majority of people and institutions!). One needs to cultivate the wisdom to consider the long-term vision and only share ideas one knows are safe for the world. Here, of course, we need a balance: too much emphasis on information security can be a tactic to thwart other’s work and may be undully onerous and stifling. Striking the right balance is the goal.

The full synergy between these three principles of Cognitive Sovereignty, I think, is what allows people to think new thoughts.

I also cover two new key ideas: (a) Canceling Paradise and (b) Multi-level Selection and how it interacts with Organizational Freedom.

~Qualia of the Day: Long Walks on the Beach~

Relevant links:

In this talk we analyze the perfume category called “Aromatic Fougère” in order to illustrate the aesthetic of “Qualiacore” in its myriad manifestations.

Definition: The Qualiacore Aesthetic is the practice and aspiration to describe experiences in new, meaningful, and non-trivial ways that are illuminating for our understanding of the nature of consciousness.

At a high-level, we must note that the classic ways of describing the phenomenology of scents tend to “miss the target”. Learning about the history, cultural imports, associations, and similarities between perfumes can be fun to do but it does not advance an accurate phenomenological impression of what it is that we are talking about. And while reading about the “perfume notes” of a composition can place it in a certain location relative to other perfumes, such note descriptions usually give you a false sense of understanding and familiarity far removed from the complex subtleties of the state-space of scent. So how can we say new, meaningful, and non-trivial things about a smell?

Note-wise, Aromatic Fougères are typically described as the combination of herbs and spices (the aromatic part) with the core Fougère accord of oak moss, lavender/bergamot, geranium, and coumarin. In this video I offer a qualiacore-style analysis of how these “notes” interact with one another in order to form emergent gestalts. Here we will focus on the phenomenal character of these effects with an emphasis on bringing analogies from dynamic system behavior and energy-management techniques within the purview of the Symmetry Theory of Valence.

In the end, we arrive at a phenomenological fingerprint that cashes out in a comparison to the psychoactive effect of “Calvin Klein” (cocaine + ketamine*), which blends both stimulation and dissociation at the same time – a rather interesting effect that can be used to help you overcome awkwardness barriers in everyday life. “Smooth out the awkwardness landscape with Drakkar Noir!”

I also discuss the art of perfumery in light of QRI’s 8 models of art:

  1. Art as family resemblance (Semantic Deflation)
  2. Art as Signaling (Cool Kid Theory)
  3. Art as Schelling-point creation (a few Hipster-theoretical considerations)
  4. Art as cultivating sacred experiences (self-transcendence and highest values)
  5. Art as exploring the state-space of consciousness (ϡ☀♘🏳️‍🌈♬♠ヅ)
  6. Art as something that messes with the energy parameter of your mind (ꙮ)
  7. Art as puzzling valence effects (emotional salience and annealing as key ingredients)
  8. Art as a system of affective communication: a protolanguage to communicate information about worthwhile qualia (which culminates in Harmonic Society).

~Qualia of the Day: Aromatic Fougères~

* Extremely ill-advised.

Relevant links:

How do you know for sure that other people (and non-human animals) are conscious?

The so-called “problem of other minds” asks us to consider whether we truly have any solid basis for believing that “we are not alone”. In this talk I provide a new, meaningful, and non-trivial solution to the problem of other minds using a combination of mindmelding and phenomenal puzzles in the right sequence such that one can gain confidence that others are indeed “solving problems with qualia computing” and in turn infer that they are independently conscious.

This explanatory style contrasts with typical “solutions” to the problem of other minds that focus on either historical, behavioral, or algorithmic similarities between oneself and others (e.g. “passing a Turing test”). Here we explore what the space of possible solutions looks like and show that qualia formalism can be a key to unlock new kinds of understanding currently out of reach within the prevailing paradigms in philosophy of mind. But even with qualia formalism, the radical skeptic solipsist will not be convinced. Direct experience and “proof” is necessary to convince a hardcore solipsist since intellectual “inferential” arguments can always be mere “figments of one’s own imagination”. We thus explore how mindmelding can greatly increase our certainty of other’s consciousness. However, skeptical worries may still linger: how do you know that the source of consciousness during mindmelding is not your brain alone? How do you know that the other brain is conscious while you are not connected to it? We thus introduce “phenomenal puzzles” into the picture: these are puzzles that require the use of “qualia comparisons” to be solved. In conjunction with a specific mindmelding information sharing protocol, such phenomenal puzzles can, we argue, actually fully address the problem of other minds in ways even strong skeptics will be satisfied with. You be the judge! 🙂

~Qualia of the Day: Wire Puzzles~

Many thanks to: Everyone who has encouraged the development of the field of qualia research over the years. David Pearce for encouraging me to actually write out my thoughts and share them online, Michael Johnson for our multi-year deep collaboration at QRI, and Murphy-Shigematsu for pushing me over the edge to start working on “what I had been putting off” back in 2014 (which was the trigger to actually write the first Qualia Computing post). In addition, I’d like to thank everyone at the Stanford Transhumanist Association for encouraging me so much over the years (Faust, Karl, Juan-Carlos, Blue, Todor, Keetan, Alan, etc.). Duncan Wilson for the beautiful times discussing these matters. Romeo Stevens for the amazing vibes and high-level thoughts. And of course everyone at QRI, especially Quintin Frerichs, Andrew Zuckerman, Anders and Maggie, and the list goes on (Mackenzie, Sean, Hunter, Elin, Wendi, etc.). Likewise, everyone at Qualia Computing Networking (the closed facebook group where we discuss a lot of these ideas), our advisors, donors, readers, and of course those watching these videos. Much love to all of you!

Relevant links:

“Tout comprendre, c’est tout pardonner” – To understand all is to forgive all.

New scientific paradigms essentially begin life as conspiracy theories, noticing the inconsistencies the previous paradigm is suppressing. Early adopters undergo a process that Kuhn likens to religious deconversion.” – Romeo Stevens

The field of consciousness research lacks a credible synthesis of what we already know about the mind. One key thing that is holding back the science of consciousness is that it’s currently missing an adequate set of methods to “take seriously” the implications of exotic states of consciousness. Imagine a physicist saying that “there is nothing about water that we can learn from studying ice”. Silly as it may be, the truth is that this is the typical attitude about exotic consciousness in modern neuroscience. And even with the ongoing resurgence of scientific interest in psychedelics, outside of QRI and Ingram’s EPRC there is no real serious attempt at mapping the state-space of consciousness in detail. This is to a large extent because we lack the vocabulary, tools, concepts, and focus at a paradigmatic level to do so. But a new paradigm is arriving, and the following 8 new research methods and others in the works will help bring it about:

  1. Taking Exotic States of Consciousness Seriously (e.g. when a world-class phenomenologist says that 3D-printed Poincaré projections of hyperbolic honeycombs make the visual system “glitch” when on DMT the rational response is to listen and ask questions rather than ignore and ridicule).
  2. High-Quality Phenomenology: Precise descriptions of the phenomenal character of experience. Core strategy: useful taxonomies of experience, a language to describe generalized synesthesia (multi-modal coherence), and a rich vocabulary to convey the statistical regularities of textures of qualia (cf. generalizing the concept of “mongrels” in the neuroscience of visual perception to all other modalities).
  3. Phenomenology Club: Critical mass of smart and rational psychonauts.
  4. Psychedelic Turk for Psychophysics: Real-time psychedelic task completion.
  5. Generalized Wada Test: What happens when half of your brain is on LSD and the other half is on ketamine?
  6. Resonance-Based Hedonic Mapping: You are a network of coupled oscillators. Act like it!
  7. Pair Qualia Cartography: Like pair programming but for exploring the state-space of consciousness with non-invasive neurostimulation.
  8. Cognitive Sovereignty: Furthering a culture that has a “Yes &” approach to creativity, keeps track of meta-data, and takes responsibility for the information it puts out.

~Qualia of the Day: Being Taken Seriously~

Relevant links:

Many people report experiencing “higher dimensions” during deep meditation and/or psychedelic experiences. Vaporized DMT in particular reliably produces this effect in a large percentage of users. But is this an illusion? Is there anything meaningful to it? What could possibly be going on?

In this video we provide a steel man (or titanium man?) of the idea that higher dimensions are *real* in a new, meaningful, and non-trivial sense. 

We must emphasize that most people who believe that DMT experiences are “higher dimensional” interpret their experiences within a direct realist framework. Meaning that they think they are “tuning in” to other dimensions, that some secret sense organ capable of perceiving the etheric realm was “activated”, that awareness into divine realms became available to their soul, or something along those lines. In brief, such interpretations operate under the notion that we can perceive the world directly somehow. In this video, we instead work under the premise that we live in a compact world-simulation generated by our nervous system. If DMT gives rise to “higher dimensional experiences”, then such dimensions will be phenomenological in nature.

We thus try to articulate how it can be possible for an *experience* to acquire higher dimensions. An important idea here is that there is a trade-off between degrees of freedom and geometric dimensions. We present a model where degrees of freedom can become interlocked in such a way that they functionally emulate the behavior of a *virtual* higher dimension. As exemplified by the “harmonograph”, one can indeed couple and interlock multiple oscillators in such a way that one generates paths of a point in a space that is higher-dimensional than the space inhabited by any of the oscillators on their own. More so, with a long qualia decay, one can use such technique to “paint” entire images in a *virtual* high dimensional canvas!

High-quality detailed phenomenology of DMT by rational psychonauts strongly suggests that higher virtual dimensions are widely present in the state. Also, the unique valence properties of the state seem to follow what we could call a “generalized music theory” where the “vibe” of the space is the net consonance between all of the metronomes in it. We indeed see a duality between spatial symmetry and temporal synchrony with modality-specific symmetries (equivariance maps) constraining the dynamic behavior.

This, together with the Symmetry Theory of Valence (Johnson), makes the search for “special divine numbers” suddenly meaningful: numerological correspondences can illuminate the underlying makeup of “heaven worlds” and other hedonically-loaded states of mind!

I conclude with a discussion about the nature of “highly-meaningful experiences”. In light of all of these frameworks, meaning can be understood as a valence effect that arises when you have strong consonance between abstract (narrative and symbolic), emotional, and sensory fields all at once. A key turning point in your life combined with the right emotion and the right “sacred space” can thus give rise to “peak meaning”. The key to infinite bliss!

~Qualia of the Day: Numerology~

Relevant links:

Thumbnail Image Source: Petri G., Expert P., Turkheimer F., Carhart-Harris R., Nutt D., Hellyer P. J. and Vaccarino F. 2014 Homological scaffolds of brain functional networks J. R. Soc. Interface.112014087320140873 – https://royalsocietypublishing.org/doi/full/10.1098/rsif.2014.0873

How can a bundle of atoms form a unified mind? This is far from a trivial question, and it demands an answer.

The phenomenal binding problem asks us to consider exactly that. How can spatially and temporally distributed patterns of neural activity contribute to the contents of a unified experience? How can various cognitive modules interlock to produce coherent mental activity that stands as a whole?

To address this problem we first need to break down “the hard problem of consciousness” into manageable subcomponents. In particular, we follow Pearce’s breakdown of the problem where we posit that any scientific theory of consciousness must answer: (1) why consciousness exists at all, (2) what are the set of qualia variety and values, and what is the nature of their interrelationships, (3) the binding problem, i.e. why are we not “mind dust”?, and (4) what are the causal properties of consciousness (how could natural selection recruit experience for information processing purposes, and why is it that we can talk about it). We discuss how trying to “solve consciousness” without addressing each of these subproblems is like trying to go to the Moon without taking into account air drag, or the Moon’s own gravitational field, or the fact that most of outer space is an air vacuum. Illusionism, in particular, seems to claim “the Moon is an optical illusion” (which would be true for rainbows – but not for the Moon, or consciousness).

Zooming in on (3), we suggest that any solution to the binding problem must: (a) avoid strong emergence, (b) side-step the hard problem of consciousness, (c) circumvent epiphenomenalism, and (d) be compatible with the modern scientific word picture, namely the Standard Model of physics (or whichever future version achieves full causal closure).

Given this background, we then explain that “the binding problem” as stated is in fact conceptually insoluble. Rather, we ought to reformulate it as the “boundary problem”: reality starts out unified, and the real question is how it develops objective and frame invariant boundaries. Additionally, we explain that “classic vs. quantum” is a false dichotomy, at least in so far as “classical explanations” are assumed to involve particles and forces. Field behavior is in fact ubiquitous in conscious experience, and it need not be quantum to be computationally relevant! In fact, we argue that nothing in experience makes sense except in light of holistic field behavior.

We then articulate exactly why all of the previously proposed solutions to the binding problem fail to meet the criteria we outlined. Among them, we cover:

  1. Cellular Automata
  2. Complexity
  3. Synchrony
  4. Integrated Information
  5. Causality
  6. Spatial Proximity
  7. Behavioral Coherence
  8. Mach Principle
  9. Resonance

Finally, we present what we believe is an actual plausible solution to the phenomenal binding problem that satisfies all of the necessary key constraints:

10. Topological segmentation

The case for (10) is far from trivial, which is why it warrants a detailed explanation. It results from realizing that topological segmentation allows us to simultaneously obtain holistic field behavior useful for computation and new and natural regions of fields that we could call “emergent separate beings”. This presents a completely new paradigm, which is testable using elements of the cohomology of electromagnetic fields.

We conclude by speculating about the nature of multiple personality disorder and extreme meditation and psychedelic states of consciousness in light of a topological solution to the boundary problem. Finally, we articulate the fact that, unlike many other theories, this explanation space is in principle completely testable.

~Qualia of the Day: Acqua di Gio by Giorgio Armani and Ambroxan~

Relevant links:

Why are we conscious?

The short answer is that bound moments of experience have useful causal and computational properties that can speed up information processing in a nervous system.

But what are these properties, exactly? And how do we know? In this video I unpack this answer in order to explain (or at least provide a proof of concept explanation for) how bound conscious states accomplish non-trivial speedups in computational problems (e.g. such as the problem of visual reification).

In order to tackle this question we first need to (a) enrich our very conception of computation, and (b) also enrich our conception of intelligence.

(a) Computation: We must realize that the Church-Turing Thesis conception of computation only cares about computing in terms of functions. That is, how inputs get mapped to outputs. But a much more general conception of computation also considers how the substrate allows for computational speed-ups via interacting inner states with intrinsic information. More so, if reality is made of “monads” that have non-zero intrinsic information and interact with one another, then our conception of “computation” must also consider monad networks. And in particular, the “output” of a computation may in fact be an inner bound state rather than just a sequence of discrete outputs (!).

(b) Intelligence: currently this is a folk concept poorly formalized by the instruments with which we measure it (primarily in terms of sequential logics-linguistic processing). But, alas, intelligence is a function of one’s entire world-simulation: even the shading of the texture of the table in front of you is contributing to the way you “see the world” and thus reason about it. So, an enriched conception of intelligence must also take into account: (1) binding, (2) the presence of a self, (3) perspective-taking, (4) distinguishing between the trivial and significant, and (5) state-space of consciousness navigation.

Now that we have these enriched conceptions, we are ready to make sense of the computational role of consciousness: in a way, the whole point of “intelligence” is to avoid brute force solutions by instead recruiting an adequate “self-organizing principle” that can run on the universe’s inherent massively parallel nature. Hence, the “clever” way in which our world-simulation is used: as shown by visual illusions, meditative states, psychedelic experiences, and psychophysics, perception is the result of a balance of field forces that is “just right”. Case in point: our nervous system utilizes the holistic behavior of the field of awareness in order to quickly find symmetry elements (cf. Reverse Grassfire Algorithm).

As a concrete example, I articulate the theoretical synthesis QRI has championed that combines Friston’s Free Energy Principle, Atasoy’s Connectome-Specific Harmonic Waves, Carhart-Harris’ Entropic Disintegration, and QRI’s Symmetry Theory of Valence and Neural Annealing to shows that the nervous system is recruiting the self-organizing principle of annealing to solve a wide range of computational problems. Other principles to be discussed at a later time.

To summarize: the reason we are conscious is because being conscious allows you to recruit self-organizing principles that can run on a massively parallel fashion in order to find solutions to problems at [wave propagation] speed. Importantly, this predicts it’s possible to use e.g. a visual field on DMT in order to quickly find the “energy minima” of a physical state that has been properly calibrated to correspond to the dynamics of a worldsheet in that state. This is falsifiable and exciting.

I conclude with a description of the Goldilock’s Zone of Oneness and why to experience it.

~Qualia of the Day: Dior’s Eau Sauvage (EDT)~

Relevant links:

Wada Test + Phenomenal Puzzles: Testing the Independent Consciousness of Individual Brain Hemispheres

by Quintin Frerichs

One of the most pressing problems in philosophy of mind is solving the so-called ‘problem of other minds‘, the difficulty of proving that agents outside oneself have qualia. A workable solution to the problem of other minds would endow us with the ability to define the moral patienthood of present-day biological entities, evade our solipsistic tendencies, and open the door to truly understanding future nonhuman intelligences, should they prove to be conscious. Even more strangely, it would allow us to evaluate whether dream characters or the products of dissociative identity disorder are separate consciousnesses. Irrevocably proving the existence of qualia in other biological life which lacks the capacity for language and higher-order thought is not, to my knowledge, even conceptually feasible at this time. In the case of two agents with the capacity to communicate and problem solve, however, this solution has been proposed, which requires the agent being tested to prove they have qualia by solving a “phenomenal puzzle”. Crucially, the solution does not require that the two agents experience the same qualia, simply that there exists a mapping between their respective conscious states.

If an agent A wishes to prove the existence of qualia in agent B using the above procedure, then A and B must have the following:

  1. A phenomenal bridge (e.g. a biological neural network that connects your brain to someone else’s brain so that both brains now instantiate a single consciousness).
  2. A qualia calibrator (a device that allows you to cycle through many combinations of qualia values quickly so that you can compare the sensory-qualia mappings in both brains and generate a shared vocabulary for qualia values).
  3. A phenomenal puzzle (as described above).
  4. The right set and setting: the use of a proper protocol.

I contend that there may already be a procedure which can be used to generate a reversible phenomenal bridge between two separate minds: a way to make two minds one and subsequently one mind two. Moving in each of these two directions has apparently been demonstrated; by craniopagus twins connected with a thalamic bridge and by corpus callosotomy separating the two cerebral hemispheres. There is tantalizing evidence in each case that consciousness is being fused or fissioned, respectively. In the case of the Hogan sisters, the apparently unitary mind  has access to sensory information from the sensory organs of each cranium. In the case of separating hemispheres there is some debate: alien hand syndrome has suggested the existence of dual consciousness, while other findings have cast doubt on the existence of two separate consciousnesses. While a surgical procedure for separating the hemispheres is as yet permanent, a chemically-induced separation of the hemispheres via the Wada test may provide new avenues for testing the problem of other minds. While some forms of communication (namely language, which is largely left-lateralized) are impaired by the Wada test, other forms such as singing can be left intact. Thus, I believe a combination of Gazzinaga’s procedure and Gómez Emilsson’s phenomenal puzzle approach, in conjunction with a working qualia calibrator, could demonstrate the existence or absence of dual consciousness in the human mind-brain. A version of the Wada test with higher specificity may also be required, to negate some of the characteristic symptoms of confusion, hemineglect, and loss of verbal comprehension.


The procedure (utilizing the state space of color, with agents L and R corresponding to the left and right hemispheres) would be as follows: 

Note: a difficulty of utilizing the below outlined procedure is determining which hemisphere should serve as the benchmark. While often language ability is dominant in the left hemisphere (especially in right-handed individuals) and therefore eliminated when the left hemisphere is inactivated during the Wada test, this is not always the case. In cases where at least some language ability is preserved in each hemisphere, either can reliably serve as the point of comparison. 

  1. Design a phenomenal puzzle, such that the solution corresponds to reporting the number of just noticeable differences required to produce a linear mapping between two locations in the state space of color. 
  2. Separate the left and right visual fields (Gazzaniga).
  3. Sodium amobarbital is administered to the left internal cardioid artery via the femoral artery and EEG confirms inactivation of the left hemisphere. In the LVF a consent checkbox for performing the experiment is given to the right hemisphere, Y/N checked using the left hand.
  4. Similarly, sodium amobarbital is administered to the right internal cardioid artery via the femoral artery and EEG confirms inactivation of the right hemisphere. Consent can be verbally obtained from the left hemisphere. 
  5. With both hemispheres activated, qualia calibration on the state space of color is performed (see: A workable solution to the problem of other minds). 
  6. With R inactivated, the phenomenal puzzle is presented to L without enough time for L to solve the puzzle.
  7. Both hemispheres are activated, and L tells the phenomenal puzzle to LR.
  8. L is inactivated and R attempts to solve the puzzle on its own. When R claims to have solved the puzzle (in writing or song most likely), both hemispheres are again reactivated in order to produce LR. R shares its solution with LR.
  9. R is inactivated, and L shares the solution to the phenomenal puzzle. If the solution is correct, then R is conscious! 

Point-of-view characterization of above procedure (Under the assumption that both hemispheres are, in fact, conscious):

  1. From the perspective of the left brain: A researcher asks “do you consent to the following procedure?” You answer ‘yes’, perhaps wondering if you’ve lost just a part of your computational resources, or created an entirely separate consciousness. A short period of darkness and sedation ensues while consent is obtained from the right brain. Suddenly, the amount of consciousness you’re experiencing expands greatly and new memories are available. The computer screen in front of you rapidly cycles through a series of paired color values. The Qualia Calibrator confirms a match by waiting for consensus of the right motor cortex (in lieu of a button press) and from verbal confirmation of the left hemisphere. It feels like an eye exam at hyper speed: “Color one or color two? Color two or color three?”, but for thousands of colors, many of which you don’t have a name for. Then, you sleep, for some indeterminate amount of time. When you awaken, the researcher explains to you the puzzle to solve. Your consciousness is then expanded again, and you repeat the puzzle to yourself, with the strange feeling that “part of you didn’t know about it”. You go dark again. And when the lights are turn on again, things feel normal, but you have a prominent new memory, the solution to the puzzle. Quickly you check. Take this strange shade of cyan and change it once, twice, three times…yup! That’s the mellow orange you were looking for, and in the same number of “just noticeable differences”.
  2. From the perspective of the right brain: You awaken to a scrollable consent form with a checkbox, and a left-handed mouse. Despite your state of relative confusion and lack of verbal fluency, you’re able to understand the form and check the box. Suddenly, your conscious experience expands and your fluency erupts. The computer screen in front of you rapidly cycles through a series of paired color values. The Qualia Calibrator confirms a match by waiting for consensus of the right motor cortex (in lieu of a button press) and from verbal confirmation of the left hemisphere. It feels like an eye exam at hyper speed: “Color one or color two? Color two or color three?”, but for thousands of colors, many of which you don’t have a name for. Again you sleep, your consciousness is briefly expanded, and you learn of the puzzle you are to solve. How did you learn about it? It is weird, you started “repeating” the puzzle to yourself, with the strange feeling that “part of you already had heard it before”. But either way, now you feel like you have heard it really well. Next, it feels like you took a strong sedative and a memory-loss drug at the same time. Now, in this highly impoverished cognitive state, you have to solve a complicated puzzle. To prove that you exist. Ugh. Fortunately, you have help, in the form of an AI which provides the linear mapping you need to discover, provided you answer how many just noticeable differences occur between each set of two points. Half man and machine collaborate to find the solution, and you commit it to memory. Reunited once more, you “share your findings to yourself”. It turns out you’re conscious. The world now knows: the right hemisphere is conscious on its own when the left one is unconscious. Hooray!

Empathetic Super-Intelligence

I suspect quite a lot of AI researchers would think of empathy as a very, kind of, second rate form of intelligence, and will confuse it with the mere personality dimension of agreeableness. But in fact empathetic understanding is extraordinarily cognitively demanding. It is worth recalling that what it is like to be another subject of experience, and what it is like to be able to apprehend fourth, fifth, and even -in the case of someone like Shakespeare- sixth order intentionality is as much a property of the natural world as the rest mass of the electron. So in so far as one wants to actually understand the nature of the natural world one is going to want to understand other subjects of experience.


Now most of us -and it is true for good evolutionary reasons- are not mirror-touch synesthete. We don’t feel the pain of others as if it were our own, we don’t experience their perspectives as if they were our own. But… I think with a greater full-spectrum of super-intelligence, as one actually comes to understand the perspectives of other subjects of experience, as one starts to obtain this god-like capacity to impartially understand all possible subjects of experience, this will entail expanding our circle of compassion. It is not possible if you are a mirror-touch synesthete to act in a non-friendly hostile way to another sentient being, and I would see a generalization of mirror-touch synesthesia as part and parcel of being a full-spectrum super-intelligence.


Any supposedly intelligent being that doesn’t understand the nature of consciousness -that doesn’t understand that there are other subjects of experience as real as you or me right now- is in a fundamental sense ignorant. And if we are talking about super-intelligence, as distinct from savant minds or insentient malware systems, one must remember that by definition a super-intelligence is not ignorant.


– David Pearce, in The Mind of David Pearce

David is responding to a question I posed about the relationship between empathy and super-intelligence. One could in principle imagine an Artificial Intelligence system that is capable of designing nanotechnology without ever being aware of other minds. The AI could take over the world from the ground up and never suspect that anyone actually lived in it. The AI could simply model other agents to the extent that is necessary to predict their behavior within the parameters that define the conditions of its success and failure. No need to experience the colors, aromas, feelings and thoughts of humans when you can approximate them well enough with a Bayesian system trained on past observed behaviors.

A lot of people seem to be worried about this sort of scenario. Admittedly, if one thinks that all there is to intelligence is the capacity to optimize a given utility function, then yes, super-intelligences could in principle be completely ignorant of the matter-of-fact about the qualia we are experiencing right now. AI safety organizations and researchers mostly care about this sort of intelligence. As far as the safety concerns go, I think this is fair enough. The problem comes when the view that intelligence is nothing more than utility function maximization conceptually spills over into one’s full conception of what intelligence is and will always be.

The contention here, I think, is the way we conceptualize intelligence. Depending on one’s background assumptions one will end up with some or other idea of what this concept can or cannot mean:

On the one hand, if one starts by exclusively caring about the way autonomous systems behave from a third-person point of view and in turn disregards the computational importance of consciousness, then any talk of “a deep understanding of the nature of other’s experiences” will seem completely besides the point. On the other hand, if one starts from an empathetic mindset that acknowledges the reality -and ethical weight- of the vastness of the state-space of consciousness, one may prefer to define intelligence in terms of empathetic understanding. I.e. as the capacity to explore, navigate, contrast, compare and utilize arbitrarily alien state-spaces of experience for computational and aesthetic purposes.

Most likely, an enriched conception of genuine super-intelligence entails a seamless blend between a deep capacity for introspection and empathy together with the extraordinary power of formal logico-linguistic reasoning. Only by combining the empathizing and systematizing styles of mental activity, together with a systematic exploration of the state-space of consciousness, can we obtain a full picture of the true potential that lies in front of us: Full-Spectrum Super-Sentient Super-Intelligence.

A Single 3N-Dimensional Universe: Splitting vs. Decoherence

A common way of viewing Everettian quantum mechanics is to say that in an act of measurement, the universe splits into two. There is a world in which the electron has x-spin up, the pointer points to “x-spin up,” and we believe the electron has x-spin up. There is another world in which the electron has x-spin down, the pointer points to “x-spin down,” and we believe the electron has x-spin down. This is why Everettian quantum mechanics is often called “the many worlds interpretation.” Because the contrary pointer readings exist in different universes, no one notices that both are read. This way of interpreting Everettian quantum mechanics raises many metaphysical difficulties. Does the pointer itself split in two? Or are there two numerically distinct pointers? If the whole universe splits into two, doesn’t this wildly violate conservation laws? There is now twice as much energy and momentum in the universe than there was just before the measurement. How plausible is it to say that the entire universe splits?


Although this “splitting universes” reading of Everett is popular (Deutsch 1985 speaks this way in describing Everett’s view, a reading originally due to Bryce Dewitt), fortunately, a less puzzling interpretation has been developed. This idea is to read Everett’s theory as he originally intended. Fundamentally, there is no splitting, only the evolution of the wave function according to the Shrödinger dynamics. To make this consistent with experience, it must be the case that there are in the quantum state branches corresponding to what we observe. However, as, for example, David Wallace has argued (2003, 2010), we need not view these branches -indeed, the branching process itself- as fundamental. Rather, these many branches or many worlds are patterns in the one universal quantum state that emerge as the result of its evolution. Wallace, building on work by Simon Saunders (1993), argues that there is a kind of dynamical process; the technical name for this process is “decoherence,” that can ground the emergence of quasi-classical branches within the quantum state. Decoherence is a process that involves an interaction between two systems (one of which may be regarded as a system and the other its environment) in which distinct components of the quantum state come to evolve independently of one another. That this occurs is the result of the wave function’s Hamiltonian, the kind of system it is. A wave function that (due to the kind of state it started out in and the Shrödinger dynamics) exhibits decoherence will enter into states capable of representation as a sum of noninteracting terms in particular basis (e.g., a position basis). When this happens, the system’s dynamics will appear classical from the perspective of the individual branches.




Note the facts about the quantum state decohering are not built into the fundamental laws. Rather, this is an accidental fact depending on the kind of state our universe started out in. The existence of these quasi-classical states is not a fundamental fact either, but something that emerges from the complex behavior of the fundamental state. The sense in which there are many worlds in this way of understanding Everettian quantum mechanics is therefore not the same as it is on the more naive approach already described. Fundamentally there is just one universe evolving according to the Schrödinger equation (or whatever is its relativistically appropriate analog). However, because of the special way this one world evolves, and in particular because parts of this world do not interfere with each other and can each on their own ground the existence of quasi-classical macro-objects that look like individual universes, it is correct in this sense to say (nonfundamentally) there are many worlds.




As metaphysicians, we are interested in the question of what the world is fundamentally like according to quantum mechanics. Some have argued that the answer these accounts give us (setting aside Bohmian mechanics for the moment) is that fundamentally all one needs to believe in is the wave function. What is the wave function? It is something that as we have already stated may be described as a field on configuration space, a space where each point can be taken to correspond to a configuration of particles, a space that has 3N dimensions where N is the number of particles. So, fundamentally, according to these versions of quantum mechanics (orthodox quantum mechanics, Everettian quantum mechanics, spontaneous collapse theories), all there is fundamentally is a wave function, a field in a high-dimensional configuration space. The view that the wave function is a fundamental object and a real, physical field on configuration space is today referred to as “wave function realism.” The view that such a wave function is everything there is fundamentally is wave function monism.


To understand wave function monism, it will be helpful to see how it represents the space on which the wave function is spread. We call this space “configuration space,” as is the norm. However, note that on the view just described, this is not an apt name because what is supposed to be fundamental on this view is the wave function, not particles. So, although the points in this space might correspond in a sense to particle configurations, what this space is fundamentally is not a space of particle configurations. Likewise, although we’ve represented the number of dimensions configuration space has as depending on the number N of particles in a system, this space’s dimensionality should not really be construed as dependent on the number of particles in a system. Nevertheless, the wave function monist need not be an eliminativist about particles. As we have seen, for example, in the Everettian approach, wave function monists can allow that there are particles, derivative entities that emerge out of the decoherent behavior of the wave function over time. Wave function monists favoring other solutions to the measurement problem can also allow that there are particles in this derivative sense. But the reason the configuration space on which the wave function is spread has the number of dimensions it does is not, in the final analysis, that there are particles. This is rather a brute fact about the wave function, and this in turn is what grounds the number of particles there are.


The Wave Function: Essays on the Metaphysics of Quantum Mechanics. Edited by Alyssa Ney and David Z Albert (pgs. 33-34, 36-37).

A workable solution to the problem of other minds

Deciding whether other entities are also conscious is not an insoluble philosophical problem. It is tricky. A good analogy might be a wire puzzle. At a first glance, the piece you have to free looks completely locked. And yet a solution does exist, it just requires to represent a sufficiently large number of facts and features that our working memory is not enough.


Usually showing the solution once will not fully satisfy one’s curiosity. It takes some time to develop a personally satisfying account. And to do so, we need to unpack how the various components interact with one another. After a while the reason why the free piece is not locked becomes intuitive, and at the same time you may also encounter mathematical arguments and principles to complement your understanding.

At first, though, the free piece looks and feels locked.

I think the problem of other minds is perceived similarly to a wire puzzle. At first it looks and feels insoluble. After a while, though, many suspect that the problem can be solved. This essay proposes a protocol that may point in the right direction. It could have some flaws as it is currently formulated, so I’m open to refinements of any kind. But I believe that it represents a drastic improvement over previous protocols, and it gets close to being a fully functioning proof of concept.

Starting from the basics: An approach that is widely discussed is the application of a Turing test. But a Turing test has several serious flaws when used as a test of consciousness. First, many conscious entities can’t pass a Turing test. So we know that it could have a very poor recall (missing most conscious entities). This problem is also present in every protocol I’m aware of. The major problem with it is that when an entity passes a Turing test, this can be counted as probabilistic evidence in favor of a large number of hypothesis, and not only to the desired conclusion that “this entity is conscious.” In principle highly persuasive chatbots could hack your entity recognition module by presenting hyperstimuli created by analyzing your biases for styles of conversation.

Your brain sees faces everywhere (cartoons, 2D computer screens, even clouds). It also sees entities where there are none. It might be much more simple to *trick* your judgement than actually create a sentient intelligence. Could the entity given the Turing test be an elaborate chatobot with no phenomenal binding? It seems likely that could take place.

Thus passing a Turing test is also not a guarantee that an entity is conscious. The method would have low recall and probably low accuracy too.

The second approach would be to simply *connect* your brain to the other entity’s brain (that is, of course, if you are not talking about a disembodied entity). We already have something like the Corpus Callosum, which seems to be capable of providing a bridge that solves the phenomenal binding problem between the hemispheres of a single person. In principle we could create a biologically similar, microfunctionally equivalent neural bridge between two persons.

Assuming physicalism, it seems very likely that there is a way for this to be done. Here, rather than merely observing the other person’s conscious experience, the point of connecting would be to become one entity. Strong, extremely compelling personal identity problems aside (Who are you really? Can you expect to ‘survive’ after the union? If you are the merged entity, does that mean you were always the same consciousness as the one with whom you merged?, etc. More on this on later posts), this possibility opens up the opportunity to actually corroborate that another entity is indeed conscious.

Indeed separate hemispheres can have very different opinions about the nature of reality. Assuming physicalism, why would it be the case that you can’t actually revert (or instantiate for the first time) the union between brains?

The previous idea has been proposed before. I think it is a significant improvement over the use of a Turing test, since you are directly addressing the main phenomenon in question (rather than its ripples). That said, the method has problems, and epistemic holes.  In brief, a big unknown is the effect that interfacing with another conscious experience has on both conscious experiences. For example, some people have (like Eliezer Yudkowsky and Brian Tomasik) argued that your interaction with the other brain could functionally expand your own mind. As it were, the interaction with the other brain could be interpreted as expanding your own mind by obtaining a large hardware upgrade. Thus it could be that the whole experience of being connected and becoming one with another entity is a fantasy of your recently-expanded mind. It can give you the impression that the other brain was already conscious before you were connected to it. So you can’t rule out that it was a zombie before and after the connection was over.

But there is a way out. And this is the stimulating part of the essay. Because I’m about to untangle the wires.

The great idea behind this solution is: Phenomenal puzzles. This one phenomenal puzzle linked here is about figuring out the appropriate geometry of color (arranging the state-space in an Euclidean manifold so that the degrees of subjective differences between colors are proportional to their distances). Doing this requires the ability of comparing the various parts of an experience to each other and being able to remember the comparison. In turn this can be iterated and generate a map of subjective differences. This is an instance of what I call qualia computing, where you need to be in touch with the subjective quality of your experience and to be capable of comparing sensations.

In brief, you want to give the other entity a puzzle that can only be solved by a conscious entity via manipulating and comparing qualia. The medium used to deliver the puzzle will be a first-person merging of brains: To share the puzzle you first connect with the entity you want to test.

By doing this, by sharing the puzzle when you are connected to the other entity, you will be able to know its inner referents in terms of qualia. While connected, you can point to a yellow patch and say “this is yellow.” Possibly, both halfs will have their own system of private referents (a natural consequence of having slightly different sense organs which make variable mappings between physical stimuli and qualia). But as a whole the merged entity will be able to compare notes with itself about the mapping of stimuli to qualia in both halfs. The entity could look at the same object from the point of view of its two heads at the same time and form an unified visual field, which incorporates the feed from the two former “personal-sized” visual fields (similarly to how you incorporate sensory stimuli from two eyes. Now you’ll see with four). The color appearance of the object could have a slightly different quality when the two visual fields are compared. That’s the fascinating thing about phenomenal binding. The differences in mappings between stimuli and qualia of the two former entities can be compared, which means that this difference can be analyzed and reasoned about and added to both repertoires of hippocampal snapshots of the current experience.

Then, when you disconnect from the other and there are two streams of consciousness going on again, you will both know what that “yellow” referred to. This overcomes the age-old problem of communicating private referents, and mutually agreeing on name for private referents. This way, the pieces of the (phenomenal) puzzle will be the same in both minds.

For the test to work, the specific question needs to stay secret until it is revealed briefly before merging.

Imagine that you have a set of standardized phenomenal puzzles. Psychologists and people who have done the test before tend to agree that the puzzles in the set do require you to explore a minimum number of states of consciousness. The tests have precise conceptual answers. These answers are extremely difficult to deliver by accident or luck.

The puzzles may require you to use external tools like an image editor or a computer. This is because computers can enable you to program combinations of sensory input in precise ways. This expands the phenomenal gamut you can reach. In turn one can calibrate sensory input to have nice properties (ex. use gamma correction).  The puzzles will also be selected based on the time sentient beings typically take to solve them.

When you want to perform the test, you meet with the entity right after you finish reading the phenomenal puzzle. The puzzle is calibrated to not be solvable in the time it will take you to connect to the other entity.

When you connect your brain to the other entity and become one conscious narrative, the entire entity reads the puzzle to itself. In other words, you state out loud the phenomenal puzzle by clearly pointing to the referents of the puzzle within your own “shared” experience. Then you disconnect the two brains.

In the time that the other entity is trying to solve the puzzle you distract yourself. This way you can prevent yourself from solving the puzzle. Ideally you might want to bring your state of consciousness to a very low activity. The other entity will have all of its stimuli controlled to guarantee there is no incoming information. All the “qualia processing” is going on through approved channels. When the entity claims to have solved the puzzle, at that point you connect your brain back to it.

Does the merged entity know anything about the solution to the puzzle? You search for a memory thread that shows the process of solving the puzzle and the eventual answer. Thanks to the calibration of this puzzle (it has also been given to “merged” entities before) we know you would need more time to solve it. Now you may find yourself in a position where you realize that if the other entity was a zombie, you would have somehow solved a phenomenal puzzle without using experience at all. If so, where did that information come from?

With the memory thread you can remember how the other entity arrived at the conclusion. All of the hard work can be attributed to the other entity now. You witness this confirmation as the merged entity, and then you disconnect. You will still hold redundant memories of the period of merging (both brains do, like the hemispheres in split-brain patients). Do you know the answer to the puzzle? You can now check your memory for it and see that you can reconstruct the answer very quickly. The whole process may even take less time than it would take you to solve the puzzle.

If you know the answer to the puzzle you can infer that the other entity is capable of manipulating qualia in the same way that you can. You would now have information that your mind/brain could only obtain by exploring a large region of the state-space of consciousness… which takes time. The answer to the puzzle is a verifiable fact about the structure of your conscious experience. It gives you information about your own qualia gamut (think CIELAB). In summary, the other entity figured out a fact about your own conscious experience, and explained it to you using your own private referents.

You can then conclude that if the entity solved the phenomenal puzzle for you, it must be capable of manipulating its qualia in a semantically consistent way to how you do it. A positive result reveals that the entity utilizes conscious algorithms. Perhaps even stronger: It also shares the generalizable computational power of a sapient mind.

Unfortunately just as for the Turing test, not passing this test is not a guarantee that the other entity lacks consciousness. What the test guarantees is a high precision: Near every entity that passes the test is conscious. And that is a milestone, I think.

Do you agree that the problem of other minds is like a wire puzzle?

Now go ahead and brainstorm more phenomenal puzzles!