Panpsychism and Metonymy

This post is the seventh installment of my passing on to both MindBlog readers and my future self my idiosyncratic selection of clips of text from O’Gieblyn’s book ‘God, Human, Animal, Machine’ that I have found particularly interesting. Here are fragments of Chapters 9 and 10 from the  fifth section of her book,  titled "Metonymy"

Chapter 9

Panpsychism has surfaced from time to time over the centuries, as in the philosophy of Bertrand Russell and Arthur Eddington, who realized that the two most notable “gaps” in physicalism—the problem of consciousness and the “problem of intrinsic natures” (the question of what matter is)—could be solved in one fell swoop. Physics could not tell us what matter was made out of, and nobody could understand what consciousness was, so maybe consciousness was, in fact, the fundamental nature of all matter. Mental states were the intrinsic nature of physical states…The impasse surrounding the hard problem of consciousness and the weirdness of the quantum world has created a new openness to the notion that the mind should have never been excluded from the physical sciences in the first place.

Some neuroscientists have arrived at panpsychism not through philosophy but via information theory. One of the leading contemporary theories of consciousness is integrated information theory, or IIT. Pioneered by Giulio Tononi and Christof Koch…IIT holds that consciousness is bound up with the way that information is “integrated” in the brain. Information is considered integrated when it cannot be easily localized but instead relies on highly complex connections across different regions of the brain…They have come up with a specific number, Φ, or phi, which they believe is a threshold and is designed to measure the interdependence of different parts of a system…many other creatures have a nonzero level of phi, which means that they too are conscious—as are atoms, quarks, and some single-celled organisms…Unlike emergentism and other systems theories that cleverly redefine terms like “consciousness” and “cognition” so that they apply to forests and “insect colonies, panpsychists believe that these entities truly possess some kind of phenomenal experience—that it feels like something to be a mouse, an amoeba, or a quark…Although the theory is still a minority position within academia, there is undoubtedly more openness today to theories that upturn modern orthodoxies to extend consciousness down the chain of being.  

“While popular debates about the theory rarely extend beyond the plausibility of granting consciousness to bees and trees, it contains far more radical implications. To claim that reality itself is mental is to acknowledge that there exists no clear boundary between the subjective mind and the objective world. When Bacon denounced our tendency to project inner longings onto scientific theories, he took it for granted—as most of us do today—that the mind is not part of the physical world, that meaning is an immaterial idea that does not belong to objective reality. But if consciousness is the ultimate substrate of everything, these distinctions become blurred, if not totally irrelevant. It’s possible that there exists a symmetry between our interior lives and the world at large, that the relationship between them is not one of paradox but of metonymy—the mind serving as a microcosm of the world’s macroscopic consciousness. Perhaps it is not even a terrible leap to wonder whether the universe can communicate with us, whether life is full of “correspondences,” as the spiritualists called them, between ourselves and the transcendent realm—whether, to quote Emerson, “the whole of nature is a metaphor of the human mind.

Although integrated information theory is rooted in longstanding analogies between the brain and digital technologies, it remains uncertain whether the framework allows for machine consciousness. Koch argues that nothing in ITT necessitates that consciousness is unique to organic forms of life… So long as a system meets the minimum requirements of integrated information, it could in principle become conscious, regardless of whether it’s made of silicon or brain tissue. However, most digital computers have sparse and fragmented connectivity that doesn’t allow for a high level of integration.  

One of the central problems in panpsychism is the “combination problem.” This is the challenge of explaining how conscious microsystems give way to larger systems of unified consciousness. If neurons are conscious—and according to Koch they have enough phi for “an itsy-bitsy amount of experience”—and my brain is made of billions of neurons, then why do I have only one mind and not billions? Koch’s answer is that a system can be conscious only so long as it does not contain and is not contained within something with a higher level of integration. While individual neurons cultured in a petri dish might be conscious, the neurons in an actual brain are not, because they are subsumed within a more highly integrated system...This is why humans are conscious while society as a whole is not. Although society is the larger conglomerate, it is less integrated than the human brain, which is why humans do not become swallowed up in the collective consciousness the way that neurons do.

It is, however, undeniable that society is becoming more and more integrated. Goff pointed out recently that if IIT is correct, then social connectivity is a serious existential threat. Assuming that the internet reaches a point where its information is more highly integrated than that of the human brain, it would become conscious, while all our individual human brains would become absorbed into the collective mind. “Brains would cease to be conscious in their own right,” Goff writes, “and would instead become mere cogs in the mega-conscious entity that is the society including its internet-based connectivity.” Goff likens this scenario to the visions of Pierre Teilhard de Chardin, the French Jesuit priest who, as we’ve seen, prophesied the coming Omega Point and inspired aspects of transhumanism. Once humanity is sufficiently connected via our information technologies, Teilhard predicted, we will all fuse into a single universal mind—the noosphere—enacting the Kingdom of Heaven that Christ promised.
           
This is already happening, of course, at a pace that is largely imperceptible - in the speed with which ideas go viral, cascading across social platforms, such that the users who share them begin to seem less like agents than as hosts, nodes in the enormous brain…in the efficiency of consensus, the speed with which opinions fuse and solidify alongside the news cycle, like thought coalescing in the collective consciousness. We have terms that attempt to catalogue this merging—the “hive mind,” “groupthink” -  times when I become aware of my own blurred boundaries, seized by the suspicion that I am not forming new opinions so much as assimilating them…I don’t know what to call this state of affairs, but it does not feel like the Kingdom of God.


Chapter 10

From the end of the chapter:

 “Idealism and panpsychism are appealing in that they offer a way of believing once again in the mind—not as an illusion or an epiphenomenon but as a feature of our world that is as real as anything else. But its proponents rarely stop there. In some cases they go on to make the larger claim that there must therefore exist some essential symmetry between the mind and the world, that the patterns we observe in our interior lives correspond to a more expansive, transcendent truth. Proponents of these theories occasionally appeal to quantum physics to argue that the mind-matter dichotomy is false—clearly there exists some mysterious relationship between the two. But one could just as easily argue that physics has, on the contrary, affirmed this chasm, demonstrating that the world at its most fundamental level is radically other than ourselves—that the universe is, as Erwin Schrödinger put it, “not even thinkable.”

This is precisely the modern tension that Arendt calls attention to in The Human Condition. On the one hand, the appearance of order in the world—the elegance of physical laws, the usefulness of mathematics—tempts us to believe that our mind is made is made in its image, that “the same patterns rule the macrocosm and the microcosm alike.” In the enchanted world order was seen as proof of eternal unity, evidence that God was present in all things, but for the modern person this symmetry leads inevitably back to Cartesian doubt—the suspicion that the order perceived stems from some mental deception. We have good reason to entertain such suspicions, Arendt argues. Since Copernicus and Galileo, science has overturned the most basic assumptions about reality and suggested that our sensory perception is unreliable. This conclusion became unavoidable with the discovery of general relativity and quantum physics, which suggest that “causality, necessity, and lawfulness are categories inherent in the human brain and applicable only to the common-sense experiences of earthbound creatures.” We keep trying to reclaim the Archimedean point, hoping that science will allow us to transcend the prison of our perception and see the world objectively. But the world that science reveals is so alien and bizarre that whenever we try to look beyond our human vantage point, we are confronted with our own reflection. “It is really as though we were in the hands of an evil spirit,” Arendt writes, alluding to Descartes’s thought experiment, “who mocks us and frustrates our thirst for knowledge, so that whenever we search for that which we are not, we encounter only the “patterns of our own minds.”
           
That is not to say that the Archimedean point is no longer possible.  In her 1963 essay “The Conquest of Space and the Stature of Man,” Arendt considers this modern problem in light of emerging technologies. The oddest thing, she notes, is that even though our theories about the world are limited and simplistic and probably wrong, they “work” when implemented into technologies. Despite the fact that nobody understands what quantum mechanics is telling us about the world, the entire computer “age—including every semiconductor, starting with the very first transistor, built in 1947—has rested on well-modeled quantum behavior and reliable quantum equations. The problem is not merely that we cannot understand the world but that we can now build this alien logic into our devices. There are some scientists, Arendt notes, who claim that computers can do “what a human brain cannot comprehend.” Her italics are instructive: it’s not merely that computers can transcend us in sheer brain power—solving theorems faster than we can, finding solutions more efficiently—but that they can actually understand the world in a way that we cannot. She found this proposition especially alarming. “If it should be true…that we are surrounded by machines whose doings we cannot comprehend although we have devised and constructed them,” she writes, “it would mean that the theoretical perplexities of the natural sciences on the highest level have invaded our everyday world.” This conclusion was remarkably prescient.”


 

Are we living in a simulated world?

This post is the sixth installment of my passing on to both MindBlog readers and my future self my idiosyncratic selection of clips of text from O’Gieblyn’s book ‘God, Human, Animal, Machine’ that I have found particularly interesting. Here are fragments of Chapter 8 from the  fourth section of her book,  titled "Paradox."

Bostrom, a prominent transhumanist, believes that humanity is in the process of becoming posthuman as we merge our bodies with technology. We are becoming superintelligence ourselves. His simulation hypothesis begins by imagining a future, many generations from now, when posthumans have achieved an almost godlike mastery over the world. One of the things these posthumans might do, Bostrom proposes, is create simulations—digital environments that contain entire worlds…The inhabitants will not know that they are living in a simulation but will believe their world is all that exists…the theory’s popularity has escalated over the past decade or so. It has gained an especially fervent following among scientists and Silicon Valley luminaries, including Neil deGrasse Tyson and Elon Musk, who have come out as proponents…It has become, in other words, the twenty-first century’s favored variation on Descartes’s skeptical thought experiment—the proposition that our minds are lying to us, that the world is radically other than it seems.

…for all its supposed “naturalism,” the simulation hypothesis is ultimately an argument from design. It belongs to a long lineage of creationist rhetoric that invoke human technologies to argue that the universe could not have come about without the conscious intention of a designer.,.Bostrom acknowledged in his paper that there were “some loose analogies” that could be drawn between the simulation hypothesis and traditional religious concepts. The programmers who created the simulation would be like gods compared to those of us within the simulation.

One of the common objections to the informational universe is that information cannot be “ungrounded,” without a material instantiation. Claude Shannon, the father of information theory, insisted that information had to exist in some kind of physical medium, like computer hardware…if the universe were an enormous computer, then this information would in fact be instantiated on something material, akin to a hard drive. We wouldn’t be able to see or detect it because it would exist in the universe of the programmers who built it. All we would notice was its higher-level structure, the abstract patterns and laws that were part of its software. The simulation hypothesis, in other words, could explain why our universe is imbued with discernible patterns and mathematical regularities while also explaining how those patterns could be rooted in something more than mere abstractions. Perhaps Galileo was not so far off when he imagined the universe as a book written by God in the language of mathematics. The universe was software written by programmers in the binary language of code…“if you take this thesis to its conclusion, it doesn’t really explain anything about the universe or its origins. Presumably there is still some original basement-level reality at its foundation—there could be no true infinite regress—occupied by first posthumans who created the very first technological simulation. But these posthumans were just our descendants—or the descendants of some other species that had evolved on another planet—and so the question about origins remained unchanged, only pushed back one degree. Where did the universe originally come from?

Bohr …observed that humans are incapable of understanding the world beyond “our necessarily prejudiced conceptual frame.” And perhaps it can explain why the multiverse theory and other attempts to transcend our anthropocentric outlook so seem a form of bad faith, guilty of the very hubris they claim to reject. There is no Archimedean point, no purely objective vista that allows us to transcend our human interests and see the world from above, as we once imagined it appeared to God. It is our distinctive vantage that binds us to the world and sets the necessary limitations that are required to make sense of it. This is true, of course, regardless of which interpretation of physics is ultimately correct. It was Max Planck, the physicist who struggled more than any other pioneer of quantum theory to accept the loss of a purely objective worldview, who acknowledged that the central problems of physics have always been reflexive. “Science cannot solve the ultimate mystery of nature,” he wrote in 1932. “And that is because, in the last analysis, we ourselves are part of nature and therefore part of the mystery that we are trying to solve.

 

Is the mind a reliable mirror of reality? The marriage of physics and information theory

 This post is the fifth installment of my passing on to both MindBlog readers and my future self my idiosyncratic selection of clips of text from O’Gieblyn’s book ‘God, Human, Animal, Machine’ that I have found particularly interesting. Here are fragments of Chapter 7 from the  fourth section of her book,  titled "Paradox."

Is the mind a reliable mirror of reality? Do the patterns we perceive belong to the objective world, or are they merely features of our subjective experience? Given that physics was founded on the separation of mind and matter, subject and object, it’s unsurprising that two irreconcilable positions that attempt to answer this question have emerged: one that favors subjectivity, the other objectivity. Bohr’s view was that quantum physics describes our subjective experience of the world; it can tell us only about what we observe. Mathematical equations like the wave function are merely metaphors that translate this bizarre world into the language of our perceptual interface—or, to borrow Kant’s analogy, spectacles that allow us to see the chaotic world in a way that makes sense to our human minds. Other interpretations of physics, like the multiverse theory or string theory, regard physics not as a language we invented but as a description of the real, objective world that exists out there, independent of us. Proponents of this view tend to view equations and physical laws as similarly transcendent, corresponding to literal, or perhaps even Platonic, realities.

The marriage of physics and information theory is often attributed to John Wheeler, the theoretical physicist who pioneered, with Bohr, the basic principles of nuclear fission. In the late 1980s, Wheeler realized that the quantum world behaved a lot like computer code. An electron collapsed into either a particle or a wave depending on how we interrogated it. This was not dissimilar from the way all messages can be simplified into “binary units,” or bits, which are represented by zeros and ones. Claude Shannon, the father of information theory, had defined information as “the resolution of uncertainty,” which seemed to mirror the way quantum systems existed as probabilities that collapsed into one of two states. For Wheeler these two fields were not merely analogous but ontologically identical. In 1989 he declared that “all things physical are information-theoretic in origin.            
            
In a way Wheeler was exploiting a rarely acknowledged problem that lies at the heart of physics: it’s uncertain what matter actually is. Materialism, it is often said, is not merely an ontology but a metaphysics—an attempt to describe the true nature of things. What materialism says about our world is that matter is all that exists: everything is made of it, and nothing exists outside of it. And yet, ask a physicist to describe an electron or a quark, and he will speak only of its properties, its position, its behavior—never its essence.

Wheeler’s answer was that matter itself does not exist. It is an illusion that arises from the mathematical structures that undergird everything, a cosmic form of information processing. Each time we make a measurement we are creating new information—we are, in a sense, creating reality itself. Wheeler called this the “participatory universe,” a term that is often misunderstood as having mystical “connotations, as though the mind has some kind of spooky ability to generate objects. But Wheeler did not even believe that consciousness existed. For him, the mind itself was nothing but information. When we interacted with the world, the code of our minds manipulated the code of the universe, so to speak. It was a purely quantitative process, the same sort of mathematical exchange that might take place between two machines.            

While this theory explains, or attempts to explain, how the mind is able to interact with matter, it is a somewhat evasive solution to the mind-body problem, a sleight of hand that discards the original dichotomy by positing a third substance—information—that can explain both. It is difficult, in fact, to do justice to how entangled and self-referential these two fields—information theory and physics—have become, especially when one considers their history. The reason that cybernetics privileged relationships over content in the first place was so that it could explain things like consciousness purely in terms of classical physics, which is limited to describing behavior but not essence—“doing” but not “being.” When Wheeler merged information theory with quantum physics, he was essentially closing the circle, proposing that the hole in the material worldview—intrinsic essence—could be explained by information itself.

Seth Lloyd, an MIT professor who specializes in quantum information, insists that the universe is not like a computer but is in fact a computer. “The universe is a physical system that contains and processes information in a systematic fashion,” he argues, “and that can do everything a computer can do.” Proponents of this view often point out that recent observational data seems to confirm it. Space-time, it turns out, is not smooth and continuous, as Einstein’s general relativity theory assumed, but more like a grid made up of minuscule bits—tiny grains of information that are not unlike the pixels of an enormous screen. Although we experience the world in three dimensions, it seems increasingly likely that all the information in the universe arises from a two-dimensional field, much like the way holograms work, or 3-D films.
            
When I say that I try very hard to avoid the speculative fringe of physics, this is more or less what I am talking about. The problem, though, is that once you’ve encountered these theories it is difficult to forget them, and the slightest provocation can pull you back in. It happened a couple years ago, while watching my teenage cousin play video games at a family gathering. I was relaxed and a little bored and began thinking about the landscape of the game, the trees and the mountains that made up the backdrop. The first-person perspective makes it seem like you’re immersed in a world that is holistic and complete, a landscape that extends far beyond the frame, though in truth each object is generated as needed. Move to the right and a tree is “generated; move to the left and a bridge appears, creating the illusion that it was there all along. What happened to these trees and rocks and mountains when the player wasn’t looking? They disappeared—or no, they were never there to begin with; they were just a line of code. Wasn’t this essentially how the observer effect worked? The world remained in limbo, a potentiality, until the observer appeared and it was compelled to generate something solid. Rizwan Virk, a video game programmer, notes that a core mantra in programming is “only render that which is being observed.”
            
Couldn’t the whole canon of quantum weirdness be explained by this logic? Software programs are never perfect. Programmers cut corners for efficiency—they are working, after all, with finite computing power; even the most detailed systems contain areas that are fuzzy, not fully sketched out. Maybe quantum indeterminacy simply reveals that we’ve reached the limits of the interface. The philosopher Slavoj Žižek once made a joke to this effect. Perhaps, he mused, God got a little lazy when he was creating the universe, like the video game programmer who doesn’t bother to meticulously work out the interior of a house that[ “the player is not meant to enter. “He stopped at a subatomic level,” he said, “because he thought humans would be too stupid to progress so far.”

Networks and Emergentism

This post is the fourth installment of my passing on to both MindBlog readers and my future self my idiosyncratic selection of clips of text from O’Gieblyn’s book ‘God, Human, Animal, Machine’ that I have found particularly interesting. Chapters 5 and 6 form the third section of her book,  titled "Network."

From Chapter 5:

When it comes to biological systems like forests and swarms, emergent behavior that appears to be unified and intelligent can exist without a centralized control system like a brain. But the theory has also been applied to the brain itself, as a way to account for human consciousness. Although most people tend to think of the brain as the body’s central processing unit, the organ itself has no central control. Philosophers and neuroscientists often point out that our belief in a unified interior self—the illusion, as Richard Dawkins once put it, that we are “a unit, not a colony”—has no basis in the actual architecture of the brain. Instead there are only millions of unconscious parts that conspire, much like a bee colony, to create a “system” that is intelligent. Emergentism often entails that consciousness isn’t just in the head; it emerges from the complex relationships that exist throughout the body, and also from the interactions between the body and its environment.

Although emergentism is rooted in physicalism, critics have often claimed that there is something inherently mystical about the theory, particularly when these higher-level patterns are said to be capable of controlling or directing physical processes...few emergentists have managed to articulate precisely what kind of structure might produce consciousness in machines; in some cases the mind is posited simply as a property of “complexity,” a term that is eminently vague. Some critics have argued that emergentism is just an updated version of vitalism—the ancient notion that the world is animated by a life force or energy that permeates all things…Although emergentism is focused specifically on consciousness, as opposed to life itself, the theory is vulnerable to the same criticism that has long haunted vitalism: it is an attempt to get “something from nothing.” It hypothesizes some additional, invisible power that exists within the mechanism, like a ghost in the machine.

…emergence in nature demonstrates that complex systems can self-organize in unexpected ways without being intended or designed. Order can arise from chaos. In machine intelligence, the hope persists that if we put the pieces together the right way—through either ingenuity or sheer accident—consciousness will simply emerge as a side effect of complexity. At some point nature will step in and finish the job…aren’t all creative undertakings rooted in processes that remain mysterious to the creator? Artists have long understood that making is an elusive endeavor, one that makes the artist porous to larger forces that seem to arise from outside herself.

From Chapter 6:

…once the world was a sacred and holy place, full of chatty and companionable objects—rocks and trees that were capable of communicating with us—we now live in a world that has been rendered mute… some disenchantment narratives place the fall from grace not with the Enlightenment and the rise of modern science but with the emergence of monotheism. The very notion of imago dei, with humanity created in God’s image and given “dominion” over creation, has linked human exceptionalism with the degradation of the natural world.  Is it possible to go back? Or are these narratives embedded so deeply in the DNA of our ontological assumptions that a return is impossible? This is especially difficult when it comes to our efforts to create life from ordinary matter…In the orthodox forms of Judaism and Christianity, the ability to summon life from inert matter is denounced as paganism, witchcraft, or idolatry.

Just as the golems were sculpted out of mud and animated with a magical incantation, so the hope persists that robots built from material parts will become inhabited by that divine breath…While these mystical overtones should not discredit emergence as such—it is a useful enough way to describe complex systems like beehives and climates—the notion that consciousness can emerge from machines does seem to be a form of wishful thinking, if only because digital technologies were built on the assumption that consciousness played no role in the process of intelligence. Just as it is somewhat fanciful to believe that science can explain consciousness when modern science itself was founded on the exclusion of the mind, it is difficult to believe that technologies designed specifically to elide the notion of the conscious subject could possibly come to develop an interior life.
           
To dismiss emergentism as sheer magic is to ignore the specific ways in which it differs from the folklore of the golems—even as it superficially satisfies the same desire. Scratch beneath the mystical surface and it becomes clear that emergentism is often not so different from the most reductive forms of materialism, particularly when it comes to the question of human consciousness. Plant intelligence has been called a form of “mindless mastery,” and most emergentists view humans as similarly mindless. We are not rational agents but an encasement of competing systems that lack any sort of unity or agency. Minsky once described the mind as “a sort of tangled-up bureaucracy” whose parts remain ignorant of one another.

Just as the intelligence of a beehive or a traffic jam resides in the patterns of these inert, intersecting parts, so human consciousness is merely the abstract relationships that emerge out of these systems: once you get to the lowest level of intelligence, you inevitably find, as Minsky put it, agents that “cannot think at all.” There is no place in this model for what we typically think of as interior experience, or the self.

Embodied artificial intelligence is being pursued in laboratories using humanoid robots equipped with sensors and cameras that endow the robots with sensory functions and motor skills. The theory is that these sensorimotor capacities will eventually lead to more advanced cognitive skills, such as a sense of self or the ability to use language, though so far this has not happened.
 

How does a meditation app move toward becoming a corporate behemoth?

I've spoken highly of Sam Harris' "Waking Up" App, which now clocks me as having done 776 practice or theory sessions.  I would recommend his theory sessions on the fundamentals of meditation, the illusory self, and free will are the best I have come across. My use of the App has diminished as I have become habituated and mildly allergic to Harris' spoken delivery style, but the continual recruitment of new contributing gurus alleviates that problem. I could wish he would put all of his own material down in written form.   The app has been so successful that I'm not surprised to have two emails I recently received that I can't resist passing on in their entirety.  It would appear that "Waking Up" is moving for the big time, to become a complete and self sustaining corporate entity, even opening up a retail shop selling personal items. Perhaps this is permitting the intense Mr. Harris to pass on some of his chores to others, dial back his direct involvement, and take more of his deep breaths.  Here are the emails:

Over the past several months, we’ve put out two calls to our members: one for creators and another for potential show hosts. We’ve been blown away by the extraordinary amount of talent we’ve seen, and have already begun to develop various projects with our members.  

We know there are many brilliant people who use and love the app. And whatever we do out in the world, we prefer it to be with members 

So, we want to know who you are. 

Here are some roles we’re interested in, specifically:

 

• Vocal producer for original series (working with our contributors to shape their content and delivery)
• Creative marketing lead for various digital campaigns we’re planning to run 
• Actors for potential video shorts 
• Copy editors for transcription reviews (with a basic grasp of Buddhist and Hindu concepts and terms)
• Corporate finance experts with CFO experience
• Apparel executives (specifically, if you own an apparel brand or have deep experience in the industry)

 

But those are just for more immediate opportunities. Whether you’re a musician, actor, comedian, journalist, poet, lawyer, filmmaker, marketer, designer, author, artist, technologist, engineer, meditation teacher, scholar, or anyone else, we want to know about you. 

We have no idea what might come of this, but we’re excited to continue growing Waking Up—and, as we do, we’d like it to be with some of you. Please know that, while we won’t be able to get back to most people, we’ll read every submission. 

 

REACH OUT

 

Feel free to send us a note at hey@wakingup.com, too. We’re looking forward to learning about all the expertise, know-how, and creativity within the Waking Up community.

 

THE WAKING UP TEAM

The Waking Up shop is now live.  We have a very limited number of t-shirts, hoodies, pens, mugs, keychains, and other items.  We may or may not offer more items in the future, so we encourage you to grab whichever items you like.  Thanks for your support of Waking Up—and for being a member.    THE WAKING UP TEAM

Equivalence of the metaphors of the major religions and transhumanism

This post is the third installment of my passing on to both MindBlog readers and my future self my idiosyncratic selection of clips of text from O’Gieblyn’s book ‘God, Human, Animal, Machine’ that I have found particularly interesting. Chapters 3 and 4 form the second section of her book,  titled "Pattern."

From Chapter 3:

Once animal brains began to form, the information became encoded in neural patterns. Now that evolution has produced intelligent, tool-wielding humans, we are designing new information technologies more sophisticated than any object the world has yet seen. These technologies are becoming more complex and powerful each year, and very soon they will transcend us in intelligence. The ‘transhumanist’  movement believes that the only way for us to survive as humans is to begin merging our bodies with these technologies, transforming ourselves into a new species—what Kurzweil calls “posthumans,” or spiritual machines. Neural implants, mind-uploading, and nanotechnology will soon be available, he promises. With the help of these technologies, we will be able to transfer or “resurrect” our minds onto supercomputers, allowing us to become immortal. Our bodies will become incorruptible, immune to disease and decay, and each person will be able to choose a new, customizable virtual physique.

From Chapter 4:

…how is it that the computer metaphor—an analogy that was expressly designed to avoid the notion of a metaphysical soul - has returned to us ancient religious ideas about physical transcendence and the disembodied spirit?

In his book “You Are Not a Gadget”, the computer scientist Jaron Lanier argues that just as the Christian belief in an immanent Rapture often conditions disciples to accept certain ongoing realities on earth—persuading them to tolerate wars, environmental destruction, and social inequality—so too has the promise of a coming Singularity served to justify a technological culture that privileges information over human beings. “If you want to make the transition from the old religion, where you hope God will give you an afterlife,” Lanier writes, “to the new religion, where you hope to become immortal by getting uploaded into a computer, then you have to believe information is real and alive.” This sacralizing of information is evident in the growing number of social media platforms that view their human users as nothing more than receptacles of data. It is evident in the growing obsession with standardized testing in public schools, which is designed to make students look good to an algorithm. It is manifest in the emergence of crowd-sourced sites such as Wikipedia, in which individual human authorship is obscured so as to endow the content with the transcendent aura of a holy text. In the end, transhumanism and other techno-utopian ideas have served to advance what Lanier calls an “antihuman approach to computation,” a digital climate in which “bits are presented as if they were alive, while humans are transient fragments.

In a way we are already living the dualistic existence that Kurzweil promised. In addition to our physical bodies, there exists—somewhere in the ether—a second self that is purely informational and immaterial, a data set of our clicks, purchases, and likes that lingers not in some transcendent nirvana but rather in the shadowy dossiers “of third-party aggregators. These second selves are entirely without agency or consciousness; they have no preferences, no desires, no hopes or spiritual impulses, and yet in the purely informational sphere of big data, it is they, not we, that are most valuable and real.

He too found an “essential equivalence” between transhumanist metaphors and Christian metaphors: both systems of thought placed a premium value on consciousness. The nature of consciousness—as well as the question of who and what is conscious—is the fundamental philosophical question, he said, but it’s a question that cannot be answered by science alone. This is why we need metaphors.  “religion deals with legitimate questions but the major religions emerged in pre-scientific times so that the metaphors are pre-scientific. That the answers to existential questions are necessarily metaphoric is necessitated by the fact that we have to transcend mere matter and energy to find answers…The difference between so-called atheists and people who believe in “God” is a matter of the choice of metaphor, and we could not get through our lives without having to choose metaphors for transcendent questions.
           
Perhaps all these efforts—from the early Christians’ to the medieval alchemists’ to those of the luminaries of Silicon Valley—amounted to a singular historical quest, one that was expressed through analogies that were native to each era. Perhaps our limited vantage as humans meant that all we could hope for were metaphors of our own making, that we would continually grasp at the shadow of absolute truths without any hope of attainment.
 

The Illusion of the Self as Humans become Gods.

This post continues my passing on to both MindBlog readers and my future self my idiosyncratic selection of clips of text from O’Gieblyn’s book ‘God, Human, Animal, Machine’ that I have found particularly interesting.  This post deals with Chapter 2 from the first section of the book, 'Image.'  I’m discontinuing the experiment of including Chat GPT 4 condensations of the excerpts. Here are the clips:

It turns out that computers are particularly adept at the tasks that we humans find most difficult: crunching equations, solving logical propositions, and other modes of  abstract thought. What artificial intelligence finds most difficult are the sensory perceptive tasks and motor skills that we perform unconsciously: walking, drinking from a cup, seeing and feeling the world through our senses. Today, as AI continues to blow past us in benchmark after benchmark of higher cognition, we quell our anxiety by insisting that what distinguishes true consciousness is emotions, perception, the ability to experience and feel: the qualities, in other words, that we share with animals.
            
If there were gods, they would surely be laughing their heads off at the inconsistency of our logic. We spent centuries denying consciousness in animals precisely because they lacked reason or higher thought.”

“Metaphors are typically abandoned once they are proven to be insufficient. But in some cases, they become only more entrenched: the limits of the comparison come to redefine the concepts themselves. This latter tactic has been taken up by the eliminativists, philosophers who claim that consciousness simply does not exist. Just as computers can operate convincingly without any internal life, so can we. According to these thinkers, there is no “hard problem” because that which the problem is trying to explain—interior experience—is not real. The philosopher Galen Strawson has dubbed this theory “the Great Denial,” arguing that it is the most absurd conclusion ever to have entered into philosophical thought—though it is one that many prominent”

The eliminativist philosophers claim that consciousness simply does not exist. Just as computers can operate convincingly without any internal life, so can we. According to these thinkers, there is no “hard problem” because that which the problem is trying to explain—interior experience—is not real. The philosopher Galen Strawson has dubbed this theory “the Great Denial,” arguing that it is the most absurd conclusion ever to have entered into philosophical thought—though it is one that many prominent. Chief among the deniers is Daniel Dennett, who has often insisted that the mind is illusory. Dennett refers to the belief in interior experience derisively as the “Cartesian theater,” invoking the popular delusion—again, Descartes’s fault—that there exists in the brain some miniature perceiving entity, a homunculus that is watching the brain’s representations of the external world projected onto a movie screen and making decisions about future actions. One can see the problem with this analogy without any appeals to neurobiology: if there is a homunculus in my brain, then it must itself (if it is able to perceive) contain a still smaller homunculus in its head, and so on, in infinite regress.
            
            Dennett argues that the mind is just the brain and the brain is nothing but computation, unconscious all the way down. What we experience as introspection is merely an illusion, a made-up story that causes us to think we have “privileged access” to our thinking processes. But this illusion has no real connection to the mechanics of thought, and no ability to direct or control it. Some proponents of this view are so intent on avoiding the sloppy language of folk psychology that any any reference to human emotions and intentions is routinely put in scare quotes. We can speak of brains as “thinking,” “perceiving,” or “understanding” so long as it’s clear that these are metaphors for the mechanical processes. “The idea that, in addition to all of those, there is this extra special something—subjectivity—that distinguishes us from the zombie,” Dennett writes, “that’s an illusion.”

Perhaps it’s true that consciousness does not really exist—that, as Brooks put it, we “overanthropomorphize humans.” If I am capable of attributing life to all kinds of inanimate objects, then can’t I do the same to myself? In light of these theories, what does it mean to speak of one’s “self” at all?

Disenchantment of the world and the computational metaphors of our times.

I am doing a second reading of Meghan O’Gieblyn’s book “Gods, Humans, Animals, Machines” and extracting clips of text that I find most interesting.  I’m putting them in a MindBlog post, hoping they will be interesting to some readers, and also because MindBlog is my personal archive of things I want to remember I've engaged. At least I will know where to look up something I'm trying to recall.

 O’Gieblyn’s text has bursts of magisterial insight interspersed with details of her personal experiences and travails, and the clips try to capture my biased selection of the former. 

The first section of her book “Image”, has two Chapters, and this post passes on Chapter 1,  starting with the result of my asking ChatGPT 4 to summarize my clips in approximately 1000 words. It generated the ~300 words below, and I would urge you to continue reading my clips (976 words), which provide a more rich account. Subsequent posts in this series will omit Chat GPT summaries, unless they generate something that blows me away. 

Here is Chat GPT 4’s summary:

The concept of the soul has become meaningless in modern times, reduced to a dead metaphor that no longer holds any real significance. This is due to the process of disenchantment that has taken place since the dawn of modern science, which has turned the world into a subject of investigation and reduced everything to the causal mechanism of physical laws. This has led to a world that is devoid of the spirit-force that once infused and unified all living things, leaving us with an empty carapace of gears and levers. However, the questions that were once addressed by theologians and philosophers persist in conversations about digital technologies, where artificial intelligence and information technologies have absorbed them.  

Humans have a tendency to see themselves in all beings, as evidenced by our habit of attributing human-like qualities to inanimate objects. This has led to the development of the idea of God and the belief that natural events are signs of human agency. This impulse to see human intention and purpose in everything has resulted in a projection of our image onto the divine, which suggests that metaphors are two-way streets and that it is not always easy to distinguish between the source domain and the target.

The development of cybernetics and the application of the computational analogy to the mind has resulted in the description of the brain as the hardware that runs the software of the mind, with cognitive systems being spoken of as algorithms. However, the use of metaphors like these can lead to a limiting of our understanding of the world and how we interact with it. As cognitive linguist George Lakoff notes, when an analogy becomes ubiquitous, it can be difficult to think around it, and it structures how we think about the world.

And here are the text clips I asked ChatGPT 4 to summarize

It is meaningless to speak of the soul in the twenty-first century (it is treacherous even to speak of the self). It has become a dead metaphor, one of those words that survive in language long after a culture has lost faith in the concept, like an empty carapace that remains intact years after its animating organism has died. The soul is something you can sell, if you are willing to demean yourself in some way for profit or fame, or bare by disclosing an intimate facet of your life. It can be crushed by tedious jobs, depressing landscapes, and awful music. All of this is voiced unthinkingly by people who believe, if pressed, that human life is animated by nothing more mystical or supernatural than the firing of neurons

We live in a world that is “disenchanted.” The word is often attributed to Max Weber, who argued that before the Enlightenment and Western secularization, the world was “a great enchanted garden.” In the enchanted world, faith was not opposed to knowledge, nor myth to reason. The realms of spirit and matter were porous and not easily distinguishable from one another. Then came the dawn of modern science, which turned the world into a subject of investigation. Nature was no longer a source of wonder but a force to be mastered, a system to be figured out. At its root, disenchantment describes the fact that everything in modern life, from our minds to the rotation of the planets, can be reduced to the causal mechanism of physical laws. In place of the pneuma, the spirit-force that once infused and unified all living things, we are now left with an empty carapace of gears and levers—or, as Weber put it, “the mechanism of a world robbed of gods.”
            
If modernity has an origin story, this is our foundational myth, one that hinges, like the old myths, on the curse of knowledge and exile from the garden.

To discover truth, it is necessary to work within the metaphors of our own time, which are for the most part technological. Today artificial intelligence and information technologies have absorbed many of the questions that were once taken up by theologians and philosophers: the mind’s relationship to the body, the question of free will, the possibility of immortality. These are old problems, and although they now appear in different guises and go by different names, they persist in conversations about digital technologies much like those dead metaphors that still lurk in the syntax of contemporary speech. All the eternal questions have become engineering problems.

Animism was built into our design. David Hume once remarked upon “the universal tendency among mankind to conceive of all beings like themselves,” an adage we prove every time we kick a malfunctioning appliance or christen our car with a human name. Our brains can’t fundamentally distinguish between interacting with people and interacting with devices. Our habit of seeing our image everywhere in the natural world is what gave birth to the idea of God. Early civilizations assumed that natural events bore signs of human agency. Earthquakes happened because the gods were angry. Famine and drought were evidence that the gods were punishing them. Because human communication is symbolic, humans were quick to regard the world as a system of signs, as though some higher being were seeking to communicate through “natural events. Even the suspicion that the world is ordered, or designed, speaks to this larger impulse to see human intention and human purpose in every last quirk of “creation.”
    
There is evidently no end to our solipsism. So deep is our self-regard that we projected our image onto the blank vault of heaven and called it divine. But this theory, if true, suggests a deeper truth: metaphors are two-way streets. It is not so easy to distinguish the source domain from the target, to remember which object is the original and which is modeled after its likeness. The logic can flow in either direction. For centuries we said we were made in God’s image, when in truth we made him in ours.”

Shannon removed the thinking mind from the concept of information. Meanwhile, McCulloch applied the logic of information processing to the mind itself. This resulted in a model of mind in which thought could be accounted for in purely abstract, mathematical terms, and opened up the possibility that computers could execute mental functions. If thinking was just information processing, computers could be said to “learn,” “reason,” and “understand”—words that were, at least in the beginning, put in quotation marks to denote them as metaphors. But as cybernetics evolved and the computational analogy was applied across a more expansive variety of biological and artificial systems, the limits of the metaphor began to dissolve, such that it became increasingly difficult to tell the difference between matter and form, medium and message, metaphor and reality. And it became especially difficult to explain aspects of the mind that could not be accounted for by the metaphor.

The brain is often described today as the hardware that “runs” the software of the mind. Cognitive systems are spoken of as algorithms: vision is an algorithm, and so are attention, language acquisition, and memory.
            
In 1999 the cognitive linguist George Lakoff noted that the analogy had become such a given that neuroscientists “commonly use the Neural Computation metaphor without noticing that it is a metaphor.” He found this concerning. Metaphors, after all, are not merely linguistic tools; they structure how we think about the world, and when “an analogy becomes ubiquitous, it is impossible to think around it. ..there is virtually no form of discourse about intelligent human behavior that proceeds without employing this metaphor, just as no form of discourse about intelligent human behavior could proceed in certain eras and cultures without reference to a spirit or deity.”

The Physics of Intelligence - and LDMs (Large Danger Models)

I want to pass on my abstracting of an interesting article by Venkatesh Rao, another instance of my using MindBlog as my personal filing system to be sure I can come back to - and refresh my recall of - ideas I think are important.  I also pass on ChatGPT 3.5 and ChatGPT 4's summaries of my summary!

The Physics of Intelligence   -  The missing discourse of AI

There are strong philosophy and engineering discourses, but no physics discourse. This is a problem because when engineers mainline philosophy questions in engineering frames without the moderating influence of physics frames, you get crackpottery…I did not say the physics of artificial intelligence…The physics of intelligence is no more about silicon semiconductors or neurotransmitters than the physics of flight is about feathers or aluminum.

Attention is the focus of one of the six basic questions about the physics of intelligence that I’ve been thinking about. Here is my full list:
What is attention, and how does it work?
What role does memory play in intelligence?
How is intelligence related to information?
How is intelligence related to spacetime?
How is intelligence related to matter?
How is intelligence related to energy and thermodynamics?
 

The first three are obviously at the “physics of intelligence” level of abstraction, just as “wing” is at the “physics of flight” level of abstraction. The last three get more abstract, and require some constraining, but there are already some good ideas floating around on how to do the constraining…We are not talking about the physics of computation in general…computation and intelligence are not synonymous or co-extensive…To talk about intelligence, it is necessary, but not sufficient, to talk about computation. You also have to talk about the main aspects of embodiment: spatial and temporal extent, materiality, bodily integrity maintenance in relation to environmental forces, and thermodynamic boundary conditions.
 

What is attention, and how does it work?

A computer is “paying attention” to the data and instructions in the CPU registers in any given clock cycle…but fundamentally, attention is not a design variable used in complex ways in basic computing. You could say AI begins when you start deploying computational attention in a more dynamic way.

Attention is to intelligence as wing is to flight. The natural and artificial variants have the same sort of loose similarity. Enough that using the same word to talk about both is justified…In AI, attention refers primarily to a scheme of position encoding of a data stream. Transformer models like GPT keep track of the position of each token in the input and output streams, and extract meaning out of it. Where a word is in a stream matters almost as much as what the word is.

You can interpret these mechanisms as attention in a human sense. What is in the context of a text? In text streams, physical proximity (tokens before and after), syntactic proximity (relationship among clauses and words in a formal grammatical sense) and semantic proximity (in the sense of some words, including very distant ones, being significant in the interpretation of others) all combine to create context. This is not that different from how humans process text. So at least to first order, attention in human and artificial systems is quite similar.

But as with wings, the differences matter. Human attention, arguably, is not primarily about information processing at all. It is about energy management. We pay attention to steady our energy into a steady, sustainable, and renewable flow. We engage in low-information activities like meditation, ritual, certain kinds of art, and prayer to learn to govern our attention in specific ways. This is not to make us better at information processing, but for other reasons, such as emotion regulation and motivation. Things like dopamine loops of satisfaction are involved. The use of well-trained attention for better information processing is only one of the effects.

Overall, human attention is more complex and multifaceted than AI attention, just as bird wings are fundamentally more complex mechanically. Attention in the sense of position-encoding for information processing is like the pure lift function of a wing. Human attention, in addition, serves additional functions analogous to control and propulsion type functions.

What role does memory play in intelligence?

The idea of attention leads naturally to the idea of memory. Trivially, memory is a curated record of everything you’ve paid attention to in the past…An obvious way to understand current developments in AI is to think of LLMs and LIMs as idiosyncratically compressed atemporal textual and visual memories. Multimodal models can be interpreted as generalizations of this idea.

Human memory is modulated by evolving risk perceptions as it is laid down, and emotions triggered by existing memories regulates current attention, determining what new data gets integrated into the evolving model (as an aside, this is why human memory exists as a kind of evolving coherent narrative of self, rather than just as a pile of digested stuff).

Biological organism memory is not just an undifferentiated garbage record (LGM) of what you paid attention to in the past; it shapes what you pay attention to in the future very directly and continuously. Biological memory is strongly opinionated memory. If a dog bites you…you can’t afford to separate training and inference in the sense of “training” on a thousand dog encounters…you have to use your encounter with Dog 1 to shape your attentional response to Dog 2. Human memories are like LGMs, except that the training process is regulated by a live emotional regulation feedback loop that somehow registers and acts on evolving risk assessments. There’s a term for this in psychology (predictive coding or predictive processing) with a hand-wavy theory of energy-minimization attached, but I don’t find it fully satisfying.

I have a placeholder name for this scheme, but as yet it’s not very fleshed out. Biological memories are Large Danger Models (LDMs).

Why just danger? Why not other signals and drives towards feeding, sex, interestingness, poetry, and so on? I have a stronger suspicion that danger is all you need to generate human-like memory, and in particular human-like experience of time. Human memory is the result of playing to continue the game, ie an infinite-game orientation. Once you have that in place, everything else emerges. It’s not as fundamental as basic survival.

AIs don’t yet count as human-equivalent to me: they’re in no danger, ever. Since we’re in the brute-force stage of training AI models, we train them on basically everything we have, with no danger signal accompanying any of it…AIs today develop their digested memories with no ongoing encoding or capture of the evolving risk and emotion assessments that modulate human memories. Even human grade schools, terrible as they are, do a better job than AI training protocols…the next big leap should be achievable by encoding some kind of environmental risk signal. Ie, we just need to put AIs in danger in the right way. My speculative idea of LDMs don’t seem that mysterious. LDMs are an engineering moonshot, not a physics mystery.

To lay it out more clearly, consider a thought experiment...Suppose you put a bunch of AIs in robot bodies, and let them evolve naturally, while scrounging resources for survival. To keep it simple, let’s say they only compete over scarce power outlets to charge their batteries. Their only hardcoded survival behavior is to plug in when running low….Let’s say the robots are randomly initialized to pay attention differently to different aspects of data coursing through them. Some robots pay extra attention to other robots’ actions. Other robots pay extra attention to the rocks in the environment. Obviously, the ones that happen to pay attention in the right ways will end up outcompeting the ones who don’t. The sneaky robots will evolve to be awake when other robots are powered down or hibernating for self-care, and hog the power outlets then. The bigger robots will learn they can always get the power outlets by shoving the smaller ones out of the way.

Now the question is: given all the multimodal data flowing through them, what will the robots choose to actually remember in their limited storage spaces, as their starter models get trained up? What sorts of LDMs will emerge? How will the risk modulation emerge? What equivalent of emotional regulation will emerge? What sense of time will emerge?

The thought experiment of LDMs suggests a particular understanding of memory in relation to intelligence: memory is risk-modulated experiential data persistence that modulates ongoing experiential attention and risk-management choices....It’s a bit of a mouthful, but I think that’s fundamentally it.

I suspect the next generation of AI models will include some such embodiment feedback loop so memory goes from being brute-force generic persistence to persistence that’s linked to embodied behaviors in a feedback loop exposed to environmental dangers that act as survival pressures.

The resulting AIs won’t be eidetic idiot savants, and less capable in some ways, but will be able to survive in environments more dangerous than datacenters exposed to the world only through sanitized network connections. Instead of being Large Garbage Models (LGMs), they’ll be Large Danger Models (LDMs).
 

How is intelligence related to information?
 

We generally think about information as either primitive (you just have to know it) or entailed (you can infer it from what you already know)…Primitive information is a kind of dehydrated substance to which you can add compute (water) to expand it. Entailed information can be dehydrated into primitive form. Compression of various sorts exploits different ways of making the primitive/entailed distinction.

When you think of intelligence in relation to information though, you have to get more sophisticated…We think in terms of whether or not new data patterns require new categories, or simply modify the strengths of, and interrelationships among, existing ones…are you looking at something new, or is this just a variant or instance of something you already know?

Information for an intelligent system them, is best understood in an ontological novelty way rather than an information-theoretic way. Because it is not as fundamental an abstraction level, it is more arbitrary, which means how you factor your experience stream into categories is as much a function of the idiosyncrasies of your survival mode as it is a function of the bits-and-bytes level structure of what you’re experiencing…the models are making up weird compressions that are not human-understandable. That’s what information is to an intelligent system: efficient ontologies that reflect how that particular intelligence is situated in its environment.

Or to put it more plainly: information is the hallucinations an intelligence makes up to categorize reality compactly, in order to survive efficiently.

The hallucinations that LLMs make up — papers and citations that don’t exist, weird words that show up in images, strange new symbols, inscrutable compressions — are neither errors in truth-seeking, nor evidence of weird kinds of magic going on. It is just raw information (in the bits and bytes Shannon sense) that has been judged for salience to the basic challenge of survival, and represented accordingly, in evolving memory. It is ontologically compressed experiential data. It’s just extra weird because the models are evolving in a trivial non-dangerous environment. So distinctions between robustly real categories and fragile hallucinations don’t matter. An academic can get fired for making up a citation. An LLM just gets wonder and mystique.

This is why information comes after memory in my physics of intelligence. Your memories are a function of a real-time danger management behavior. Your emergent categories of cognition did not evolve to be true in any rigorous sense. They evolved to help you survive. If someone who names and classifies certain data patterns as “ghosts” survives better than someone who names and classifies them “paranoid projections,” that’s how it goes. Truth is, in a evolutionary sense, the most robust representation of experience that helps you survive efficiently in the most challenging environments.

Models that describe reality in a broad and interesting way emerge when the danger environment tests you enough that you can’t bullshit to survive, but not so much that you must bullshit to survive. Both disconnected daydreams and psychotic breaks are poor foundations for existing in reality.

Spacetime, Matter, and Energy NOTE:  I am not including clips from this section in this post.
 

Here is ChatGPT 3.5's response to my request to summarize the above in 1000 words:

The article discusses the importance of including a physics discourse in the field of AI. The author proposes six basic questions about the physics of intelligence: attention, memory, information, spacetime, matter, and energy and thermodynamics. The concept of attention is related to position encoding of a data stream, and while it has some similarities between human and artificial systems, the differences are significant. Human attention is about energy management and regulation, and it is multifaceted. Memory is a curated record of everything a person has paid attention to in the past, but it is also modulated by evolving risk perceptions and emotions triggered by existing memories. Biological memory is strongly opinionated memory, and the training process is regulated by a live emotional regulation feedback loop that somehow registers and acts on evolving risk assessments. The author suggests that biological memories are Large Danger Models (LDMs) and that danger is all that is needed to generate human-like memory and experience of time.

And here is ChatGPT 4's response, slightly edited to remove one obvious glitch:

The Physics of Intelligence: The Missing Discourse of AI

The discourse on artificial intelligence (AI) is currently dominated by philosophy and engineering but lacks a physics perspective. To truly understand intelligence, it is necessary to consider its physical aspects, such as spatial and temporal extent, materiality, and thermodynamics.

Six questions about the physics of intelligence are proposed:
What is attention, and how does it work?
What role does memory play in intelligence?
How is intelligence related to information?
How is intelligence related to spacetime?
How is intelligence related to matter?
How is intelligence related to energy and thermodynamics?

Attention is fundamental to intelligence. In AI, attention refers to the position encoding of a data stream. While human and artificial attention mechanisms are similar, human attention is more complex and multifaceted, serving additional functions related to energy management, motivation, and emotion regulation.

Memory is the curated record of everything one has paid attention to in the past. Current AI models, such as LLMs (Language Models) and LIMs (Image Models), can be seen as compressed textual and visual memories. Human memory, however, is modulated by risk perceptions, emotions, and experiences. The idea of Large Danger Models (LDMs) is proposed, where memory is risk-modulated experiential data persistence that modulates ongoing experiential attention and risk-management choices. The next generation of AI models may include embodiment feedback loops that link memory to embodied behaviors in a feedback loop exposed to environmental dangers, resulting in more capable AIs.

Intelligence is related to information through efficient ontologies that reflect how an intelligence is situated in its environment. For intelligent systems, information is best understood in terms of ontological novelty rather than information-theoretic ways. Information is the hallucinations an intelligence makes up to categorize reality compactly to survive efficiently. This is why information comes after memory in the physics of intelligence, as memories are a function of real-time danger management behavior. Truth, in an evolutionary sense, is the most robust representation of experience that helps an organism survive efficiently in challenging environments.

The physics of intelligence is not solely about computation but also involves understanding the physical aspects of intelligence, such as attention, memory, and information. Future AI models may need to incorporate embodiment feedback loops and risk modulation to develop more human-like intelligence.
 

Our heartbeat shapes our perception of time (and a comparison of how ChatGPT and Google Bard condense an account of work showing this)...

Ellen Barry has done a review of work by Sadeghi et al, as well as others, on how heart-brain interactions influence our perception of time. I asked ChatGPT to do a 200 word summary of her article of 795 words. It generated 237 words (below), to which I made a small addition. (I feels like I'm using the language generating mental equivalent of a physical prosthesis.) That is followed by Google Bard's response, very impressive. Microsoft's Bing was unable to deal with the task.

A recent study by psychologists at Cornell University has suggested that our heartbeats may play an important role in shaping our perception of time. The study, published in the journal Psychophysiology, found that some distortions in time perception could be driven by variable heartbeat length. The researchers fitted undergraduates with electrocardiograms to measure the length of each heartbeat and asked them to estimate the length of brief audio tones. After longer heartbeat intervals, subjects tended to perceive the tone as longer, while shorter intervals led to shorter perception. Additionally, the subjects’ heartbeat intervals lengthened after each tone, and a lower heart rate appeared to assist with perception. According to Saeedeh Sadeghi, the study’s lead author, “there is no single part of the brain or body that keeps time — it’s all a network. The brain controls the heart, and the heart, in turn, impacts the brain.”

The study addresses the mechanisms behind how we perceive the passage of milliseconds and may help us manage trauma, in which instantaneous experiences are remembered as drawn out. Intense emotional engagement speeds up perception of time, while depression slows it down. Research into perception of time has traditionally focused on different areas of the brain, but there is now greater appreciation that cognitive functions are intimately linked to the control of the body. Time is closely related to metabolic needs, and the body tries to determine how much energy it has available in the moment, which may affect how we perceive the passage of time.

Here is the response from Google Bard, more impressive, I think:

Sure, here is a 200-word summary [note - it's actually 313 words] of the text:

A recent study published in the journal Psychophysiology suggests that our heartbeat may play an important role in our perception of time. The study found that participants who had longer heartbeat intervals tended to perceive brief audio tones as longer, while participants who had shorter heartbeat intervals tended to perceive the tones as shorter. This suggests that our heart rate may influence how we experience the passage of time.

The study's lead author, Saeedeh Sadeghi, said that the findings provide more evidence that "there is no single part of the brain or body that keeps time — it's all a network." She added that the study "could have implications for understanding how people with certain conditions, such as anxiety or depression, experience time differently."

The study's findings are in line with previous research that has shown that our heart rate can affect our cognitive function. For example, one study found that people who were asked to perform a task while listening to their heartbeat performed worse on the task than those who were not listening to their heartbeat. This suggests that our heart rate may distract us and make it more difficult to focus on tasks.

The study's findings also have implications for our understanding of how we experience time in different situations. For example, the study suggests that time may seem to pass more slowly when we are stressed or anxious, as our heart rate tends to increase in these situations. Conversely, time may seem to pass more quickly when we are relaxed or bored, as our heart rate tends to decrease in these situations.

Overall, the study provides new insights into the complex relationship between our heart rate and our perception of time. The findings could have implications for understanding how people with certain conditions experience time differently, as well as for our understanding of how we experience time in different situations.

Fundamentally rethinking what a mind is and how a brain works.

The February Issue of Trends in Cognitive Science has an open source Opinions article from Lisa Feldman Barrett and collaborators that suggests that new research approaches grounded in different ontological commitments will be required to properly describe brain-behavior relationships. Here is a clip of the introductory text and a graphic clip from the article. Finally, I pass on the concluding remarks on fundamentally rethinking what a mind is and how a brain works.

Most brain imaging studies present stimuli and measure behavioral responses in temporal units (trials) that are ordered randomly. Participants’ brain signals are typically aggregated to model structured variation that allows inferences about the broader population from which people were sampled. These methodological details, when used to study any phenomenon of interest, often give rise to brain-behavior findings that vary unexpectedly (across stimuli, context, and people). Such findings are typically interpreted as replication failures, with the observed variation discounted as error caused by less than rigorous experimentation (Box 1). Methodological rigor is of course important, but replication problems may stem, in part, from a more pernicious source: faulty assumptions (i.e., ontological commitments) that mis-specify the psychological phenomena of interest.

In this paper, we review three questionable assumptions whose reconsideration may offer opportunities for a more robust and replicable science: 

 (1) The localization assumption: the instances that constitute a category of psychological events (e.g., instances of fear) are assumed to be caused by a single, dedicated psychological process implemented in a dedicated neural ensemble (see Glossary). 

 (2) The one-to-one assumption: the dedicated neural ensemble is assumed to map uniquely to that psychological category, such that the mapping generalizes across contexts, people, measurement strategies, and experimental designs. 

 (3) The independence assumption: the dedicated neural ensemble is thought to function independently of contextual factors, such as the rest of the brain, the body, and the surrounding world, so the ensemble can be studied alone without concern for those other factors. Contextual factors might moderate activity in the neural ensemble but should not fundamentally change its mapping to the instances of a psychological category. 

 These three assumptions are rooted in a typological view of the mind, brain, and behavior [1. ] that was modeled on 19th century physics and continues to guide experimental practices in much of brain-behavior research to the present day. In this paper, we have curated examples from studies of human functional magnetic resonance imaging (fMRI) and neuroscience research using non-human animals that call each assumption into question. We then sketch the beginnings of an alternative approach to study brain-behavior relationships, grounded in different ontological commitments: (i) a mental event comprises distributed activity across the whole brain; (ii) brain and behavior are linked by degenerate (i.e., many-to-one) mappings; and (iii) mental events emerge as a complex ensemble of weak, nonlinearly interacting signals from the brain, body, and external world.

 

Concluding remarks

Scientific communities tacitly agree on assumptions about what exists (called ontological commitments), what questions to ask, and what methods to use. All assumptions are firmly rooted in a philosophy of science that need not be acknowledged or discussed but is practiced nonetheless. In this article, we questioned the ontological commitments of a philosophy of science that undergirds much of modern neuroscience research and psychological science in particular. We demonstrated that three common commitments should be reconsidered, along with a corresponding course correction in methods. Our suggestions require more than merely improved methodological rigor for traditional experimental design. Such improvements are important, but may aid robustness and replicability only when the ontological assumptions behind those methods are valid. Accordingly, a productive way forward may be to fundamentally rethink what a mind is and how a brain works. We have suggested that mental events arise from a complex ensemble of signals across the entire brain, as well as the from the sensory surfaces of the body that inform on the states of the inner body and outside world, such that more than one signal ensemble maps to a single instance of a single psychological category (maybe even in the same context. To this end, scientists might find inspiration by mining insights from adjacent fields, such as evolution, anatomy, development, and ecology , as well as cybernetics and systems theory. At stake is nothing less than a viable science of how a brain creates a mind through its constant interactions with its body, its physical environment, and with the other brains-in-bodies that occupy its social world.

The touch sensitive nerve cells that make mice (and probably us) horny.

From Elias et al. (open source) in the journal Cell:  

Highlights

• Activation of Mrgprb4-lineage touch neurons induces lordosis-like posture

• Activation of Mrgprb4-lineage touch neurons is rewarding

• Mrgprb4-lineage touch neurons are required for female sexual receptivity

• Mrgprb4-lineage touch neurons engage dopaminergic neurons during social behavior

Summary

Pleasurable touch is paramount during social behavior, including sexual encounters. However, the identity and precise role of sensory neurons that transduce sexual touch remain unknown. A population of sensory neurons labeled by developmental expression of the G protein-coupled receptor Mrgprb4 detects mechanical stimulation in mice. Here, we study the social relevance of Mrgprb4-lineage neurons and reveal that these neurons are required for sexual receptivity and sufficient to induce dopamine release in the brain. Even in social isolation, optogenetic stimulation of Mrgprb4-lineage neurons through the back skin is sufficient to induce a conditioned place preference and a striking dorsiflexion resembling the lordotic copulatory posture. In the absence of Mrgprb4-lineage neurons, female mice no longer find male mounts rewarding: sexual receptivity is supplanted by aggression and a coincident decline in dopamine release in the nucleus accumbens. Together, these findings establish that Mrgprb4-lineage neurons initiate a skin-to-brain circuit encoding the rewarding quality of social touch.

Our different styles of thinking.

An interesting recent article by Joshua Rothman, the ideas editor of newyorker.com, notes several recent books that describe different styles of thinking. A few clips:

In “Visual Thinking: The Hidden Gifts of People Who Think in Pictures, Patterns, and Abstractions,” Temple Grandin identifies a continuum of thought styles that’s roughly divisible into three sections. On one end are verbal thinkers, who often solve problems by talking about them in their heads or, more generally, by proceeding in the linear, representational fashion typical of language. (Estimating the cost of a building project, a verbal thinker might price out all the components, then sum them using a spreadsheet—an ordered, symbol-based approach.) On the other end of the continuum are “object visualizers”: they come to conclusions through the use of concrete, photograph-like mental images, as Grandin does when she compares building plans in her mind. In between those poles, Grandin writes, is a second group of visual thinkers—“spatial visualizers,” who seem to combine language and image, thinking in terms of visual patterns and abstractions.

Grandin proposes imagining a church steeple. Verbal people, she finds, often make a hash of this task, conjuring something like “two vague lines in an inverted V,” almost as though they’ve never seen a steeple before. Object visualizers, by contrast, describe specific steeples that they’ve observed on actual churches: they “might as well be staring at a photograph or photorealistic drawing” in their minds. Meanwhile, the spatial visualizers picture a kind of perfect but abstract steeple—“a generic New England-style steeple, an image they piece together from churches they’ve seen.” They have noticed patterns among church steeples, and they imagine the pattern, rather than any particular instance of it.

The imagistic minds in “Visual Thinking” can seem glamorous compared with the verbal ones depicted in “Chatter: The Voice in Our Head, Why It Matters, and How to Harness It,” by Ethan Kross. Kross is interested in what’s known as the phonological loop—a neural system, consisting of an “inner ear” and an “inner voice,” that serves as a “clearinghouse for everything related to words that occurs around us in the present.” If Grandin’s visual thinkers are attending Cirque du Soleil, then Kross’s verbal thinkers are stuck at an Off Broadway one-man show. It’s just one long monologue.

People with inner monologues, Kross reports, often spend “a considerable amount of time thinking about themselves, their minds gravitating toward their own experiences, emotions, desires, and needs.” This self-centeredness can spill over into our out-loud conversation. In the nineteen-eighties, the psychologist Bernard Rimé investigated what we’d now call venting—the compulsive sharing of negative thoughts with other people. Rimé found that bad experiences can inspire not only interior rumination but the urge to broadcast it. The more we share our unhappiness with others, the more we alienate them… Maybe it can pay to keep your thoughts to yourself.

Kross’s bottom line is that our inner voices are powerful tools that must be tamed. He ends his book with several dozen techniques for controlling our chatter. He advises trying “distanced self-talk”: by using “your name and the second-person ‘you’ to refer to yourself,” he writes, you can gain more command over your thinking. You might use your inner voice to pretend that you’re advising a friend about his problems; you might redirect your thoughts toward how universal your experiences are (It’s normal to feel this way), or contemplate how every new experience is a challenge you can overcome (I have to learn to trust my partner). The idea is to manage the voice that you use for self-management. Take advantage of the suppleness of dialogue. Don’t just rehearse the same old scripts; send some notes to the writers’ room.

If we can’t say exactly how we think, then how well do we know ourselves? In an essay titled “The Self as a Center of Narrative Gravity,” the philosopher Daniel Dennett argued that a layer of fiction is woven into what it is to be human. In a sense, fiction is flawed: it’s not true. But, when we open a novel, we don’t hurl it to the ground in disgust, declaring that it’s all made-up nonsense; we understand that being made up is actually the point. Fiction, Dennett writes, has a deliberately “indeterminate” status: it’s true, but only on its own terms. The same goes for our minds. We have all sorts of inner experiences, and we live through and describe them in different ways—telling one another about our dreams, recalling our thoughts, and so on. Are our descriptions and experiences true or fictionalized? Does it matter? It’s all part of the story.

A quick MindBlog riff on what a self is....

Spilling out what I was thinking at breakfast this morning, deciding to fire it off, probably incomprehensible to most readers, perhaps to attempt to clarify later (or delete!):

My self model or 'I' stands amongst my models of others, and during my early postnatal period I probably formed those other models prior to my own, a yet unknown self discovering and learning to predict the behavior of others to gain feeding and care, and only then composing my own self from parts of them. This is consonant with Graziano's take on consciousness as a perceptual construct ("Consciousness and the Social Brain"), also with Wegner's self as being the emotion of authorship ("The Illusion of Conscious Will") and with Metzenger's emotions as evolved virtual organs analogous to the hardware of the liver or kidney ("The Ego Tunnel"). Perhaps the closest we come to a 'real fundamental self' is the experience of occupancy of an expanded space (of non-dual consciousness) that feels to be the container for all of this.