Index

Interview, Katherine Hayles and David Familian

David Familian and Professor N. Katherine Hayles, scholars aligned in their art-science interests, met at UC Irvine in August 2024 to discuss the exhibition Future Tense: Art, Complexity, and Uncertainty, which was then running at the Beall Center for Art + Technology at UC Irvine from August 2024 through January 2025. They used this opportunity to further explore Hayles’ work relating to chaos and complexity, as well as her early observations of cybernetics.

David Familian: Can you talk a little about your background and your interest in chaos and complexity in your research?

Katherine Hayles: I started my professional career in the sciences, as a chemist. I did my undergraduate work in chemistry and then got a master’s degree in the field, and only then did I start the serious study of literature and culture. What I acquired during my scientific training were the basic mathematical tools to understand the world of science. I was really interested in how ideas circulate between the humanistic and scientific communities. At the time that I started my research into quantum field theory, there were a lot of influence studies–the influence of Newton on Alexander Pope and so forth–but it seemed to me that there existed much richer connections. My first book, The Cosmic Web: Scientific Field Models and Literary Strategies in the 20th Century (1984), was an attempt to begin to develop a theory in which one could talk about those interconnections. My second book, Chaos Bound: Orderly Disorder in Contemporary Literature and Science (1990), was a case study of how that actually works in practice. So, my interest in chaos goes back to the 1980s and 1990s. Chaos science seemed to me a marvelously fertile paradigm. When it matured into complexity theory, it was able to explain and investigate a huge range of phenomena—which is on display in this show.

DF: One of the things about your Chaos book that I remember is when you were writing about Mandelbrot, you talked about how his contemporaries were making fun of his work, as if it were too feminine or intuitive. How could a scientist not be curious, or not have intuition?

KH: Or, how could a scientist not be human, and have all of the insights and frailties of humans?

DF: It’s fascinating how you went from the sciences to the humanities. I’m reading a book now which mentions Heidegger saying that philosophy is not the handmaiden of science. But then, thirty years later, he gave that lecture where he said that cybernetics is the new metaphysics.  And in your book, How We Became Posthuman (1999), you go back to the origins of cybernetics, if I remember correctly. 

KH: I went back to the Macy Conferences [on Cybernetics, held in New York from 1946 to 1953] and did a close reading of several of their annual conferences. But I was really interested in some fundamental questions, one of which was how information lost its body. And I was also interested in the emergence of this new vision of what the human was, a notion I labeled as the Posthuman, which was rapidly subverting and rearranging traditional ideas from the Enlightenment like free will, the autonomous self, and so forth, and cybernetics had a role to play in that. It’s kind of a conundrum that even as cybernetic ideas diffused into culture generally, cybernetics as an academic discipline virtually disappeared. Cybernetic ideas were taken up and became central in any number of fields, but not in themselves as a coherent discipline. 

DF: What’s interesting in the Steve Strogatz book I’m reading, Sync, is that he mentions cybernetics and claims, falsely, that we don’t practice cybernetics any more, yet his whole book is about ideas that came out of cybernetics. The way I look at it is that cybernetics is a methodology, not necessarily a science. It’s a way of looking at our world. Maybe the idea, like Wittgenstein says, is that we don’t think up language, we only pick it up socially. It’s the feedback between us that makes us human, it’s not all internal.

KH: Absolutely. 

KH: Some of the ideas of cybernetics are being resurrected in other contexts, for example one of the important papers that Norbert Wiener co-wrote was called “Behavior, Purpose and Teleology.” Their argument was that cybernetics leads to teleological conclusions, because the whole idea of goal-seeking behavior was one of the fundamentals of their early robotic installations. More recently, Michael Levin at Tufts University has picked up that argument about teleological behavior in the context of microorganisms, bacteria, and such, arguing that the only way to understand these microscopic forms of behavior is as a desire to continue their existence. He collaborated on an essay with Daniel Dennett called “Agents with Agendas.” Their argument basically is “if you don’t understand the agenda, you can’t understand the behavior,” which is precisely the argument that Weiner was making in the 1950s. So these arguments get resurrected. Now, of course, Levin is talking about microorganisms, not about robotics, but I think there’s a deep connection there. 

DF: Can you define teleological?

KH: Teleological means behavior directed toward some goal, and that the goal is preset and defined, that the goal dictates the behavior rather than the behavior dictating the end result.

DF: And then the goal changes because you have to adapt to new environments. So the environment then becomes a trigger.

KH: Absolutely. There’s a fascinating recent paper out by Stewart Kauffman, a theoretical biologist, and Guiseppo Longo, a French mathematician, and they’re basically arguing that there’s a definitive divide between physical systems and living systems. The difference is precisely that living systems are teleological. Living systems want to continue their existence. And physical systems don’t want anything, things just happen, like a lake evaporating or a mountain eroding. There’s no agent there to give it a teleological impetus. But as soon as we get into the biological realm, those teleological impulses are everywhere. The progress of a physical system, even very complex ones with criticality points and so on, can be mapped into  phase spaces showing how their trajectories will proceed.  With biological systems, no such tidy evolutionary trajectory is possible.

KH: Kaufman and Longo give the example of the lungfish, a species which breathes air and water through both gills and lungs. They say that as water entered the fish’s lungs, the organ turned into a swim bladder and was used to regulate buoyancy. This created a new niche and opened the pathway for a new species—say a worm or a bacterium– to evolve that would exploit this development. That’s what Kaufman means by the adjacent possible.  Something opens a new opportunity adjacent to an existing opportunity, and now evolution can take on a new trajectory.

DF: In Gail Wight’s work in the show, Ostracod Rising, global warming is affecting evolution in microorganisms and creating new adjacent possibilities for these species to evolve and enter new environments.  

KH: Maybe we can use that as a segue to talk about the exhibition. What really struck me about the show was the equal playing field on which robots, microorganisms, non-human species and humans appear, all woven together in complex ecology. If you think in environmental terms, that’s exactly the way that complex systems work. It may start with symbiosis between two species but then begins to spread more and more. 

My new book, Bacteria to AI: Human Futures with our Nonhuman Symbionts, tries to approach these complex interactions through the notion of cognition. Cognition was very carefully chosen because the human species considers itself to have superior cognitive powers to any other species, and that’s what accounts for our putative ability to dominate every other species on earth. But this new research, of the kind in which Michael Levin engages, is beginning to expand the notion of cognition beyond the human, into the nonhuman. These moves are inviting a radical reappraisal of what constitutes cognition. It inevitably feeds back to affect how we think about human cognition as well; instead of a simplistic idea of human superiority, now we have this much more complex and humbling view of human cognition as one form of cognition active with many other forms in complex ecosystems. I very much saw that on display in this exhibition, and it’s a wonderful way to approach complex systems and complexity in general. 

DF: One of the goals of this show was not just to have people intellectually process the idea of a complex system, which I think is very important to our survival, but to feel it. That’s what art allows us to do is to feel what this looks like, because our minds don’t work that way. We try to bring sequential order to our lives, but now, in order to understand the world, we have to change that. We have to see the world as a complex system, and our brains have to change to think in patterns rather than in cause and effect. We’re trapped in this linear thinking that has produced all this wonderful knowledge, but it’s almost useless for solving the wicked problems we face today. 

Responding to your comment, I specifically wanted the artworks included in Future Tense to each engage multiple systems.

KH: Right, and at different scales as well, from the intercellular to the forest. I was really taken by Laura Splan’s work, Baroque Bodies (Sway). That was, to me, quite remarkable, both visually and conceptually. It showed this interplay between the environmental and genetic factors, and how they could work together to create a very complex system.

I was also extremely interested in Cesar & Lois’s sculptural display of the ecosystem in Being hyphaenated, with the plants and the fungi collaborating to convey messages back and forth. I recently had occasion to read Suzanne Simard’s seminal paper on what would come to be called the “Wood Wide Web.” Her research was fundamental in showing the way fungi and root systems collaborate to carry messages and distribute nutrients, leading to a really complex symbiotic system. I thought the sculptural quality of that artwork made these interactions visually apparent and quite appealing. 

I’ll add one more element to this tapestry we’re weaving here, and that is Lynn Hershman Leeson’s piece on facial recognition and AI interpretations. I think if we’re going to re-envision cognition, crucial components of that are the cognitive abilities of computational media, including AI, algorithms, and so forth. We’re beginning to understand more fully how there is this deep interconnection between human cognition and the cognitive abilities of computational media, and to explore our ongoing symbiosis with computational media. Re-envisioning  cognition, in my view, has to have a place not only for non-human life forms, but also for non-human cognizers. 

DF: So it’s not just biological, it’s also computational.

KH: That’s right. I call this new framework to understand cognition the Integrated Cognitive Framework, the ICF. The “integrated part” of that phrase refers to emphasizing and exploring more fully the way in which feedback loops are operative throughout this system. From AI to human, from human to AI, from nonhuman life forms to human and back again.

DF: Feedback is the engine, it’s what keeps the thing alive.

In Roy Ascott’s idea of moistmedia, there is a constant exchange between the “dry” computation and “moist” nature. Maybe AI needs more than the inputs we provide based on what we want to get out of it, but something else that comes from the environment or other sources.

KH: Imagine an AI that could choose its data training set. What if it really wants the data from a forest in England, for example, rather than human-authored texts. That’s fascinating. 

Notes

  1. For more information and recordings documenting the Macy Conferences, see https://www.asc-cybernetics.org/foundations/.
  2. For more information, see: Sophie Yeo, “The ‘wood wide web’ theory charmed us all – but now it’s the subject of a bitter fight among scientists,” The Guardian, July 9, 2024, .

Curator’s Introduction

David Familian

Future Tense: Art, Complexity, and Uncertainty is an exhibition of contemporary artists whose work explores complex systems at the nexus of art and science. The word complex,  derived from the Latin plectere “to weave,” describes how interconnected, complex parts in each system are woven together, but also interact with other systems. One cannot think of them in isolation because they are constantly interacting with each other through feedback, generating chaos, emergent behavior, and self-organization, all which create uncertainty. For instance, climate change, pandemics, social unrest, and geo-political turmoil are all generated within complex interactions between elements that lead to unpredictable, dynamic outcomes. Another element in complex systems is that we can never have complete knowledge of every interaction of a given system. All systems become less predictable over time, producing tension and uncertainty, which explains the exhibition’s title.

Future Tense: Art, Complexity, and Uncertainty includes interdisciplinary works of art that represent, demonstrate, and embody the fundamental nature of complex systems. The emerging and established artists selected for this exhibition focused on different aspects of complexity, using both traditional media and new technologies such as computer modeling, robotics, and dynamic AI generated data visualizations. The works explored complex systems at various scales from that of microscopic organisms to the totalizing implications of global warming on a planetary scale. The exhibition endeavored to help audiences understand how complexity functions within the individual works but also engaged them to actively experience the overarching aesthetics and effect of each system, which is reflected in the exhibition’s installation.    

A Walk Through Future Tense: Art, Complexity, and Uncertainty

Future Tense: Art, Complexity, and Uncertainty includes interdisciplinary works of art that represent, demonstrate, and embody the fundamental nature of complex systems. The emerging and established artists selected for this exhibition focused on different aspects of complexity, using both traditional media and new technologies such as computer modeling, robotics, and dynamic AI generated data visualizations. The works explored complex systems at various scales from that of microscopic organisms to the totalizing implications of global warming on a planetary scale. The exhibition endeavored to help audiences understand how complexity functions within the individual works but also engaged them to actively experience the overarching aesthetics and effect of each system, which is reflected in the exhibition’s installation.    

The exhibition is arranged thematically in three distinct galleries, each with a different ambience aimed to produce a disparate effect. The first gallery focuses on one characteristic of complex systems: chaos, where works demonstrate various chaotic elements or systems out of control. For instance, Clare Rojas’s Circle of Infinite Chaos (2022), a representational painting of a woman (possibly the artist) lying peacefully in a hollow below grade with objects buzzing above her reflecting chaos in her inner mind. The tension between both chaos and order is visible in several works: Julie Mehretu’s Landscape Allegories (2004), etchings of turbulence landscapes; Fernando Palma Rodriguez’s Huitzlampa (2023), kinetic sculptures programmed to respond to live weather in Los Angeles; and Ralf Baecker’s Interface I (2016), a kinetic sculpture of thin bands driven by signals from the ambient radiation of the earth, some that form smooth sine waves, others that move with frenetic energy. Carolina Caycedo and David de Rozas’s Measuring the Immeasurable (2022), a hanging installation of surveying tools and drawings of indigenous rock paintings, references how the Public Land Survey System (PLSS) created displacement and environmental chaos for native peoples and their land.  

The second gallery features three video projections in a dark, interstitial, liminal space where viewers could have a respite from the previous chaos. Laura Splan’s Baroque Bodies (Sway) (2022), an interactive video projection on a wall, zoomed in and out in response to the movement of participants moving in the space as they explored the impact of the environment on gene expression. Theresa Schubert’s Glacier Trilogy — Part 3: Simulating glacial water systems (2022), included two large flat-screen monitors stacked vertically screening a real-time simulation of melting glacial ice that varied according to the amount of carbon dioxide in the room. David Rojas and Carolina Caycedo’s video, Teaching of the Hands (2020), a companion piece to Measuring the Immeasurable, oscillates between a documentary about the history of colonization with its ravaging extraction policies and a poetic meditation on indigenous knowledge and caretaking of their land.

The third gallery focuses on the complex and unknowable in both past histories and speculative futures. Gail Wight’s Ostracod Rising (2024), a timeline drawn like a 19th century naturalist illustration, explores both previous and anticipated future extinctions of organisms on our planet. Chico MacMurtrie’s Dual Pneuma (2024) is a large installation of futuristic, soft robots whose movement is powered by air from pneumatic tubes. They are installed alongside ceramic “doubles” cast from the robots, which play sounds using the same water whistle technology as ancient Meso-American flutes. Pilar Yoldas’s Alphabet of Life (2024) are glass orbs etched with the molecular structures of twenty amino acids, the building blocks of life. Hege Tapio’s Ephemeral (2024) consists of a promotional video, didactic materials, and a prototype to imagine a fictitious corporation where venture capitalists embrace a brand new technology: hormonal implants to alter our emotions. Cesar and Lois’s Being hyphaenated (Ser hifanizado) (2024), a living sculpture/experiment with sensors, measures the complex communication between mycelium and other plants with the data visualized on a computer. 

The final part of this exhibition in the fourth gallery features two artists who provide cautionary tales for the future: Lynn Hershman Leeson, one of the first media artists, and Newton Harrison, an innovator of environmental art. Lynn Hershman Leeson’s Logic Paralyzes the Heart (2022), a photo and video installation about AI-generated life forms, includes a character that reveals the historical secrets of past surveillance technology and potentially dystopic future technologies. Newton Harrison’s Epitaph (2022), his final work, is a drawing of an imagined tombstone for himself and his long-time collaborator, the late Helen Mayer Harrison. Referencing their dialogical artistic process, the text on the tablet-like tombstone is a conversation between Harrison and what he calls the “life web.” The penultimate line on the tombstone reads, “Human, Human to survive, learn from your companion species how to rejoin me,” which reflects Newton Harrison’s frequent admonition for humans to coexist with nature to prevent human extinction.

The overarching goal of Future Tense: Art, Complexity and Uncertainty, was for audiences to understand how complexity functions in our everyday life through works of art. Audiences could see and experience (perhaps even feel) the dynamic interplay of chaos and order, uncertainty and unpredictability in extreme weather events and climate change, robotics and AI, and in biological systems in plants and within our own bodies, just to reiterate a few. Ultimately, the artists in Future Tense: Art, Complexity and Uncertainty propose ideas about this paradigm of complex systems that helps us understand that while we cannot solve all these vexing global issues, we must learn to manage them, or our survival will continue to be at risk.

Historical and Curatorial Precedents

For the last twenty years as a curator, I have had a long-standing interest in the concepts of chance and probability that control randomness and can generate uncertainty in art and science. At critical junctures, paradigmatic shifts occurred in art, philosophy and science that embraced randomness, indeterminacy, and unpredictability.  In the visual arts, the modernist avant-garde redefined the very meaning, function, and materiality of art, by welcoming chance in the production and reception of art.

A few voices in the late 19th century began to question the determinism of science and its goal of certainty. For instance, scientists including physicist/mathematician James Clerk Maxwell and physicist/philosopher Ludwig Boltzmann, could only understands the kinetic  behavior of the molecule through probability using statistical mechanics. In trying to solve the “Three-body problem” (why do three celestial objects i.e. planets, stars, or suns with similar mass exert force on each other when they are in proximity?) physicist/mathematician Henri Poincaré realized even a minute miscalculation in the starting position of each body would give an inaccurate result, as the systems are so chaotic and unpredictable. 

This skepticism about certainty continues into the 20th century.  In his Creative Evolution (1907) philosopher Henri Bergson, argued that Darwinian mutation cannot be predictable, but must involve chance and uncertainty.  As scientists looked further into the structure of atoms, they found bizarre behavior which led to the theory of quantum mechanics. In 1927 when Werner Heisenberg and Niels Bohr presented their “Uncertainty Principle” positing that you cannot know both the speed and the position of a particle at the same time, they confronted much opposition because it depended on probability. Albert Einstein, who did not believe that nature is unpredictable, reacted to their principle famously stating that:“god does not play with dice.”

Artist Marcel Duchamp became interested in the concept of uncertainty and read the writings of Henri Poincaré, including Science and Hypothesis (1903) and Esprit Jouffret’s book on the fourth dimension, a popularization of Poincaré’s book that read by many artists at that time.  When most art historians think of Duchamp it is in relation to his impact on the development of conceptual art, but equally important is how he dealt with uncertainty, indeterminacy, and chance. One may see this in his Three Standard Stoppages (1913-14) where three one-meter threads held horizontally were each dropped from a height of one meter onto a piece of canvas and fixed in position by means of varnish. His composition Erratum Musical (1913) a score for three voices composed by Duchamp and his two sisters, Yvonne and Magdeleine, both musicians, was created by randomly picking up a range of twenty-five notes from a hat.

Artists responded to the rupture of World War I also using chance along with found objects and nonsensical language in raucous performances at Hugo Ball’s Cabaret Voltaire in Zurich. This is where Richard Huelsenbeck reportedly slid a paper knife into a dictionary and randomly selected the word “Dada”—hobbyhorse in French––as the name for the group of artists. In the 1920s surrealists embraced the unconscious and the irrational to reflect the extreme level of destruction, death, and trauma of war. Like the scientists and philosophers, Dada and surrealist artists also continued question certainty, predictability and rationality, which became the zeitgeist of the post-World War I era.

In the 1950s, John Cage developed “chance operations” indeterminate procedures to make visual scores for compositions, often open-ended and including audience participation. Beginning with has famous Untitled Theater Piece #1 (1952) at Black Mountain College, he developed this early intermedia performances combining painting, poetry, dance, music, everyday sounds and found objects. Influenced by Cage, Fluxus artists wrote their own “event scores “for brief, multi-sensory intermedia performances. For instance, La Monte Young’s  “Composition 1960 #10,” also known as Draw A Straight Line and Follow It, was interpreted by Nam June Paik in his Zen for Head (1961) where he draws a straight line by dipping his head (or sometimes his tie) in ink and drags it along the paper, making what looks like a Zen ink brush scroll.

Complexity, Wicked Problems and Systems Thinking

When I first heard about Getty’s PST Art and Science Collide theme, I knew that it presented an opportunity to expand further upon the concepts of probability and uncertainty that I engaged with in previous Beall exhibitions. What I did not know was this would result in four years of research into adaptive complex systems, its histories and methodologies. This started out with a deep dive into the literature of complexity theory that led me to cybernetics, Immanuel Kant’s philosophy of the organics, and eventually, to ubiquitous, adaptive complex systems all around us that effect our lives in very profound ways we cannot ignore. 

 René Descartes described the old scientific method of problem-solving succinctly: “Divide each difficulty into as many parts as is feasible and necessary to resolve it.” In short, everything is like a clock: in that manner of thinking one knows what every part does and can predict with certainty how it will operate. In contrast, Bruno Latour explains in a discussion about global warming: “The disorientation people feel regarding the planet, and the fact that they can’t react quickly to a situation that everyone knows is catastrophic, is largely because they continue to be in the world in the past, one where there are objects that have no agency and can be controlled by calculation and science.” Today, like  Latour, we assume climate change consists of a set of complex, dynamic, interrelated systems that produce unpredictable outcomes that, unlike the “clockwork” paradigm, cannot be resolved by calculations or science.

Adaptive complex systems theory attempts to explain how large numbers of relatively simple entities organize themselves into a collective whole that creates a pattern, such as a group of flocking birds. While adaptive complex systems y more accurately reflect our current conditions, their complexities make them difficult to comprehend. In 1973, urban planners Horst W.J. Rittel and Milton M. Webber coined the phrase “wicked problems”:

A wicked problem has innumerable causes, is tough to describe, and doesn’t have a right answer… Environmental degradation, terrorism, and poverty—these are classic examples of wicked problems. They’re the opposite of hard, but ordinary problems, which people can solve in a finite time by applying standard techniques. Not only do conventional processes fail to tackle wicked problems, but they may exacerbate situations by generating undesirable consequences.

Twenty years later, Barry Richmond developed the idea of “systems thinking,” proposing a possible way to solve “wicked problems.” Richmond emphasizes how systems thinking       observes complex systems bi-focally and that “one must see both the forest and the trees.” Systems thinkers strive to see both the generic and the specific, as well shifting patterns in an event. Finally, Richmond noted if one does not employ systems thinking and tries to change just one element of a complex problem, the chance of unintended consequences will increase over time. To summarize, we cannot fix these problems easily and must consider they are within a matrix of many intersecting nodes of a complex system.

Helen and Newton Harrison were aware of the concepts of wicked problems and systems thinking, which they integrated into their practice from the beginning. They employed systems thinking in conversations with one another, and with collaborators in architecture, urban planning, marine biology, and environmental science across the globe. As Newton Harrison stated: “we have to live with nature, not try to control it.” 

Today, this kind of global systems thinking resonates with Yuk Hui, a philosopher of technology, who recently wrote,  “To think planetary…means formulating a language of co-existence that will allow diverse people and species to live on the same planet.”  The essential aspect of complex systems—feedback—combined with collaborative, interdisciplinary systems thinking, could possibly help to begin to a co-existence where we can tackle our current wicked problems and the cataclysmic events that will continue into the future.  

Notes

  1. This “Three body” conundrum was not solved until discovery of chaos theory in the 1970s.
  2. Henri Bergson, Creative Evolution, translated by Arthur Mitchell. (New York: Henry Holt and Company), 1911.
  3. Presented at the Solvay Conference in Denmark, this became known as the “Copenhagen Interpretation.” 
  4. Herbert Molderings, Duchamp and the Aesthetics of Chance: Art as Experiment. (New York: Columbia University Press), 2006, pp references Jouffret’s Traité Élémentaire De Géométrie À Quatre Dimensions. (Elementary Treatise of Geometry in Four Dimensions. (Paris: Gauthier-Villars), 1903.
  5. Ibid, 6. Many years after Duchamp made this work, he would state that it was his most important work of art. 
  6. Ya-Ling Chen, Tout-Fait Marcel Duchamp, issue 1, vol. 1, December 1999, accessed at https://www.toutfait.com/issues/issue_1/Music/erratum.html      
  7. Ibid. Jean Arp, Johannes Baader, Hugo Ball, Marcel Duchamp, Max Ernst, Elsa von Freytag-Loringhoven, George Grosz, Raoul Hausmann, John Heartfield, Emmy Hennings, Hannah Höch, Richard Huelsenbeck, Francis Picabia, Man Ray, Hans Richter, Kurt Schwitters, Sophie Taeuber-Arp, Tristan Tzara, and Beatrice Wood, among others.
  8. These previous exhibitions include: Drawn from a Score (2017), which featured artists whose work emanates from a written, visual or code-based score https://beallcenter.uci.edu/exhibitions/drawn-score Vera Molnar: Variations (2022), a solo show of a pioneer of computational works https://beallcenter.uci.edu/exhibitions/vera-molnar-variations and Computational Poetics (2023), curated with art historian Hannah Higgins, that surveyed human/computer collaborations in poetry, with historic work from the 1960s and contemporary experimentation. https://beallcenter.uci.edu/exhibitions/computational-poetics
  9. René Descartes, Discourse on Method and Meditations on First Philosophy, 4th edition. (New York: Hackett, 1998), 11. 
  10.  Interview with Bruno LaTour, Part I, date to be added, video, length, ARTE.tv, accessed at https://www.youtube.com/watch?v=sYfwkTgEpmE.com.
  11. UC Berkeley Planning professors coined the phrase “wicked problems” in 1973. See Horst W.J. Rittel and Milton M. Webber, “Dilemmas in a General Theory of Planning,” Policy Sciences 4, no. 2 (1973): 155-69.   
  12. Barry Richmond, “Systems Thinking: Critical Thinking Skills for the 1990s and Beyond.” Systems Dynamics Review 9, no. 2 (1993).
  13. Barry Richmond, “System Dynamics/Systems Thinking: Let’s Just Get On With It,” transcript from a lecture at the International Systems Dynamics Conference in Sterling, Scotland, System Dynamics Review vol 10, issue 2-3, (summer-fall 1994): 135-157, accessed at https://doi.org/10.1002/sdr.4260100204
  14. Ibid.
  15. Newton Harrison, multiple verbal conversation with the author, 2019 onwards.     
  16. Yuk Hui, Machine and Sovereignty: For a Planetary Thinking (Minneapolis: University of Minnesota Press, 2024): 1.









Emergent Meaning

Jeffrey Barrett

A central theme of the exhibition Future Tense: Art, Complexity, and Uncertainty is the capacity of complex systems to self-assemble ordered structure. A notable example of this is when meaning emerges from randomness. The meaning may be expressed in the intentions of an artist or the interpretations of a viewer experiencing the artist’s work where both the artist and viewer are understood as complex systems interacting with each other and the world. In order to understand better how meaning might arise from random interactions, we will focus on two simple models that illustrate the emergence of meaningful language—a signaling game and a coding game where randomness leads to successful communication.

The effects of randomness are manifest in the behavior of complex systems. We see them in the shape of cracks in the sidewalk, the behavior of markets, the flow of history, the genetic mutations that cause cancer, and the acts of friends.

Our best physical theories aim to characterize the sort of randomness we find in nature and how it behaves. The second law of thermodynamics describes the effects of the random motions of molecules. It says that entropy, a measure of microscopic randomness, tends to increase with time. A quick example illustrates the type of phenomena the law describes.

Consider an intricate ice sculpture on the beach on a hot day. It might start depicting a bouquet of flowers with intricately carved stems and petals. But as the molecules in the surrounding air randomly bounce against the sculpture, the ice is warmed, and it begins to melt. As it melts, the representational information encoded in its structure is irretrievably lost. Someone looking at the patch of wet sand an hour later will be unable to tell what the ice flowers looked like or even that there was once a sculpture. The process that destroys macroscopic information through random microscopic interactions is itself statistically inevitable.

The gradual loss of representational structure, of information, ultimately applies to all we create. Nearly all that the ancient Greeks did, said, and made is forever lost. And such processes apply to us as complex biological systems. As the Book of Common Prayer instructs the congregation on Ash Wednesday, “Remember that you are dust, and to dust you shall return.”

But randomness also plays an essential role in creation. Meaningful order can emerge from random interactions in the context of an adaptive dynamics, an evolutionary process with positive feedback. When this sort of dynamics acts on a system, it may adapt the system to a pattern or purpose in surprising ways.

An example of order from randomness is the evolution of life itself, but a simpler example is seen in the spontaneous formation of a crystal. The crystal forms with the appearance of a random seed that provides an initial scaffolding. The seed might be an impurity in the medium in which the crystal forms or a scratch in the container holding the solution. The elements of the crystal then begin to self-organize by means of random local interactions that settle the molecules into positions of minimum energy. This process tends to build and complete sequential layers of elements. And a highly ordered crystalline lattice thereby emerges. 

A similarly simple evolutionary process can explain the emergence of meaningful signals in the context of a signaling game. The philosopher David Lewis used signaling games to explain how linguistic conventions might be established without the aid of prior linguistic conventions.1 Brian Skyrms, professor of Logic and Philosophy of Science at UC Irvine, later generalized Lewis’s framework using evolutionary signaling games to show how meaningful language might emerge from random interactions.2 The simplest sort of signaling game involves two players: a sender and a receiver as in figure 1. The sender can see the state of nature and send a signal, but she cannot act. The receiver cannot see the state of nature, but he can see the signal and can act in a way that might benefit both agents depending on the current state of nature. We will suppose that each player learns by simple reinforcement. Simple reinforcement plays the role of an adaptive dynamics in the evolutionary game. How it works can be represented in terms of drawing balls from urns and adding new balls when the agents’ actions are successful.

IMG 1

On each play of the signaling game, the current state of nature is determined in a random and unbiased way by the toss of a fair coin. The sender has two urns, one for each possible state (0 and 1), and each of these urns starts with two balls, one for each possible signal (a and b). To determine her signal, she observes the state of nature (whether 0 or 1) then draws a signal ball at random from the corresponding urn. Then she sends that signal. She may send a or may send b on a play. Initially, the probability of each is equal as there is one ball of each type in the urn. The receiver has one urn for each possible signal (a and b), and each of these urns starts with one ball for each possible act (0 and 1). The receiver sees the sender’s signal then draws an act ball at random from the corresponding urn. Then he performs the act, whether 0 or 1. The sender and receiver are successful if and only if the receiver’s act matches the current state of nature. In the case of success, each player returns their ball to the urn from which it was drawn and adds a ball of the same type to the urn, thus increasing the probability of this ball being picked again; otherwise, each simply replaces the ball she drew.

This simple type of trial-and-error reinforcement learning is found throughout nature.3 A puppy who finds a scrap of salmon under a picnic table at the park will be more likely to look under that table on future walks. A commuter who gets home easier driving a new route will be more likely to use the new route on future commutes. When an agent learns by simple reinforcement, she may not even reflect on her experience as her dispositions slowly adapt to the world by trial and error. We are using balls and urns to model an adaptive dynamics where the probability of an action increases when the state where that action was successful occurs again.

Consider a concrete example. Suppose state 0 is “it’s sunny,” state 1 is “it’s raining,” signal a is “flash a green light,” signal b is “flash a blue light,” action 0 is “take two straw hats to the picnic” (the right thing to do on a sunny day) and action 1 is “take two umbrellas to the picnic” (the right thing to do on a rainy day). Here the sender wants to send a signal that communicates the weather to the receiver, and the receiver wants to take straw hats if it is sunny and umbrellas if it is raining. But the green and blue signals are meaningless, so there is initially no way to communicate.

On each day it is either sunny or rainy at random and with equal probability. Suppose it is sunny on the first day. The sender sees the sun and draws a ball at random from her corresponding 0 urn. Suppose that she draws a b ball and so flashes a blue light. The receiver sees the flash and draws a ball at random from his corresponding b urn. Suppose he draws a 0 ball, so he takes straw hats to the picnic, the right thing to do on a sunny day. This was a lucky draw since he might have drawn a 1 ball and taken umbrellas. But since he took straw hats on a sunny day, the play is successful, and each player returns the ball she drew to the urn from which it was drawn and adds another ball of the same type to that urn. This makes it more likely in the future that if the sender sees that it is sunny, then she will flash a blue light and more likely that if the receiver sees a blue flash, then he will take straw hats to the picnic. Had the receiver brought umbrellas, the play would have been unsuccessful, and each player would just return their ball to the urn from which it was drawn. In that case, the probabilities of signals and actions would remain the same as they were at the beginning of the day.

It is easy to write a computer program that models two players repeatedly playing this game. On simulation, the sender and receiver initially signal and act at random since each urn starts with one ball of each type and their draws are random. As a result, their signals are initially meaningless. But sometimes the receiver’s random act, by chance, matches the current state and the play is successful. As the players learn by simple reinforcement on what they did when they were successful, their signals gradually evolve meanings that allow the sender to communicate the state of nature reliably and the receiver to do the right thing. Argiento, Pemantle, Skyrms, and Volkov have proven that a perfect signaling language will almost surely eventually emerge in this very simple signaling game.4 And when we run this on a computer, the players typically evolve a reliable signaling language in a few dozen plays. 

In this simple game, meaningful order emerges from random trial-and-error learning as the behavior of the two players evolves, and each signal ends up communicating precisely one bit of information. Of course, there is nothing in the system that determines up front what the meaning of each signal will be. Their meanings are created by the players as they play. They are the product of random events in the context of the adaptive learning dynamics. A more complicated game illustrates a more subtle type of emergence.5 The coding game involves two senders and one receiver as in figure 2. At the start of each play, nature chooses one of four states, each with equal probability. The two senders observe the state, then each randomly draws a 0 or 1 signal ball from her corresponding urn. The receiver observes both signals and who sent them then draws an act ball from his corresponding urn and performs the action.

IMG 2

As in the simple signaling game we considered earlier, a play here is successful if and only if the receiver’s action matches the current state. If so, each player returns their ball to the urn from which it was drawn and adds a ball of the same type; otherwise, each player just returns their ball to the urn from which it was drawn.

In the coding game, neither sender has the resources required to communicate the state on her own. In order to evolve an optimal language, they must learn to partition nature in a systematic way so that the two signals together fully express which of the four states of nature the sender observes. One way that this might happen is if sender A learns to distinguish between nature being either state 0 or 2 (and sends a 0 if this is true) or state 1 or 3 (and sends a 1 if this is true) and sender B learns to distinguish between nature being either state 1 or 2 (and sends a 0 if this is true) or state 0 or 3 (and sends a 1 if this is true). In this case, 00 would mean state 2, 01 would mean state 0, 10 would mean state 1, and 11 would mean state 3 (see the left hand side of figure 3). This requires each sender to learn to attend to the conventional properties they have jointly invented as they play. When successful, they create and learn to use a systematic code to represent each of the four possible states and actions.

On simulation, the players in the coding game always evolve a meaningful signaling language, but an optimal language evolves in this game only about 73% of the time. When the players are successful in evolving an optimal language, random trial-and-error learning has led to a perfect system for communicating the information required for successful coordinated action. But again, this can only happen when the players create systematically interrelated properties and then attend to whether not each property holds. It is impossible to predict which properties the players will create on a run. Figure 3 shows the properties the players created and learned to track on two different runs. On the first run (on the left), A sends 0 and B sends 0 to represent state 2. But on the second run (on the right), A sends 1 and B sends 0 to represent state 2. The adaptive dynamics allows the players to evolve an optimal language on each run, but the inherent randomness in the dynamics leads to different languages on different runs.

IMG 3

As with the simple signaling game, the coding game illustrates how a meaningful language may emerge in the context of a random, trial-and-error adaptive dynamics. In both games, meaning is created as the players interact with each other and the world. But the coding game also requires the agents to learn to attend to their created properties in the world.

The evolution of attention is the key idea behind large language models like ChatGPT and Claude. The transformer architecture of such models was invented and first described in a paper by a group of Google scientists entitled “Attention is All You Need,” a play on the Beatles’ song “All You Need is Love.”6

A large language model (LLM) is a network with ordered layers of nodes connected by weighted edges. One might picture the network as a set of dots (nodes) and lines (edges) that connect nodes on one layer to nodes on the next layer. Every node is connected to at least one other, and each edge is assigned a numbered weight between 0 and 1 — the larger the number, the stronger the effect of one node on the nodes it is connected to on the next layer. When an input is presented to the input nodes of a trained model, the network produces a random result in the output nodes with probabilities that depend on the weights associated with the edges in the network. The weights are determined by how the model was trained. An LLM is trained using a huge collection of data, a standard of success, and an adaptive dynamics that gradually fits the behavior of the network to the standard of success by a trial-and-error learning process.

As a transformer model is trained, the features of the input to which the model attends and how it behaves when it observes these features, both of which depend on edge weights, are gradually tuned by the adaptive dynamics to fit the actual output of the model to the best possible output given the user-specified standard of success. In this way, as the system evolves, it learns both what to attend to and how to act on what it finds. Later, when it is presented with something it has never seen, it looks in places that have mattered for successful action in the past, then it uses what it sees to produce an output.

One can assess how well a transformer model learns saliences and connections by probing it with inputs that are unlikely to have been used in its training data. Consider the following prompt and Anthropic Claude 3.5 Sonnet’s reply.

Prompt: Explain two connections between emergent meaning by means of a random adaptive dynamics and art, complexity, and uncertainty.

Reply: There are several interesting connections between emergent meaning through random adaptive dynamics and the concepts of art, complexity, and uncertainty. Here are two key connections to consider:

Unpredictability and creative emergence: Both random adaptive dynamics and artistic processes often involve unpredictable outcomes emerging from complex interactions. In adaptive systems, meaning can emerge unexpectedly as elements interact and evolve over time without a predetermined plan. Similarly, in art, the creative process often involves experimentation and allowing unexpected results to emerge. Artists may start with an initial idea but then respond intuitively to how their work develops, embracing uncertainty and complexity. The final artistic product often has emergent qualities that weren’t fully anticipated at the outset. This parallel highlights how both domains harness uncertainty and complexity as generative forces.

Pattern recognition and meaning-making: Adaptive systems and artistic interpretation both rely heavily on pattern recognition to derive meaning from complexity. In random adaptive dynamics, meaningful structures or behaviors can self-organize out of initially disordered states as the system identifies and amplifies useful patterns. Likewise, both artists and viewers engage in pattern recognition to create and interpret meaning in artworks. Abstract art in particular often presents complex visual information that viewers must actively engage with to discern patterns and construct meaning. This process mirrors how meaning emerges from the complexity of adaptive systems, with the human mind acting as the pattern-recognition mechanism that extracts signal from noise.

The prompt asks Claude 3.5 for connections between the themes of the present exhibition and the related themes of this essay. While Claude likely never saw this prompt when it was trained, it does strikingly well in its reply. Strengthening Claude’s reply, I would argue that both artists and viewers are nothing but adaptive systems whose actions are forged by random adaptive processes; but given the inherent uncertainty in its audience, Claude shows wisdom in its more modest position.

Future AI systems will certainly do better, but that Claude has learned to associate a rich collection of topics with the present meager prompt and to thread them together to form cogent, and interesting positions is impressive. Its behavior illustrates how well a simple trial-and-error algorithm can learn to identify natural saliences and to find connections between them if presented with enough data.

While the details are a little different, the emergent behavior of an LLM like Claude is similar to that of the players in the coding game. Each system is initially capable of only random actions. The players in the coding game learn by trial and error to communicate using a meaningful language they gradually create for the purpose. Claude learns by trial and error to identify salient aspects of a prompt then learns patterns in these aspects and how to generate sensible responses. In each case, the adaptive system’s ability to identify saliences and to exploit them for successful action emerges from a trial-and-error adaptive dynamics as it interacts with the world.

Inventing languages, finding saliences, and learning connections involve creativity not unlike that exhibited by an artist. Each of the processes we have considered involves a random element. It is this that makes the process unpredictable.  The players in the coding game must create conventions and learn to adhere to them in order to be successful. It is impossible to predict which conventions they will create. Claude must learn to reply to questions it has never been asked to be successful, and in doing so it may say things that have never been said. And, like the works in the exhibition, its creations may spark new insights.

Our capacities have evolved under trial-and-error natural selection and by means of trial-and-error learning. The inherent randomness of these processes is baked into our nature. It is this that endows us with the ability to create things that are novel and surprising. The present exhibition itself is the product of randomness in the context of an adaptive dynamics. Each artist’s work has been influenced by their noisy experience. The curator has selected works in ways that depend on his experience and interactions with the artists. The resulting collection has the capacity to inspire new insights and understanding in us. The artworks become a part of us, a part of how we act and understand.

Notes

  1. David Lewis, Convention (Harvard University Press, 2020). 
  2. Brian Skyrms “Signals,” Philosophy of Science 75 (5) (2006): 489–500. 
  3. See Richard J. Herrnstein, “On the Law of Effect,” Journal of the Experimental Analysis of Behavior 13 (1970): 243–266, for early work on reinforcement learning in birds. For an example of reinforcement learning in humans, see Alvin E. Roth and Ido Erev, “Learning in Extensive Form Games: Experimental Data and Simple Dynamical Models in the Immediate Term,” Games and Economic Behavior 8 (1995): 164–212.4.
  4. See Raffaele Argiento, Robin Pemantle, Brian Skyrms and Stanislav Volkov, “Learning to Signal: Analysis of a Micro-Level Reinforcement Model,” Stochastic Processes and Their Applications 119, issue 2 (2009): 373–390. The theorem only applies to this two-state, two-term, two-action signaling game with unbiased nature. Convergence is not guaranteed if there are more than two states and acts or if nature is biased. The coding game discussed below is an example of a game where convergence is uncertain.
  5. See Jeffrey A. Barrett, “Dynamic Partitioning and the Conventionality of Kinds,” Philosophy of Science 74 (2007): 527–546, for a discussion of this game.
  6. Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aiden N. Gomez, Łukasz Kaiser and Illia Polosukhin, “Attention is All you Need,” Advances in Neural Information Processing Systems 30 (2017), 31st Conference on Neural Information Processing Systems (NIPS 2017), Long Beach, CA, USA, accessed February 2, 2025.

Cesar & Lois

“Being hyphaenated is an attempt to fight against the single point perspective in general, and the human perspective in a broad sense. We now understand that the whole planet is connected, and the behavior of one thing changes–sometimes dramatically–the behavior of another.”

Cesar & Lois is an art collective that probes humanity’s relationship to the planet by interweaving technological, biological and social systems. Their practice layers living networks, like mycorrhiza, over human technologies in order to challenge anthropocentric thinking and move the future of technology towards embodied planetary (and plant) intelligence. Cesar & Lois’s artworks often propose artificial intelligences based on those living networks, imagining machines that learn from Earth’s ecosystems. Formed in 2017 by Lucy HG Solomon (California, US) and Cesar Baio (São Paulo, Brazil), the collective has received numerous international awards for innovations in media art, BioArt, and the usage of AI.

Lucy HG Solomon: One of the things that comes up for us, and it came up in your article [refers to “A Brief on Complex Systems,” by David Familian], too, is this challenge of understanding timescales from the view of the planet. What processes take place over the course of millennia? We’re thinking about similar impediments to human sensing and engagement with real-time information that’s happening all around us through our lack of perception of wider scales of activity, both the molecular and the microscopic, and then planetary scales, while considering the independent systems and timescales of plants and fungi. We subconsciously consider these systems–of course, we’re always breathing CO2, we’re part of this breathing planet, but it would seem that intellectually we would have grown the capacity to feel the world in ways that would have maybe kept our own rampant development in check and our consciousness of the living world more in the forefront of our decision-making and our machines’ decision-making.

David Familian: Right, we tend to look at things through this one-point perspective. People still don’t see through the periphery of their vision.

Lucy HG Solomon: Cesar, I’m reminded of the first time that we met, and one of the things that made us interested in working together was your hostility towards one-point perspective. It was when we met in Plymouth, and you were talking about the tyranny of perspective, and I think that was at the core of some of our initial thinking, and widening that perspective to plants, to nonhuman perspectives. And then we looked at a lot of Indigenous-originating theories like multinaturalism and perspectivism, documented and coined by Déborah Danowski and Viveiros de Castro, who write of a perspective that is more community-based, of thinking along with and thinking through, in opposition to singular points of view.

Cesar Baio: Yeah, I think the title of this work, Being hyphaenated (Ser hifanizado) is an attempt to fight against this perspective in both ways: the single point perspective in general, and the human perspective in a broad sense. We can now understand that the whole planet is connected, and the behavior of one thing changes–sometimes dramatically–the behavior of other living things in other parts of the world.

We don’t sense how complex this system is. We know rationally that the ecosystem is composed of many living beings that interact in ways that we cannot predict and that are nonlinear. When we think of a living being as connected to and dependent on its interactions with its surroundings, we understand how important it is for people to translate these relational interactions into an aesthetic experience.

Lucy HG Solomon: In this work, we invite people to imagine how we are part of this broad intelligence system. If we can make the leap to having more inputs into the digital and machine systems that we create so that they take into account not just human concerns but this web of interactions, that would be transformational for AI.

“In this work, we invite people to imagine how we are part of this broad intelligence system. If our machine systems could take into account this web of interactions, they’d be transformational.”

Cesar Baio: I think you’re right when you point out that our work is really based on interactions. We are talking about these complex interactions. And, of course, as artists, we can only track a few of them. However, by tracking these few interactions, because there are many interactions between these organisms, we can also talk about what emerges from these interactions. You could think, for example, that living beings are fighting at any moment. When our bodies get sick, they’re fighting for permanence. When we get sick, our bodies are seeking to self-organize in a way that allows the body to survive.

When we think about climate change, there is an inevitable crossing of these two different forms of intelligence—human intelligence and ecosystemic intelligence–and by that, I mean intelligence that emerges from the forest, from the ecosystem, from the whole planet, which makes life possible. How these interact is a key point for us not only to understand better what life is but also to stay alive as humans and as a society.

Lucy HG Solomon: Right now, there are so many existential dilemmas that humanity moves forward with, like the continuation of new nuclear testing, which is likely, and all of these human decisions that make no sense. There’s no check on our destruction of a planet, despite the patterns that have already shown us that we should go in another direction. If we’re gonna trust AI to do so many other things, maybe we could trust it to keep some of our worst impulses in check–not a human-based AI, but an ecosystemic AI.

David Familian: Or it’ll do it for us. But I think one of the things I’m hearing from both of you, too, is that we have to stop simplifying the complex. Our minds want to simplify and simplify further, and that’s what the right-wing does and what the left-wing does. Everyone wants to simplify and essentialize. And the idea is we have to take this wider view and accept that there’s nothing to simplify anymore. There is no simplicity. That is an illusion–an aesthetic illusion, really. I think it’s an illusion that died with Einstein’s e=mc2. Since his discovery, we haven’t been able to simplify the way we had been. 

For 300 years, simplification was a successful method for understanding our world. But we’re not doing anything with that understanding. That’s one of the things introduced in the cybernetics conference: the question of whether scientists and the world will ever accept the complexity of these systems. There exists a constant and simultaneous pessimism and hope.

Lucy HG Solomon: What’s funny is that, even in accepting complexity, we’re also looking at some of the simplest interactions. In our own bodies, for example, multiple organisms in our gut compete for our decision-making.

David Familian: That’s what your work has been about and why I wanted you involved. You make it simple so people see the complexity. For the general public, we want to simplify the problem without getting rid of the complexity. That’s what, I’m hoping, a lot of the works will do, that they remain legible and engage a few discrete systems while the exhibition bombards visitors with the whole of global complexity. Though my initial instruction to the artists was to allow visitors to feel complexity viscerally, that can only happen if each work is not too complex.

Cesar Baio: I think this is an interesting aspect of our work. As a viewer, you can relate to our work on different levels. Without approaching the work too closely, you can see the lights but not the organisms, perhaps, but you can feel that something is happening. The interaction between the lights is implicit. When you get closer to the work, you see the wiring and the living organisms, and you see that they are connected within a system. So, some responses are being collected and presented, and you understand that some sort of feedback loop is occurring. And then you see the interface, which provides more information. You can go one or two steps deeper into how these complex interactions are taking place and what is happening within the artwork. 

So, as a viewer, you can enter as far as you’d like, and at each point, you can construct a different understanding of the work. If you spend time there, you will see the system’s patterns changing, and you can read on the interface how the CO2 you are breathing is changing the behavior and signaling of the organisms. This is something we want people to experience in our work.

“As a viewer you can construct a different understanding of the work. If you spend time with it, you’ll see the system’s patterns changing, and the interface shows you how the CO2 you are breathing is changing the behavior and signaling of the organisms.”

Lucy HG Solomon: Small shifts can significantly change our perspectives.

David Familian: There are different systems of complexity that exist in the city and in nature, but I think we just have to learn to see it everywhere. When you talk about the patterns changing, do you see emergence happening all the time, or do patterns build up? This is where the temporal thing comes in. Patterns generate the energy for emergence, which may lead to self-organization. The other thing that seems apparent in the work is that regulatory homeostasis is an illusion. Because once you have emergence and self-organization, it may seem to be an equilibrium, but the system has changed.

Lucy HG Solomon: I think of this work as a question. We’re wondering what patterns will emerge. Having these systems in observation in this setup for this amount of time is as close to a laboratory experiment as we can construct, and it may reveal whether patterns emerge from chaos.

David Familian: After the piece has exhibited in Future Tense, do you imagine that the work would continue to run as an ongoing experiment?

Cesar Baio: Actually, we want that. We are engaging more scientists and technicians to help us observe and extract more scientific data from what we are building and what we are doing as artists and to frame our project in scientific terms. Regarding emergence, the work evolves. It does not reproduce what we understand as nature; rather, it responds to a concept that has become very important to the environmental movement in the last two decades. That is the concept that everything is integrated and that we cannot separate from nature.

Lucy HG Solomon: Back to the web of life.

Cesar Baio: That’s why we directed AI to these living beings, which are working and communicating with each other, because we are also complex, and our technology is complex, and everything we project from our minds gets into this whole web of life.

We are not thinking about going back to some imagined time before technology. We cannot forget our culture; we have to rethink and rebuild. Other experiences of nature and technology, such as those that we try to create as artists, can give some insights into how different intelligences can integrate.

David Familian: So, how is your project using generative AI and General AI for pattern recognition?

Cesar Baio: General AI ideally behaves and acts like a human. In our work, we try to imagine a general AI that could behave like a planet or a forest. We wanted to shift away from a human-centric perspective and think of AI as capable of following not only human criteria and models.

Lucy HG Solomon: That’s true of Degenerative Cultures, which uses Physarum polycephalum as the model for an AI. In developing that project, we were thinking about nonhuman information and complexity and some of the limitations of humans that we’ve already talked about: scale and the lack of a human capacity for sensing that leads to a lack of empathy for a planet, for other living beings.

David Familian: That’s what Jim Crutchfield proposes in his work. People get really freaked out when they hear it because they think he’s suggesting that nature operates along computational processes, but he’s not. Natural intelligence could form a language or chemical or biological systems. 

One of the things I thought was interesting about your piece is that it attracts scientists in a way that makes one wonder whether its appeal is the concept of the experiment you set up, or its artistic qualities which entice them to enter this world you’ve created. Scientists don’t create worlds.

I’ve had colleagues at Irvine come into some shows and say, “Oh, that’s not art; that’s a science experiment.” And they’re partially correct, but what I like about your piece is that it’s a living system. A lot of BioArtists don’t work with real living systems, they work with artifacts of living systems. Being hyphaenated will continue to live. I think it’s interesting anthropologically, the fact that scientists are so compelled by your work.

Lucy HG Solomon: I think our engagement with the Treseder Lab was mutually invigorating. A lot of the scientists aren’t used to non-scientists tackling these questions from a totally different angle. Multidisciplinary collaboration opens a rare opportunity for discussion that scientists, even engaged environmentalists, don’t have in their labs. We’re so invested in scientific information, as artists, because it’s a key component of building the artwork, and it allows us to ask deeper and deeper questions that circle back to the relation of their research to other fields, to the planet. It may be inflating our work to say this, but I do think we offer an opportunity for people to engage with scientists’ critical interests in ways that scientists don’t normally get.

“Many scientists are not used to non-scientists tackling these questions from a totally different angle. Multidisciplinary collaboration opens a rare opportunity for discussion that scientists don’t have in their labs.”

David Familian: I was talking to a woman recently who received her PhD from ZKM, and we were talking about how even complexity scientists are focused within a discipline. Even at the Santa Fe Institute, transdisciplinary practice does not necessarily happen the study of complex systems because it’s hard to get funding—because it’s too unfocused.

I pick artists that know their field. So the response you’re receiving from the scientists is not uncommon for a Black Box project. I really let the artists navigate our system on their own and see which scientists resonate, naturally allowing things to happen, and it seems to work. What’s essential is that both the artists and the scientists are collaborative.

Cesar Baio: When you do this kind of art and deal with these kinds of complex questions and complex systems, the most challenging part is how to navigate from highly specialized and often hard-to-understand scientific concepts, to experiments, to scientific papers, to artistic concepts, to the artifact–the materiality of the work. It can be something that is not didactic, like some educational tool, but that is meaningful and creates momentum when a person encounters the artwork.

Lucy HG Solomon: In this project, we’ve moved towards sculptural elements such that the work becomes a conceptual mirror, so that there is both this simple organism, the shape that you’re looking at that’s clearly some kind of nonhuman entity, and then there are all of these sub-components that are in that larger entity. I think these questions about scale, simplicity, and complexity intuitively start to build within this weird creature that is the project.

David Familian:  I was imagining what happens if this gets bigger, and becomes the size of a room. I think you’re right that this will become a template, a foundation for something that you’ll be working on for the next ten years or so.

Cesar Baio: Yeah, I think this is something to point out–the process of the residency. You gave us the freedom to work in this way. We spent this whole year maturing and thinking about possibilities, and expanding and contracting and navigating between complexity and simplicity, with these different scales of information, and through science and aesthetics. The residency was a period of time when we were building concepts, building materialities, and building knowledge through the artwork and through the process.

It’s not something that you say what you are gonna make, and then you build it.

David Familian: I appreciate that. I didn’t know exactly what you were going to do. And, you know, I knew you were going to do something. But, you know, I get anxious…

Lucy HG Solomon: One last thing to say is that I know you quoted Barry Richmond, and this idea is that, as humans, we must learn to see both the forests and the trees simultaneously. In this artwork, we’re really trying to think about experiencing the almost microscopic or chemical exchanges and an entire ecosystem, and through that, to allow viewers to get a sense of their relationship to this one component as a small entity and as part of an ecosystem with the goal of seeing the forest and the trees simultaneously.

David Familian: In reality, it’s hard to see the forest and the trees. It’s not just conceptually hard. If you’re in the forest, you’re surrounded by these trees, you’re embedded in the midst of the environment, whereas the scale of your piece allows for viewers to create the distance necessary to see at both scales.

→ Cesar & Lois, Being hyphaenated (Ser hifanizado), 2024

Gail Wight

“Our minds all go to dinosaurs when we think about the Earth’s past. But my goal was to bring up the vast amount of important biological history that’s part of this system.”

Gail Wight is a visual artist constructing biological allegories through book arts, video, and experimental media. She holds an MFA from the San Francisco Art Institute, where she was a Javits Fellow, and a BFA from Massachusetts College of Art. Wight’s art has been exhibited internationally and is held in numerous publicand private collections. She is Professor Emerita in Stanford University’s Department of Art & Art History, where she continues to teach book arts and hybrid printmaking. Hexapodarium (2017), a publication about her work, includes essays and a conversation between Wight and writer Lawrence Weschler.

Gail Wight: Ostracod Rising tackles a system of absurd scale. It’s the history of Earth from the Hadean into the far future, encompassing an absurdly large, complex system. I’m primarily interested in the evolution of plants and animals and then asking the questions, ‘Where do we go from here?’ And ‘how does the complexity of this elaborate system fix itself and heal going forward?’

When we think about the Earth’s past, we probably think of dinosaurs. But my goal was to raise awareness of the vast amount of important biological history that’s part of this system. What surprised me was the geophysical stuff that I was completely unaware of. For instance, the history of how the chemistry of the atmosphere has changed, or discovering that daytime was only four hours long in the Hadean Eon. The Earth was spinning much faster, and it’s still slowing down. So, moving into the future, the Earth will continue to slow down. 

The other surprise was that the Moon was so much closer—so close that it appeared vast on the horizon. This means the Moon’s pull on tides could have easily caused mile-long tides. There are still really extreme tides on the planet, but it used to be extreme everywhere every day. And if you consider the intertidal zones a nursery for evolution, then having those extreme, vast intertidal zones is important, right? When you throw that into this system and then consider the interaction between all of these things, it’s extraordinary. The Moon is still moving away. So what happens when the Moon is so far away that it no longer impacts the tides, and we don’t have that intertidal zone anymore? My book doesn’t go far enough into the future to have the moon too far away to impact us anymore, but hopefully it makes the point that that can happen.

David Familian: One of the ideas that gets repeated a lot about complex systems is that every system is indeterminate after a certain temporal threshold. The planets have a four million-year span of predictability, and the weather has seven days, but this just means every system is indeterminate.

Gail Wight: But even that four million is a crapshoot because there are other random things, such as numerous asteroid strikes and the tectonic plates still shuffling around. I’ve talked to many scientists during this project, asking them what their predictions are for the future, and they’ve all said, in this sort of casual way, “Same thing that’s happened in the past, and a continuation of whatever’s happening now; That’s what’s going to happen.”

We’re aware of the asteroid that hit and caused the extinction of the dinosaurs, but there are others—contended—that we’re still discovering. There have been five mass extinctions before this one, during which almost everything on the planet died. My understanding of that comes from Elizabeth Kolbert’s book The Sixth Extinction (2014), in which she walks through the five previous extinctions and their causes. There are also many minor extinctions, which we call minor because they didn’t wipe out almost everything. But if they wiped out a single species in a complex system, that could potentially impact everything else.

I’ve tried to emphasize in this piece the many, many large and small extinctions that have happened over time. When I have us become extinct in this book, it happens alongside ungulates and a swath of other species that we’re really tied up with. So cattle, pigs, and sheep, species with whom we share interdependence and various habitats—and viruses—we all go extinct together. The end of the book is 104 million years beyond where we are now. And our extinction happens around 30 to 40 million years out from today. The timeline isn’t super specific. It has epoch-sized brackets. So there’s a period that predicts 55 million to 104 million years in the future. But when you read it, it’s as if it’s the present to 49 million years in the past. So, the present is actually 104 million years in the future.

I have no great pain, no internal angst, thinking about the end of humans. I think it’s going to be a good thing for the planet. I have great pain thinking about all of the life that we’re killing on our way out. It’s horrific. I’m reading Greg King’s The Ghost Forest (2023), my latest miserable reading on this topic, about the total decimation of the redwood forest in California. People don’t understand how total that decimation has been. I didn’t. And that Save the Redwoods League was behind much of it. This forest had the world’s most massive trees, hundreds of thousands of acres stretching up the entire side of this continent. Their destruction has to have impacted global warming, yet that hasn’t come up in a single conversation I’ve encountered.

“I have no great pain, no internal angst, thinking about the end of humans. I think it’s going to be a good thing for the planet. I have great pain thinking about all of the life that we’re killing on our way out. It’s horrific.”

David Familian: Well, you know the problem. I came up with the idea that scientists are ADD without peripheral vision. There are certain areas of science where, in order to encapsulate a phenomenon, they do have to widen their view. So, someone looking at gene expression must look at the gene’s building blocks. They discovered that the gene sequence is fixed. But stuff is happening underneath that’s either turning it on or off. They don’t know whether it’s turning on and off certain letters or whether it’s tweaking them like a piece of music. So those scientists have a wider view. We all bought into the idea that DNA was fixed. That was the whole genome project. We’ll figure out the DNA, and we’ll fix all our problems. But the problems aren’t all in the DNA.

So when you say no one else thinks about this, the question is, when are they forced to widen their viewpoint? What will it take for science to really look at complex systems, instead of discrete parts of the environment? In medicine, you get money only for doing certain things. The reason why universities keep everyone in their silos is that that’s how they can raise money. So it’s a whole feedback system of research, too.

If you’re familiar with the idea of the organic versus the mechanistic in modern science, we still think the world is a machine 300 years after Descartes. I enjoy that your work encourages people to extend their sense of time beyond the immediate future, particularly when it comes to the evolution of ideas.

Gail Wight: There is a really beautiful quote from Elizabeth Kolbert, which I’ll mangle. It has to do with the fact that our legacy will end up being the depth of a cigarette paper in the geological record of time, but every organism that we can save on our way out will create exponentially more life in the future.

David Familian:  Unless we leave robots behind. You know, the thing is, we could be leaving robots behind, and then we’ll leave a new species. This is the weird part. We’re actually preparing our replacements that can live in any environment.

Gail Wight: Yeah, if they’re biological. Anyhow. I don’t mean to suggest that nobody’s thinking about redwood loss contributing to climate change. It hasn’t entered the mainstream dialogue because everybody’s siloed. You know, some people are looking at the decimation of the redwood forest. You have other people who are looking at the complete extermination of beavers in the United States who used to create these water systems and others looking at local loss of native species… We need a public central hub of research.

David Familian: Even the guy who started the Santa Fe Institute complained that it was hard for him to raise money for transdisciplinary collaborations. He couldn’t even get the scientists to do it as much as he wanted. And this space is supposed to be dedicated to complex systems. What does that mean? If in the very place that was started to look at complex systems, scientists are resisting a certain aspect of what we’re talking about. I come back to the idea over and over that the knowledge people are studying is almost useless because it’s unconnected and abstract. I don’t know what it will take.

Gail Wight: Do you know this little book by Norbert Wiener—I think it’s called Invention. He walks through four brilliant inventions that failed for four different reasons. So, for instance, early computers failed because fine machining wasn’t available. He notes four instances where technology or society wasn’t prepared to build some invention. But the fault in fixing our climate crisis just seems like human belligerence. We’ve had the facts for a long time, but we can’t wrap our heads around climate collapse because of human belligerence.

David Familian: But the thing with climate change is that our brains have become so linear that we can’t see the world in its complexity. It takes a lot of effort. This is a challenging thing to do.

Gail Wight: Elizabeth Kolbert has another book called Under a White Sky (2021). Right at the very end, she discusses these scientists who plan to seed the clouds in the sky to rain more in areas that are drying up. However, one of the side effects is that the sky will turn completely white. It won’t be blue anymore. It’s a chemical reaction. And everything that they seed the clouds with will come down, and it will cause other problems, which is classic. It was in the paper last week, and I thought, this is so crazy; this will never happen. And now there’s somebody in LA talking about this. We might have to do this. But it’s a pretty straight line between cause and effect!

David Familian: And these are all these people that don’t look at the unintended consequences because they’re looking at solving a problem that can’t be solved. It’s not possible to do that. And this is the whole wicked problems problem. These issues are entangled, you know. I’m not teaching, so I’m not confined within an academic silo, and most artists aren’t siloed either, but you see it everywhere. And you wonder, what’s going to break this system?

So from talking to you, I can see that this temporality component is very important to the work—this extended timeframe. In your readings, what have you found that makes this distant future feel more immediate and relevant to audiences?

Gail Wight: I’m considering putting the Elizabeth Kolbert quote about saving things—of every small thing being exponentially important in the future—in the colophon for this book. There are 28 pages in total. Twenty of them are about specific time periods, which vary. For instance, the first two pages are about eons, but after that, it breaks down into periods of time, epochs, and a couple of sub-epochs. I have us in the Holocene, and then four more pages follow. To ensure that it’s not overwhelming reading, there are only nine or ten small snippets of text on each page. There are so many factors that can be rolled into what’s happening on any particular page, or period of time, whether it’s the chemistry of the atmosphere, the chemistry of the seas, the creation of dirt, the movement of plates, or asteroid strikes, or instances of volcanism or inland seas, or the erasure of shoreline, or the shifting of mountains and creation of glaciers—I try to touch on all of those things briefly in each page. So, hopefully, you will become aware of this cumulative yet repetitive process. Species are constantly being eliminated, and as they’re being eliminated, new species are emerging. While dinosaurs are evolving, for example, other more ancient species are on their way out. I’ve chosen 104 as a number in the future because it’s the number in Fahrenheit, which is the medical emergency fever zone for humans, as in when your brain stops functioning.

“Eventually, every concrete dam in the world disintegrates, and residual salmon reinhabit the freed rivers. Arboreal forests will pollinate the thin soils of depopulated cities.”

Everything in this book is very succinct, and I’ve made each comment count. After humans go extinct, there is this sort of fallout of the mess we leave behind. Eventually, every concrete dam in the world disintegrates, and residual salmon still can reinhabit the freed rivers. In depopulated cities where the soil is very thin, arboreal forests will pollinate those spaces rather than lush tropical growth.

I’ve tried to follow logical cycles of what could exist after humans as well as temperature cycles. So it’s going to be really hot for a while, but temperature tends to be cyclic, so there is a freezing that happens after the hot temperatures that we’ve caused begin to cool off, and then following the freeze, it becomes more temperate. Brand new species and familiar species are evolving, and things that make it through the gauntlet don’t become apparent until the end of the book. As we did—we made it through a gauntlet numerous times.

David Familian: So you point out the stress points in our time on Earth, too?

Gail Wight: Minimally. I don’t give a huge amount of space to people or dinosaurs. We’re only referred to as bipeds, and dinosaurs are only referred to as lizards. There are small species that exist here with us that we’re largely oblivious to. So those things take center stage. And even if we’re not oblivious, I think we’re not quite cognizant of how long they were here before us and how likely they are to be here in the future. This thing called a coccolithophore, for example, is this small single-celled creature that makes these beautiful calcareous structures around it. Or ostracods or copepods, viruses, and bacteria. They’ve been here for ages and will likely survive our chaos.

Different types of plants like cycads and angiosperms don’t make it–flowers are a weird and delicate thing that may not make it, but gymnosperms do, since they’re rugged. There’s a call-and-response relationship between many insects and angiosperms, or flower-making plants, so if there’s no insect, that call-and-response falls apart. But other dynamic systems between other types of plants and animals might take their place. 

Have you ever seen a map of sound space in the biological world, where every animal inhabits a specific tone in the sound space, a specific pitch, and if there’s a gap in a space, an animal will evolve with that pitch as its signal? It’s kind of like that. As things become extinct, I have other things filling those niches.

David Familian: You say that flowers will disappear, but as the Earth becomes more temperate, would they reappear somehow?

Gail Wight: There might be a flower that persists, but there will be a general collapse. It’s really rare for every variation of a species to go extinct. Some dinosaurs made it through the gauntlet and are here with us now. They’re mostly flying.

David Familian: I heard that lizards, being cold-blooded, had difficulty surviving during that period.

Gail Wight: Right. So many small dinosaurs survived. Many little permutations of things are preserved, but we humans are a pretty specialized species, so I don’t have us showing up again. Small things do make it through. And that’s why this book focuses on the small things. Big lumbering lizards didn’t make it, but the small ones that were agile and could fly and go to different places survived. Similarly, small monkeys might make it through, but these big specialized apes are probably not going make it through.

One of the interesting things about working on this has been that almost every supposition I’ve come across, somebody is arguing against it. So I have a biologist who’s fact-checking everything for me, and she’ll look up a prediction and say, “I found ten ‘yeahs,’ but I found one really angry ‘No,’” and I’ll say, “It’s a work of art, we’re going to include it.”

David Familian: I think we’re going through an intellectual and scientific revolution that may be equivalent to the beginning of science. This is huge, so it’s no surprise that emerging scientific ideas are highly disputed. This is what happens in the period we’re in now. The uncertainty we feel is more than the normal in uncertainty. It is the uncertainty of culture that is experiencing an incredibly accelerated transition.

Gail Wight: In a nutshell, I have deliberately chosen a non-traditional narrative. Even though there are traditional parameters, so for instance, I haven’t changed the timeframe of the Hadean or the Archean or the Cambrian. I’ve chosen to tell a story about how this system has operated in the past, where we are now, and where it might go in the future, reliant on both how it’s operated in the past and what’s happening right now. The emergence of new patterns and behaviors becomes very obvious in this book, as do the feedback loops seen in these call-and-response dynamics between species. Experiencing this artwork is a very internalized experience. It does what reading always does to us: It causes us to engage internally—it posits ideas in our heads.

“Experiencing this artwork is a very internalized experience. It does what reading always does to us: It causes us to engage internally—it posits ideas in our heads.”

David Familian: I think what that allows for is that there are works that you immediately have a visceral reaction to, and there are other works that plant seeds. Some works do both, and some do one or the other, but each approach is distinct.

Gail Wight: Right. I’ve also tried to keep the language very poetic. So again, every page has nine or ten snippets of text. The book can be briefly visually understood without reading more than a few numbers, but the more you read, the richer it is, and the more seeds it plants in one’s mind. The book ends 104 million years in the future, but I don’t use the term’ future.’ So, the end of the book is the concept of now.

Gabriel Tolson: On a closing note, I’d love to hear more about the incorporation of the ostracod specifically as a motif throughout the project. It gave rise to the work’s name, and I’m wondering how it threads through the book.

Gail Wight: Yeah, so it came about through an odd happenstance on a visit to the Hadley Lab. They showed me their core samples and how they could see when the atomic blast happened and when forests were cut down in California, all by looking at the composition of this core sample. They said one of the constants in the core sample was ostracods. And that’s because they are these tiny, hard-shelled crustaceans that live in every body of water on the planet, fresh or salty, and have been around for millions and millions of years.

I realized there’s this critter that has persisted. It’s been here forever, and if the future will belong to anything, it will probably belong to it, no matter what else happens. When I talked to some scientists and I asked, “what could happen to ostracods in the future?” again, their response was, “Well, you’ve got to look at what’s happened so far.” And so far the ostracod is a survivor.

Recently, someone found ostracods that have started to use their legs to walk. Previously, their legs were just thought of as swimming appendages. But they’ll walk on lily pads to chase food! They’re developing land legs. And then they have this carapace. It’s like a beetle carapace, so there is no reason (in my mind) why they couldn’t develop wings, which is what I have them do at the end. This means that ostracods will live 104 million years in the future in all three ecospheres: the land, the sea and the sky.

The final image is of this flying ostracod, a humorous take-off into the future. It’s this tiny, most minuscule thing that’s actually extremely relevant in our complex system. So many tiny plants and animals are creating potable water, breathable atmosphere, the basis of our food chain, and life forms that sustain us, and we generally have no clue. We being me, of course.

David Familian: What’s weird about all this is that we could be the only humans in the universe. We could have been a freak thing of nature. But most worlds do not have organisms that are building and altering their environment like we do.

Gail Wight: We could be. I mean, we are a fluke. I would argue that many animals are tool users, as with us, but they don’t create exorbitant waste. We don’t cope with our waste stream. Nothing has time to adapt to our staggering output. It’s at the root of all of our problems. The waste stream shows up quite a bit in this book—concrete detritus, radioactive detritus, and cesspools. We’ve created an enormous number of weird waste pits all over the planet. As we die, that waste, all kinds of cesspools, become thriving places for new species. Hope!

→ Gail Wight, Ostracod Rising, 2024

Chico MacMurtrie

“Dual Pneuma was initiated as this balancing, state-changing machine, and it evolved into a tool to make ceramics. As the ideas get more complex, they begin to reference the past, the future, the quality of being alien or ancient.”

Since the late 1980s, Chico MacMurtrie has explored the intersection of robotic sculpture, new media installation, and performance. His work investigates organic life from deep within, finding geometry in all living systems. MacMurtrie and his interdisciplinary collective, Amorphic Robot Works/ARW, have received numerous awards for their experimental new media artworks and have been presented in major museums and cultural institutions around the world.

David Familian: There are multiple areas of feedback in your work. Describe how your work uses feedback, and then, in general, how your works have dealt with the issue of feedback in various ways and how, in particular, you went from hydraulic to pneumatic muscles.

Chico MacMurtrie: Feedback is an integral element of a robotic system. I haven’t necessarily always worked strictly in robotics. I’ve used machines that didn’t have feedback. Several of these machines needed encoders or sensors—early mechanical works before hydraulics and pneumatics were introduced. For example, Totemobile, a work from 2007 commissioned by Citroën, used hard pneumatic systems with actuators, cylinders, electric motors, and a super-complex feedback system of sensors, proximity sensors, encoders, and read switches for positioning. So, there were over 350 different sensors on that system. There are 24 separate machines in that big machine. It’s run with a ladder logic and a redundant sensing system that looks at every sequence to ensure that it runs safely. And it’s completely dependent on feedback. The robotic skeletons of Skeletal Reflections had onboard encoders on it. But the interaction came from the viewer striking a pose, which was read by an early vision system and would then be turned into a little line drawing. The machine would then search the library for that pose, and then the machine would perform that pose. So it would interpolate from one posture to the next. 

The inflatables that we’re working on now aren’t new to feedback, because what we used for most of the inflatable architecture work was what we call pressure sensors, where we would measure the pressure in the machine. Then, we used that pressure on the machine to help close the loop and determine how we got the machines into different positions. Dual Pneuma, the work in the show, uses something even simpler. We’re using bend sensors which give a different value when you bend it. And that’s how you’re able to get the machine into different positions. What we have is the comparison between how artists work on robotics versus, say, a roboticist or a research student. The scientists are working on it through learning from past systems, and responding to papers that have been already addressed on the subject, and they just keep elaborating on that. So they stick real close to the lessons of traditional robotics. All these walking machines you see online are still hard-linked machines driven by motors and actuators.

“Scientists stick real close to the lessons of traditional robotics. All these walking machines you see online are still hard-linked machines driven by motors and actuators.”

When we were short on time, I told the PhD students to move on from the forward-and-reverse kinematics studies, stop taking the robot apart to try to get it to draw a C, get the robot on all four feet, have it respond to gravity, and start teaching it how to walk. So that’s what we’re doing over here at the lab. The approach we’re considering is to drive it into positions and then save those positions as presets. Now we have the option of actually recording actual movements, using a small puppet which I can use directly to drive the machine. That’s a series of encoders on a little apparatus that you can puppet with your fingers, and the machine responds directly. And then it records those motions.

Another layer is that the four points of contact will have these switches on them to know when the four points are touching the ground or if it’s three points. The way you drive it to navigate the space is that you set a rule in the code so that you always have three points of contact. So, the feedback system is the bend sensors at the joints and the pressure sensors at the feet. That’s the approach we’re using at the moment. Probably what will happen is we’ll have the bigger one do more navigation type of stuff, and the smaller one would probably do more organic things on the ground, like perform Yoga-types of positions and things of that nature.

David Familian: And how do you think the piece builds from the feedback to become more complex? 

Chico MacMurtrie: What the team at UC San Diego is trying to do is to use math and a range of references in traditional robotics, but they’re having a hard time leaning into the organic nature of Dual Pneuma. Their data sets are generated from hard machines, whereas this is a soft machine. There are two layers of feedback—one from the bend sensors and one from the pressure sensors. Part of what we’re doing now is we’re having to do some graph calculations for the resolution of the encoders.

David Familian: Maybe that has to be articulated in some way in the didactic, that in working with traditional roboticists, it became unwieldy to come up with the calculations, and it was easier for you to make your own puppet and use your mind as the processor to come up with ideas.

Chico MacMurtrie: I think what would be interesting to include is the variable techniques we went through to try to get these things working. What Allyson Chen is coding with mayy lab and they’re gonna set up a way to run different behaviors from that little machine with sensors or something.

David Familian: You’re taking the code you’ve developed with your machine and building from that, instead of starting from scratch?

Chico MacMurtrie: No, we’re starting from what Allyson created for our show at UCSD. She can get it to do things just by writing code and seeing what happens. And if necessary, we can hook her up with a little machine like what we’re working with. But the machine we’re working with will be helpful in terms of our ability to program the complexity of this new piece.

David Familian: I think it’s interesting to work with the totality of the physical remote model, as opposed to looking at a screen and moving a virtual model around. It seems like for you and the way you work, it’s better for you to have this than a virtual model on the screen.

Chico MacMurtrie: That’s right. Even if you really command that medium of a virtual model, you’re still up against real-life situations, right? So when you’re running robots in the real world, and a human performer is interfacing to drive it to the left and the right. No matter how good the model and video are, they will be insufficient at meeting the complexity of live scenarios. We’re using techniques similar to theirs. They just have a lot more sophisticated software for balance and stuff.

“Even if you really command a virtual model, you’re still up against real life. No matter how good the model is, it will be insufficient at meeting the complexity of live scenarios.”

David Familian: I’m intrigued by the fact that out of the frustration of not getting exactly what you wanted, you were forced to come up with another solution, which you may not have previously considered. Did you have a feeling you’ll have to do this anyway, at some point?

Chico MacMurtrie: Yeah, I figured that I would have returned to a previous method of robot control that I had used in the past.

David Familian: Like the control pad, or something similar, where you turn something and watch as the robot mirrors your commands. I remember you kept saying that you could control it with the usual interface. And you got it to happen. And I think that’s something to talk about a little bit in the video, too, is the challenges of this work which were not present in previous projects that didn’t need a living model, I mean a scaled-down model to work. You could intuitively work those big robots with just a few dials,  but this is a more complex system, with reverse kinematics and all that stuff going on. So it’s tough to figure that out when you’re turning knobs.

Chico MacMurtrie:  Also, with your standard slider on a Max patch, we could have 10 or 20 sliders, and you can only really move one at a time. With that robot, you could record one movement at a time on the arm and just turn that into a subsequence and keep doing that, or you could try to re-record a whole action with it. We’ll likely end up using a combination of both the new and old methods to control this robot. The truth is that we built a tool to allow me to control it and get it to do what I want for two reasons: one, it’s tough to tell the programmer what I want in animation. It takes a long time, but you can finesse the subtlety of it.

David Familian: Allyson was doing what you’re doing. She was programming it step by step herself. Her procedure is a lot harder because she has to do it a little bit at a time, and it’s a lot more trial and error, whereas yours limit the trial and error that she had to fight with. Each time she made a movement to make sure everything else followed correctly. But your model follows where you want to move it.

Chico MacMurtrie: That’s right, and we probably won’t get an extremely precise following, but you can teach it behaviors by looking at it and moving it and getting it to do something, so you’ll be able to control your puppet and get a feel for it directly. It’s exactly the way the Border Crossers (2021) had to work. With that project, we abandoned turning it into a machine completely because we had different terrain and wind conditions to deal with. So, we ended up building an interface that was more suited for a human driver. The difference here is we’re going to use that device to record what we’ll end up using for the show, and that’s in sequences. Right? So you build up a series of sequences, and that sequence is just ‘move forward, turn left, bow down,’ etc.

David Familian: So, will your presentation at the Beall be able to enact these different recorded keyframes, or will it pick from a random set of movements from time to time?

Chico MacMurtrie: I got the folks at UCSD working on a sensing system to use the sensing system to gather data on audience movements so that if people trigger a certain sensor, certain behaviors will be enacted. We’ll figure out how to trigger the more complicated things, for when you have an audience that should see the complicated stuff, and then some simpler things for the everyday audience.

David Familian:  Do you think when you’re installing, could our choreographer Kelli Sharp work with that model and translate its movements to the robot? Or is it a lot of work to encode movements.

Chico MacMurtrie: If Kelli could use the facility that she has, it would be more ideal for her to use a motion capture system that she could wear, which would be taking the role of the puppet.

David Familian: Right, I just thought it might require less translation.

Chico MacMurtrie: The idea behind the ceramics and the physical inflatables is that the inflatables pay homage to the ancestors. They are the offspring of the ceramics. And they’ll be making different kinds of sounds that set the mood of the installation.

David Familian: Can you articulate in some way how working on this piece has brought this idea of complex systems more to the fore of your practice.

Chico MacMurtrie: Sure. At the beginning of the project, I was thinking about doing more complex types of actions, utilizing balance and stuff like that. And I hadn’t really taken that on, and I’ve only recently begun to touch on the foot sensors. Early on, I was considering this humanoid form, and it took me to another place of thinking. At the point when you approached me, it triggered the beginning of this piece that had been in my mind for many years, but I didn’t have the means or the right opportunity to do it. Results were great in the beginning because there was some funding to do it, and then it also triggered the other works that are going to be in the show.

Dual Pneuma was initiated with the notion of this really complex balancing, state-changing machine, and it evolved into a tool to make ceramics. And so as the ideas get more complex, they begin to reference the past, the future, and even the quality of being alien or the product of ancient cultures. Dual Pneuma evokes a feeling that differs from the feelings you see in the more polished robots you encounter online, whose movements are precise and premeditated. In this project, viewers see how the robots move, and viewers have no sense of what they’re going to do, which makes them unique.

“The machine transitions between states of crawling and walking. When it seems to be falling over, it transitions into a different posture. It has this morphing ability to go from one state to the next.”

David Familian: And the materiality makes them more organic! I’m also curious why this piece pushed you to make fixed sculptures, which you’d never made before. Also, do you think this work is more alive than your other works?

Chico MacMurtrie: Well, it has infinite arrangements that it can do. One of the simple exercises that we got it to do on video yesterday was to use the machine as a plotter and to plot shapes, draw letters and stuff. He’s trying to figure out how to do this stuff. And so he’s going through all these exercises with this contraption you would normally use like a XYZ thing for right. And he realized that we have 350 different possibilities here. 

You have the action of an animal, an insect, an amoeba, a cell, a germ—it takes on all the qualities of all the things I’ve explored in 35 years of work because it’s boneless, in a sense. Its joints flex universally. While humans can imitate animals in an interesting way, it takes an athletic and dexterous human to do that. It can be multiple things, and that in itself is quite complex. As you move towards a deadline of an exhibition or a presentation, you have endless possibilities of what it can do, but you have to choose what you’re going to have it do to keep it cohesive and intact.

David Familian: My final question is: When we initially talked, I wanted you to make the viewer viscerally feel the relationship between order and disorder. How do you think the work is accomplishing that now? Right now, there’s a certain kind of awkwardness in the work because it’s like a baby learning to walk. It’s a little more advanced but it moves weirdly and doesn’t seem like a traditional animal because it’s learning. And you’re teaching it as you would train an animal. In your work, I see the tension between order and disorder in this space between smooth movement and awkwardness when the robot misses its mark.

Chico MacMurtrie: Yeah, I think you’re right about that. The smaller machine went between states of crawling, walking, and falling over. It has this morphing ability to go from one thing to the next. So, instead of being an accident or a fall, it can merge into another position. We’re concentrating on getting it to do some of these complex things I set out to do. The larger one will be more focused on walking around and doing things more uprightly. And if it falls over, it’ll fall into a seated position.

→ Chico MacMurtrie, Dual Pneuma, 2024

Hege Tapio

“How we experience emotions is driven by complex biochemistry. What if we could access that type of biochemical data to engineer and commodify emotions?”

Hege Tapio is a Norwegian artist based in Stavanger, the country’s oil capital. Tapio is currently pursuing artistic research with FeLT (Futures of Living Technologies) and is an interdisciplinary PhD fellow at the Innovation for Sustainability Program at OsloMet. Her practice examines the body as a landscape for “extreme self-mining” in bio-art installations, videos, and performances. She is the founder and director of i/o/lab – Center for Future Art, where she produced and curated a biennial from 2006–16.

Gabriel Tolson: It may be best to begin with the trajectory of how this work is unfolded.

Hege Tapio:  I guess my question was this: How do we deal with creating human-like entities like AI, and how will it operate in terms of interacting with us, which also have emotions, like how we are thinking of putting emotions back into the machine? That’s how I got involved with this emotion technology and work on how we are operating now with interpreting emotions, with using computers to read facial expressions and biometric data. And I thought that it’s not enough to get really into how we experience emotions because that’s also driven by biochemicals. My intention was to think about what if we could access that type of information—what if we could access the data of our biochemicals?

I also thought about how that would involve neuropeptides that signal our brain and cause us to experience emotions in our bodies, and how neuropeptides are also data that can be translated and synthetically produced. It’s trying to approach our human features when we are trying to construct this digital entity as we do with AI. Funnily enough, having conversations with more of computational-minded scientists is that their sense is that everything is—we’re able to program or compute everything. Even our emotions, many interpret as just datasets.

David Familian: Are you sure? Are you sure about that?

Hege Tapio: Well, if you listen to people like Joscha Bach, who says that everything is a simulation, and also the other conversations I’ve had.

David Familian: The problem with using the datasets is that they are limited in the dimensions used to simulate the interaction between systems or influences. The computer can only look at three or four dimensions of a complex system, and the minute you say datasets, you have to account for the dimensionality of how those datasets interact.

Hege Tapio: Yes, Joscha Bach is not talking about true and false perspectives. He’s talking about states that move along gradients. A point which continues to trouble me is the fact that we are driven by this long heritage of viewing living systems as machine existence, like from the perspective of La Mettrie’s materialist philosophy Man a Machine (1747). We are not really embracing the fact of how complex living systems are. When I started to look into emotions, I found that they consist of so many complex layers. It’s not only the cultural, learned facial expressions. It’s not only whatever can be given away from the chemical compounds in your sweat or biometrics from your heart rate. Even if we could approach the biochemical layer, that only gives us a small amount of information because it’s affected by many factors. Even the composition of our DNA determines how these emotions operate in our bodies. Also, with epigenetics, and how this is culturally formed over a long time period.

There are so many complex layers contributing to our emotional states and expressions. If we were going to truly understand and replicate emotions, I believe we would need the full embodied experience. And I have a hard time buying into the viewpoint of the true computationalists, who state that everything can be computed or programmed. The fact that we have a body gives us the opportunity to have a genuine experience. I find it hard to believe we could replicate this in a machine. We could give an illusion of doing so, as in the Chinese room or the Turing test, and I believe that we can create machines that are very sophisticated and appear to have emotions.

“Emotions are incredibly complex. From cultural, learned expressions, to the chemical compounds in your sweat, the biometrics of your heart rate, to the composition of your DNA and the epigenetics that change how genes are expressed over time.”

David Familian: What you’re saying is really important. Yuk Hui implies in his book Cybernetics for the 21st Century (2024) that we’re still living under the assumption that human beings are machines that can be quantified. This was Descartes’s stance. Kant was the first thinker to talk about the organic in Western philosophy. My response to all this is that we’re now 300 years out from Kant, and we still haven’t fully transitioned from Descartes to Kant.

Hege Tapio: And much of the problem is that we carry these dualist perspectives of understanding things. We have very limited parameters of how we can interpret or conceptualize how to grasp very complex information and how to grasp complex systems as living systems [or, living systems as complex systems].

David Familian: And then, the way the narrative goes is, you know, what are the points that we’ve made, where we’ve made progress in this shift that’s taken 300 years. And you have cybernetics in Britain dealing with biological and not the mechanical implementation of cybernetics. Then you have Virella and those people and second-order cybernetics, which talks about the body, precisely as you are, embodiment, and Umwelt. All of those ideas came out in the sixties and seventies. And so there is this narrative that is somewhat separate from science.

One of my arguments is that science has a direct trajectory of trying to understand and mechanize everything. And then you have this philosophical process in cybernetics where the two weren’t talking to one another. I’ve been asking different people whether this history is true, and so far, the answer has been a unanimous yes. That’s why it’s helpful to look at the view of cybernetics on all this: these ideas have a long history and were part of the original concept of cybernetics as advanced by the British.

Hege Tapio: Yeah, but the cyberneticists also battled with the big issues of consciousness and qualia, which is still something that we keep pondering about. Because we cannot really explain how this is all coming together. It’s how cyberneticists use the perspective of understanding biological systems and translate this into how they construct the machine. But again, it is also rooted in this perspective of coming back again to Man a Machine. So, it’s not really approaching or embracing the whole complexity. We should rid ourselves of this dualist perspective and try to look at more complexity.

David Familian: Which dualist systems are you referring to?

Hege Tapio: This dualist perspective is even found in the history of metabolism, which is rooted in the dualism of nature and society. So, we are constantly bringing in that divide between things and looking at things very separately instead of looking at things from a more complex point of view.

David Familian: Yeah. I agree. Those are two different things to me. The illusion that AI will be biologically intelligent is silly. AI, especially generative AI, is as mechanistic as the automaton to me. We’ve achieved what Descartes thought was impossible: that the mind and body could be quantified. And in some ways, we’re achieving that.

Hege Tapio: But what is interesting, and also a bit worrying, is that we’re now constructing machines, or we’re bringing in some entities in our lives that are also shaping us, to a large extent. For instance, the invention of photography really changed how we perceive and interpret, even memorize. It’s a mechanical tool, but it has affected so many ways of how we view, understand, and interpret the world around us. And I think computational tools and AI are going to have an even stronger effect on how we perceive and understand ourselves. Katherine Hayles also mentions this, referring back to cybernetics and how we are creating tools that reflect back to us, mirroring us.

I’m concerned that if we have very advanced AI with emotional capabilities in the future, and this is implemented into whatever kind of avatars or tools we interact with on a daily basis, it is going to affect the way we understand and relate, even how we deal with the emotional aspects of our lives.

David Familian: I just heard a story where they introduced the Internet to a tribe that never had any technology. They put Starlink in some area in Africa, and all these people are doing is looking at porn and just existing, doing exactly what we do. They’re obsessed with looking at themselves and using their phones, and I agree that on a societal level, it separates us. We know that AI is used to generate rumors and populate these extreme differences and viewpoints. So, I think it’s already messing us up. And this is my problem with artists who use AI to make an image and not reflecting on it critically. 

When artists created net.art, no one knew what it would be. It was brand new, and they were experimenting with something. Some people, you know, critiqued business and stuff or what the Internet would become. But now we know what the danger is. Many artists use dangerous technology to make pretty pictures.

Hege Tapio: Yeah, we’ve made dangerous stuff many times throughout history. But it’s paramount that we spend time reflecting on the possible outcomes of how we are rigging this system because it will affect so many ways in our lives that we cannot even comprehend at present.

David Familian:  Or we have to outlaw in certain areas of society. You can use it to look at tumors or other medical applications where it’s useful. Still, in any living system, AI is incredibly dangerous, and I don’t think they’ll ever be able to take out or perfect its hazardous elements. It’s sort of like when McLuhan said that every technology has good and bad attributes in relation to society. There is no proof that anyone has come up with a way to use AI in a positive way to bring us together. Theoretically, it could, but it doesn’t seem interested in doing that because it doesn’t make money.

Hege Tapio: And by that note is the question of who drives this technology. It’s a big company. So that’s also an issue. And also we talk a lot about machines and AI, but my project also involves how we deal with synthetic biology and use our knowledge of the machine to control living systems. By synthesizing emotions or designing emotions, my project opens up a discussion of where our limits are. Where do we want to go with the development of our technology? And also, how do we understand ourselves? What is genuinely human?

David Familian: I have a question about your project. Are you reflecting on, or pseudo-reflecting on, the scientific experiments that are feeding this technology? Or are you dealing with just the finished product?

Hege Tapio: Well, my project speculates where emotion technology might go. So if affective technology would go beyond what it is today, which is limited to analyzing facial expressions and biometric data. What if we could access our biochemical data, and how would that be utilized in the hands of someone with commercial interest, which is the case today with companies like Affectiva?

David Familian: Because one of the things that happens with things like this is that they think they’ve got it figured out, and then something goes haywire. It eventually generates some unintended consequences. So you’re bringing the utopian view of it, which is that it is successful. But there could be a dystopian one, too.

“I want the viewers to be worried and scared when they see the project. And that’s the reaction I’ve got when I presented it: people got really angry. And I love that.”

Hege Tapio:  I want the viewers to be worried and scared when they see it. That’s also the reaction I’ve had when I’ve presented the project; people got really angry. And I love that.

David Familian: Oh, that’s great! They’re supplying the dystopia part. You don’t have to embed it into the work. You create such an optimistic illustration of ‘Here’s what we can do,’ that people are pushed to react in horror and defensiveness. That helps me to understand your piece, too.

Hege Tapio: Yeah, people were so annoyed, saying, “What if you can create synthetic love?” And they were like, “Wait a minute. What if you discovered that the guy you were with was just wearing an implant, and he’s not really in love with you? Or, who’s going to afford real love in the future?” Or maybe we can design feelings or emotions we couldn’t imagine, like a different kind of love.

David Familian: Yeah, there’s a funny Star Trek moment where Kirk says something along the lines of “I want my fears. I don’t want to get rid of what I’m afraid of. That’s what makes me who I am.” And I think that’s part of what makes people freak out. Part of it is that we want to be rid of our foibles, our psychological weaknesses, and all that, but those faults make us who we are. Getting rid of our faults would make us all the same.

Hege Tapio: Yeah, I mean, my project is probably a transhumanist’s wet dream. I know that Bostrom has a manifesto that aspires to ‘create the best love.’ But yeah, I agree with you. We need the night and the day. We need to have a balance in things.

David Familian: Well, there’s a certain duality we do need. It is not necessarily the mind or body duality, but a Zen kind of duality. You wonder if people would just stop producing and doing anything if they had this device because you don’t get any of the rewards that you get from accomplishments.

Hege Tapio: You need the full gradient of all the emotions. Of course, you do.

David Familian:  So you’re presenting this, for lack of a better word, a deadpan, commercial version of this thing, and people are filling in their fear of it, which is rational. It’s not an irrational reaction. What’s interesting to think about is whether this is how we all react to new technology or are we now at a point where technology can so alter us as human beings that we will be transformed, and not in a good way.

Hege Tapio: Ideally, it will give you both a feeling of viewing something you would like to have and a moment of pause, where viewers ask, ‘What does this mean? Who’s going to drive this? What’s it going to look like if people start selling emotions.’

David Familian:  Your presentation in this sort of advertising format is really good. Is there a way for people to voice their fears if you had a website or somewhere where people could? And would you show that in this work, or perhaps store audience reactions for use in future works? I think there’s a lot of potential in sharing how people react. I don’t believe it is necessary to include that in this installation, but would you want to create a way for people to enter their responses into a database or something? So you have all these comments to use later in another work or another way.

Hege Tapio: That’s a very interesting idea. I presented my research in an exhibition in Oslo last year, and there, I had two boards where people could write down what kind of emotions they would like to have and what kind of emotions they would not like to have. But yeah, to have that response to the whole project would be very interesting.

David Familian: What you just said about emotions is very interesting: there were some emotions they wanted to buy and some emotions over which they still wanted to control. So come up with a series of questions, and let’s just see if we can put a QR code up and invite people to respond to the work, see what people say, and see if people use it. That would be really interesting.

Hege Tapio: Yeah, I mean, the video I’m showing is with this fake CEO running the Ephemeral Company. And she’s insinuating that companies out there are changing their slogans and will sell you the feeling of their emotions. For example, the narrator suggests that the company that currently goes under the slogan ‘just do it’ will change their slogan to ‘just feel it.’ You can even drive that toward becoming more sustainable, like if Chanel decides that it won’t produce so much fashion anymore but will sell you the feeling of Chanel. You can ask any woman why she likes to go shopping, buy makeup, or get new handbags. It’s because it makes us feel good.

“In the video I show the CEO of the fictional Ephemeral Company insinuating that major brands are pivoting from just selling you products to selling you feelings associated with those products.”

David Familian:  And guys want to buy their toys.

Hege Tapio: So we can get rid of consumers and go directly to the feeling of buying.

David Familian: What’s interesting about this is that people may not know, intellectually, that you’re talking about a complex system. But their reaction to it is that they don’t want to be controlled, which is exactly what you can’t do with a complex system. I mean, there’s a whole paradoxical thing in your work where, if they come up with this, they solve the problem of simulating a complex system. Similar to the way they use specific medications for certain mental disorders. It’s not treating the body as a complex system; it’s just supplying hormones that give you the illusion that you’re happy.

Hege Tapio: Yes, I think my work is on the borderline of medicalization. Truly. In the conversation I had with the neuroscientist who’s working with the medication, she said that when we’re medicating people with psychiatric disorders, we’re just giving them something that we think might work. We’re not even in control of how it will regulate the body. Or, it’s almost like a blind shot. That’s a very coarse way of trying to regulate our bodies as we currently do. Still, she also admitted that we have not even started looking into other possibilities of regulating our bodies without synthetic or medical compounds.

David Familian: Is there any way in the advertisement, if you haven’t already done this is to say something like, ‘This isn’t about just supplying you a particular feeling. We are solving the complex interactions of all your emotions and how they feed off each other in some language that doesn’t sound like a complex system.’ But they’re literally claiming they’ve solved the problem, which is not possible. It is impossible to solve a complex problem because there are always emergent properties. And so the minute they create a system, something invariably happens where they have to recalibrate it again. Something emerges that they can’t plan for. But is there anything in the text that propagates the idea that they’ve made this leap from Se. Working with a single hormone, or you know, like what psychotropic drugs do to help people? Is this tuned to your own body? It takes into factor your personality, something over the top.

Hege Tapio: That’s going to be part of the storyline. The way it goes is that you’re going to receive an implant that will read your biochemicals, and you will self-report the kinds of emotions you are feeling. Before you receive this implant, you know all kinds of data will be measured, including your height and weight. All this information will then be fed into a database so that they will be given more and more parameters of how these biochemicals are effecting these bodies. Then you can come to this company and say, “I want this specific feeling,” and they will be able to synthesize it based on your height, your weight, and your personal parameters. So we’re talking about individually-fitted emotions.

David Familian: Well, the interesting thing is whether they have to continually monitor you and keep track of you to adjust the chemicals. That would freak people out.  Another thing is that if a scientist walks up to this work and they go, “this is impossible, what she’s saying,” and they’re not getting that, you think it’s impossible too. I’m sure you’ve shown this to knowledgeable people who know it’s ridiculous in some way. They’re getting the joke and know that you know that this narrative you’re creating is over the top.

Hege Tapio: Of course. It is a speculative work, and I won’t hide that.

David Familian: No, no, that’s not what I’m saying. It’s like that fine line when telling a joke between insulting someone and getting them to laugh or getting someone just to say, oh, that’s silly. You know the difference between a joke being silly or insulting. There’s some tension between those two poles. The visceral part in this work can live in that dichotomy. So that’s how I’m envisioning the work to be experienced.

Hege Tapio: One of Elliot’s students picked up on that after she saw the movie. It was clear to her how our emotions are built upon many layers. And this is just one little piece of it.

David Familian: Well, that’s important, I agree. There’s this idea that language is not developed individually but socially. So if language is developed socially, and that’s the feedback system for language, how can this system account for all the complexity of the people interacting in the world? That’s what Elliott’s student is sort of saying. You certainly don’t want to be happy if someone’s beating you up. And maybe you have to say, this solves all the problems, but even when you’re interacting with people, it can adjust, like, just go over the top bit.

“Companies already create avatars with emotional capabilities. Give it five or ten years, and we’ll have a very complicated relationship between humans, human machines, and human avatars.”

Hege Tapio: But obviously, it doesn’t. I mean, even the opposite scenario as that which you’re describing, if you’re in a state of shock, you won’t be able to approach someone lovingly because your body is in shock. So, it has a very important say in how we feel about our environment and the state of our bodies. Also, back to the cybernetics again, I think an essential element of the work is how we view ourselves as living systems and how we interpret features that we can just analyze and pick out or displace, or move around because that’s what this work is implying, that we can extract emotions. And we can put them back in again.

This is what we are also trying to solve with AI, by trying to get it to operate with humans to understand our emotions and to respond to our emotions. What will it be like when you have companies like Soul Machines that are creating avatars with emotional, biochemical brains? They’ve replicated the whole nervous system in a computerized version that uses biochemical responses to generate digital biochemical response emotions. Give it five or ten years, and I think we’ll have a very complicated relationship between humans, human machines, human avatars, and whatnot.

David Familian: I know, and I don’t see how it’s going to be controlled. And I don’t think this is the traditional fear of a new technology. I believe that the more new technologies intersect with the complexity of our world, the more dangerous they get. I think.

Hege Tapio: It’s paramount that we hold onto what makes us human or try to understand what makes us human. That is necessary to preserve humanity as we know it.

David Familian: Or, as Katherine Hayles says, we’re all post-human. If we could get cybernetics scientists together to create truly transdisciplinary responses, maybe we could come up with some safeguards, and it would change the way we see all these issues.

→ Hege Tapio, Ephemeral, 2024

Laura Splan

“At the most basic level, I’m trying to evoke the environmental influences on gene expression, how genetics is not operating in a vacuum but is affected by external stimuli.”

Laura Splan is a New York City-based artist exploring intersections of culture, science and technology. Often working collaboratively and between disciplines, Splan’s practice reframes artifacts of the posthuman landscape. Her research interrogates the “GUI/gooey” or liminal spaces that mediate our relationship to nature and to our bodies. Splan has exhibited her work internationally and is held in collections including the Thoma Art Foundation. Commissions include projects for the CDC Foundation, Vanderbilt Planetarium, and the Bruges Triennial.

David Familian: My point of view now is the feedback is the engine: everything else evolves from it. There are two types of feedback: the general feedback around the environment, the outside and inside; and then there’s regulatory feedback, which is like when one gland secretes a certain hormone as its sole function.

Laura Splan:  I also kind of kept bucketing everything under feedback.

David Familian: That’s the framing. You can’t understand any of the other stuff if you don’t understand how the system you’re looking at uses feedback.

Laura Splan: On a high level, the piece, Baroque Bodies Sway, is intended to be this sensory encounter where people are hearing, they’re seeing, and they’re also moving and interacting and seeing other people move and interact. And all of the imagery and sound and research behind it, as well as the technology used to create it explores these entanglements between molecular bodies that are within our bodies and the built environment. And so it’s trying to locate these different nodes–I’ll use a term from your essay–to reveal the circuits among them. It’s trying to do that visually, and also through visitors’ agency.

Another couple of things around the elements of the installation: so there’s the interactive installation, where people moving through the space become some sort of external stimuli for the system of the installation itself. And they’re also actuating sound. Just on a really basic technical level, my work exhibits feedback loops and also processes internal and external stimuli. It’s people moving through a space and actuating a 3D model on the projection and being compelled to move more closely to that projection in order to inspect the landscapes that are reflected in the histone proteins of the nucleosome model—landscapes which are AI generated. The sounds were created in my collaboration with Adam Lamson. He was able to generate sound files off of his chromatin simulations, and then I took those and applied MIDI instruments to them. So there are multiple nodes and circuits happening in the artwork, which we can come back to.

There’s also the scaffold of the science of epigenetics that the whole piece is relying on and is inspired by. It’s a wonderful way to talk about every single one of these things that you’ve pointed out: uncertainty, feedback loops, and the emergence of new patterns and behaviors.

The thing that interests me about it and the thing that I’m trying to evoke, at the most basic level, is environmental influences on gene expression, how genetics is not operating in a vacuum—it can’t be reduced to genes—but it is affected by external stimuli or environmental influences. All of this having implications for disease or sensitivity to stimuli like scent or impacting phenotype.

“All of the imagery, the sound, as well as the technology used to create the work explore the entanglements between molecular structures that are within our bodies and the built environment. People moving through the space become external stimuli for the system of the installation itself.”

David Familian: What makes yours even more complex, and it’s going to be a challenge to display, is that the body has its own systems, of which DNA is the primary driver. But then you’re looking deeper into the complex system of DNA, which is also vulnerable to the outside world. So it’s a deeper kind of mutation.

Laura Splan: I think what you’re talking about is a mutation in the DNA sequence, versus epigenetics, which looks at how the same underlying DNA sequence is being expressed differently based on environmental influences. This is where complexity and uncertainty are introduced. You’re dealing with infinite possibilities that are unique to space and time.

David Familian: How does epigenetics translate environmental influences into mutations or diseases? What’s the pathway?

Laura Splan: It has to do with which genes get silenced and which are available to be expressed. The nucleosome model that I’m using in the exhibition is eight histone proteins that have DNA wrapped around them. That is a nucleosome. A nucleosome is a component of chromatin. Chromatin is the structural foundation of how DNA is packed into your chromosomes. And it could be packed in different ways. So that’s where Adam’s biophysical simulations of chromatin configuration are important in thinking about how DNA packs into a chromosome, and how that makes different parts of the sequence available or unavailable to be expressed, and that can be influenced by something like pesticides exposure.

One of the compelling research articles I found early on that really turned me on creatively to epigenetics was this study, where mice were exposed to a cherry blossom scent while they were being electrocuted, and then they took the electrocution away, and they would introduce the scent, and the mice would still have a trauma response to the scent, even though they weren’t being electrocuted. This response was then observed in not one, but two generations of their offspring who had not been raised by their parents and had never been electrocuted. It was a heritable trait that was not a change in the genetic sequence. It was a change in how certain genes were expressed.

David Familian: Right, so even though the sequence is the same, the way it expresses can be altered.

Laura Splan: Yes, and it can be altered over generations and over time.

David Familian: So, is the nature of these alterations to gene expression comparable to altering the speed at which a musical score is played, or missing a note? It’s almost like a DNA is a piece of music that can be played in different ways. And these all the things you’re talking about can affect how it’s played.

Laura Splan: That music analogy is really useful, and it’s why I love having sound in this piece as well. Every time somebody enters the space, they’re introducing another sound sequence. The soundscape is always going to be different, it’s never going to be the same, because people are always going to be entering at different intervals, and there will be a different number of people in the space at any given time. So the soundscape is one attempt to kind of materialize that variation.

David Familian: These kind of analogies will explain what gene expression actually means. Because it doesn’t immediately compute, when you hear of epigenetics. It’s too abstract.

Laura Splan: Participants can manipulate the cameras’ movement and point of view on the 3D model with their movement through space. So, the closer they get to the wall, the more the camera zooms in. The further they get from the wall, the more the camera moves out. But then there’s also this uncertainty, variation, maybe chaos even, presented by how many people are in the space, and if somebody is standing still they lose control. You have to be moving in order to be influencing or ‘swaying’ the visuals and sound.

David Familian: If there’s a group of people that spend enough time with it, would the chaos start to order itself in some way? Or will the number of people create a chaos?

Laura Splan: Everybody who’s moving has equal sway. So if people are moving divergently, there’s not a lot happening. But if they move together, the model is more responsive. If there’s just one person in there moving, and then a bunch of still people, that person has 100% sway. But there’s also this added uncertainty that comes from the emergence of patterns of behavior that has to do with social interactions and people being influenced by what other people are doing or not doing. And that’s the uncertainty part of it that has to do with human personalities and social behavior. So there’s the programmed side of the piece, and then there’s the unprogrammable side of the piece, which is human behavior, and the kind of soup of influence that happens depending on who’s in the space at any given time.

“There’s the programmed side of the piece, and then there’s the unprogrammable side of the piece: human behavior and the soup of influence depending on who’s in the space at any given time.”

David Familian:  If someone moves exactly the same way, will it do the same thing?

Laura Splan:  Yes, theoretically. But it depends on the movement. If adopting a kind of wild gesticular movement, that could manifest itself a little differently in the visuals. This kind of tracking I’m using is called ‘blob tracking.’ So if somebody is moving like a very similar blob to the camera, then yes, the camera would behave the same. Though we haven’t tested that particular issue yet.

The thing I’ve been playing with, and in some ways struggling with, is how to negotiate the reward system of ‘something’s happening,’ and also that problem of the ‘waving the hands.’ I don’t want it to be a one-to-one tool, or mirror interface. And in that not wanting to be a one-to-one mirror, there’s kind of a liveness to it that has a certain sense of its own agency. So I’m negotiating that in the programming side of it.

David Familian: We have been influenced by the design interfaces of our computers that are predictable all the time, so in projects that subvert a one to one interaction relationship, the struggle is to try to not make people think it’s broken, but that it’s structured. And that’s what I’ve been asking artists for years to think about.

Laura Splan: I think that the way that the piece is positioned in the gallery is going to benefit it. The fact that you’re not going into an enclosed space, where you’re only left to wave your arms, in some ways like is actually a benefit. I also like the idea that there’s incidental interaction where people are just moving through the installation space. But there’s also the intentional exploration that you described, which is inevitably going to be somebody waving their arms. I really don’t want it to seem ‘broken,’ so I am favoring the mirror over the personality of the nucleosome. But that’s definitely something I’m trying to master.

And there’s still this other layer of discovery and inspection of the landscapes, and there’s also the other layer of the sound, that the sound is always changing. So I hope that there is enough there for people to kind of be curious about.

David Familian: I think it was Caroline Jones that asked about the landscape in the reflections. There are two parts. One is the Baroque. People don’t understand the concept of the Baroque. Deleuze wrote about its folds, that it was about folds, which is what your piece is about. The second thing is the Age of Wonderment decoration or alteration, and this work is also in that tradition. The Baroque has kind of a bad rep, and we don’t think about fugues and sculptures that had cloth folding in it, that is not overly decorative, it’s expressive and very temporal.

Laura Splan: Yeah, and I was also thinking about it in terms of a baroque system, like a baroque bureaucratic system where that’s completely impenetrable. It has a bad connotation in terms of being unnecessarily complex.

David Familian:  Right. But to me, no one’s done anything better than a fugue. Anyone could take that original theme and come up with a total different set of counterpoints. There’s no rule. I don’t know if anybody’s ever done this, where they ask ten composers to take the same theme and create a piece of music. That would be really interesting, because I think that’s what’s amazing about that process.

Laura Splan: The other point that I was thinking about was from a procedural art perspective. Historically, I have developed elaborate rule systems to make my work. And I was really embracing that with the AI landscape generation by using disruptive prompts within Midjourney in ways that it wasn’t really intended to be used, and that being part of this absurd process of generating a landscape that looks like a really familiar landscape and didn’t need to be generated with AI. So the absurdity of the baroque is another part. I appreciate your thoughts on that. And then there was a whole other element about baroque peacock pearls. That was part of my collaboration with Adam. It continues to be an interesting reference point for me.

David Familian: And that book, The Fold: Leibniz and the Baroque (1988) by Deleuze, is almost impenetrable. I tried to teach it once, and totally failed at it, but I still take away the main points from the book that one can see in your work. And also the Baroque is when you have the quantification of the rate of change in a system. Calculus is figured out. Deleuze talks about liveness, too. So it’s all there.

Laura Splan: The other thing was, you know, I talked about participatory and accidental or bystander movement or stillness. I talked about the mirror quality as a tangible feedback, but also with elements of uncertainty where I’m negotiating the viewer’s sense of agency and control. Those are the things that I’m trying to kind of destabilize in an artful way.

David Familian: Can you control how far back it reads?

Laura Splan: Yes.

David Familian: That’s sort of the thing you’re figuring out, because you’ll have someone interacting.

Laura Splan: Yeah, my plan is to use the entire square or rectangle in front of that wall all the way to the door. I have four RealSense cameras.

David Familian: Oh, that’s great. That answers my question. It could be interesting if they’re there alone, and they go, “Oh, I got control of it.” And then people start walking around and they start losing control. So there’s a lot of narratives that I could see being expressed.

Laura Splan:  Yeah, and that’s where the kind of sway really becomes materialized and also politicized. Who’s in the space, who’s taking up space in the space.

I was also thinking of the AI image generation as a feedback loop of sorts, where the Midjourney model is trained on existing landscape images that have existing text descriptions. And that’s one of the things that fascinates me about this regurgitation factor of AI-generated imagery. And how, with the landscapes, certain language is used to describe them, like ‘panoramic landscape photography,’ without including the photographers’ names or anything like that in the prompts, that it continues to generate these idyllic-looking landscapes that seem a little uncanny to me. They have a little bit of a haunting quality, but they’re also kind of idyllic, with pink clouds, blue skies, and green hills.

“People navigating and negotiating control over the installation is where the ‘sway’ becomes materialized and politicized. Who’s in the space, who’s taking up space in the space?”

David Familian: It’s like surreal, or science fiction landscapes.

Laura Splan: Yeah. I’ve really enjoyed working with this existing feedback loop of AI image generation, but also trying to disrupt it. And there’s also an uncertainty in that process, where there’s like a slot machine quality to it, where you’re just like, “what is it gonna spit out this time?” We are also going to experiment with switching out landscapes on the visuals with interaction.

Correlating nodes and circuits with the nucleosome, the histone proteins are the nodes. That’s where the DNA methylation happens. And then the gene expressions form the loops. And then exposure to environmental influences like scent or pesticides form the inputs, and disease, sensitivity, and phenotype form the outputs.

David Familian:  Is the histone affected by this? Is that where things like smell and trauma get associated is in the histones?

Laura Splan: The histones play a role in DNA methylation, where genes are either expressed or silenced, or available or unavailable, and affect how chromatin is configured. The histones within the nucleosome are the ‘beads on a string’ of chromatin, and they’re packed into a chromosome, and how they pack into the chromosome is influenced by these molecular processes happening at the histone level. And that’s affecting the expression of genes, based on the way they pack into the chromosome.

David Familian:  So, would it be correct to say that the histones are genetically inherited?

Laura Splan:  The histones are directly related to what’s called genetic bookmarking.

David Familian: So when you inherit a trauma, that’s where the memory is held, in the histones?

Laura Splan: I’m not sure if I would put it like that. I also have been referring to Ellen Levy’s book, this Darcy Wentworth book that she mentioned in the Symposium meetings. There’s a really wonderful essay in there by Evelyn Fox Keller that gets right down into the science of epigenetics. It has some really wonderful explanations of epigenetics in relation to these questions that you’re asking me. It does a really wonderful job of tracing the history of the relationship between the convergence and divergence of physical sciences or physics and genetics. “In both cases, the assumption of a linear causal change promised explanatory reductionism, with the hope that an explanation of macro phenomena could ultimately be reduced to an understanding of the properties and behavior of the lowest level entities or atoms–in the case of physics–and genes–in the case of biology.” I found this chapter in particular to be really helpful for thinking about your questions. I also pulled out a couple of other quotes: “Complex systems have many interacting, active components, and the interactions between components have non-trivial or nonlinear interactions.” These are things that were just resonating with me about epigenetics. Nonlinear in terms of generations and unpredictable variables of environment and experience.

As an artist, my goal is to create some sort of sensory experience that is felt viscerally in order to be memorable and to resonate with the viewer for days, months, or years after they leave the gallery, and so the interaction to me is really intriguing. And as you’ve mentioned, this is a piece that is using tactics that I haven’t done before, and they’re really exciting to me. I’ve always thought of interaction or engagement with artwork as a rehearsal for behavior or thought or understanding that you can take beyond the artwork. I really love thinking about the human aspect of this piece, and how unpredictable it is, and it’s kind of terrifying and also exciting at the same time. That will be a sort of performative demonstration of some of the complexity that I think this exhibition is trying to get at.

In terms of the work, I think that these signifiers of the macro and micro can invite embodied explorations of the natural world through these landscapes, and that will feel like they’re situated in this confusing liminal space that’s biological, technological, and then also autonomous and interconnected. I think there will be this realization, as you mentioned, David, that one person might be in the space by themselves, and then once somebody else enters, they realize that they’re sharing space, they’re sharing control, and they’re also sharing experience.

“The macro and micro can invite embodied explorations of the natural world through these landscapes. They’re situated in this confusing liminal space that’s biological, technological, but also autonomous and interconnected.”

David Familian: I really like that you’re using unpredictable interactivity. You’re giving up a certain amount of control, and I think that will always be a scary thing. Art should be scary. Technological artists tend to want to control too much and eliminate this fear, whereas traditional artists live in fear unless they come up with a style.

This is something I think I should mention in the essay, the artist’s giving up of control. When I asked media artists to try it ten or fiteen years ago, I would just get a blank look. They’d just go: “Why would I want to do that?” And to me that’s antithetical to what you’re saying about being scared. And I love that you admit that it’s scary, because it should be scary.

Laura Splan: Well, the other thing, too, is that I am very particular. I spent so much time making those animations that I showed you in my studio, where I was obsessing over, like, whether the light should be at 90 or 91. And this progression, this evolution, this translation, this iteration of this body of work has so many factors that are by design not controlled.

David Familian: That’s sort of a good analogy of a complex system, that if we want to experience complex systems or learn to solve problems using systems thinking, we have to give up a certain amount of control that we expect to have. Because it’s an interesting thing. I just watched the beautiful mine and there’s the scene where he, Nash, does his theory, and he says that Adam says that whatever the individual goes after will be good for the group, and Nash said, “No, what’s good for the individual and the group is good for both,” and then you sit there, and there’s no explanation of well, how does that happen? How does the individual in the group get negotiated? Of course it does gets negotiated in game theory, where you have diplomats talking to work out what’s good for the both. But I think we’re still figuring that out. How do you negotiate so that the individual benefits as well as the group? And whether it’s a social thing or in any system, how do we negotiate the individual elements with the whole?  I think in the essay I said, “you have to see the trees and the forest at the same time.”

Laura Splan: I think that’s what I really love about the companion workshop to this body of work. I love developing the idea of this workshop with Hannah, because when I first came to her, I think I really only knew that her lab was exploring pesticides, and that was enough for me to be like, “Oh, this could definitely connect to my work.” But then, when I realized she was using blood and urine testing for that, which shouldn’t have been a surprise, I was intrigued further in thinking about the gooeyness of this expanded biotechnological apparatus that includes our bodies and bodily functions. But anyway, I really love the contrast that that lends to what is actually a pretty hygienic art experience.

David Familian: Right. And it also relates, I think, to Jim Crutchfield’s idea of information being part of the system. There’s a kind of information processing. And I think that urine testing is a form of information processing. And actually, it’s very controversial, since it seems like you’re making an analogy with computing. But I don’t think Crutchfield is doing that. He’s saying that information is its own language. It’s its own information processing. But it is processing information. However, you want to say it, it’s doing something and reacting to it. So in the purest form, it is information. It’s not [Claude] Shannon information, but it’s information. And this is a way of reflecting on that idea too.

Laura Splan: Yeah, and if we do food testing with dipsticks in the workshop and have immediate results, seeing how something that’s gooey and material can get quickly translated into data, into numerical data, and then also, with the urine testing, seeing how your body and its vulnerability can get located or reduced or translated into a data point.

David Familian: And also that urine testing is revealing the altering of the information. It’s saying you have something going on here, that information gets in your body.

Laura Splan: Yeah, I mean, the testing that we’re talking about is only testing for exposure. It’s not actually able to detect DNA methylation.

David Familian: And the Sway is related to the Baroque fold in a weird way. The sway is doing some of the work of the fold, where in Theresa’s work, for example, which is static, and visitors have to do the swaying in their imagination.

Laura Splan: Yeah, I think it has a lot of nuance that can be referenced in different ways and embodied in different ways.

David Familian: It feels like an older word.

Laura Splan: Well, what I like about it is that it’s kind of gentle sounding. But it can also be this invisible force that can be powerful and influential, and maybe even undetectable.

David Familian:  I mean, this is the butterfly effect. Like you’re saying, it could be both. It could be something with intention, or it could be something in the environment that makes you move.

Laura Splan: Yeah. And I really like that it lends itself to this interpretation or relationship to politics, with the idea of political sway, which is very much at play in agriculture. If you know anything about American agriculture, you know that it’s very entangled with politics. And so it’s kind of interesting to me, too, though it’s not something I’m speaking explicitly about. Sabine Seymour is doing a lot of work on that.

“People often reduce gene expression to being on or off. I’ve heard epigeneticist talk about it being more of a slider.”

David Familian: We’ve been programmed to think that everything’s in the DNA. And I think when people say that we inherit trauma, they think it’s in the DNA. I don’t think anybody understands what gene expression means.

Laura Splan:  A couple of more things about that. People often reduce gene expression to being on or off, and I’ve heard some people researching epigenetics talk about it being more of a slider.

David Familian:  So it’s like fuzzy logic. Which makes much more sense. Why would it just be on or off?

Laura Splan: And then also with the DNA methylation, making a gene available or unavailable doesn’t necessarily mean turning it on or off. Just because a gene is available doesn’t necessarily mean that it’s going to be expressed. So there’s a lot of nuance in the kind of mechanics and the physics of what’s happening, and its meaning.

David Familian: Well, it’s like with our synapses, and the question of whether there is a degree of how much electricity is in the signal. If we keep saying on and off we’re we’re reducing it to binary, which isn’t the way our bodies work. Our bodies are analog, not binary.

→ Laura Splan, Baroque Bodies (Sway), 2024

David Familian

David Familian has worked at the UC Irvine Beall Center for Art + Technology since 2005, initially serving as Associate Director before his appointment as Curator and Artistic Director in 2008. Familian has curated and organized more than thirty exhibitions at the Beall Center with a focus on artist’s projects and exhibitions which intersect new media, scientific innovation, and contemporary socio-political issues. Since initiating the Beall Center’s Black Box Projects residency program in 2013, he has supervised ten visiting artists and facilitated their collaborations with UC Irvine faculty in Art History and Visual Studies, Biology, the Center for Complex Biological Systems, Computer Science, Social Sciences, and Law.

Trained as an artist and educator, Familian received his BFA from the California Institute of the Arts in 1979 and his MFA from UCLA in 1986. For twenty years, he taught studio art and critical theory at the Minneapolis College of Art and Design, Otis College of Art and Design, Santa Clara University, San Francisco Art Institute, and UC Irvine. Familian began his artistic career in photography but embraced new media as his primary medium in 1990. His artistic practice has informed his various roles in web production and technical advisory for artists and institutions, naming the Walker Art Center, University of Minnesota, and the Orange County Museum of Art among his clients.

Installation view from Future Tense: Art, Complexity, and Uncertainty, presented by the Beall Center for Art + Technology, Irvine, CA, 2024. Photo: Will Tee Yang. Courtesy of the UC Irvine Beall Center for Art + Technology.

Ralf Baecker

Interface I, 2016

Aluminum tubes, DC motors, strings, elastic bands, custom electronics, and Geiger-Müller tubes, 189 x 23 2/3 x 70 7/8 inches

Interface I investigates the boundary between two separate interacting systems. Motors on the top and bottom pull strings, playing tug of war, and the points where the strings meet are coupled to their neighbors by elastic bands. Unpredictable signals, taken from Geiger-Müller tubes, detect the natural ambient radiation of the earth and determine the pulling strengths of each motor. The graphic shape of the red elastic mesh expresses the complex emergent behavior of the many interacting elements, and patterns develop from the contingent negotiation of individual random inputs. In Baecker’s words, “this is the beauty of chaos: it offers the potential for change.”

Ralf Baecker is a German artist working at the interface of art, science, and technology. Through installations, autonomous machines, and performances, he explores the underlying mechanisms of new media and technology. His objects perform physical realizations of thought experiments that act as subjective epistemological objects, posing fundamental questions about digital technology and complex systems and their sociopolitical entanglements. His projects provoke new imaginaries of the machinic, the artificial, and the real. His practice is a radical form of engineering that bridges traditionally discreet machine thinking with alternative technological perspectives and a new understanding of self-organizing principles.

Support for this presentation of Interface I comes from The Beall Family Foundation and Getty. Additional support was provided by NOME Gallery, the Graduate School of the University of the Arts, Berlin, and the Einstein Foundation.