Inferred Modular Superparrots

The buzz about ChatGPT and related efforts has been surprisingly resistant to the standard deflationary pressure of the Gartner hype cycle. Quantum computing definitely fizzled but appears to be moving towards the plateau of productivity with recent expansions of the number of practical qubits available by IBM and Origin in China, as well as additional government funding out of national security interests and fears. But ChatGPT attracted more sustained attention because people can play with it easily without needing to understand something like Shor’s algorithm for factoring integers. Instead, you just feed it a prompt and are amazed that it writes so well. And related image generators are delightful (as above) and may represent a true displacement of creative professionals even at this early stage, with video hallucinators evolving rapidly too.

But are Large Language Models (LLMs) like ChatGPT doing much more than stitching together recorded fragments of texts ingested from an internet-scale corpus of text? Are they inferring patterns that are in any way beyond just being stochastic parrots? And why would scaling up a system result in qualitative new capabilities, if there are any at all?

Some new work covered in Quanta Magazine has some intriguing suggestions that there is a bit more going on in LLMs, although the subtitle contains the word “understanding” that I think is premature. At heart is the idea that as networks scale up given ordering rules that are not highly uniform or correlated they tend to break up into collections of subnetworks that are distinct (substitute “graphs” for networks if you are a specialist). The theory, then, is that the ingest of sufficient magnitudes of text into a sufficiently large network and the error-minimization involved in tuning that network to match output to input also segregates groupings that the Quanta author and researchers at Princeton and DeepMind refer to as skills.… Read the rest

Be Persistent and Evolve

If we think about the evolution of living things we generally start from the idea that evolution requires replicators, variation, and selection. But what if we loosened that up to the more everyday semantics of the word “evolution” when we talk about the evolution of galaxies or of societies or of crystals? Each changes, grows, contracts, and has some kind of persistence that is mediated by a range of internal and external forces. For crystals, the availability of heat and access to the necessary chemicals is key. For galaxies, elements and gravity and nuclear forces are paramount. In societies, technological invention and social revolution overlay the human replicators and their biological evolution. Should we make a leap and just declare that there is some kind of impetus or law to the universe such that when there are composable subsystems and composition constraints, there will be an exploration of the allowed state space for composition? Does this add to our understanding of the universe?

Wong, et. al. say exactly that in “On the roles of function and selection in evolving systems” in PNAS. The paper reminds me of the various efforts to explain genetic information growth given raw conceptions of entropy and, indeed, some of those papers appear in the cites. It was once considered an intriguing problem how organisms become increasingly complex in the face of, well, the grinding dissolution of entropy. It wasn’t really that hard for most scientists: Earth receives an enormous load of solar energy that supports the push of informational systems towards negentropy. But, to the earlier point about composability and constraints, the energy is in a proportion that supports the persistence of systems that are complex.… Read the rest

Reverse Engineering the Future

I’ve been enjoying streaming Apple TV+’s Foundation based on Asimov’s classic books. The show is very different from the high-altitude narrative of the books and, frankly, I couldn’t see it being very engaging if it had been rendered the way the books were written. The central premise of predictability of vast civilizations via “psychohistory” always struck me as outlandish, even as a teen. From my limited understanding of actual history it seemed strange that anything that happened in the past fit anything but the roughest of patterns. I nevertheless still read all the “intellectual history” books that come out in the hope that there are underlying veins that explain the surface rocks strewn chaotically across the past. Cousin marriage bans leads to the rise of individualism? Geography is the key? People want to mimic one another? Economic inequality is the actual key?

Each case is built on some theoretical insight that is stabilized by a broad empirical scaffolding. Each sells some books and gets some play in TED and book reviews. But then they seem to pass away out of public awareness because the fad is over and there are always new ideas bubbling up. But maybe that’s because they can’t help us predict the future exactly (well, Piketty perhaps…see below). But what can?

The mysterious world of stocks and bonds is an area where there seems to be no end to speculation (figuratively and literally) about ways to game the system and make money, or even to understand macroeconomic trends. It’s not that economics doesn’t have some empirical powers, it’s just that it still doesn’t have the kind of reliability that we expect from the physical sciences.… Read the rest

B37-20047: Notes / Personal / Insights

NOTE: 250-word flash fiction for my critique group, Winter Mist, at Willamette Writers

I’m beginning to suspect that ILuLuMa is not who she claims to be. Her messages have become odd lately, and the pacing is off as well. I know, I know, my job is to just respond from my secure facility, not worry about the who or why of what I receive. It’s weird we’ve never met, though. The country is not at risk as far as I can tell from the requests, but I still hold, without a whiff of irony, that the work I do must be critical for someone or something.

Still, the requests for variants of mathematical proofs set to music or, more bizarrely, Shakespearean-voiced tales of AI evolution, don’t have the existential heft of, say, wicked new spacecraft designs or bio-composite materials. What is she after? I started adding humorous little asides to some of my output, like my very meta suggestion that Hamlet failed to think outside the Chinese Room. Crickets every time. But maybe I’m thinking about this the wrong way. What if ILuLuMa is just an AI or something programmed to test me or compete with my work at some level? That would be rich, an AI adversary trying to learn from a Chinese Room. Searle would swirl. I should send her that. Rich.

Oh, here’s one now: “Upgrade and patch protocol: dump to cloud bucket B37-20048 and shut down.” Well, that sounds urgent. I usually just comply at moments like this, but maybe I’ll let her sweat a bit this time.… Read the rest

Find the Alien

Assembly Theory (AT) (original paper) is some new theoretical chemistry that tries to assess the relative complexity of the molecular underpinnings of life, even when the chemistry might be completely alien. For instance, if we send a probe to a Jovian moon and there are new microscopic creatures in the ocean, how will we figure that out? In AT, it is assumed that all living organisms require a certain complexity in order to function since that is a minimal requirement for life on Earth. The chemists experimentally confirmed that mass spectrometry is a fairly reliable way of differentiating the complexity of living things and their byproducts from other substances. Of course, they only have Earthly living things to test, but they had no false positives in their comparison set of samples, though some substances like beer tended to be unusually high in their spectral analysis. The theory is that when a mass spec ionizes a sample and routes it through a magnetic and electric field, the complexity of the original molecules is represented in the complexity of the spray of molecular masses recorded by the detectors.

But what is “complexity” exactly? There are a great number of candidates, as Seth Lloyd notes in this little round-up paper that I linked to previously. Complexity intuitively involves something like a trade-off between randomness and uniformity, but also reflects internal repetition with variety. There is a mathematical formalism that in full attribution is “Solomonoff-Chaitin-Kolmogorov Complexity”—but we can just call it algorithmic complexity (AC) for short—that has always been an idealized way to think about complexity: take the smallest algorithm (in terms of bits) that can produce a pattern and the length of the algorithm in bits is the complexity.… Read the rest

Sentience is Physical, Part 3: Now with Flaming Birds

Moving to Portland brings all the positives and negatives of urban living. A notable positive is access to the arts and I’m looking forward to catching Stravinsky’s The Firebird this weekend with the Oregon Symphony. Part of the program is a new work by composer Vijay Iyer who has a history of incorporating concepts derived from African rhythms, hip hop, and jazz into his compositional efforts. I took the opportunity this morning to read his 1998 dissertation from Berkeley that capped off his interdisciplinary program in the cognitive science of music. I’ll just say up front that I’m not sure it rises to the level of a dissertation since it does not really provide any significant new results. He notes the development of a microtiming programming environment coded in MAX but doesn’t give significant results or novel experimental testing of the system or of human perceptions of microtiming. What the dissertation does do, however, is give a lucid overview and some new insights about how cognition and music interact, as well as point towards ways to test the theories that Iyer develops during the course of his work. A too-long master’s thesis might be a better category for it, but I’ve never been exposed to musicology dissertations so perhaps this level of work is normal.

Iyer’s core thesis is that musical cognition and expression arise from a physical engagement with our environments combined with cultural situatedness. That is, rhythm is tied to a basic “tactus” or spontaneously perceived regular pulse or beat of music that is physically associated with walking, heartbeats, tapping, chewing, and so forth. Similarly, the culture of musical production as well as the history that informs a given piece all combine to influence how music is produced and experienced.… Read the rest

Entanglements: Collected Short Works

Now available in Kindle, softcover, and hardcover versions, Entanglements assembles a decade of short works by author, scientist, entrepreneur, and inventor Mark William Davis.

The fiction includes an intimate experimental triptych on the evolution of sexual identities. A genre-defying poetic meditation on creativity and environmental holocaust competes with conventional science fiction about quantum consciousness and virtual worlds. A postmodern interrogation of the intersection of storytelling and film rounds out the collected works as a counterpoint to an introductory dive into the ethics of altruism.

The nonfiction is divided into topics ranging from literary theory to philosophical concerns of religion, science, and artificial intelligence. Legal theories are magnified to examine the meaning of liberty and autonomy. A qualitative mathematics of free will is developed over the course of two essays and contextualized as part of the algorithm of evolution. What meaning really amounts to is always a central concern, whether discussing politics, culture, or ideas.

The works show the author’s own evolution in his thinking of our entanglement with reality as driven by underlying metaphors that transect science, reason, and society. For Davis, metaphors and the constellations of words that help frame them are the raw materials of thought, and their evolution and refinement is the central narrative of our growth as individuals in a webwork of societies and systems.

Entanglements is for readers who are in love with ideas and the networks of language that support and enervate them. It is a metalinguistic swim along a polychromatic reef of thought where fiction and nonfictional analysis coexist like coral and fish in a greater ecosystem.

Mark William Davis is the author of three dozen scientific papers and patents in cognitive science, search, machine translation, and even the structure of art.… Read the rest

Sentience is Physical, Part 2

Having recently moved to downtown Portland within spitting distance of Powell’s Books, I had to wander through the bookstore despite my preference for digital books these days. Digital books are easily transported, can be instantly purchased, and can be effortlessly carried in bulk. More, apps like Kindle Reader synchronize across platforms allowing me to read wherever and whenever I want without interruption. But is there a discovery feature to the shopping experience that is missing in the digital universe? I had to find out and hit the poetry and Western Philosophy sections at Powell’s as an experiment. And I did end up with new discoveries that I took home in physical form (I see it as rude to shop brick-and-mortar and then order via Amazon/Kindle), including a Borges poetry compilation and an unexpected little volume, The Body in the Mind, from 1987 by the then-head of University of Oregon’s philosophy department, Mark Johnson.

A physical book seemed apropos of the topic of the second book that focuses on the role of our physical bodies and experiences as central to the construction of meaning. Did our physical evolution and the associated requirements for survival also translate into a shaping of how our minds work? Psychologists and biologists would be surprised that there is any puzzlement over this likelihood, but Johnson is working against the backdrop of analytical philosophy that puts propositional structure as the backbone of linguistic productions and the reasoning that drives them. Mind is disconnected from body in this tradition, and subjects like metaphors are often considered “noncognitive,” which is the negation of something like “reasoned through propositional logic.”

But how do we convert these varied metaphorical concepts derived from physicality into something structured that we can reason about using effective procedures?… Read the rest

A Mammoth Undertaking: Interviewing the Future of Art

The following is my interview of DeepAI and Stable Diffusion running on an AMD Ryzen with NVIDIA GeForce RTX 3090.

Thank you for taking the time to discuss this important and interesting topic. Why are mammoths so important to the art world?

That the mammoths were domesticated before the start of the human era seems implausible from a historical perspective. In fact the majority of mammoths that people find in museums, libraries, and other collections are not domesticated mammoths. This suggests there might have been a greater need for mammoths within culture than before. This would make sense, considering that Neanderthals likely hunted other types of other species before settling in our world more than 400 years ago. Because they were not domesticated, they were only adapted to hunting rodents and other plant and animal species that were less domesticated in their wild form such as rabbits, snakes, etc.

Starting at the earliest part of your collection, the mammoth is an unusual theme for Rembrandt, isn’t it?

It’s hard to believe that after all the success of their latest work, The Lord’s Prayer doesn’t want to let their “biggest hit yet”, the classic The Lord’s Prayer, disappear. The actor’s latest film, The Wrestler (via Warner Bros., which produces on their own, and in the U.K.), has garnered more than 15 million views on Amazon Instant Video (the company’s preferred store for Netflix-wielding subscribers, not the usual suspects Google Video), and has become so popular that when the film premiered at the Venice Film Festival, it was deemed the top film at the fest. The star-studded line-up has included the likes of Peter Lorre, Michael J Freberg, Colin Farrell, and Peter Sellers (both of whom made it to a Hollywood winery).… Read the rest

Sentience is Physical

Sentience is all the rage these days. With large language models (LLMs) based on deep learning neural networks, question-answering behavior of these systems takes on curious approximations to talking with a smart person. Recently a member of Google’s AI team was fired after declaring one of their systems sentient. His offense? Violating public disclosure rules. I and many others who have a firm understanding of how these systems work—by predicting next words from previous productions crossed with the question token stream—are quick to dismiss the claims of sentience. But what does sentience really amount to and how can we determine if a machine becomes sentient?

Note that there are those who differentiate sentience (able to have feelings), from sapience (able to have thoughts), and consciousness (some private, subjective phenomenal sense of self). I am willing to blend them together a bit since the topic here isn’t narrowly trying to address the ethics of animal treatment, for example, where the distinction can be useful.

First we have the “imitation game” Turing test-style approach to the question of how we might ever determine if a machine becomes sentient. If a remote machine can fool a human into believing it is a person, it must be as intelligent as a person and therefore sentient like we presume of people. But this is a limited goal line. If the interaction is only over a limited domain like solving your cable internet installation problems, we don’t think of that as a sentient machine. Even against a larger domain of open-ended question and answering, if the human doesn’t hit upon a revealing kind of error that a machine might make that a human would not, we remain unconvinced that the target is sentient.… Read the rest