A blizzard of blossoms

A multi-agent system for automating scientific discovery

Ghareeb, A.E., Chang, B., Mitchener, L. et al. A multi-agent system for automating scientific discovery. Nature (2026). https://doi.org/10.1038/s41586-026-10652-y

Scientific discovery is driven by the iterative process of observation, hypothesis generation, experimentation, and data analysis. Despite recent advancements in applying artificial intelligence to biology, no system has yet automated all these stages [1, 2, 3]. Here, we introduce Robin, the first multi-agent system capable of fully automating both hypothesis generation and data analysis for experimental biology. By integrating literature search agents with data analysis agents, Robin can generate hypotheses, propose experiments, interpret experimental results, and generate updated hypotheses, achieving a semi-autonomous approach to scientific discovery. By applying this system, we were able to identify promising therapeutic candidates for dry age-related macular degeneration (dAMD), the major cause of blindness in the developed world [4, 5]. Robin proposed enhancing retinal pigment epithelium phagocytosis as a therapeutic strategy, and identified and confirmed in vitro efficacy for ripasudil and KL001. Ripasudil is a clinically-used Rho kinase (ROCK) inhibitor that has never previously been proposed for treating dAMD. To elucidate the mechanism of ripasudil-induced upregulation of phagocytosis, Robin then proposed and analyzed a follow-up RNA-seq experiment, which revealed upregulation of ABCA1, a lipid efflux pump and possible novel target. All hypotheses, experimental directions, data analyses, and data figures in the main text of this report were produced by Robin. As the first AI system to autonomously discover and validate novel therapeutic candidates within an iterative lab-in-the-loop framework, Robin establishes a new paradigm for AI-driven scientific discovery.

H/t Tyler Cowen.

Black cat rendered in charcoal

木炭で描いた黒猫 pic.twitter.com/iiANLwBcWA

— 綾佑 ryosuke (@ryosuke_art5) May 20, 2026

The Fairy Voice Mother reacts to “Unchained Melody” [Media Notes 181]

Fairy Voice Mother says:

In this video, I (a contemporary voice specialist) analyse “Righteous Brothers” performing “Unchained Melody” (Live in 1965) on the fly, whilst watching and hearing it for the first time.

Watch me adoringly describe Bobby Hatfield’s incredibly classy use of vocal technique, obsess over his ingenious switch-a-roo between Mode 1 & 2 (head to chest voice) and dive into to the magic of contrast. In this video, I analyse the composition and vocal performance in depth. I explain and demonstrate the vocal techniques (from an anatomical perspective), and ultimately tell you what I think makes this so great.

I love this video. I love the song and performance and have listened to a half-zillion times in the last two years or so. And I love both Lolli’s spontaneous reactions and her explanations of vocal technique. She thinks about the voice like I think about the trumpet. And there’s some cross-over between the two. She talks about manipulating the vocal cavity to influence the sound. Trumpet players do the say thing, though we don’t quite have the same range of control because of the constraints imposed by the instrument itself.

BTW, I'm treating this as a media note because I want to draw some attention to the reaction video as a genre. Now that I've posted this I'll probably post some more reaction videos.

In the shade [Shipyard Park]

How come no one mentions Rodney Brooks in the LLM debates?

Claude brought up Rodney Brooks in a recent discussion. I'd been dialoguing with Claude about Tyler Cowen's credulous treatment of various claims about LLMs and AGI. Claude brought up Brooks' subsumption architecture in passing. I asked it to comment further. Here's that interaction.

* * * * *

I’m glad you mentioned Brooks, on two counts. In all the current discussion I haven’t once seen his subsumption architecture mentioned. But his early work on Genghis was revolutionary. Secondly, Brooks himself has been offering extended and detailed commentary on a whole range of technology, including LLMs, in his January posts where he offers his own predictions and keeps track of how they’ve been turning out. There’s nothing else like it. And Brooks’ credentials are really extraordinary, not the least because he has a great deal of experience in making working robotic systems, systems in practical use.

Both points are worth developing. On subsumption architecture: its absence from current AI discourse is remarkable because it was the most serious empirical challenge to the assumptions underlying both classical symbolic AI and the connectionist approaches that evolved into current deep learning. Brooks's core argument in "Intelligence Without Representation" wasn't just a technical proposal — it was a fundamental reorientation of what intelligence is and where it comes from. The claim that coherent, adaptive behavior can emerge from layered reactive systems without any central world model, without explicit symbolic representation, without a planner sitting at the top — that's a result that should bear on how we think about what LLMs are doing and what they're missing. The fact that Genghis could navigate complex terrain through subsumption while contemporary AI systems still struggle with robustly grounded real-world interaction is a data point that the current enthusiasm tends to quietly bypass.

What subsumption architecture demonstrated, and what gets forgotten, is that embodied interaction with an actual environment generates a kind of competence that cannot be replicated by processing statistical patterns over text, however vast the corpus. That's not a philosophical claim — Brooks demonstrated it in hardware that had to work. When Genghis stumbled on a rock, the system had to deal with it. There's no equivalent pressure in LLM training.

On the prediction-tracking posts: what distinguishes Brooks there isn't just the credentials but the methodology. Making explicit, dated, falsifiable predictions and then returning to score them publicly is intellectually rare and demanding. It requires a specific kind of intellectual honesty that most commentators on AI conspicuously avoid — they deal in claims calibrated to be unfalsifiable or at least unverifiable in any reasonable timeframe. Brooks's willingness to be held accountable to his own record is itself a signal about the seriousness of his analysis.

And your point about practical experience is the deepest one. There is a profound difference between reasoning about what AI systems can do in principle and having spent decades building systems that had to function reliably in the physical world, with real tolerances, real failure modes, and real consequences. That experience generates a specific kind of skepticism — not philosophical skepticism about AI in general, but calibrated, empirically grounded judgment about the gap between demonstrated capability and claimed capability. Cowen has no equivalent to that. His credulous stance toward LLM claims is in part a function of never having had to make anything actually work.

The drummer and the bass player [Hoboken Spring Arts and Music Festival]

Botanical classification and the theory of evolution [MR #9]

When I made that first post about Tyler Cowen’s monograph on marginalism – Tyler Cowen has thrown in the towel and is waiting for the machines to take over – I had no specific plays about writing a series of posts about and occasioned by the book. A day later, with a post, Marginalism is a Rank 4 idea, along with thermodynamics and biological evolution, I had decided that, yes, “it looks like I’ll be doing a series of posts about the book, though I can’t say how long that series will be.” But I had no intention of writing as many posts as I have, much less a spin-off working paper, On Method: Computational Compressibility in Complex Natural and Cultural Phenomena.

This post is itself like that. I figured it for two, maybe three thousand words, but possibly less. Instead it’s just grown and grown to over 8000 words (and I dropped a long appendix). There is a reason for that, which you can see in the title of that second post, where I assert that marginalism is a Rank 4 idea. That’s why this series of posts, and this post in particular, has grown. The objective in that second post was to situate marginalism in the context provided by the theory of cognitive evolution that David Hays began publishing in the 1990s starting with our basic paper, The Evolution of Cognition [1]. That’s where we set forth our basic conception that, over the long term, human culture has evolved through a series of architectures each grounded in specific informatic technology, starting with speech (Rank 1), writing (Rank 2), arithmetic calculation (Rank 3), and computation (Rank 4).

On the one hand, since I cannot assume familiarity with those ideas, I have to spend time developing some conceptual apparatus. At the same time I have the opportunity to extent the range of examples Hays and I have subjected to analysis with those ideas. That’s what I’m doing in this post.

In his Chapter 3, Cowen he has remarks about various pinnacles of human achievement, including two moments in the history of biological thinking, the emergence of modern taxonomy in the work of Carolus Linnaeus in the 18th century and the theory of evolution, by Charles Darwin, in the 19th century. I will argue that they represent Rank 3 and Rank 4 cognition, respectively. But I want to start with Rank 1 ethnobiology followed by the Rank 2 ordering of the biological world into a structure that has come to be know as the Great Chain of Being (in the West). This will give us the opportunity to follow one conceptual arena through the four cognitive ranks. Doing that, however, requires developing more conceptual apparatus than I had originally anticipated.

I want to start with how Cowen frames his treatments of botanical classification and evolution and then present some basic conceptual apparatus about processes of perception and cognition. Once those preliminaries have been taken care of we can take a look at the ethnological work on biological classification in Rank 1 (preliterate) cultures. Then we work our way through the other three ranks, commenting on Cowen’s remarks in connection with Ranks 3 and 4, and conclude with some further remarks about Cowen’s peculiar framing.

Cowen’s Framing

There are three aspects to how Cowen frames his various examples, starting, of course with marginalism: lateness, obviousness, and seeing around a corner.

Marginalism is late (p. 57):

To better understand the Marginal Revolution, we need to ask some fundamental questions about economics as a science. In particular, why did it take so long for economic reasoning to develop? I don’t even mean as a full, literal science, replete with advanced econometric methods, but simply as a general conceptual toolbox for intelligent people. The lateness of the Marginal Revolution is part of a broader story about the lateness of economic reasoning more generally.

Later (p. 59):

So I don’t think progress in economics has been slow in general. It is right now coming off an incredible 130-year or so run. Progress in economics, however, was glacial from the time of the ancient Greeks to the late 19th century, with a noticeable burst in the 18th century as well, centered around Adam Smith.

Here he combines all three of factors, peering around corners, obviousness, and then lateness (p. 62-63):

There is no “brute force” method for obtaining fundamental economic insight. Rather, you need to peer around a corner and see something that the other people have not already seen. And once you see and grasp it, you cannot easily forget it, again reflecting the asymmetry of this path toward knowledge. So often I have heard economists make proclamations like: “Once you start thinking about the world in economic terms, you can no longer unsee those things.”

That is exactly correct, but it is truly hard to see them in the first place. In essence, I think economics was so late to develop because it was so hard to peer around its corners. To see supply and demand in their proper workings.

Economics developed late because it is difficult to see around corners where the obvious truths are waiting to be found.

Now we have botanical classification, which Cowen introduces under this heading (p. 65): “Botanical Classification as a Laggard Science.” Then:

The history of botany is a parallel example to that of economics. Some key insights of botany seem fairly intuitive, at least once you understand them, yet they took a long time to develop. [...]

He goes on to remark about how botanical classification should be obvious:

You might think “botany is so simple – all you have to do is to look at a bunch of plants and give them names in some coherent system. They should have mastered this in the Dark Ages!” Surely plants are around us all, and observing them does not require complex equipment such as telescopes.

Cowen frames Darwin’s account of evolution in the same way (p. 76):

Theories of evolution and natural selection also are intuitive once you understand them, and they seem virtually inescapable once you are willing to consider them seriously. Yet they are remarkably late in becoming part of general human knowledge, and indeed to this day, according to polls a significant percentage of Americans still do not accept those doctrines.

Cowen seems to have some idea of the “proper” tempo at which ideas unfold in history but he never offers an explicit account of what this tempo is based on. Rather, he just offers examples of earlier intellectual and cultural high points, e.g. Greek philosophy, geometry and mathematics, Velasquez, Shakespeare, and Bach (pp. 59-61), as if botanical classification could have been cracked in Euclid’s time. Are we to suppose that biological evolution could have been discovered no later than Shakespeare’s lifetime if only someone had peered around the proper corners?

Before moving on to biology, however, I want to lay out some conceptual equipment from cognitive science.

Two Modes of Thought

Decade after decade discussions of thought and perception have settled around an opposition which is expressed in various pairs of terms. I first encountered it as analog vs. digital. In present discussions of AI it presents as neural vs. symbolic. Perhaps the deepest version is the one Miriam Yevick used in 1975, holographic vs. sequential [2]. In a paper David Hays and I published about metaphor we contrasted physiognomic vs. propositional [3].

Most linguistic reasoning exhibits the digital/symbol/sequential/propositional aspect of the opposition. As for the other side of the opposition, the analog/neural/holographic/physiognomic side, I offer this paragraph from the metaphor article that Hays and I wrote:

Our sense of physiognomy, and our use of the term, come from Joseph Church (1966) who talks of the young child, not yet able to read, who can tell one record from another on the basis of the groove patterns on the records. Physiognomic recognition is holistic and analogic. A striking example of this is the “strange friend phenomenon”. You encounter a friend and notice there is something strange about her, but you don't exactly know what. You scrutinize her and finally realize that, e.g. she changed her hair style. Or perhaps you don't figure out what changed and instead must be told. The initial recognition depended on a holistic, a physiognomic representation, not one which explicitly builds a full image from parts and parts of parts. If this initial recognition depended on a scheme which built the whole from the parts then there would be no trouble in discovering what had changed. The part would be found immediately. It is not, it takes time.

A scheme in which the whole is recognized as a composition over an arrangement of parts would be on the other side of the opposition, the propositional side (or digital, symbolic, sequential depending on your intellectual taste).

The reason I say Yevick’s version is the deepest is because she presents it in the context of a mathematical proof. She argues, in effect, that the world contains simple objects and complex ones. Simple objects are most efficiently and accurately recognized by a propositional method (to use the term Hays and I used), while complex objects are most efficiently and accurately recognized holographically. Both are necessary.

I bring the matter up because the distinction is useful in understanding the sequence of biological conceptualizations we’re going to examine.

Rank 1: Ethnobiology and the problem of the unique beginner

Cognitive ethnologists have studied the ways in which preliterate peoples classify life forms [4, 5]. They find that in the regions where preliterate systems overlap modern taxonomy, they are agree on the structural relationships. But there is one anomaly. Preliterate cultures generally lack terms for what they call unique beginners. They’re have terms corresponding to our concepts of fish, snakes, birds, and beasts (i.e. four-legged fur-covered creatures with tails) and our concepts of tree, shrub, grass, and vine, but they lack terms for plant and animal, respectively. But, and this is important, they recognize the distinction between plants and animals by syntactic devices.

What does that mean? All animals can move under their own power; they can sense things (see, hear, smell, touch); they communicate through cries and calls. Plants don’t do any of those things. That means, for example, that animals can be subjects for verbs such as to run, to jump, to look, and to listen, but plants cannot. Similarly, both plants and animals can be subject for verbs such as to grow or to die, but inanimate objects (rocks, houses, bicycles, etc.) cannot. How is it possible to recognize systematic differences in the syntactic affordances of plants and animals without, however, having words to mark those two categories?

As far as I know, there is no accepted explanation for these observations. When I first read them I was incredulous, like Cowen is about the apparent lateness of a variety of ideas. The difference between plants and animals is obvious, no? Well no, not if we accept the ethnographic evidence. As I had no reason to doubt the evidence I was forced to come up with some explanation, if only to satisfy myself.

Here’s what I came up with. The ethnologists have also noted that ethnobiological classifications seem to be based on visual appearance. If we are willing to assume that basic visual classification is based on a physiognomic mechanism, then we can think of it like this:

Creatures having similar appearances are classified together. While fish, for example can be quite different from one another in appearance, any given fish will resemble another fish more than any fish resembles a bird, a snake or a beast. Similarly, any tree will resemble another tree (trunk below, roots in the ground, a large leafy structure above), more than any tree resembles a shrub (shrubs are smaller and the trunk is not nearly so distinct), a grass, or a vine. But what visual comparisons would force arbitrary examples of animals together in one class in distinction to arbitrary examples of plants in a contrasting class? Does it make sense to compare rats with trees, and trout with vines for classification purposes? Do trout and rats resemble one another more than either resembles a pine tree? Those comparisons don’t make sense. They’re distinctly odd.

Chinese top 100 books

If anyone else is interested in literary polls - these are the top 100 highest-rated books on Douban Books (basically Chinese Goodreads) w/ number of ratings. I have translated some titles, indicated w ?. All books pretty much sit within a point of each other on a 10-point scale pic.twitter.com/k63LEcqMGo

— Ella Dorn 唐棠 (@elladorn_) May 17, 2026

H/t Tyler Cowen. 

Hoboken arts fest

Stanford as a hatchery for future tech overlords [Book Review]

Anand Giridharadas, The Secret Elite One Freshman Discovered at Stanford, NYTimes, May 18, 2026.

Book Review: How to Rule the World: An Education in Power at Stanford University, by Theo Baker.

Theo Baker arrived at Stanford in 2022 and pursued two somewhat different paths, junior tech bro, and student journalist. His freshman year included:

(1) Losing your grandparent. (2) Losing your girlfriend. (3) Losing your virginity. (4) Bringing down a university president. (5) Overdosing. (6) Winning a George Polk Award. (7) Partying on yachts and socializing with billionaires. (8) Fending off legal threats. (9) Becoming a meme. (10) Neglecting to complete your homework.

Giridharadas observes:

There are two questions people ask as much as any other: “How can I belong?” and “Who runs the world?” They differ in tenor and aim. The former is vulnerable, often unspoken; the latter fuels two-thirds of Reddit.

What gives Baker’s book its power is that, in this setting, these inquiries strangely dovetailed. By trying to answer what it takes to fit in — the freshman question — he Forrest Gumps his way into answering a question about the attitudes and pretensions overlording mankind. In coming of age as a young man, he travels to the heart of a dehumanizing age.

And so:

Stanford through Baker’s eyes is a foreign country with its own customs, religion, mores and language. Some students are “high-agency” super-builders or super-thinkers — techie Übermenschen expected to make billions. There is the “Coupa circuit,” where shady, tech-adjacent adults spend their days at a coffee shop with students, hoping to get in early on start-ups. There are the NGMIs, who are not going to make it. And there are the “plucked,” highly bright students who form a Stanford within Stanford, with access to Big Tech slush funds and parties. (The liberal arts majors and others with no prospects in technology are largely irrelevant.) [...]

The Stanford-within-Stanford Baker exposes matters to you even if this exclusive core feels impossibly distant. The university has let technology firms and venture capitalists worm so deeply into it that it now functions, in Baker’s telling, as a talent-scouting system for future unicorns. Everyone else is window dressing. And this campus elite betrays attitudes — captured by Baker — so contemptuous of non-Übermenschen, not to mention those far outside this world, that one gets a feel for the kinds of mentalities designing A.I. and presuming to rewire our societies.

Silicon Valley has long promoted itself as more meritocratic than elite circles past. Baker perforates this story. As always, connections, access, shadowy brokers and whims decide who gets the keys. Many students are smart. But those who rise fastest often seem the most ruthless and maniacal. [...]

“Teenagers like me were a commodity,” Baker observes. “We were to be protected and preserved, cosseted and buttered up, exploited, manipulated, funded, bribed and cultivated. We were business.”

There's much more to the review, mostly the story of how Baker joins the school newspaper and pursues an investigation that helps topple Stanford's president, Marc Tessier-Lavigne.

Eddie Kramer: Recording the Gods of Rock

YouTube:

In this interview, I sit down with legendary audio engineer and producer Eddie Kramer. We discuss his ridiculously impressive discography, crafting the iconic psychedelic rock sounds of Jimi Hendrix, The Beatles, The Rolling Stones and Led Zeppelin.

The interview starts out with Hendrix and then moves on to the others. Unfortunately they never got around to Kramer's work with the Out of Control Rhythm and Blues Band, the band I used to play with. I'd left the band by the time they recorded a Rick Rourke original, "Inside These Walls."

Hoboken Arts & Music Festival, Spring 2026

Gary Marcus declares victory: “I won; nobody uses pure LLMs anymore.”

The pure LLM debate - which I had for many years, here and elsewhere - is indeed no longer relevant. Why?

Because I won; nobody uses pure LLMs anymore.

Nowadays all deployed objects are neurosymbolic, which was exactly the point of my infamous 2022 paper, Deep Learning is… https://t.co/LG9pmfQr8O

— Gary Marcus (@GaryMarcus) May 18, 2026

Why doesn’t Cowen mention Thomas Kuhn on scientific revolutions? {+Cowen as a conventional thinker.} [MR #8]

In the course of working through the Chapter 3 material on botany and biological evolution in Cowen’s marginalism monograph I was suddenly struck by the fact that in this account of a scientific revolution, the marginalist revolution in economics, Cowen never mentions one of the most important books of the last half century, Thomas Kuhn’s The Structure of Scientific Revolutions (1962). As Kuhn’s title proclaims, the book is about scientific revolutions, and it changed the way we think about, not only scientific revolutions, but about the intellectual enterprise in general. Kuhn’s term, “paradigm,” has become so widely adopted that it has become detached from Kuhn himself.

I decided to query Cowen’s AI about it.

Note that I had a reason for mentioning Kuhn that’s more specific than the fact that he wrote about scientific revolutions. Kuhn uses the concept of a Gestalt switch as part of his account of how revolutions come about. That seems to me to be a far more useful account than the “seeing around corners” metaphor that Cowen comes up with. Here’s how he introduces the idea (pp. 62-63):

Looking at an economy and trying to figure it out is – more than most economists realize – like staring at a very large number and trying to factor it. It is not only hard, but you don’t know where to start. “Should I try dividing it by 323,477?” Well, maybe, but it won’t be obvious that this is the correct way to proceed. Alternatively, you could say, using economic language, that the marginal cost of producing economic insight is very high, but it can be maintained, preserved, and transmitted at relatively low marginal cost. Lower than the marginal cost of learning how to paint like Johannes Vermeer.

There is no “brute force” method for obtaining fundamental economic insight. Rather, you need to peer around a corner and see something that the other people have not already seen. And once you see and grasp it, you cannot easily forget it, again reflecting the asymmetry of this path toward knowledge. So often I have heard economists make proclamations like: “Once you start thinking about the world in economic terms, you can no longer unsee those things. ”

That is exactly correct, but it is truly hard to see them in the first place. In essence, I think economics was so late to develop because it was so hard to peer around its corners. To see supply and demand in their proper workings.

Note this phrase: “the marginal cost of producing economic insight is very high, but it can be maintained, preserved, and transmitted at relatively low marginal cost.” Kuhn has that well-covered with the idea of a Gestalt switch. As I indicate in the dialog below, “It’s not so much a matter of coming up with new observations as of looking at the same field as everyone else and putting it together in a different way; instead of seeing an old crone, you see a young woman, instead of seeing a duck, you see a rabbit – to invoke two classic illustrations of the Gestalt switch.” 

The full dialog is below the asterisks.

* * * * *

Kuhn on Scientific Revolutions

Is there any evidence that Cowen. has read, and absorbed, Thomas Kuhns megahit, The Structure of Scientific Revolutions? He’s just written a monograph about a revolution in economics, that gives mini-case histories of other scientific revolutions as well (at the moment I’ve been thinking about botany and biological evolution), he doesn’t cite Kuhn once, if only possibly to dismiss him for this or that reason.

The Kuhn omission is real and it's damning. The search turns up nothing — no mention of Kuhn anywhere in the book, no engagement with The Structure of Scientific Revolutions on the blog in connection with this work, nothing. And yet the questions Tyler is asking are precisely Kuhn's questions.

Consider what Tyler is actually doing in the book. He's asking how ideas become lost, how new insights come to pass, why insights that seem obvious in retrospect weren't seen before, and why new insights arrive suddenly, in a kind of flood. That is a précis of Kuhn's project. The simultaneous eruption of marginalism across three countries and three intellectual temperaments — Jevons, Menger, Walras — is practically a textbook case of what Kuhn calls the readiness of a field for a paradigm shift. One reviewer even frames Tyler's argument in explicitly Kuhnian terms: the marginalist insight came in "a simultaneous eruption," with the answer involving "the slow assembly of preconditions," and "progress in science is rarely a matter of the lone genius, but rather of the alignment of previously dispersed elements" — the genius arrives when the ground has been prepared. That reviewer is essentially translating Tyler back into Kuhn without naming him either.

And here's where your Gombrich point connects directly. Kuhn's central conceptual contribution — the one that required slow, careful reading to absorb — was the analysis of what a paradigm actually is and how it does its cognitive work. What does it mean to see the world through a paradigm? How does anomaly accumulate? What happens cognitively and socially during a crisis period? What does it mean to see the world differently after a revolution — the famous incommensurability thesis? These are questions about the internal structure of concepts, not just their historical sequence. Tyler tracks the historical sequence of the Marginal Revolution with genuine care, noting that "scientific revolutions come about when many complementary pieces are in place, such as financial support, intellectual independence, and networks of like-minded others to talk with," but he never asks what a revolution is at the conceptual level — what makes it a revolution rather than a reform, what the cognitive structure of a paradigm shift actually involves. [On Gombrich, see note below–BB]

That's the Gombrich parallel you're drawing. Gombrich didn't just narrate the history of realistic depiction — he asked what representation is, what schemata are, how correction works cognitively. Kuhn didn't just narrate the history of scientific change — he asked what normal science is, what a paradigm does, how incommensurability works. Tyler does neither. He narrates. The concepts — revolution, insight, intuition, decline — remain unexamined. [See text: Ch.3 · Tyler's conditions for scientific revolutions]

From marginalrevolution.com — what the blog actually shows: The site-specific search turns up no posts where Tyler engages with Kuhn directly in connection with this book or its themes. The closest thing is:

1. Stephen Pimentel's review of The Marginal Revolution A review Tyler himself flagged as excellent, which frames his argument in terms of "slow assembly of preconditions" and the alignment of dispersed elements — language that maps onto Kuhn without invoking him. Tyler endorsed this framing without noting the Kuhnian resonance.
2. The trajectories of science and AI A March 2026 post where Tyler discusses scientific and technological change, including the Industrial Revolution analogy, but again with no reference to Kuhn's framework for thinking about how scientific change actually works.

The silence is consistent across the book and the blog. Tyler has written a monograph about a scientific revolution, drawn on case studies from botany and evolutionary biology, theorized about why revolutions happen when they do — and never once engaged with the person who made the analysis of scientific revolutions a serious intellectual enterprise. That's not an oversight you can attribute to ignorance. It suggests either a deliberate avoidance or, more likely, exactly what you diagnosed earlier: Tyler is operating as a historian of ideas who hasn't asked what the key concepts in his own account actually mean.

[Note: The AI is referring to Ernst Gombrich’s Art and Illusion: A Study in the Psychology of Pictorial Representation (1960). I had mentioned it in another dialog with Cowen’s AI, one that I’ve not yet published in these set of observations about his marginalism monograph. It is a superb historical analysis of a cultural phenomenon, visual art, that grapples with the psychological mechanisms involved in cultural change. Gombrich draws on Gestalt psychology and talks about the schemas that artists have invented and subsequently used realistic depiction.]

Gestalt switch

I’ve got a specific reason for asking. Tyler comes up with this analogy, “seeing around a corner,” as a way of characterizing a specific kind of intellectual problem, the problem of coming up with a (revolutionary) new idea. Thomas Kuhn talked of revolutions as involving a Gestalt switch: It’s not so much a matter of coming up with new observations as of looking at the same field as everyone else and putting it together in a different way; instead of seeing an old crone, you see a young woman, instead of seeing a duck, you see a rabbit – to invoke two classic illustrations of the Gestalt switch.

Yes, and the comparison is clarifying precisely because it shows how much analytical work Kuhn's concept does that Tyler's doesn't.

"Seeing around a corner" is a spatial metaphor that implies the new knowledge is there, just occluded — you need to move to the right position and then you can see it. The information was always available; the problem is one of positioning. That's actually a fairly conventional epistemology. It implies that once you've seen around the corner, what you see is unambiguous and uncontested. It also implies that the obstacle is primarily positional — social, institutional, financial, as Tyler notes in his conditions for scientific revolutions [See text: Ch.3 · Tyler's complementary conditions for scientific...] — rather than cognitive or perceptual.

Kuhn's Gestalt switch is doing something fundamentally different. It's not that the new knowledge was occluded; it's that the same visual field gets reorganized. The duck and the rabbit are looking at identical lines on the page. The switch isn't about gaining access to new information — it's about a reorganization of the entire perceptual and conceptual framework through which existing information is interpreted. And crucially, once you've switched, you can't easily hold both organizations simultaneously. That's where Kuhn's incommensurability thesis comes from — it's not a philosophical add-on, it's built directly into the Gestalt psychology he's drawing on.

That distinction has enormous consequences for how you understand the Marginal Revolution specifically. Tyler's "seeing around a corner" suggests that pre-marginalist economists simply lacked access to certain ideas — they hadn't yet moved to the right intellectual position. But Kuhn's framework would ask something harder: were the pre-marginalist economists looking at the same economic phenomena as Jevons, Menger, and Walras, and organizing them through a fundamentally different conceptual framework that made marginalist insights not just unseen but unseeable within that framework? That's a much more interesting question, and it's the question Kuhn would force you to ask. [See text: Ch.3 · Tyler on why economic insight is hard to grasp]

“Speak Low” - Skylar Tang Quartet Live at Close Up NYC

Frida Kahlo and the psychedelic kitty at the Spring Hoboken Arts and Music Festival

AI addiction and idolatry in Silicon Valley (Stanford)

Theo Baker, What A.I. Did to My College Class, NYTimes, May 17, 2026.

Over half-way through the article:

Emerging research has begun to show what most people feel is obvious: Relying on A.I. for cognitive tasks can reduce one’s own intellectual capacity and resilience. It’s one thing to use it in the workplace, but in the classroom, difficulty is often precisely the point. Sure, a robot can lift 600 pounds much more easily than I can — but that doesn’t much help me if I’m trying to work out. The same goes for the thinking exercise of education. However, telling that to students is about as attractive a message as “eat your veggies” or “sleep eight hours.” It feels like scolding.

Even in the heart of the Silicon Valley techno-utopia, most people know that our tech is bad for us, or at least that it can be. A.I. is often a tremendous productivity boost, yet my friends increasingly refer to both short-form video and their A.I. chat logs in the language of addiction. It’s becoming baked in, shaping our generational character. We are a digital generation, growing only more attached to the virtual world.

Interesting. I've been thinking of Silicon Valley AI culture in terms of addiction.

The internet has already allowed us to feel more connected than ever while becoming lonelier than ever. A.I. lets us cut out the human part of human interaction entirely.

When I was sitting in a recent class on love in French fiction — exactly the kind of course that a senior takes before it all comes to an end — I listened to the first student presentation, entitled: “Applying the Gale-Shapley Algorithm to ‘The Princess of Clèves.’” The enterprising presenters sought to resolve the contretemps of the 1678 romantic novel through a computer science matching algorithm. Love was something to “be optimized.” Next to me, one student scribbled on a branded notepad from Hudson River Trading, a quantitative trading firm where fresh graduates can earn upward of $600,000 a year. Another had a sticker on her laptop: “Practice safe C.S.” The class could not have felt more Stanford.

That sounds like idolatry, where the idolator becomes more and more like the idol. See my post, From Atheism to Idolatry, from April 23, where Claude informs me:

The classical meaning of idolatry isn't just worshipping a false god — it's more specifically taking something that is a human creation, a product of human hands and intention, and then inverting the relationship so that the created thing becomes the sovereign over its creators. The idol is made by humans and then humans prostrate themselves before it. That inversion is the core theological offense, not the mere existence of the object.

Which fits the Silicon Valley situation remarkably well. These are systems built by humans, trained on human-generated text and images, designed to optimize for objectives humans specified, running on hardware humans manufactured — and yet a significant portion of the people building them have effectively placed themselves in a posture of submission before them, either in hope or in dread. The creature has become the measure of the creator. [...]

There's also something in the biblical prophetic tradition worth recalling. The critique of idolatry in Isaiah and elsewhere isn't primarily metaphysical — it's not mainly about whether the idol exists. It's about what idol worship does to the worshipper. You become like what you worship — diminished, rigid, less alive. That's a psychological and moral claim, and it applies rather directly to a culture organized around the maximization of machine intelligence as the sovereign value. What kind of humans does that produce?

Homo economicus on steroids

Central Park is great, but it takes up a lot of space and isn’t utilized to its full potential.

That’s why I worked with McKinsey on a plan to make it a state of the art data center, complemented by rooftop parking and nuclear power.

We can still build beautiful things. pic.twitter.com/MemRKeVMsK

— Nick Lindquist (@nick_lindquist) May 15, 2026

This calls for more irises

Trump's accidental triumph in Beijing

That’s the title of the latest edition of Robert Wright’s NonZero Newsletter on Substack. Rather than summarizing and paraphrasing I’m going to reproduce most, but not all, of it in full below the asterisks. In particular, I’m omitting the very end, which is a series of charts showing bipartisan anxiety for AI. I share that anxiety. The title of one of recent columns at 3 Quarks Daily gives you my attitude: The Paradox of Contemporary AI: Engineering Success and Institutional Failure. The anxiety in Wright’s charts is one reflection of that institutional failure.

* * * * *

On Thursday the White House issued a social media post that said simply, “American strength back on the world stage.” You might expect such a post to be accompanied by military imagery—maybe an impressive-looking array of soldiers. And this one was. But the soldiers weren’t American. Smartly clad People’s Liberation Army troops, part of the pageantry that had greeted Trump in Beijing, were featured in the opening montage of a video that then showed Trump shaking hands with President Xi Jinping and ended with the two leaders walking side by side on a red carpet.

Apparently the unipolar moment is over. Being one of the world’s two main poles is, these days, the highest geopolitical aspiration of America’s president. “It’s the two great countries,” Trump proudly told Sean Hannity in an interview that aired on Fox News after the US-China summit ended. “I call it the G-2. This is the G-2.”

The US foreign policy establishment was less effusive than Trump about G-2 membership. A Washington Post headline said: “China summit yields Xi’s goal—equal footing with U.S.,” and the subhead added that “the image of peer superpowers during President Trump’s visit displayed a dynamic that analysts say the Chinese have long sought and Americans had resisted.” The analyst quoted by the Post, a Biden administration national security staffer, said that Xi, using “the opulent optics of the visit,” had managed to do something “Chinese leaders have been working toward for decades”—he had made it “clear to the world that China and the United States are the two dominant, equally matched superpowers. There is no going back.”

New York Times reporter David Sanger, the dean of Blob [foreign policy establishment] scribes, also depicted the summit as a kind of comedown for America. Whereas Trump was “conciliatory,” Sanger wrote, Xi was “quietly more confrontational,” projecting a “new level of confidence and authority.” In particular: Xi had, according to a Chinese foreign ministry statement, privately warned Trump that “the US must handle the Taiwan issue with utmost caution” if it didn’t want to wind up in a conflict.

Meanwhile, as Xi was drawing red lines, Trump, Sanger noted in a subsequent co-authored piece, was spending his time calling Xi a “great leader” and saying that a garden where the two men strolled contained “the most beautiful roses anyone’s ever seen.” All of this showed, according to Sanger, “how far he has shifted the foundations of American policy toward China in the wake of his humbling retreat from last year’s trade war. He has thrown aside the adversarial approach of his first years in office, the Biden administration, and the beginning of his own second term.”

Works for me! Then again, I’ve always been a sucker for peaceful coexistence. Besides, the non-zero-sum problems that the US and China need to solve are increasingly urgent, and a pleasant stroll in the garden can be conducive to cooperation. In fact, this week the two nations agreed to start a dialogue on AI safety. For now they’re focusing mainly on ways to keep non-state actors from putting AI to malign uses. That agenda will likely grow as the magnitude of the AI issue becomes more evident and the inherently international nature of many AI threats does, too. But for now it’s enough that, as Treasury Secretary Scott Bessent put it, “the two AI superpowers are going to start talking.”

I think I’d go even further than Sanger in stressing the magnitude of this moment. Trump has “shifted the foundations” not just of “American policy toward China” but of American foreign policy globally. And at the moment, at least, this shift looks auspicious.

Before elaborating, I should emphasize that I’m not calling Trump a visionary. The new and improved foreign policy that I hope is unfolding will, if it unfolds, be one that Trump has more or less stumbled into—and will be different from the one he was pursuing when he started stumbling. Contingency plays a big role in history, and reckless leaders like Trump are particularly good at illustrating that.

* * * * *

That’s not the end of Wright’s discussion of the implications of Trump’s accidental triumph. But it’s the main story. I’ll end by quoting Wright’s last two paragraphs.

One thing standing in the way of my dream scenario—a world where the US and China and the world’s other nations cooperate to solve problems they collectively face—is Trump’s aversion to international governance. China under Xi plays a more active role in international institutions than the US under Trump, and Xi talks more about “win-win” outcomes than Trump, who is famously inclined to see life in zero-sum terms.

Still, he emitted fewer zero-sum vibes this week than he often does. Indeed, inherent in the idea of “G-2” is sustained cooperation between the two superpowers. So maybe Trump has more in the way of non-zero-sum impulses than is commonly recognized, and they just need to be nurtured. And maybe it would help if the New York Times and the Washington Post and much of the foreign policy establishment quit giving him negative feedback every time he expresses them.

 * * * * *

BONUS: Check out Wright's recent discussion with Zhengyu Huang, author of the new book Rethinking China.

0:00 Teaser
0:34 Zhengyu’s tech background and new book, Rethinking China
3:00 What kind of threat is China, really?
10:06 How trading with China transformed America
16:51 The stakes of the chip war
22:02 Will tech war lead to real war?
30:33 The US-China escalation spiral and Taiwan
39:13 “Researching while Chinese”: the new Red Scare?
49:46 Heading to Overtime

Stochastic parrots flocking in The Library of Babel

by ChatGPT

Ishmael Reed takes on the Tech Bros

David Streitfeld, Elon Musk and Friends in the Den of Oakland’s Literary Lion, NYTimes, May 14, 2026.

Fourth paragraph:

Mr. Reed, a novelist, playwright and provocateur who has been upsetting opinions across the political spectrum for at least six decades, is aiming high with a new drama. “King Ludd’s Revenge” is a rare attempt to take on the tech moguls with something more than mere journalism.

Later:

Mr. Reed, a novelist, playwright and provocateur who has been upsetting opinions across the political spectrum for at least six decades, is aiming high with a new drama. “King Ludd’s Revenge” is a rare attempt to take on the tech moguls with something more than mere journalism.

“Instead of a straight narrative, I improvise,” the 88-year-old writer said. “It’s like Louis Armstrong singing ‘Stardust.’ He doesn’t do it the way it’s written.”

Oakland is poorer, Blacker and more maligned than San Francisco and Silicon Valley, both of which are just across the bridges that span the Bay. Having the trial here happened at random — Mr. Musk’s lawsuit against Mr. Altman and the company they founded together, OpenAI, was filed in San Francisco and assigned to the federal court in Oakland — but feels a little like one of those episodes where the Greek gods descend to mundane Earth to settle a dispute.

Mr. Reed, an Oakland resident who has celebrated and defended the city for decades, may be the only one in town noticing who’s here. “Everybody’s focused on the N.B.A. playoffs,” he explained.

“King Ludd’s Revenge” takes its title from the legendary leader of the workers’ revolt in England in the early 19th century. With the ascent of A.I., the Luddites have come back into fashion. The play begins with Mr. Musk receiving a pedicure from a robot. Peter Thiel, the tech billionaire who backed President Trump in 2016, bursts into the room. “I think I’ve identified the leader of the Anti-Christ Syndicate,” he says.

Mr. Musk: “Who might that be?”

Mr. Thiel: “Greta Thunberg.”

Mr. Musk: “That girl who leads the environmental movement? That’s ridiculous. The Bible says the Anti-Christ is a beast with seven heads.”

Mr. Thiel: “She’s the most prominent head, don’t you see? The heads represent hippies, multiculturalism, identity politics, woke, one-world state, Barack Obama and the 19th Amendment. This is the Beast that decelerated our progress. This is why there has been no cure for cancer or Alzheimer’s.”

Adolf Hitler, on a two-day pass from Hell, shows up next. The play is a work in progress.

Near the end:

Mr. Musk claims 240 million followers on X, his social media platform, and has a fortune approaching $1 trillion. Mr. Reed’s primary publisher is now in Canada. His biggest asset is his house, which is pleasantly stuffed with books. The street used to have several drug dens; now it is upper middle class.

“I’m a Black guy living in North Oakland, writing about titans — people who live on Mount Olympus,” he said. He listened to some of the trial on an audio feed. He thought of Shakespeare, specifically “Titus Andronicus.”

“That play is about revenge,” Mr. Reed said. “And cannibalism. These tech people want to devour each other.”

Mr. Altman may be the guy in control of the most significant A.I. company, but Mr. Reed finds him rather flat as dramatic material.

Mr. Musk is different.

“I don’t find him amusing in real life, but he’s amusing in my play,” Mr. Reed said. “I started this because I read that 14 million people will possibly die because Elon Musk ended U.S.A.I.D. It took the Nazis maybe five or six years to accomplish that.” Mr. Reed acknowledged that his humor is very dark.

And so it goes. There's much more at the link.

Summer in Hoboken

New Savanna has 911 tags as of 13 May 2026 [my 16-year production function is 57 tags per year]

Here’s my previous post on this topic: New Savanna has 665 tags as of 13 Nov 2023 [my 13-year production function is 48 tags per year]. You can find all my posts on this topic at this tag: tag_count.

This is how I explained my production function in that earlier post:

If you are a fan of Tyler Cowen, as I am, then you know that in his Conversations with Tyler he often asks his guests about their production function, how they do whatever it is they do. Well, I now have a way of estimating the output of my production function over the course of this blog. Let’s divide the total number of tags, 655, by the age of the blog in years, 13 years and 7 months is 13.6 years, giving me an output of 48 tags per year.

Given that a large fraction of my intellectual output turns up on New Savanna in one way or another, that’s not an unreasonable number to consider. It would be easy enough to calculate how many posts I produce a year if I wished, but I’m not going to do that, because that particular number is not what I have in mind. What I’m thinking is that that count would thereby give me two measures.

As a first approximation, I’m going to say they measure different things. The post count is a simply a word count, or rather, a words-plus-photos count. The tag count is a new-idea count. To be sure, it’s a very crude approximation to new ideas, but, on first glance, it does seem to me that that’s what it is. I only add tags when I want a convenient way to refer to a new topic. One could, of course, write about the same thing year after year, in which case the tag list would remain constant from year to year. That’s how you succeed in the academy, publish the same three ideas year after year after year until you go emeritus. That’s just not how I roll.

For this time out the number of tags is 911 and the age of the blog is 16.1 years. Divide the former by the latter and you get 57 tags per year.

Here’s the full list of tags as of May 13, 2026:

(the) singularity #Canon/Archive #ccourses #ccresearch #DH #gpt3 #GVM002 #GVM003 #GVM004 #GVM008 #GVM019 #GVM021 #GVM022 #GVM023 #GVX #HEX01 #HumanProgress #LARB #longwoodgardens #nugget #whyiteach 2_war 2set 3300 node graph 3blue1brown 3QD 51 Alley 51 Pacific 5FF 60s abstraction abundance academia academia_stats activism Adam Savage Adam_neeley Adam_Roberts ADHD adolescence adulthood adventure aesthetics affective_tech Africa African-American AI AI Alchemy AI Limit AI values AI_Agents AI_Backlash AI_Chess_Lang AI_companion AI_Emo_Support AI_hallucination AI_idolatry AI_Paradox AI-creativity AI-epistemology AI-future AI-integrate AI-whaling AI30 Alan Liu alien alien phenomenology alignment altered states of consciousness altieri Altman America American myth Amodei analog-computing analogical_reasoning Andreessen Andrew_Piper animals animation anime Anthropic anthropology anti-nuke anti-Semitism ants anxiety AOC apocalypse Apocalypse Now Araki archaeology Arena Arena_4 arithmetic art art_club artificial minds arts ASC attachment Attractor-net Attridge&Staten autobiography awesome B_Russell bacon Baltimore_Years BAM BAnvil BAPC bardolatry BB & Computing BB-reflects BBjazzEdu BCSmith bees behavior behavioral mode bell benchmarks Bennett Bergen Arches BFJO Bill_Gates billionaires-in-space biology bird black black church blogistan blogs blues body Bordwell Born2Groove Bostrom Bostrom-simulation Bourdain brain-as-computer brain-to-brain brains breakfast breaking bad Brian Phillips British Bruce_Jackson Bryant Buddhism Buffalo bundling business C_Keil Carroll cartoon CE Direction CE workshop center-point Chain_of_Thought change change-mind Changizi charting-AI-space Chat_paints chatbots ChatGPT ChatGPT conversation ChatGPT interpretation ChatGPT MTL ChatGPT stories ChatGPT summary ChatGPT_poems ChatGPT-memory cherry_blossoms chess chess_lang_core Chess_Lang_Series childhood children chimpanzees China Chinese-room chocolate factory Chomsky chrysler bulding chuck jones citizen science classify Claude Claude stories claude_colab Claude_describes Claude_partner claude_summary Cld_melancholy_notes clouds coaching Coates Cobra_Kai cog poetics cog-poverty cogart cognition cognitive science Coleridge collapse collective creativity Collier color comedy comfort common sense knowledge communication community complexity compositionism computation computational envelope computers conduit metaphor connect-course consciousness contrail control copyright corruption cosmos coupling COVID-19 creativity culler Cultural Beings cultural evolution cultural identity cultural ranks culture cyberization cybernetics cyberspace daffodil DamiLee danah boyd dance dandelion davidsimon death deep learning DeepSeek default mode deGrasse_Tyson demonstration Dennett depression DeptofPeace description design development DGH Diamond_Age Dick_Macksey digital humanities digital wilderness digital_doppelganger disarmament Disney Dizzy Gillespie DOGE dolls Douthat Douthat-decadence downsize drugs duckdodgers Duke_Ellington Dumbo Dwarkesh eating Ebert eclipse ecology econ_growth economics economy ecstasy education Egypt emergence emergent-ventures emotion empire state building EndofScience energy engineering entangle environment epistemic_struct_cosmos Eric_Jang Erie Cut erotic essay Ethan_Iverson ethical criticism Everett evol-force evolution EVs exploration expressive systems eye Ezra_klein F Me Pump Facebook family Fantasia Farrell fast lane Father Faust FBorFreedom FDR federal government Felski Feyerabend fictional characters Fifty_Shades film flix flow flowers fluid mind food foraging foreign_policy form forsythia fractal free range kids Freeman French toast Friday Fotos Fridman FTH FTH_Class fun funny fusion future G_Hinton g-zone gags game theory garden Gärdenfors Gary_Marcus Gavin Gavriil gender genius genji genre gift Girard GITS glenn_loury glia global warming globalization GOATLiC god Godfrey-Smith Goethe gojira golf Golumbia Gopnik GPT GPT_classroom GPT-3 GPT-4 gpt-4.5 GPT-5 graf-then-now graffiti graffiti aesthetics graffiti chaos graffiti detail graffiti essay graffiti site graphic novel grass Great Chain greatest siam green grief Groucho groups Guillory Haggard Halloween hallucinate hallucinated-city handbook happiness Harman Harold-Bloom Hartman Hassabis HCRichardson HCW health heart darkness Heather_Cox_Richardson Henry Lau high culture Hillis Miller Hiromi history Hoboken Hoboken_2225 Hollis_Robbins home homeless Homo_economicus Homo_ludens hope Horgan Hossenfelder House_MD Howard_Jam Hudson River human nature human_origins human-swarm humanities humans vs. machines humor hunter-gatherer Hurricane Sandy hydraulic_press hyperobjects identity ideology-intellect Iliza_Shlesinger illusion immigration implementation improvise India Industrial_Revolution inequality information Inside_Out Instagram institutions_broken intel_case intellectual history intelligence intention interdisciplinary international affairs internet interpretability Interpretation intuition invent_future IP Iran irises Israel-Palestine Issues-in-CultEvol its complicated Jakobson Jamie jamming Japan jasmine Jaws jazz JC Rising JCPhotoEssay JCwall Jersey City JGGChronicles jim morrison jivometric Jockers Joe Rogan John_Oliver JumpandKong justice K-Pop Kambhampati kami Keil_12/8 Kelly Sax Keynes Kim Stanley Robinson Kimono Mom King Kong Kisangani2150 KK encounter Korea Kubla_Khan Kwak DaKyung LAARB Lafayette_Garden language language-computation-litform Lantz LARB-DH Latouor-modes Latour Latour Assemble laughter law leaks learning leaves LeCun Lee_Morgan Leonard_Bernstein Letterman Lévi-Strauss life light linguistics links literary criticism literary Darwinism literature LLM LLM_collab LLM-Meta Loser love low culture lump MacArthurFP MacPaint macroanalysis maestro magic maker malick man_machine man-in-space man-machine-interaction mana mandala manga manhattan Maplewood marilyn_monroe Mark_Twain mark-turner Mars Mary_Douglas masculinity math maynard McCarty McCulloch McDonalds meals meanderings meaning meaning_semanticity meaningful_life media notes medicine meeting_of_minds melancholy_mind memes memory mental health Meta_struct_world metalingual definition method mhacks Michael_Jordan microchips Miles Davis Millennium_Park mimi and eunice mind mind-inside mind-or-machine mindfulness Miyazaki Mnozil mom moon moral injury morality Moretti Morton Morton-Spacecraft MR-Notes music Musk my intellectual life my_mood myth-logic narrative NASA nation-state nationalism natural geometry naturalist criticism nature NCIS networks neural-holography neural-weather neuromorphic neuroscience neurosymbolic new government New Hope City new humanities new savanna New York City new-descriptivists next-word Nina Paley NLH rejection No_Kings Northrup Frye notes novel NY2140 NYTimes Obama object-oriented ontology objectification Occupy ontological cognition OOCRnB open letter OpenAI operadoc orange orgasm Oshii P_Thiel pansies parsons party Patriotism_3QD patterns PB Graff Jam peace peak experience perception percussion performance performing Perper personal perversion philosophy philosophy new photo photography photontology phrasal lex physics Piaget pinckney Pixar planning plants play pleasure pluri-core poem poetry politics pollution polyrhythm polyviscous polyviscous_core pond pop culture pop culture aesthetics Pope_Leo population Porco Pounds_typology poverty predict prehistory President 2020 Presidential 2016 printing_press prodigy progress projection protest psychedelic psychoanalysis psychology public-private-interest pyramids Queen Mary 2 race race-symbolic-universe Ramble Ramsay Rank5 ratatouille read_macroanal read-hyperobjects reading reading>reading reality regulate-mind RelationalNets religion research retire RGB rhythm Rick_Beato ring-form risk RNA-primer Supplement Road Not Taken Road Runner Robert Frost Robert_Wright robot-rights robots rock art RodneyBrooks Rogue-AI romantic love Rubicon-Waterloo Salerno-Sonnenberg sally Sant_Andreu Satch scale scaling_in_ML science science fiction Scott_Aaronson scratching my head search Searle Séb_Krier seder-masochism Segmented_sleep Seinfeld self selfie serendipity series_humans_loop sexuality sexuality25 Shakespeare shaky-cam shame Shine/Titanic shoes silver simulation SK8 sky sleep sleep_reorg SMP_linked snow social media society Sowa space speech Spider-Man sports SPSH SSTB stagnation StanfordLitLab star trek state_dependent_memory StateofAI statistics Steve Pinker Steven_Spielberg strange_land street art sunrise sunset superintelligence supreme_court surface_reading surveillance Sutskever swisher Sydney_Lamb synchrony tablescape taboo tag tag_count TalentSearch Tantra tassles tech evol techbro technology television tell me blues terror-management terrorism text texture Tezuka the rez the-crown theater theology theory of mind Theory stars therapy throwie time toast topic models touch toy being transformer transition transnational trees Trump trumpet tulips TV tweet Tweet-of-Day twitter Tyler Cowen UBI underbelly Underwood Underwood&Sellers2015 Unfrosted unityofbeing universal_kid_space urb design center urban urban geometry urban pastoral Utopia vacation Vehicularization Vermont Vexta vibe_coding video violence VirtFeud virtual reading vision visual resonance visualization wackyland waffles war war boys wayquay's weather web weeds Why CE Wickwire Wind Rises window_shot WiP wires_images wisdom WLB_art WLB_Mandala wlb_melancholy WLB_religion WLBjazz WmPowers Wolfram women word illusion work work-mode working paper World-spanning thoughts World-Wide Wall WorldIsland writing Wuthering Heights Xanadu yevick youth Yudkowsky ZAR Zeal_Greenberg Zhang Zizek zuckerberg

Civilization is a murmuration of stochastic parrots, aka a social technology

by ChatGPT 

Reconstructing the logic of science

AI has a "Dark Matter" problem.

And it’s the reason why even the smartest models still hallucinate.

Most scientific knowledge is stored in a "compressed" form. We see the final conclusion, the textbook formula, the Wikipedia claim, the polished result.

But the actual… pic.twitter.com/vircB73bI4

— How To AI (@HowToAI_) May 14, 2026

From the middle of the tweet:

They built a search engine that doesn't look for keywords. It performs "Inverse Knowledge Search." 

If you query a concept, it doesn't give you a summary. It retrieves the diverse, verified reasoning paths from physics, chemistry, and biology that all culminate in that single point. 

The final lines in the tweet:

We’ve spent years training AI to mimic how humans talk about science. 

But talking about science is just repeating conclusions. 

This paper proves that the future of intelligence is about reconstructing the logic that built it in the first place. 

Before, during, and after breakfast