Floral escalation

Rear Window – myth logic around the edges [Media Notes 168]

I just watched Rear Window (1954) on Netflix last night, but I’m sure I’ve seen it before, and on the big screen, perhaps in college in a film series. Here’s the first two paragraphs of Wikipedia’s plot summary:

Professional photojournalist L.B. “Jeff” Jefferies, recuperating from adventurous assignment-related injuries, in a cast from his waist to his foot, is confined to a wheelchair in his Greenwich Village apartment. His mid-floor rear window looks out onto a courtyard with small garden plots, surrounded on four sides by apartments in adjoining buildings. Jeff is regularly visited by Stella, a middle-aged nurse, and his couture-dressed girlfriend, Lisa Fremont, a socialite who works in fashion.

During a heat wave, Jeff watches his neighbors through open windows, including a professional dancer coined “Miss Torso”; a songwriter with writer's block; a spinster who pantomimes dates with pretend suitors, “Miss Lonely-Hearts”; and traveling costume jewelry salesman Lars Thorwald, who is hen-pecked by his bedridden wife. One night, Jeff hears a woman scream followed by the sound of breaking glass. Later that night, Jeff wakes as a thunderstorm breaks; he observes Thorwald making repeated excursions carrying his Halliburton aluminum sample case. After Jeff has fallen asleep, Thorwald leaves his apartment along with a woman obscured by a large black hat.

If you’re thinking the Thorwald murdered his wife, you’re correct. Just how Jeff, along with Stella, Lisa, and Jeff’s police detective pal, Tom Doyle, figured that out and managed to trap Thorwald before he skipped town, that’s the central plot of the movie.

But that’s not what interests me. I’m interested in the secondary plot, which involves the relationship between Jeff and Lisa. When we first see Lisa, played by Grace Kelly, early in the film, she’s pushing Jeff (Jame Stewart) for a deeper, more committed relationship, and he’s resisting, pleading the differences between them. She’s a wealthy socialite, sporting a $1100 dress ($13K in 2025 dollars) and he’s a globe-trotting photographer who barely makes ends meet. At the end of the movie things are quite different. Both of them got caught up in Thorwald’s dramatic and violent capture, with Jeff breaking his other leg, and are now resting contentedly in his apartment. Presumably their relationship is now resolved.

How’d that happen? In his own thoughts about the movie, Henry Oliver notes:

Grace Kelly and Jimmy Stewart are not Sherlock and Watson—they combine the traditional “merry war” of comic lovers with the competition between sleuths. It is by becoming the daring Sherlock in her own right that this Beatrice wins her Benedick. It is not just private detective against police, or woman trying to pin down man, but a subtle marriage of the two story lines, making neither as clichéd as they otherwise would be.

That is to say, just as the two plots in Much Ado About Nothing, Claudio/Hero and Beatrice/Benedick, each serve as a device to allow the other one to move successfully toward marriage. So in Rear Window the murder plot functions as a device to move Jeff and Lisa from stasis toward marriage.

Getting a couple from attraction to commitment is always problematic; it’s a central concern of comedy. I devoted some attention to the problem in my paper on Much Ado About Nothing, Othello, and The Winter’s Tale, but I’m not going to attempt that in this short note. For the purposes of this note we’ll have to chalk it up to what I’ve taken to calling “myth logic.” My point is simply that there is a pattern here, and it can be analyzed and decoded, but not here and now, nor by me.

And that pattern “bleeds” out beyond the Jeff and Lisa story. In the movie’s final moments we see that Miss Lonely Hearts, who had been on the edge of suicide at one point, has met up with the songwriter and the dancer’s boyfriend has returned from military deployment. Those events, and a couple others, are part of the same pattern of myth logic. In the case of the relationship between Jeff and Lisa it’s not that there is any directly causality between the murder and their relationship, but rather that the murder provided them with an opportunity for mutual participation in a common cause, figuring out what had happened. The relationship between the murder and those other two developments is even more indirect. They just happened within the same time-frame.

Where they all come together is in the hearts and minds of the audience (us). That’s where myth logic is operative.

* * * * *

Addendum, Aug. 1, 2025: I’ve watched the film again. There’s as much dialog about marriage and relationships as there is about the murder. The two topic, of course, do intersect.

After establishing that we’re in Jeff’s room his nurse, Stella, arrives to give him a massage. They talk about his girlfriend, Lisa, and why he doesn’t want to marry her, though she expects it. They’re too different, he says, from different worlds, etc. Stella urges marriage, Jeff resists.

Stella leaves. The newlyweds arrive, and pull down the blinds. Jeff smiles at that. Obviously we’re to assume that they’re having sex.

The next evening, Lisa is in Jeff’s arms, kissing him. We see this in a close-up. He’s paying attention to what’s happening outside in the dark. He wonders what the salesman had in his sample case that he left the apt with it three times. Now he’s cleaning a knife. He’s obviously wondering whether or not he’s killed his wife and is removing her body piece by piece. He’s speculating out loud and now Lisa’s scared, but interested. All this time she’s kissing him. Lisa leaves his arms to smoke a cigarette. They argue and speculate.

The film may be about a murder, but it’s saturated with marriage.

From the AI wars: Dario vs. Zuck

Anthropic CEO Tells Zuck to Shove It Newsletter, AI Secret, July 31, 2025.

📌 What’s happening: While Meta drops $100M signing bonuses like candy and poaches CEOs like trading cards, Anthropic’s Dario Amodei publicly slammed the brakes on joining the AI talent arms race. No negotiations. No bidding. No Zuck DMs. 

🧠 How this hits reality: Anthropic’s level-based comp structure is a middle finger to Big Tech’s talent grab. It's a calculated bet: keep the cult-like mission intact or risk culture collapse chasing Meta's money. Meanwhile, Meta flaunts its fresh kill list on earnings calls, positioning itself as the Real Madrid of AI, minus the trophies. 

🛎️ Key takeaway: Meta’s buying horsepower; Anthropic’s selling belief. One burns cash, the other burns slowly.

Mirror, mirror, on the wall, who's the gross-out king over all? [DJT 47]

YouTube:

Democrats Launch Early Offensive as Trump STUMBLES!

Sarah Longwell is joined by Lauren Egan to break down how Democrats are using the August recess to go on the offensive. From the shadow of Biden’s rough summer in 2021 to the GOP’s current Epstein chaos, they discuss how public opinion is hardening earlier than ever, and why Dems are seizing the moment with coordinated attacks.

Hoboken terminal

Intellectual creativity, humans-in-the-loop, and AI: Part 1, On the boundaries of cognition in humans and machines

This is the first in a series in which I think about intellectual creativity, the relationship between humans and machines in intellectual activity, and the limitations of machines. Do these limitations reflect only the limitations of current architectures or are they inherent in the nature of artificial intelligence? The idea is to refine my thinking about the problem so as to better specify that nature of those possible limitations. Perhaps when they are more closely specified we can see what would be required to overcome them.

* * * * *

Back in 1990 David Hays and I published an article, The Evolution of Cognition, in which we asserted:

A game of chess between a computer program and a human master is just as profoundly silly as a race between a horse-drawn stagecoach and a train. But the silliness is hard to see at the time. At the time it seems necessary to establish a purpose for humankind by asserting that we have capacities that it does not. It is truly difficult to give up the notion that one has to add “because ... “ to the assertion “I’m important.” But the evolution of technology will eventually invalidate any claim that follows “because.” Sooner or later we will create a technology capable of doing what, heretofore, only we could.

Just what did we have in mind? It seemed obvious at the time, at least I think it seemed obvious to us. Take that final sentence. Was it predicting what is now sometimes called AGI (artificial general intelligence) or only that sooner or later some computer would perform any (intellectual) task as well as (the best?) a human? That’s not clear.

That was a long time ago. It would be seven years before Deep Blue would beat Gary Kasparov at chess to become the first computer to beat a reigning human champion. The linguistic fluency of LLM-based chatbots was decades in the future. Back then the issue seemed distant and so clarity and specificity were not needed. These days the situation is quite different. Some are telling us that AGI will happen any day now, then then super-intelligence will not be far behind. The fact that neither AGI nor super-intelligence are well-defined is no deterrence to such predictions. Are these people only asserting what Hays and I had said 25 years ago?

I don’t know. But I want to take another crack at the problem. Current systems are, for the most part, benchmarked using bounded problems. The problems may be difficult to very difficult. The best current LLM-based systems do very well on such benchmarks, leaning many in the industry to believe that AGI is just around the corner. Those who are skeptical about that nonetheless believe that AGI will be accomplished when the current architectures are sufficiently scaled.

I’m not impressed. That’s quite different from real intellectual activity, which is often unbounded. In that situation the first problem is simply to identify a bounded problem. Once that has been done, one can proceed to solve it. LLM systems can’t do this because they operate only when given a prompt, and the prompt thereby serves as a boundary. So that’s one thing I want to look at, unbounded problems.

Here’s how I’m framing it:

All consequential intellectual activity takes place in a network of interconnected agents. These agents provide various intellectual services to one another. Some or all of the agents are human; some or all are computers. I assume that there are at least some, perhaps many, activities where a completely computerized network is more effective than any network where there is at least one human agent. The job of that human agent is to place a boundary in the space so that there is a solvable problem. Are there any activities such that a network with at least one (highly trained) human agent is more effective than any completely computerized network?

I am going to think through this issue by considering two specific cases: 1) interpreting Spielberg’s Jaws using the ideas of René Girard, 2) analyzing the population of Xanadu ‘memes’ on the web. I’ve chosen those two problems because: 1) I have done both of them myself and so can talk about how I bounded the problem space, and 2) I have directed ChatGPT to perform them. That will give us the next two posts in this series.

In the fourth post I want to consider the problem of creating a cognitive network diagram that expresses some of the semantics underlying Shakespeare’s sonnet 129. I have done this, and ChatGPT has failed to do it. It is not at all clear to me whether or not Whether or not that is so, it involves establishing a close relationship between a linguistic object, the sonnet, and a visual object, the diagram. I also want to discuss chess in this context as it has both a linguistic aspect, the rules of the game, and a visual aspect, the disposition of pieces on the game board.

In the fifth post I want to take up the issue of a problem solution that requires creating a new paradigm, in the sense Thoms Kuhn used the term in The Structure of Scientific Revolutions (1962). Solving such problems requires access to the external world so that one can make observations and, I believe, it also requires discussions with other epistemic agents, agents as powerful as the one proposing a solution. At the moment humans are the only such agents. Will there ever be a computer that is such an agent? That’s the question, isn’t it? Access to the external world seems to be a solvable problem. I’m not sure about epistemic power.

In the sixth final post I’ll discuss memory in humans and machines, for that’s what I think the issue is, the nature of memory. The by now conventional assumption is that more is better, the more memory the better. When we get enough memory, along with computer and model parameters, BINGO! we’ll hit AGI, and super-intelligence will not be far behind. This assumption fails to take account of the fact that the machine must be able to access the contents of its memory both efficiently and accurately. That’s what I’ll be discussing the sixth and final post.

Views from the table top

Inferring Consciousness in Phylogenetically Distant Organisms

Peter Godfrey-Smith; Inferring Consciousness in Phylogenetically Distant Organisms. J Cogn Neurosci 2024; 36 (8): 1660–1666. doi: https://doi.org/10.1162/jocn_a_02158

Abstract: The neural dynamics of subjectivity (NDS) approach to the biological explanation of consciousness is outlined and applied to the problem of inferring consciousness in animals phylogenetically distant from ourselves. The NDS approach holds that consciousness or felt experience is characteristic of systems whose nervous systems have been shaped to realize subjectivity through a combination of network interactions and large-scale dynamic patterns. Features of the vertebrate brain architecture that figure in other accounts of the biology of consciousness are viewed as inessential. Deep phylogenetic branchings in the animal kingdom occurred before the evolution of complex behavior, cognition, and sensing. These capacities arose independently in brain architectures that differ widely across arthropods, vertebrates, and cephalopods, but with conservation of large-scale dynamic patterns of a kind that have an apparent link to felt experience in humans. An evolutionary perspective also motivates a strongly gradualist view of consciousness; a simple distinction between conscious and nonconscious animals will probably be replaced with a view that admits differences of degree, perhaps on many dimensions.

Introduction

When we encounter octopuses and some other complex invertebrate animals, we find behavioral indicators, or at least suggestions, of various kinds of subjective experience. We might see suggestions of pain, for example, and can note an attentive engagement by the animal with events around them. First impressions based on behavior are not enough to infer that felt experience is actually present. If we want to work out whether it really feels like something to be one of these animals, how should we proceed? Further observation can give us a richer sense of their behavioral capacities, and we can also try to work out what is going on inside them. When we look inside, we find similarities to ourselves along with many differences. We find a nervous system, but one with a different architecture from ours. In some respects, these different nervous systems are evidently doing similar things: Octopuses and bees can see; they can navigate and learn. However, the neural structures that figure in recent attempts to explain consciousness are generally absent—they have no cortex or thalamus, for example. Which similarities between us and them matter, and which do not? How can inferences about consciousness in phylogenetically distant animals be more than speculation?

This Perspective article offers a position on these matters. The topic is consciousness or felt experience in a minimal sense—whether it feels like something to be one of these animals (Nagel, 1974). The problem will be approached through an evolutionary framing, looking at the history of nervous systems and the phylogenetic relationships between different animals alive now. I will link this evolutionary perspective to a general view about the biological basis of conscious experience, and consider several invertebrate groups. The discussion will focus on animals but will suggest conclusions about other organisms as well. My positive account of the biology of consciousness is speculative in many respects, as are its rivals. I can offer defenses for some claims, but it is not possible in a short essay to establish it as the best option. The aim of the discussion is to outline the view, link it to empirical work, and consider how it relates to some alternatives.

Fireworks

Jane Juska on the Body

I suppose I discovered Jane Juska in 2017 when Maggie Jones wrote about her in The New York Times. Here’s how she opened her profile:

You are a 66-year-old mother and retired high-school English teacher, bred in a small, puritanical Ohio town. Though you’ve been divorced for 30 years and celibate for almost that long, your life is full in many ways, teaching a college education course, volunteering as a writing instructor at San Quentin State Prison, escorting women for abortions at Planned Parenthood.

None of it compensates for the lack of a man’s touch. The conventional avenues for dating at your age — senior hikes, senior bird-watching, senior mixers (you even hang out in hardware stores) — have netted little. Online dating is not yet commonplace. So, one October day in 1999, you write 30 words that will appear as a personal ad in The New York Review of Books. “Before I turn 67 — next March — I would like to have a lot of sex with a man I like. If you want to talk first, Trollope works for me.”

Within weeks, the letters begin to arrive from the Review of Books to your Berkeley, Calif., cottage. In total, you will receive 63, in seven manila envelopes.

Once I’d decided to write about sex for 3 Quarks Daily I picked up a copy of Juska’s memoire, A Round-Heeled Woman: My Late-Life Adventures in Sex and Romance (2003), and used it to end the piece, Redeeming Pleasure: Women Lead A Second Sexual Revolution. Juska’s book was successful. I don’t know whether or not it made any best-seller lists, but she did readings and signings and became someone people recognized on sight. And so she wrote a sequel, Unaccompanied Woman: Late-Life Adventures in Love, Sex, and Real Estate (2007), which I am currently reading. Is it better, the same, or not so good as the first? I don’t know, haven’t made up my mind, does it matter?

Whatever.

Here’s two passages from Chapter 12, “The Body Electric.” This is about her own body:

Yet, at another reading, during the question-and-answer period, I am asked the age range of the men I got naked with. “Eighty-four to thirty-two,” I answer, and there is a gasp. Then, from a woman who looks directly at my torso, “What would a thirty-two-year-old want with you?” Again and again, wherever I go to read, to sign books, the question or a variation of it arises: “How do you get undressed in front of those men?” My answer, which always brings laughter, is, “Fast.” But it’s true. Faster than a speeding bullet I have covered myself from top to toe in, if I’m lucky, 400-thread-count linens while he was still wrestling with the top button of his shirt. More powerful than a locomotive, I have dived beneath bedclothes while he’s still pulling at his socks. “Where did you go?” he asks, and, half-hoping he won’t find me, I whisper from the depths of sheets and blankets and pillows, “Here I am.” (pp. 127-128)

And this is about the bodies of her male lovers:

When I think about the bodies of the men I have come to know, when I recall the enjoyment I took from a body that was seventyfive years old, a body that was thirty-two, and a few in between, I remind myself that much of the pleasure came because I liked, even loved, the person who inhabited that body. I remember unhappy encounters with men whose bodies became repellent to me, not because they were ugly or old, but because the men who wore them were selfish or greedy or ill-tempered. (p. 131)

Basic foods

The Elite Panic at the Heart of Liberal Attacks on Mamdani

Tressie McMillan Cottom, The Elite Panic at the Heart of Liberal Attacks on Mamdani, NYTimes, July 27, 2025.

Zohran Mamdani’s campaign is driving some people mad.

Mamdani is, of course, the young, charismatic, charming and decidedly left-of-center candidate upsetting the political status quo. He is also Muslim and of Indian and Ugandan descent. The recent political attacks against him are coming from all directions — Republicans, Democrats and the real estate lobby. Some of these attacks are about political interests — of course, landlords wouldn’t like affordable housing and tenant-friendly Mamdani.

But a lot of these attacks are thinly veiled racism. They conflate Mamdani’s left-wing political messaging with the “otherness” of his racial and ethnic heritage. It is an old racial trope that worked unevenly against President Barack Obama. Be afraid of the cheerful brown man. He isn’t a “real” American. He is dangerous because he wants to take from the rich to give to the undeserving poor.

It makes sense that Republicans play this card. They already dally in the irrational world of race fantasy, where white Americans are an oppressed majority. But Democrats are supposed to know better. Being the party that knows that race is real, that it works in measurable ways and that those ways matter to their base is kind of their brand. They had it figured out when these attacks were deployed against Obama.

If they knew it was wrong in Obama’s case, why are they falling for it in Mamdani’s? [...]

A primal fear of minorities drove a lot of voters toward Donald Trump. It should be commonly accepted by now that his political rhetoric targets minorities and uses violent stereotypes to dehumanize them and that millions of his supporters don’t just accept that — they relish it.

But at the same time, Donald Trump managed to appeal to some racial minorities during this last election. That caused liberals and poll watchers a lot of angst. How can anyone explain his support among the very racial and ethnic groups that he endangers?

The long and short of it is that multiculturalism is not a natural deterrent to racism.

Dylan Rodriguez, a professor at the University of California, Riverside, calls this moment “white Reconstruction,” a term that draws on the 19th-century attempt to enfranchise Black Americans after the Civil War. Rodriguez argues that the long post-civil rights era that flowed from the Civil Rights Act was not one where progress inevitably won out; it was one where the accommodation of social progress looked like racial equality but ultimately undermined it.

Where the Reconstruction of the 1860s and 1870s attempted to make Black Americans whole, today’s white Reconstruction tries to make white Americans not more whole, but more powerful. On the right, white Reconstruction looks like relentless, shameless attempts to claw back rights from poor people, minorities and women. But on the left, it looks more like what Olufemi O. Taiwo, a professor of philosophy at Georgetown University, calls elite capture, or the co-option of radical ideas (in this case, diversity) by powerful institutions. Elite capture is a way for those with power to accommodate social progress through the performance of diversity while keeping their hold on political hegemony. It’s action that looks like progress, but in reality it changes very little.

Incoherence all around:

This is all good context for the incoherent discussion of Mamdani, which frames him simultaneously as a threat and the embodiment of the American dream. He represents the American ideal of diversity — an immigrant who worked hard, studied at Bowdoin College and wanted to be a public servant. But at the same time, there are people on both sides of the political spectrum who want to challenge the institutions, especially the elite colleges, that made his American story possible.

Conservatives may despise higher education’s cultural elitism. Liberals may pretend that they don’t worship it. Both groups channel their anxieties about their own place in our country’s pecking order through it. [...] While Democrats obsess over the middle class, Mamdani’s economic policies prioritize poor and working-class people. He has, in a way, betrayed the white liberal investment in the institutions that made him possible.

Checking identity boxes on official forms:

Checking multiple boxes — or not checking one at all — is an individual accommodation of empirical reality. It is also a threat to the idea of race as something that conservatives can easily vilify or that liberals can easily commodify.

(Mamdani said as much in his statement about how he self-identified on his college application. He checked all the boxes that applied, because no single box, not even the combination of boxes he checked, could effectively capture the completeness of his identity.) [...]

When both sides of the political spectrum share an obsession with interrogating one’s racial purity, maybe it’s time to confront an uncomfortable truth: A lot of us are exactly who Donald Trump believes that we are.

Hydrangeas

Alpha School combines AI for "raw" skills with PBL for practical skills

Pooja Salhotra, A.I.-Driven Education: Founded in Texas and Coming to a School Near You, NYTimes, 7.27.25.

In Austin, Texas, where the titans of technology have moved their companies and built mansions, some of their children are also subjects of a new innovation: schooling through artificial intelligence.

And with ambitious expansion plans in the works, a pricey private A.I. school in Austin, called Alpha School, will be replicating itself across the country this fall.

Supporters of Alpha School believe an A.I.-forward approach helps tailor an education to a student’s skills and interests. MacKenzie Price, a podcaster and influencer who co-founded Alpha, has called classrooms “the next global battlefield.”

“I’ve seen the future,” she wrote on social media, “and it isn’t 10 years away. It’s here, right now.”

To detractors, Ms. Price’s “2 Hour Learning” model and Alpha School are just the latest in a long line of computerized fads that plunk children in front of screens and deny them crucial socialization skills while suppressing their ability to think critically.

“Students and our country need to be in relationship with other human beings,” said Randi Weingarten, the president of the American Federation of Teachers, a teachers’ union. “When you have a school that is strictly A.I., it is violating that core precept of the human endeavor and of education.”

But it’s not strictly A.I.

Alpha officials and guides say the various A.I. programs they use tailor instruction to each child’s level instead of teaching to the average student. That frees teachers to attend to students’ emotional needs.

It is not a “screen school,” argued Ms. Price, who had grown dissatisfied with her daughter’s public school education. Students at Alpha spend the majority of their school day in workshops where they collaborate with other students, Ms. Price said in an interview. The A.I.-led lessons free up guides to focus on motivating students instead of on time-intensive tasks like lesson planning and grading, several guides said.

Much later in the article:

But Alpha isn’t using A.I. as a tutor or a supplement. It is the school’s primary educational driver to move students through academic content.

In the afternoons, students focus on projects that require interaction with other students, such as wilderness training, cooking and sports. For example, fifth and sixth graders last year decided to create a food truck. To accomplish their goal, they learned how to budget, form a business plan — with the help of a chatbot — and to cook eggs.

“When we were all in the kitchen, it would get really stressful,” Byron said. “Working through that calmly and together is something I really improved on.”

Resistence:

To the tech weary, Alpha’s pitch is shopworn. Education technology companies and philanthropists have pushed computers in classrooms for decades. Those experiments have had mixed results and proved difficult to scale. For example, a Silicon Valley-based program called Summit Learning, funded by Mark Zuckerberg and his wife, Priscilla Chan, has been resisted by public school students from New York to Kansas.

Alpha’s endeavor for Unbound Academy has been met with skepticism. State boards of education in Pennsylvania, Texas, Utah, Arkansas and North Carolina all rejected the program, some citing a lack of evidence that it works.

“The artificial intelligence instructional model being proposed by this school is untested and fails to demonstrate how the tools, methods and providers would ensure alignment to Pennsylvania academic standards,” the Pennsylvania Department of Education’s decision read, citing “multiple, significant deficiencies.”

Although Alpha says it offers students opportunities to collaborate, some have decided to leave after middle school to embrace a high school experience with team sports, student council and prom night. Byron, the rising seventh grader at Alpha, said he was not sure whether he wants to go to high school at Alpha.

“If you think of the purpose of schools as to prepare people for the roles of citizenship and democracy, there’s lot of places where you aren’t trying to get kids to race as fast as they can,” said Justin Reich, director of the Teaching Systems Lab at the Massachusetts Institute of Technology and author of the book “Failure to Disrupt: Why Technology Alone Can’t Transform Education.”

Masterpieces:

Several Alpha high school students said their favorite part about the school was working on what Alpha calls their “masterpieces,” a time-intensive project coinciding with the student’s passion. For such projects, students have built a chatbot that offers dating advice, an emotional support teddy bear and a 120-acre mountain bike park, now the largest in Texas.

To complete the projects successfully, students said, they must surpass A.I.’s knowledge base and come up with a “spiky point of view,” or unexpected and novel perspectives.

“To be a useful person in the age of A.I., you have to have unique insights that A.I. doesn’t really agree with,” said Alex Mathew, 16, a rising senior at Alpha High School. “That’s the real differentiator,” he continued. “We are trying to beat A.I.”

A mini Moravec's paradox within robotics

I'm observing a mini Moravec's paradox within robotics: gymnastics that are difficult for humans are much easier for robots than "unsexy" tasks like cooking, cleaning, and assembling. It leads to a cognitive dissonance for people outside the field, "so, robots can parkour &… pic.twitter.com/LzBUNeQXGt

— Jim Fan (@DrJimFan) July 25, 2025

H/t Tyler Cowen.

Some basic fluids: water, coffee (& cream), syrup

Hallucination, it's what we do [LLMs and humans alike]

It's doubtful LLMs will replace human workers. Jobs require understanding context, problem-solving, and adaptability. LLMs mimic but can't do them robustly. Their architecture makes it impossible. Relying on them for fact-based, high-stakes work is an insane gamble.
(2/n)

— Wendy (@wendyweeww) July 26, 2025

Use LLMs where they shine. To create, not calculate. To communicate, not control. Where flexibility matters more than precision. This may sound cliche, but they're here to augment, not replace. They're the kind of worker that's highly dependent on you to lead. (4/n)

— Wendy (@wendyweeww) July 26, 2025

Read the whole argument here.

Neurochemicals, brains, sex, and relationships: Rena Malik, M.D., interviews Dr. Jim Pfaus

YouTube:

In this episode, Dr. Rena Malik, MD is joined by neuroscientist Dr. Jim Pfaus to explore the neuroscience of sexual attraction, desire, and bonding. They discuss how early sexual experiences shape our preferences, the role of dopamine and oxytocin in relationships, the impact of hookup culture and pornography, and the science behind sexual synchrony. Listeners will gain insightful perspectives on the brain’s influence over intimacy, pleasure, and partner connection, along with practical takeaways for fostering deeper relationships.

00:00:00 Introduction
00:00:26 Guest background & episode topics
00:01:43 Brain and sexual attraction
00:06:39 First sexual experiences
00:12:08 Navigating bad sexual experiences
00:15:18 Masturbation, porn, and impact
00:23:17 Sexual synchrony and bonding
00:33:31 Orgasm: brain chemistry
00:44:09 Semen retention & arousal
00:51:34 Porn, compulsion, and addiction
01:01:04 Oxytocin and bonding
01:12:20 Neuroplasticity, love, and long-term relationships
01:22:36 Sexual trauma and healing the brain
01:33:10 How hookup culture rewires desire
01:42:44 Takeaways

You can find papers by Dr. Pfaus on ResearchGate.

* * * * * 

This is a fascinating, rambling, and wide-ranging interview. Find a topic that interests you and dig in. Then listen to the whole thing. I’m particularly interested in the discussion of Oxytocin and bonding (starting at 01:01:04 and pretty much going on through to the end).

Why? Because I’ve been thinking about oxytocin ever since I read Walter Freeman’s Societies of Brains: A Study in the Neuroscience of Love and Hate (1995). Freeman was speculating about the role of intense ritual mediated by music and suggested that oxytocin would be released during such rituals and that that would facilitate bonding between the participants. What’s interesting, though, is the mechanism he suggested: Oxytocin released during the ritual would loosen the connectivity between neurons in the brains of individuals. The result would be that, as connectivity was reestablished, the patterns of connectivity within individuals would be similar across the population of participants, thus reducing their differences. I found that fascinating and made it central to my book on music, Beethoven’s Anvil: Music in Mind and Culture (2001), though in a somewhat different form, which I discussed in chapters two and three.

This is quite different from the discussion in the video, which is about pair-bonding between individuals. Malik and Pfaus are interested in the role of post-coital cuddling where bonding between the pair is mediated by oxytocin. Crudely put, when individuals cuddle there’s bonding, no cuddling, no bonding. But individuals can choose whether or not they cuddle, no? Yes. So what’s the range of “viable lifestyle choices”? (Ugh! what a phrase!) We don’t know.

So I’ll trot out my standard metaphor for the relationship between biology and culture: chess. Biology provides the basic rules of the game: the game board, the individual pieces, and the moves each piece is allowed to make. But there is a great deal of latitude in how one deploys those pieces during actual gameplay. That’s where culture comes in. The tactics and strategies one uses, that’s culture.

Biology doesn’t dictate behavior, not for individuals, not for whole societies. But it places constraints on behavior. Those constrains, by the very fact of constraint, open up possibilities for design and structure. This video is about some of those biologically-given constraints. As for the possibilities they open up, that remains to be seen.

I’d say that we have a lot of work to do. Well, it may be work for the scientists. But for the rest of us, it looks like play to me.

Communication breakdown

UFOs in the archives [& reality?]

Ross Douthat, What if the Government Believes in U.F.O.s More Than You Do? NYTimes, July 24, 2025.

Ross Douthat: From New York Times Opinion, I’m Ross Douthat and this is “Interesting Times.”

There have been a bunch of flying saucer crazes in American history, but the one we’re living through started in 2017, when my newspaper, The New York Times, reported on these weird encounters experienced by U.S. military pilots. Since then, we’ve had congressional hearings, would-be U.F.O. whistle-blowers and we’ve had a brief panic over mysterious objects in the sky over the state of New Jersey.

I’m not persuaded that we’re actually being visited by E.T. However, this era has left me with a lot of weird unanswered questions. For instance, what do all of these government bureaucrats and whistle-blowers actually know — or think they know — about unidentified aerial phenomena? Does at least part of the U.S. government really, really want Americans to believe in U.F.O.s? And if so, why?

To help me search for answers, I asked Diana Walsh Pasulka to join me. She’s a religious studies professor who writes about U.F.O. experiences as a very American kind of religion, but she’s also been pulled into this weird world of apparent government believers — and she’s become something of a believer herself.

Pasulka started looking in the archives to study how Catholics thought about what happens to the soul after death.

Pasulka: So I’ve been studying religion for many years. [...] I didn’t believe in U.F.O.s. I had never seen “Close Encounters of the Third Kind.” I wasn’t a person who was interested in that topic. But I was interested in the ways in which people thought of transformation, spiritual transformation, but also transformation that happens on Earth through these narratives of going into another place, an “other world” journey.

Douthat: How did that pull you into studying people who claim to have had a U.F.O.-style encounter?

Pasulka: When I was doing my work for the book about the Catholic doctrine of Purgatory, that brought me to a lot of archives. I’d go into the archives — and archives are places where things aren’t digitized — and I started to look into how Catholics viewed how souls ascended into Heaven or Purgatory.

What I found was a lot of documents from 1,000 years ago, 800 or 500 years ago, about recorded sightings of aerial phenomena that Catholics had from Europe.

Douthat: And these are things flying in the air?

Pasulka: Yeah, aerial phenomena. And they interpreted these in different ways.

Here’s a good example: In the 1800s, there’s this young nun and she’s living in a convent. Every night, this ball of light comes through her cell, and she’s pretty upset about this. So she tells the Mother Superior and she says: This is happening.

And the mother superior says: You’re having a bad dream. The nun is pretty certain this is happening — it happens nightly. At one point the Mother Superior says: OK, I’m going to be with you at night to see what’s going on. And they determine that this is a soul from Purgatory that needs to be prayed back into Purgatory. So the whole convent gets together and they go through a process of prayers to kick this orb or this flame of light out of her cell.

I saw these kinds of things, and I started to keep track of them. Sometimes they were interpreted as flying houses. Sometimes they were interpreted as little beings about three feet tall and shiny. I shared this with a couple of friends of mine and I said: What do you all think of this? One of them said: It looks like modern-day reports of U.F.O.s.

That shocked me. I didn’t accept it, to tell you the truth. I thought it was hogwash. I was like, no, it can’t be that.

There was a U.F.O. conference in town called MUFON — the Mutual U.F.O. Network — and I decided to check it out. When I was there, I heard people talking about their experiences encountering U.F.O.s, and it sounded very similar to the log I had of reports of Catholics in Europe talking about this.

So I started to do a lot more intensive work. I met academics who were studying this. Before I knew it, people who were a part of aerospace companies and the military began to want to correspond with me and see the data and the research that I had been doing. That’s what got me into this topic.

Douthat himself:

I read a book around the time that U.F.O.s came back into the news, which would’ve been when my own newspaper, The Times, reported on weird sightings of aerial phenomena by U.S. pilots. I had not watched “The X-Files” in the 1990s, had not been a U.F.O. person in any meaningful sense of the term, but I got sucked into reading a little bit of the literature.

One of the most persuasive books that I read was by a famous U.F.O. researcher shrouded in mystery, a guy named Jacques Vallée. He wrote books pretty early, I think, in the modern U.F.O. phenomena, where he connected this not just to past religious experiences but also to a whole realm of folklore around, let’s say, fairy abductions.

And I thought Vallée’s argument was quite persuasive, that there is this persistent phenomenon in human history that suddenly gets reinterpreted as the space age dawns, in terms of creatures from other planets, but in fact is this kind of folklore substrate that just takes different forms depending on the cultural context.

That seems to be a version of the argument you’re making in linking modern U.F.O. sightings to the experience of Catholic nuns or religious mystics in the past. So you think that whatever we call the U.F.O. phenomena doesn’t start in 1947 with Roswell or anything like that, but rather, there’s some consistent historical phenomenon that’s part of human religious sociology.

What's real?

Pasulka: As for me, I try to stay out of it. I’m not on any side. I’m watching this happen just like you are and just like other people are. I might have more insight into what’s going on because I know several of these people on both sides, both on the part where people are basically saying it’s all not real — I know those people — and I know the people who are saying that it’s real. It’s definitely something that’s not transparent.

Douthat: It’s definitely not transparent. And I think that what you just described is a good description of my own perception that there are people who work within the government, some of whom themselves believe that there is a real phenomenon, or — related to or overlapping with that — want Americans to think there’s a real phenomenon, and then there is an official government narrative that there’s some weird stuff out there, but the government doesn’t know any more than you or I do. [...]

Pasulka: OK. So part of it was that — and by the way, I don’t advocate believing this for anyone. They have to do their own research. So I’m not advocating belief in U.F.O.s or U.A.P.

But I became convinced that there was definitely something to this when I met so many people who interfaced with the phenomena through their jobs, which happened to take them high into the stratosphere, launching rockets into space so that they had a view of what was happening in space. They’ve witnessed aerial phenomena that are not ours, and they are not Russia’s or China’s.

And when you meet 10 of these people and they all have similar reports, it’s interesting. It changes one’s view. These people are not public — some of them are, but most of them are not. They don’t want to be associated with this work that they do. They don’t want people to know about it. And they’re everyday Americans.

Friday Fotos: Tastes of Hoboken

This 2nd Sexual Revolution is about a change in NORMS

Just a quick update on this second sexual revolution argument. I realized why I found the sales figures for Fifty Shades of Grey so convincing. It’s one thing if you think of it as indicating the preferences of a lot of women, 150 million worldwide by 2017. That’s just a statement about individual people, a lot of them to be sure, but still, just people. But I realize, in retrospect, that I was taking it as an index of cultural norms. 

That’s very different. That’s a cultural revolution, when norms change. Similarly, that’s why the publication and success of Jane Juska’s Round-Heeled Woman is significant, it signals a shift if norms. The same with all those YouTube videos, especially the stories in The Mystery Box Show, out of Portland, Oregon. There aren't that many such stories. What is significant is the fact that they exist at all, and on YouTube.

Is this interpretation justified? I don’t know. It’s not something I arrived at by deductive reasoning. Heck, I didn’t even realize that I’d done that until a day ago, and then it just hit me, no reasoning involved. And I’ve still not done any reasoning about it. It’s just an intuitive judgement. Based on what? The whole gestalt. Gestalt of what? Good question.

Come to think of it, perhaps this is why the mainstream media hasn’t picked up on the story. This change in norms isn’t that visible. Playboy magazine, that was very visible, all those photos of nude women on ordinary newsstands. Ms. magazine, visible. Feminist demonstrations, visible. Conversations about sex between consenting adults, not at all visible.

I’ve got some thinking to do, but not here, not now.

More later.

Parent-child co-sleeping is common in Asia [East and West]

Mike Ives, Sharing a Bed With Your Kid? It’s Totally Normal in Asia. NYTimes, July 22, 2025.

In the United States and some other Western countries, many parents wince at the idea of sharing a bed with their young child on a regular basis.

But in other places, long-term bed sharing through infancy, toddlerhood and beyond is seen as totally normal. For many families in Asia, in particular, the question is not whether to do it, but when to stop.

How and where young children sleep is a big deal for the whole family. It can have implications for an infant’s safety and a child’s development. It can also affect parental sleep, intimacy and mental health, and can influence how families configure their homes.

Western practice:

In the West, and especially in the United States, bed sharing tends to be unpopular and contentious. That is partly because the American Academy of Pediatrics and other experts warn that it can be unsafe for infants 6 months of age or younger.

Many Western parents put infants to sleep in cribs or beds in a separate room — often using a practice known as “sleep training,” in which infants are taught to sleep independently. Modern ideas about separating mothers and babies at night have their roots in campaigns by “Victorian-era influencers” in Britain and the United States, according to “How Babies Sleep,” a book published this year by the anthropologist Helen Ball.

Even though there isn’t much scientific literature on bed sharing, studies generally show that the practice is far more common in Asia than in the West. [...]

One multicountry survey of parents of infants and toddlers from 2010 found that bed-sharing rates were over 60 percent in China, Japan and South Korea, and over 70 percent in India and parts of Southeast Asia. The rates in Australia, Canada, New Zealand and the United States ranged from 5 to 15 percent.

Priorities:

In some Asian societies, many couples prioritize the mother-child bond over their own sleep health and marital relationships, said Heejung Park, a professor of psychology at Scripps College in California who has studied bed sharing in the region. [...]

In India, the cultural attachment to bed sharing is so deep that it tends to persist even among urban elites who are exposed to “Western sleep training culture,” said Himani Dalmia, a sleep specialist in New Delhi who runs a support group for parents and shares a bed with her children, 7 and 9.

Singapore is an exception:

One apparent exception in the region is Singapore, a wealthy city-state where reported bed sharing rates are lower than in other East and Southeast Asian countries. Sleep training seems to be increasingly popular there, and some Singaporean parents are reluctant to admit to bed sharing, said Elaine Chow, the president of a local breastfeeding support group.

Ah, those “intimacy” issues:

Some of Ms. Kim’s friends have children who stayed in the family bed until age 12, even at the expense of their parents’ sleep quality and sex lives. That would be too much for her, she said. So she and her husband have decided that their girls will move into what is now their playroom in about two years.

There's more at the link.

Authentic Chinese Bluegrass – "Amarillo by Morning"

One of these doesn't belong in the group

Project-Based Learning (PBL) and AI

Here’s how Wikipedia characterizes project-based-learning:

Project-based learning is a teaching method that involves a dynamic classroom approach in which it is believed that students acquire a deeper knowledge through active exploration of real-world challenges and problems. Students learn about a subject by working for an extended period of time to investigate and respond to a complex question, challenge, or problem. It is a style of active learning and inquiry-based learning. Project-based learning contrasts with paper-based, rote memorization, or teacher-led instruction that presents established facts or portrays a smooth path to knowledge by instead posing questions, problems, or scenarios.

Around the corner Hollis-Robbins has outlined a program to use AI in teaching the general education requirements of the California State University system (where she was a dean for a number of years). PBL is part of the program. It’s worth taking a look at.

Arnold Kling picks up on it in a post, Project Learning in the age of AI. He talks about how he has used PBL:

When I taught AP economics in high school and “Economics for the Citizen” at George Mason, I liked giving students a project to outline a business. I told them to think in terms of a “strip-mall business,” to avoid anything too complex or online. An ice cream store. A barber shop. A video game arcade.

I wanted the students to calculate costs in terms of the main factors of production: labor, land, and capital. I wanted them to identify key ratios that would determine success or failure of the business. Sales per hour is a good example. I wanted them to identify key roles and responsibilities. I wanted them to think about issues related to marketing, including location. I wanted them to identify key unknowns, such as local demographics or potential competition. I wanted them to think about inventory management.

He used it as a group project at the high school and undergraduate levels. Today, however...

I would give the assignment to students individually. They would not need other students with whom to brainstorm, because they could use AI. I could handle thousands of students, because assessment would be done by AI. If necessary, we can assign a monitor to be present to make certain that the student is not cheating by using an AI during the assessment.

I would have the AI interview each student about that student’s business idea. The AI would assign a grade and offer feedback based on a rubric that I would provide.

The other day I had a conversation about PBL with ChatGPT in which I focused on writing, making a distinction between sentence-level sentence craft and the overall process of thinking things through. I’ve appended that conversation below.

* * * * *

Project-based learning, basics

Tell me about project-based learning. Where is it used, what are the advantages claimed for it, what are the criticisms.

Project-Based Learning (PBL) is an educational approach in which students gain knowledge and skills by working for an extended period of time to investigate and respond to complex, real-world questions, problems, or challenges. Rather than passively receiving information, students actively construct it through experience, collaboration, and reflection.

---

Where is Project-Based Learning Used?

PBL is used across a wide range of educational settings:

1.     K–12 Education:

o   U.S. public and charter schools (e.g., High Tech High, Expeditionary Learning Schools).

o   International schools with progressive curricula (e.g., International Baccalaureate programs).

o   STEM-focused initiatives like Project Lead The Way.

2.     Higher Education:

o   Engineering and design programs (e.g., Olin College, MIT) often use PBL to simulate professional contexts.

o   Medical and business schools sometimes employ it under the label of problem-based learning, a close cousin.

3.     Informal and After-School Settings:

o   Maker spaces, robotics clubs, environmental programs, and community service learning often use PBL approaches.

4.     Workforce Development and Corporate Training:

o   Used in team-based professional development, particularly where practical, hands-on solutions are valued.

---

Advantages Claimed for Project-Based Learning

1.     Deeper Understanding:
Students develop a more thorough and lasting understanding of content because they apply knowledge to real-world problems.

2.     21st-Century Skills:
PBL emphasizes skills such as collaboration, communication, critical thinking, creativity, and self-management.

3.     Intrinsic Motivation:
Working on meaningful problems tends to increase student engagement and ownership of learning.

4.     Cross-Disciplinary Learning:
Projects often integrate multiple subject areas—e.g., combining math, science, and writing in a climate change project.

5.     Preparation for the Real World:
Mimics how learning and problem-solving happen in workplaces and life outside of school.

6.     Equity and Inclusion:
Advocates argue that when well-designed, PBL can allow students of diverse backgrounds to showcase talents not captured by traditional testing.

---

Criticisms and Challenges of Project-Based Learning

1.     Inconsistent Implementation:
Poorly designed projects can become aimless or superficial, with little academic rigor. “Projects” may be bolted onto a traditional curriculum rather than driving the learning.

2.     Assessment Difficulties:
Measuring individual learning outcomes can be complex. There's ongoing debate over how to assess process vs. content, group vs. individual work.

3.     Teacher Preparation and Workload:
PBL demands high-level planning, cross-disciplinary coordination, and new forms of evaluation. Many teachers lack the training or support to do it well.

4.     Equity Risks:
Without careful scaffolding, PBL can exacerbate achievement gaps, as students with stronger background knowledge or support networks are better positioned to succeed.

5.     Curricular Constraints:
In highly standardized education systems (e.g., U.S. states with heavy testing mandates), PBL can be difficult to integrate without sacrificing coverage of tested content.

6.     Superficial Engagement:
There's a risk of “fun but fluffy” projects where students build models or presentations without deep conceptual learning.

---

Conclusion

Project-Based Learning is a powerful approach with the potential to transform education by making it more experiential, relevant, and skill-oriented. But it’s not a magic bullet. Its success depends on thoughtful design, skilled facilitation, and structural support. At its best, PBL can align school with the way people naturally learn and solve problems in the real world; at its worst, it can become performative, shallow, and inequitable.

Would you like examples of successful PBL implementations or a comparison with traditional teaching models?