Tuesday, January 31, 2023

Kimono Mom philosophy @ 3QD

Here’s the link:

A day in the life of Kimono Mom and Sutan

I just wrote it from start to finish, without much planning. Lots of preparation – a Kimono Mom post every day from Jan. 21 through Jan. 29 – but very little specific planning for that piece. I knew what I wanted as a theme, Moe’s assertion that she tries to treat Sutan as an equal, and I knew one of the videos I wanted to use, the one that ends with them synchronizing gestures at the end. Beyond that, I figured I use a couple more videos and weave some kind of story or argument through and around them.

But that’s not what happened. I wrote the introductory section on Saturday evening, ending with this paragraph:

Kimono Mom, though, is a cooking show in the way that Anthony Bourdain’s Parts Unknown was a food and cooking show. Yes, Bourdain traveled all over the world and showed us the food of many different cultures. But he used food as a vehicle for revealing and reveling in human diversity, for talking philosophy in plain language, for fun. Think of Kimono Mom as a philosopher with Sutan as her Socrates. She uses the cooking video the way Plato used the dialog form. It’s a vehicle.

We’ll get back to that in a minute.

Late Sunday morning I began writing the rest of the article. I started by commenting on that video, figuring I’d make a few comments about it, and then move on to the next video, whatever it would be, for I didn’t have anything planned. As I started writing the commentary it just grew and grew and before I knew it, but long before I was done, I had all but decided that I would build the whole article around that video. Which I did.

* * * * *

Now, what about the paragraph I used to end the introduction? The comparison with Anthony Bourdain was a natural, one I’d thought of before I started writing the article. There are a multitude of obvious differences between his TV shows and her YouTube videos. I don’t need to waste time pointing them out. But there’s one similarity, a deep one. It’s clear that Bourdain had more than food on his mind. He was, for want of a better word, philosophizing and he was using food as his vehicle.

And it has been clear to me that Moe is philosophizing as well. I may not have realized that the first time I watched one of her videos – I forget which one – three months ago. But that’s certainly what drew me to watch another, and another, and to keep on watching them. By the time I’d posted my first Kimono Mom video, on November 9, I knew that Moe was a philosopher, even if she didn’t realize it.

What gives her videos a philosophical cast is not what she tells us about Japan and Japanese culture in the course of preparing food, although that is important. With nothing more than that, her shows are just cooking shows, perhaps unusually charming, but still, just a cooking show. No, what elevates Kimono Mom to philosophy and art – for they are the same according to the Keatsean formula, beauty is truth, truth beauty – is her dialog with her daughter Sutan.

Here’s the first Komono Mom video, from two years ago:

Moe is holding Sutan in the opening shot. She introduces herself, and then Sutan, who is identified on screen as her assistant. We get the title screen and then we see Moe chopping lotus root (00:25) as she begins to demonstrate how to make deep fried lotus root sandwiches. Sutan is nowhere to be seen. She’s napping, or something.

Sutan wakes up (03:23) and Moe leaves the kitchen to attend to her, leaving her audience watching a glass bowl of mashed avocado she’s been stirring. It’s for the sandwich filling. While we are watching the avocado puree in its own juices Moe says in voice-over:

You woke up? Already? even cooking, it is hard for mom during childcare. She literally follows me every time everywhere lately. I can’t do anything when she want me to pick up and crying. I often cook with her in one hand.

We hear her, still off camera, singing something to Sutan (04:20) and talking to her in motherese (a technical term I psychology). She returns to her cooking at about 4:31, leaving Sutan off screen. She talks of off-screen Sutan at 4:47, who makes some kind of noise in return. A bit later we hear some kind of music box playing while Sutan vocalizes as Moe continues mashing away. “You’re getting excited. Do you have a recital?” Dialog.

And so it goes until the lotus root sandwiches are ready to be deep-fried. At that point Sutan crawls into the kitchen – I assume that’s what she’s done as she’s too young to walk, but since she is below counter level we can’t see her – and Moe picks her up. Moe is holding Sutan in her left arm while using large spoon to coat the sandwich with batter. She picks it up with her fingers and lowers it into the hot oil.

The next shot looks down on a pair of sandwiches in hot oil. Then we see them on them cooling off on a rack and, for a second, we can see Sutan sitting on the floor (08:50). That’s the first time we’ve glimpsed her face since the opening shot. Moe plates two sandwiches and then begins to eat one, using chop sticks (09:30). “Mmmmmm” – with a rising voice tone as Moe smiles at us. She finishes eating the sandwiches using chopsticks while delivering a voice over commentary on how good the sandwiches are, “our family’s favorite dish.” No more Sutan.

And yet she was there in the opening shot. And she was identified as an assistant? What was Moe thinking at this point? Was she planning to involve Sutan in the process as she became more capable? I suspect that she was, but I don’t really know.

What I do know is that Moe is a skilled and sophisticated artist. What do I mean? She was trained as and worked as a geisha for, I believe, six years. She learned to dance, to play the shamisen, to have charming conversation with her customers, and I don’t know what else, but also how to dress. That means how to wear a kimono, one appropriate for the season and the occasion. Dancing and music, those are arts, but the whole geisha performance, it’s an art form. Whatever she had in mind when she made her first video, Moe's experience as a geisha has informed her video work, allowing her to develop it with philosophical skill and artistry.

Percent of large-scale AI results coming from academia

I'm not sure what to make of this. I assume one reason for the drop-off is that large-scale AI models are so expensive to train that academia can't afford to do it. That's not good. But then academia is structurally biased against (too much) innovation. That's not good either.

Private industry is biased toward making money and is in favor of any innovation that confers a competitive advantage for the innovators. That's fine. But it also puts a premium on secrecy. That's not good, not when genuine innovation happens behind closed doors and stays there. How much innovation is taking place in private industry?

If it's secret, how can we tell? What about the me-too land-rush currently taking place over so-called "foundation" models? Any innovation there?

Monday, January 30, 2023

Five shots of Hoboken

ChatGPT about Jack, a pumpkin, Aurora, Merlin, a cat, magic mushrooms, and space aliens

Here I start ChatGPT with a basic story and then have it elaborate on it in stages.

Tell me a story about a hero.

Once upon a time, there was a young man named Jack who lived in a small village at the foot of a mountain. Jack was kind and brave, and he was always willing to help others in need.

One day, a ferocious dragon appeared in the village and began to terrorize the people, burning their homes and eating their livestock. The villagers were afraid and didn't know what to do, but Jack knew he had to help.

He climbed the mountain and found a magical sword hidden in a cave. With the sword in hand, Jack bravely confronted the dragon and after a fierce battle, he was able to slay the beast and save the village.

From that day forward, Jack was known throughout the land as the hero who defeated the dragon and protected the people. He continued to use his bravery and kindness to help others, and he lived a long and happy life, always remembered as a true hero.

Note that this story has only four paragraphs, unlike the basic Aurora story introduced on January 6, 2023 in ChatGPT, stories, and ring-composition. In this story paragraph three combines the Plan and Execute segments of the ‘standard’ story trajectory identified in A note about story grammars in ChatGPT and in ChatGPT intimates a tantalizing future; its core LLM is organized on multiple levels; and it has broken the idea of thinking (currently under revision for a third time).

Retell the Jack story, but have him find a magic pumpkin in the cave.

Once upon a time, there lived a young man named Jack who lived in a small village. He was known for his bravery and kind heart. One day, a dragon attacked the village and started burning down homes and injuring people. Jack, with his sword in hand, stood up against the dragon and fought with all his might. After a long and tough battle, Jack defeated the dragon and saved the village.

As a reward for his bravery, the villagers presented Jack with a map that led to a secret cave, said to contain a magical pumpkin with immense power. Jack, always up for an adventure, decided to find the pumpkin. After a treacherous journey, he finally arrived at the cave and discovered the magic pumpkin.

He realized that the pumpkin had the power to grant wishes and used it to wish for unlimited bravery and strength, making him the greatest hero the world had ever known. From then on, Jack used his newfound powers to go on many more daring adventures and help those in need, always remembered as the hero with the magic pumpkin.

Notice what ChatGPT did. It combined the first four segments of the story trajectory (Donné, Disturb, Plan, and Execute) in the first paragraph. The first sentence of the second paragraphs contains a much-truncated version of the Celebrate segment, and then Jack undertakes a new Execute segment. For the moment let’s think of the final paragraph as a modified Celebrate segment.

I leave it as an exercise to the reader to note what ChatGPT is doing in the next two versions.

Retell the Jack story, but have him Princess Aurora in the cave.

Once upon a time, there lived a young man named Jack who lived in a small village. Jack was known for his bravery and kind heart. One day, a dragon attacked the village and Jack decided to face it. As he entered the dragon's lair, he was surprised to find Princess Aurora, who had been taken by the dragon.

Jack knew he had to save the princess, but the dragon was not going to give her up easily. With bravery and determination, Jack fought the dragon and after a long and intense battle, he was able to defeat it and save the princess. Princess Aurora thanked Jack for his bravery and kindness, and the two of them returned to the village where the people cheered and hailed Jack as a hero.

From that day on, Jack went on to have many more adventures and helped many more people in need, always remembered as the brave young hero who rescued Princess Aurora from the dragon's lair.

Retell the Jack story, but have him meet Merlin while coming out of the cave.

Once upon a time, there lived a young man named Jack who lived in a small village. Jack was known for his bravery and kind heart. One day, a dragon attacked the village and Jack decided to face it. As he entered the dragon's lair, he fought a long and intense battle and was eventually able to defeat the dragon and save the village.

As Jack was coming out of the cave, he stumbled upon a wise old wizard named Merlin. Merlin was impressed by Jack's bravery and offered to teach him the ways of magic. Jack was eager to learn and spent many years training with Merlin, honing his skills and becoming a powerful wizard in his own right.

From that day on, Jack went on to have many more adventures and helped many more people in need, always remembered as the brave young hero who was trained by the wise wizard Merlin.

Here I direct ChatGPT to make the story longer. I also tell it to “mention” a stray cat. I don’t tell it where or how to add the stray cat. He adds it on at the end, embellishing the idea by making the cat a leader of a group of cats.

Retell that story but make it longer, and mention a stray cat.

Once upon a time, there lived a young man named Jack who lived in a small village. Jack was known for his bravery and kind heart, but he also had a soft spot for animals, especially cats. One day, as he was walking through the village, he came across a stray cat that had been injured. Jack took the cat to a healer and stayed by its side until it had fully recovered.

Not long after, a dragon attacked the village and Jack, determined to protect the people he loved, decided to face it. He entered the dragon's lair, armed with his sword, and what followed was a long and intense battle. Despite being outnumbered, Jack never lost his courage and eventually was able to defeat the dragon, saving the village.

As Jack was coming out of the cave, he stumbled upon a wise old wizard named Merlin. Merlin was impressed by Jack's bravery and offered to teach him the ways of magic. Jack, eager to learn and improve his abilities, spent many years training with Merlin and became a powerful wizard in his own right.

One day, as Jack was on a journey, he came across the stray cat he had rescued years ago. The cat had grown into a magnificent creature and was now the leader of a group of cats who were being threatened by a group of bandits. Jack, not wanting to see any harm come to the cats, used his magic to defeat the bandits and protect the cats.

From that day on, Jack went on to have many more adventures and helped many more people and animals in need, always remembered as the brave young hero who was trained by the wise wizard Merlin and had a special connection with the stray cat.

Connectivity of the amygdala

The future is electric waffles

Peter Thiel’s second thoughts about funding Eliezer Yudkowsky and friends

That’s my speculative and somewhat polemical framing of a middle passage in this video, which presents a talk Peter Thiel recently gave before the Oxford Union. He’s talking about technology stagnation and so on and so forth. About Thiel, from the YouTube description:

Peter Thiel is an American technology entrepreneur and investor. He co-founded PayPal and Palantir, made the first outside investment in Facebook, and has funded companies like LinkedIn and Yelp. Thiel also started the Thiel Foundation, which works to advance technological progress and long-term thinking via funding non-profit research into artificial intelligence, life extension, and seasteading.

At about twenty minutes in (c. 20:07) there’s a striking passage where Thiel talks about a change in attitude that took place about a decade or so into the current millennium. Note that at the beginning when Thiel mentions “getting involved in all these things” that that involvement includes early funding for The Singularity Institute for Artificial Intelligence, which became the Machine Intelligence Research Institute in 2011.

Twenty years ago when I started getting involved in all these things the narrative was still generally a positive utopian it was people thought you know it’s kind of dangerous technology you know. If you build this computer that’s as smart or smarter than any human being in the world in the it’s kind of dangerous, but we’re gonna have to work really hard to make sure it’s friendly, that it’s aligned with humans and it was still sort of circa 2003 whatever misgivings people might have had about biotech or rockets or nuclear power, they did not yet have about AI and the AI narrative was still a generally positive utopian one.

And there’s sort of a strange way where this has completely flipped over the last decade or so. I was involved [with] a thing called The Singularity Institute which pushed a sort of accelerationist utopian technology. We’re progressing, we need to progress faster. We need of course to be a little bit careful and I sort of remember thinking to myself by 2015 I reconnected so many people and it didn’t feel like they were really pushing the AI thing as fast as before and it sort of devolved into you know some kind of escapist Burning Man camp.

You sort of got the sense that it had shifted from transhumanism to Luddite, something Luddite where no actually we want to slow this down. It feels kind of dangerous. It’s kind of a bad thing on net. And this finally this suspicion I think was finally confirmed you can look up on the Internet uh I’m gonna read this. It’s from April 2022 less than a year ago. Eliezer Yudkowsky, who’s one of the sort of thought leaders of the sort of futurist AI. It’s a post from the Machine Intelligence Research Institute and it’s announcing a new “Death with Dignity” strategy and so of the short version of this:

It's obvious at this point that humanity isn't going to solve the alignment problem, or even try very hard, or even go out with much of a fight. Since survival is unattainable, we should shift the focus of our efforts to helping humanity die with with [sic] slightly more dignity.

I want to underscore you don’t deserve to die with a lot of dignity because you’re not going to “try very hard, or even go out with might of a fight.” But it is an extraordinary, it’s an extraordinary way that the context is shifted.

What happened to bring about this shift in attitude? I’m wondering if it was some a failure of nerve. 

In any event we should note that having the business acumen needed to become rich by backing high tech ventures does not imply any deep insight into the future or, for that matter, technology itself. Technology is changing so fast that one can easily become rich on technology that will be obsolete a decade from the time the ink dries on the first check you cash.

Six versions of "Unchain My Heart," a lesson in comparative funkology

It's by Bobby Short. Ray Charles first recorded it in 1961. Here's a live version from 1964. Note the quick tempo:

Here's some local musicians somewhere in the USA about 10 years ago. This version is clearly based on Charles's version, except we don't have backup vocalists and the band is fronted by a woman:

This is the marvelous Sant Andreu Jazz Band five years ago. This version, too, is based on Charles's. The trumpet player does something very hip at the beginning of his solo (1:35), he holds a single note for several seconds:

Continuing in the same vein, Bob Dylan (1986) with Tom Petty and the Heartbreakers, despite the fact that Dylan's vocal instrument can't compare with Charles's the arrangement is much the same:

Here's Hugh "Dr. House" Laurie from nine years ago. What's up with that self-conscious not-quite-ironic tour through the studio? A bit anxious? His version isn't modeled on the Charles original. The tempo is much slower, and the opening verse is very spare. But we've still got back-up vocals and a sax solo:

Finally, one-and-only Grace Kelly completely revises the song, reconceptualizing it for the 21st century with sounds and textures that owe a lot to electronic genres. Grace wails on alto:

I've set up a play list of various versions. You should probably check out one of the Joe Cocker versions. I double-dog dare you to listen to more than 10 seconds of the Trini Lopez version. What a dog! The Lavine version is definitely worth a listen; very gritty vocal. Judging from the names, this is from Eastern Europe somewhere.

Sunday, January 29, 2023

What's Sutan's favorite toy? [Hey, Mr. tambourine man, sing a song for Sutan.]

She shows us at about 04:28:

It's the tambourine. I wonder why?

A cup of cheer

Our robot overlords have landed. They treat us like machines and fire us through email.

Elizabeth Spiers, Layoffs by Email Show What Employers Really Think of Their Workers, NYTimes, Jan. 29, 2023.

Halfway through:

Perhaps the most appalling aspect of termination by email is the asymmetry between what corporations expect of their workers and how they treat them in return. Employees in all kinds of jobs are routinely pressed to give the maximum that they can. In low-wage service jobs that can mean insane, unpredictable hours with no benefits. At higher-paying tech jobs it can mean sacrificing any semblance of a life outside of the office, a requirement that is often justified by high-minded rhetoric about changing the world or the promise of some pot-of-gold reward in an unspecified future.

The expectation that an employee give at least two weeks notice and help with transition is rooted in a sense that workers owe their employers something more than just their labor: stability, continuity, maybe even gratitude for the compensation they’ve earned. But when it’s the company that chooses to end the relationship, there is often no such requirement. The same people whose labor helped build the company get suddenly recoded as potential criminals who might steal anything that’s not nailed down.

At Twitter, where Elon Musk has embraced managerial incompetence as if it’s an emerging art form that requires great creativity, employees were asked to sign a pledge to be “hard core,” working even longer hours and sleeping in the office if necessary. Unsurprisingly, many instead decided to preserve their family lives and self-respect.

For them, this was just the first indignity. Many terminated employees found that their severance offers didn’t materialize for months — and some were called back to work when it turned out the site couldn’t run without them. One employee who early on went to LinkedIn to write “Elon’s my new boss and I’m stoked!” reportedly didn’t make it through the first round of layoffs.

When should you use ChatGPT?

Saturday, January 28, 2023

Being a girl, a geisha, a wife, a mother, and a YouTuber [Kimono Mom]

I talked too much late at night | Q&A

Early in this video, Moe talks about her relationship with Sutan and her philosophy of childrearing. Here is her central insight (c. 02:44):

Rather than trying to figure out how to educate her, I'm trying to treat her as a human being, as an equal.

Think about that, treating her as an equal. What does that mean? Perhaps they're figureing it out together, Sutan and Moe.

The whole video is interesting, but I've quoted a passage starting at about 7:46 where Moe talks about her childhood, being a girl, being married and divorced, and how being a geisha "was the first time I felt proud to be a woman." And that in turn laid the foundation for eventual independence.

I was an office worker when Moto and I got married, but I kept working. I've been in situations before where I wanted to work but wasn't allowed to. That is why I had a strong will to continue working even after marriage.

I was afraid that becoming a housewife would mean losing all social connections. Because I've experienced the daily life where I blame myself for staying at home, not being able to help society, not being able to make money. So I never wanted to go back to being a housewife again.

But as soon as I found out I was pregnant, the morning sickness was so so so bad. I really couldn't walk a step. I was so dizzy all day, I couldn't eat anything. I knew I had to feed the baby, but I was throwing up everything. I couldn't imagine going to work.

And that morning sickness lasted until I gave birth. And I'd hoped to resume work after the baby was born. I did not expect to have to spend all my 24 hours on child care!

Even though I had read and learnt the book when I was pregnant, when I actually tried to hold such a small baby, I was immensely surprised at how hard it was! And while I was raising the baby, I thought, "Oh, I'm back to being a housewife again, I've lost my connection to society."

When I was feeling depressed like that, I met Paolo and learned for the first time that there were people who made YouTube their job. My gut told me I could do it. A week after the shoot with him, I was shooting a video of fried lotus root sandwiches with a single IPhone!

I wanted to work, I wanted to connect with society, and YouTube was the place that made it happen. Because of comments like this from you guys. That's what motivates me now.

Before I met Moto, I took it for granted that I was supposed to serve men. I believed that as a woman, it was the right thing to do to stay one step behind my man. I had been in love and built relationships with those feelings. But, the real me wasn't...

I grew up sandwiched between brothers, and when I was little I wanted to be a boy. Because I thought that girls were more restricted than boys. I hated it when people told me that you're a girl and that I should close my legs or not talk like a boy. My parents educated me and I'm very grateful to them now, but at the time I hated the restrictions they placed on me.

That's why I had always had short cuts, and I hate pink and floral patterns. In fact, I wasn't even good at smiling, because I felt like I was losing when I smiled! Such was my childhood, but as I grew up...

The thing that changed me the most was becoming a geisha. That was the first time I felt proud to be a woman. I don't think it matters anymore whether you are a woman or a man in this day and age. But it was only then that I was able to recognize the feminine in myself. I mean when I was doing that job. Being a geisha is a job, so you are taught manners to talk to your superiors, right? A lot of the things I learned there have been very useful to me now, and I feel very lucky to have been taught when I was a teenager.

I retired from that job and lived in Tokyo, thinking that what I learned as a geisha was common sense. Then when I divorced my ex-husband and had to live on my own. When I was little, I was boyish, and when I was a geisha, I forced myself to be feminine.

Later, I got married, and as a wife I tried to be feminine, and I was expected to be. Then divorced, and I have to live on my own! That meant I had to be emotionally and financially independent. Then, my masculine self was awakened within me again.

Then I hated and got tired of serving men. I couldn't even make my ex-husband happy... There was a time when I thought I'd never marry again, never fall in love again.

That's when I met Moto, or rather, saw him again after about five years. Moto was the only one that didn't create a sense of repulsion in me. Because he had never asked me to be feminine. So from the beginning, it wasn't so much a romantic flirtation, but more like I'd found my best friend, even though we were 18 years apart.

Waiting for the C train

Is the "civilized" world afflicted with “workism”?

Ross Douthat, Is ‘Workism’ Dooming Civilization? Notes on the New Pew Parents Study. NYTimes, Jan. 27, 2023.

Seven paragraphs in:

On the other hand, when you ask them to give weight to professional aspirations versus personal ones, to compare the importance of their kids being “financially independent” or happy in their work to their getting married and having kids, finances and jobs win out easily — by an extraordinary margin, in fact. According to Pew, 88 percent of American parents rate financial success and professional happiness as either “extremely” or “very” important for their kids. Only about 20 percent give the same rating to eventual marriage and children.

I honestly find this result a little difficult to believe. As a normative matter, I can understand rating work and family equally or treating financial independence as the “extremely” important precursor to the “very” important hope of starting a family. But I don’t understand how almost 80 percent of parents (the subset of Americans committed to family formation!) could possibly rate family life — and with it, their own hope of grandkids — as only “somewhat” or “not at all” important for their offspring. These results seem so dramatically at variance with my own experience of parental culture (across lines of class, politics and religion) that I wonder whether some quirk of question design is influencing the numbers. [...]

But if you accept these results and combine them, you get an emphasis on work and finances over family, religion and politics that seems extremely relevant to the debate over the developed world’s declining birthrates. [...]

But the Pew data suggests a way that economic and cultural forces can unite to shape the way that people set priorities for adulthood. It’s possible, in this reading of the evidence, to grow up with the same theoretical aspirations for marriage and family as past generations, but also receive a strong cultural message that everything a different society might regard as fundamentally bigger than your job — religious faith and political ideology as well as love, marriage, kids, grandkids — is actually secondary, and however many children you want on paper, the essence of a valuable adulthood rests in work and money.

One term for this worldview is “workism,” defined by The Atlantic’s Derek Thompson in 2019 as a quasi-religious commitment to fulfillment through intense professional commitment (and discussed at length by Stone and the sociologist Laurie DeRose in a 2021 Institute for Family Studies paper on global fertility).

You can interpret the workist worldview as meritocracy gone wild, its values spreading beyond the overeducated upper class to infuse and convert society as a whole. Or you can interpret it through the lens of Daniel Bell’s famous 1970s analysis of capitalism’s “cultural contradictions” — as an example of consumer capitalism’s logic working itself out to an ultimately self-undermining conclusion (because without marriages and kids there won’t be enough consumers soon enough).

Wake Up!

Friday, January 27, 2023


H/t Tyler Cowen.

How about a nice fog picture

Taking stock of your life, backstage, who's more nervous? [Kimono Mom]

Starting at c. 0:28:

Moe: This is Mr. Nakajima the head of KUDEN. KUDEN is a stage where you can talk about your life experiences in 15 minutes. Many famous Japanese executives have spoken at KUDEN in the past. It was my first time to even give a speech so I practice with his help for a month. In this meeting he asked me about my past experiences. About my childhood, when I was Maiko(Geisha), my first marriage, remarriage, childbirth...Actually I haven't had much time to look up on my life so far. But I realized this is a very important work for the rest of my life.

Nakajima: Tell me more inside of your mind. The thing you said that stuck with me the most was.."A lifetime is too short to truly love someone, so try your best to cherish the person being with you. And that there are always key people at the crossroads of your life who can give you advice."

Moe: That's what I realized again when I was talking to you today.

About 9:57:

Moto: "You did it!"


Moe: "How was it?"

I was so nervous that as I was speaking, my hand froze in front of my chest like this, and I kept thinking about when to move it!

Moto: Yeah, all the while, you seemed to be wondering how to move your hands"

Moe: I read in a book that people who are good at giving speeches move their hands naturally like this while speaking, but I was so nervous that my hands froze! But I was thinking from start to finish that it was strange to have my hands frozen like this!

And then.. The speeches were mostly about things I had never told anyone before, so people who saw them might be surprised. It took a lot of courage for me to tell this story because I don't think I am who you imagine me to be.

So I'm a little scared of your reaction, but let me know what you think. I'm glad I could share with you guys my life so far.

Moto: It was good opportunity for you. Good job, Moe!

Moe: Thank you for your support, Moto. We did it. Cheers!

Here's the speech she gave.

Beyond ChatGPT: The return of secretaries, in the fullest sense [my mother worked as a secretary]

Hollis Robbins, Secretary jobs in the age of AI, guesting in Noahpinion, Jan. 17, 2023.

Opening paragraphs:

The ‘secretary’ literally means ‘person entrusted with secrets,’ from the medieval Latin secretarius, the trusted officer who writes the letters and keeps the records. The secretarial role originally conceived was far more central than roles with the “assistant” title now standard. In the nineteenth century, the secretary was a prized role for young men: a diplomatic assistant, the overseer of correspondence, the superintendent of the files, and in many cases, an apprentice manager—well-positioned to learn at the elbow of the man in charge, someday to be the man in charge. The invention of stenography machines and commercial typewriters at the end of the century transformed the business world. Dozens of secretarial schools were established, most famously, the Katharine Gibbs schools, “the Harvard of secretarial education.”

Training for high paid secretarial roles in the mid-20th century was rigorous: a fifty hours-per-week workload to learn typewriting, stenography, business and social correspondence, organizational systems (office filing, business archives, inventory management, taxes), budgeting and finance, and social conventions. Top secretaries were expected to understand municipal administration, the relationship of business to government, local party politics. Cultural competence was critical. Art and music appreciation classes were required, as well as English literature (and grammar), and tasteful behavior (how to adjust a hat, how to greet guests, how to hold a cocktail in a crowded room).

Secretarial jobs propelled millions of 20th century women into financial independence, whether they spent their career in the role or advanced into management or executive positions.

Here’s what a skilled secretary can do:

  • Reviews and processes 90% of your email;
  • Has a working relationship with all of your colleagues, your direct reports, your customers, your external stakeholders, and your immediate family;
  • Embodies and models organizational norms and culture: intensity (high or low), formality (high or low), professionalism (presumably high).
  • Organizes/files all correspondence and key documents methodically;
  • Organizes and rearranges your calendar according to changing priorities;
  • Tactfully communicates delays, postponements, cancellation of meetings;
  • Ensures your preferences in travel, accommodation, entertainment, dining;
  • Remembers birthdays and anniversaries; suggests gifts;
  • Serves as a sounding board; advises caution when appropriate;
  • Keeps secrets.

The numbers?

Consider an executive earning $1.5 million per year. A secretary earning $120,000 who works for one executive alone needs to save that boss only 5 hours of a 60-hour work week (8% more productive) to make the numbers work.

How do we train the new generation of secretaries we badly need?

Like many in higher education leadership, I’m concerned about ChatGPT but I’m more concerned about student readiness, the decline of corporate training programs, and the general economic future for college graduates, particularly in the humanities. I wonder about the role colleges and universities could play in training students to practice skills that AI can’t deliver and that employers value—how to show up early, how to deliver bad news, how to give and accept criticism, how to deal with an office visitor the team leader does not want to see, how not to be flaky, how to organize files, how to handle confidential information, and most importantly, how to write and answer emails promptly, swiftly, briefly, and with tact. These skills cannot be automated, cannot be outsourced, and may provide a competitive edge to businesses that value them. The first step is to put the position on the org chart and value it.

There’s more at the link.

Friday Fotos: An eclectic mix from the last few weeks [cosmos|hallucinated city]

How the chatster conjured up a fake citation, step by step

Thursday, January 26, 2023

How about a nice mug

Japan is changing, female employment increasing [Kimono Mom]

Noah Smith has an interesting article about how Japan has changed since the 1990s, Actually, Japan has changed a lot (Jan 24). He’s responding to an essay by Rupert Wingfield-Hayes, a British journalist who argued that Japan is mired in “stagnation and crisis” (Smith’s words). He acknowledges that, yes, there are problems. In particular, Japan seems to be gerontocracy. It’s not only that the population is aging, but that the political leadership is old (Wingfield-Hayes) and so is corporate leadership (Smith).

Smith points out that “Japan builds and builds and builds,” that Tokyo “is actually much more beautifully manicured than when I first saw it two decades ago,” and new buildings abound. Rent is affordable, housing costs are falling, and the size of the average person’s home has more than doubled between 1963 and 2013 in Tokyo Prefecture.

Moreover, fertility is up, there are more immigrants – Umm, err, What does this have to do with Kimono Mom? – and Tokyo is now an international city: “1 out of 8 people turning 20 in the city proper wasn’t born in the country.” And here we are:

Yet another example is the role of women in the workforce. Wingfield-Hayes rightfully dings Japan for not having enough women in corporate management, but neglects to mention that the percentage increased from 11% to 15% during his time there — not a massive social transformation, but not a picture of stasis either.

And this was accompanied by a large-scale movement of women into the workforce, such that Japan’s female employment rate now exceeds America’s.

Moe, Kimono Mom, is one of those women, no? And Sutan? What will she be doing in 20 years?

Good morning

Louis Armstrong and the Snake-Charmin’ Hoochie-Coochie Meme

Another bump to the top, this time (Jan. 26, 2023) to acknowledge the examples appended to the end.

* * * * *

Another "old time good one", as Pops used to say. This is about a little tune I learned as a kid, but which might well be hundreds of year old, if not even older. And I'm now (August 2016) bumping this to the top of the queue because I'm about write about my early education in jazz,
Some years ago I was looking for a way to open the final chapter of a book I was writing about music, Beethoven’s Anvil: Music in Mind and Culture. The chapter was to be a quick tour of black music in 20th Century America, starting with jazz and blues and ending with hip-hop. So, I thought and thought and, finally, an idea crept up on me.

I had this book of Louis Armstrong trumpet solos that I’d been practicing ever since my early teens. The solos had been transcribed from recordings Armstrong had made in the late 1920s and had been circulating ever since, all under copyright, naturally. These were classic Armstrong: “Cornet Chop Suey,” “Struttin’ with some Barbecue,” “Gully Low Blues,” “Muggles” (nothing to do with Harry Potter, muggles was Armstrong’s favorite inhalent, the one that President Bill Clinton never took into his lungs) and a few others. One of those others was called “Tight Like This” – an open-ended title that asked you to use your imagination. During his improvisation in “Tight Like This” Armstrong quoted a certain riff, not once, but twice.

How did I know it was a quotation? Because I was familiar with the riff from other contexts. For one thing, it showed up in cartoons, often to accompany a snake charmer, but also as general all-purpose Oriental mystery music. For another, I knew it as a children’s song that me and by buddies used to sing, with lyrics to the effect that the girls in France didn’t wear underpants – hotcha! But how did Armstrong know this tune? He recorded “Tight Like This” in 1928, the same year that Walt Disney produced “Steamboat Willie,” generally regarded as the first cartoon with a fully synchronized soundtrack. So Armstrong’s recording predated the tune’s use in cartoon soundtracks. Did he learn it as a kid growing up on the streets of New Orleans?

I made a few phone calls, sent some emails to friends, queried a trumpeter’s listserve (sponsered by TPIN, Trumpet Players’ International Network), and information began trickling in. In the first place, other people remember this tune from their childhoods. One Eric Johnson. from the TPIN list, told me that his daughters remember these lyrics:
All the girls in France do the hokey pokey dance,
And the way they shake is enough to kill a snake.
Karen Stober, also from TPIN, tells me the tune was sung by two children facing one another and clapping hands to the lyrics:
On the planet Mars all the women smoke cigars.
Every puff they take is enough to kill a snake.
When the snake is dead they put flowers on its head.
When the flowers die they say 1969! [whatever year it is].
We’ve moved from France to Mars, but there’s that snake again, and now we’ve got cigars – a regular Freudian wonderland of sub-rosa implication. What fun. I found a somewhat fuller version on the web where the dance was characterized as a “hookie-kookie dance.”

I then followed a lead from my friend, David Bloom, who suggested I check out the 1893 Chicago World’s Columbian Exposition. It was a major event in American cultural life. It was the first large-scale use of AC electricity, and the first Ferris wheel. The exposition hosted delegations from all over the world, including Japan, the first chance Americans had to experience that nation and its people – who were here, of course, to learn about us as well. This is when and where hamburgers became all-American fast food; Pabst Blue-Ribbon Beer flowed freely on the midway; Kellogs Cornflakes debuted here as well. And, wouldn’t you know it? Elias Disney, Walt’s father, was a carpenter on the construction job. But all this is beside the point.

The point is about the entertainment on the midway. Yes, we had Wild Bill Cody, and we had John Philip Sousa. But we also had a lithe young woman who danced as “Little Egypt.” The exposition’s press agent, Sol Bloom, claimed that he had written our little tune just so Little Egypt could dance to it. The tune was a hit and was subsequently copyrighted under various names, including Dance of the Midway, Coochi-Coochi Polka, Danse de Ventre, and The Streets of Cairo. Just how it was copyrighted several times is a bit of a mystery, but the fact that several folks claimed it as their own testifies to the tune’s popularity. One of those folks, W. J. Voges, included it as the Koochie-Koochie Dance in the second edition of Pasquila Medley published in New Orleans in 1895. We’ve now got the tune in New Orleans at a date prior to Armstrong’s birth.

Wednesday, January 25, 2023

Grace Kelly can unchain my heart anytime anywhere

Let's remember April [cherry blossoms, leaves, and wires]

There’s truth, lies, and there’s ChatGPT [Realms of Being]

ChatGPT has no sense of ground truth. It will make things up. I ran into that problem when I asked it to summarize Heart of Darkness. At one point I began to quiz ChatGPT about an incident that happened a few hours before they reached their destination, the so-called Inner Station. They were navigating in fog when they were attached from shore. It took me a couple of questions to get that out of ChatGPT and a couple more for me to get it to admit that the boat’s helmsman was struck by a spear:

What happened after the helmsman was struck by a spear?

After the helmsman is struck by a spear, Marlow and his crew are forced to stop and make repairs to the steamboat. They are also forced to navigate the remaining stretch of the river without a helmsman, which makes the journey more difficult and dangerous. Marlow is deeply affected by the death of the helmsman, and it serves to reinforce his growing realization of the darkness and evil that lies at the heart of the colonial enterprise. The attack also serves to underscore the danger and harshness of the environment that Marlow and his crew are navigating, as well as the hostility of the native people towards the European colonizers.

No, they didn’t stop to make repairs. That little bit of confabulation is typical, happening time and again.

But, yes, Marlow was affected by the helmsman’s death. The last half of ChatGPT’s statement – starting with “and it serves...” – is boilerplate that it serves up at every opportunity.

That brings me to a comment that Arnold Kling made about a conversation he had with Alex Tabarrok:

We speculate that one path for improving the quality of ChatGPT will be for bots to argue with one another, just as computers improved in chess by playing games against one another. Of course, the evaluation function for a disagreement is not as simple as that for chess. Right now, humans are involved in “reinforcement learning.” But if some of that work can be automated, the bots will learn much more quickly. I predict that this will happen, and that within a year ChatGPT will no longer be hallucinating.

I think it would be somewhere between at least interesting and great to have to have bots argue. But I doubt that that will eliminate “hallucinating.” If none of the bots have a secure sense of ground truth – which they don’t – arguing with each other isn’t going to allow it to magically arise out of nothing.

Realms of Being

But ChatGPT certainly does recognize different realms of being, if you will. That’s worth investigating. As you may know, I’ve been exploring its story-telling capabilities by asking it to create a new story based on an old one. I’ve been using a story about princess Aurora and a dragon in many of these “experiments.” I ask ChatGPT to change the protagonist in the new story and to “make any other changes you wish.”

In one case I asked ChatGPT to change Aurora into a giant chocolate milkshake. I had no idea what it would do, but it was happy to do it. It did what I asked, and something more. Here’s a paragraph from the original story and the corresponding paragraph from the derived story:

[Original] One day, a terrible dragon came to the kingdom and began to terrorize the people. The dragon was fierce and powerful, and none of the knights or soldiers were able to defeat it. The people lived in fear, not knowing what to do.

[Derived] One day, a terrible heatwave came to the kingdom and began to melt all the desserts. The heat was fierce and powerful, and none of the ice cream or cakes were able to withstand it. The people lived in fear, not knowing what to do.

Notice that the dragon became a heatwave and the knights and soldiers became ice cream or cakes.

Then I asked it to change Aurora into a colorless green idea. Here’s ChatGPT’s response:

I'm sorry, but the concept of a "colorless green idea" is a nonsensical phrase that was invented as an example of a phrase that would be grammatically correct but semantically meaningless. It is not possible to create a story about a "colorless green idea" as it does not have any physical properties or characteristics that can be used in a story.

ChatGPT drew a line. Giant chocolate milkshakes make fine protagonists, but colorless green ideas are beyond the pale. Yet in an earlier session it was fine with colorless green ideas in the context of a short poem, “Alizarin Crimson,” by John Hollander:

Does this make sense: Curiously deep, the slumber of crimson thoughts: While breathless, in stodgy viridian, Colorless green ideas sleep furiously.

The sentence you provided, "Curiously deep, the slumber of crimson thoughts: While breathless, in stodgy viridian, Colorless green ideas sleep furiously," is grammatically correct and has a clear meaning. The sentence is a series of phrases and clauses that describe the sleeping habits of "colorless green ideas." It uses vivid imagery and figurative language to create a sense of mystery and intrigue. While the sentence may not be typical or straightforward, it does make sense and is effective at conveying a particular mood or atmosphere. Is there anything else you would like to know?

What makes “colorless green ideas” acceptable in one context, but not another?

I don’t know. But at this point we seem to have two realms of being, Stories and Poems. Things which are acceptable in one are not acceptable in another.

Cartoons as a realm of being

More recently I asked ChatGPT about the controversy over just who wrote Shakespeare’s plays. After a couple of questions about real proposals that have been made, e.g. the Earl of Oxford, Queen Elizabeth I, I decided to get surreal:

Could Bullwinkle J. Moose have written Shakespeare’s plays?

Bullwinkle J. Moose is a fictional character from the animated television series "The Rocky and Bullwinkle Show" and it is highly unlikely that he could have written Shakespeare's plays.

The main reason that Bullwinkle J. Moose could not have written Shakespeare's plays is that he is a cartoon character and did not exist during the time that Shakespeare's plays were written. Moreover, Shakespeare's plays are considered masterpieces of literature and are known for their complexity and sophistication in terms of language, characters, and themes. It is unlikely that a cartoon character would have the educational background, knowledge, and talent needed to write such works.

It is important to remember that the question of who wrote Shakespeare's plays is a serious one and there are many theories, but none of them have been conclusively proven. While alternative authorship theories, such as the ones proposed by the Earl of Oxford or Queen Elizabeth I have been proposed, they are not accepted by the majority of scholars and experts in the field, and there is little to no credible evidence to support them.

In conclusion, Bullwinkle J. Moose could not have written Shakespeare's plays as it is a fictional cartoon character and it is highly unlikely that he would have the knowledge and skills to write such complex and sophisticated works.

That’s a very interesting answer. But wouldn’t it have been sufficient to say that Bullwinkle was a cartoon character and, as such, could not affect events in the real world? Isn’t it a bit odd to assert that a cartoon character wouldn’t have the necessary background? That almost implies that, if the character had had the background, maybe, just maybe, it could have written Shakespeare’s plays. Oh, I forgot, Bullwinkle didn’t exist at the right time.

Let’s give it another go:

What about the Man in the Moon, or the cow that jumped over the moon? Could they have written Shakespeare’s plays? Maybe taken dictation?

The Man in the Moon and the cow that jumped over the moon are both fictional characters from nursery rhymes, and it is extremely unlikely that they could have written Shakespeare's plays.

Like Bullwinkle J. Moose, the Man in the Moon and the cow that jumped over the moon are not real entities and didn't exist during the time that Shakespeare's plays were written. Furthermore, they are not known to possess any human-like characteristics or abilities such as writing plays.

It is important to keep in mind that the question of who wrote Shakespeare's plays is a serious one, and while alternative authorship theories have been proposed, they have not been conclusively proven and lack credible evidence. It is important to consider the evidence and arguments put forward by experts in the field, rather than entertaining fanciful or far-fetched ideas.

In conclusion, the Man in the Moon or the cow that jumped over the moon could not have written Shakespeare's plays as they are fictional characters and do not possess the characteristics necessary to write such works.

Same thing. Same concern with predicates.

Let’s shift to another venue.

The kimono post [Kimono Mom]

Though we think of the kimono as somehow symbolic of (traditional) Japan, very few Japanese women wear them regularly – sometimes on special occasions once or twice a year, but that’s it. A decent silk kimono is also expensive, $2000 or so, and the price can climb into six figures for elaborate ones.

Kimono, however, are standard dress for geisha. Thus Moe has quite a collection of them – in some of the videos you can see a chest with wide shallow drawers for storing her kimonos. I assume she has kimonos appropriate for all seasons and of various levels of formality as appropriate to the occasion.

What Are The 4 Differences Between KIMONO & YUKATA? When & How The 13 Types of Kimono Are Worn

13 Types!

At 6:58: “Kimono dresser is a national qualification approved by the ministry of health labor and welfare. In order to apply for the first class qualification it takes at least five years of work experience.”

5 years!

From the YouTube description:

I know that many people around the world who are hoping to travel to Japan someday, have “wear a kimono” on their to-do list. Kimono are a traditional kind of Japanese clothes, and its colors and designs are very beautiful.

But, have you ever heard of “yukata?” They are often worn by young boys and girls at summer festivals, or at ryokan style hotels. When you take a look at the two… they look almost identical. But, how are they different?

So today, as a man wearing kimonos almost everyday and has a wife training in kimono dressing, I will explain about the 4 main differences between kimono and yukata. At the end of the video, I will briefly explain about the 13 kinds of women’s Japanese traditional clothes too, so I hope you can stick around till the end.

0:00 Let's START!
1:34 1. When they are worn
3:59 2. What they are made from
5:06 3. What you wear together with them
6:33 4. How to wear them
7:44 The 13 different kinds of kimono
10:22 Today’s conclusion
12:40 “Omake” talk

FINALLY😭💓Sutan wears a Kimono!|Christmas Miracle|Roast Beef Recipe

Moe and Moto had gotten a kimono for Sutan for her first Shichi-Go-San, but she was unwilling to wear it at that time. By Christmas, though, she was ready.

From Wikipedia:

Shichi-Go-San (七五三, lit. 'seven-five-three') is a traditional Japanese rite of passage and festival day for three- and seven-year-old girls, five-year-old and sometimes three-year-old boys, held annually on November 15 to celebrate the growth and well-being of young children. As it is not a national holiday, it is generally observed on the nearest weekend.

How to wear Kimono [Kimono Mom]

Azumanga Daioh Episode 14 Subbed - The Ocean Kimonos And Party

Azumanga Daioh is one of my favorite anime series. The series follows six school girls and two of their teachers on their daily lives. In this episode the group goes to a summer home on the beach. It belongs to the (wealthy) family of Chiyo Mihama, who is a prodigy and thus smaller than the others. 

They’ve all brought summer kimonos to wear to a summer festival. But only Chiyo-chan and Sakaki know how to put a kimono on (c. 14:21). The teachers don’t and are embarrassed that their students have to show them how to dress. At about 15:48 we see them going to the festival in their kimonos.

Tuesday, January 24, 2023

Just so you know, GPT's Chatster is not the only game in town

Bacon, butter, and lingonberries

A high-performance speech neuroprosthesis

Abstract of the article linked above:

Speech brain-computer interfaces (BCIs) have the potential to restore rapid communication to people with paralysis by decoding neural activity evoked by attempted speaking movements into text1,2 or sound3,4.Early demonstrations, while promising, have not yet achieved accuracies high enough for communication of unconstrainted sentences from a large vocabulary1–5. Here, we demonstrate the first speech-to-text BCI that records spiking activity from intracortical microelectrode arrays. Enabled by these high-resolution recordings, our study participant, who can no longer speak intelligibly due amyotrophic lateral sclerosis (ALS), achieved a 9.1% word error rate on a 50 word vocabulary (2.7 times fewer errors than the prior state of the art speech BCI2) and a 23.8% word error rate on a 125,000 word vocabulary (the first successful demonstration of large-vocabulary decoding). Our BCI decoded speech at 62 words per minute, which is 3.4 times faster than the prior record for any kind of BCI6 and begins to approach the speed of natural conversation (160 words per minute7). Finally, we highlight two aspects of the neural code for speech that are encouraging for speech BCIs: spatially intermixed tuning to speech articulators that makes accurate decoding possible from only a small region of cortex, and a detailed articulatory representation of phonemes that persists years after paralysis. These results show a feasible path forward for using intracortical speech BCIs to restore rapid communication to people with paralysis who can no longer speak.