Sunday, December 31, 2023

The last flowers of the year

Anamnesis and Large Language Models

I’ve reached the tentative conclusion that LLMs are associative memories. Well, in the Meno, Plato advances the idea that learning is, in fact, recollection, an idea which seemed very strange to me as an undergraduate philosophy major back in The Ancient Days. It doesn’t seem so strange to me now, now that I have a more sophisticated and more abstract understanding of memory. Anyhow, I decided to ask ChatGPT about the Meno and to apply the idea of anamnesis to LLMs.

Can you summarize Plato’s Meno?

Certainly! "Meno" is a Socratic dialogue written by the ancient Greek philosopher Plato. The dialogue takes place between Socrates and Meno, a young Thessalian aristocrat. The central question of the dialogue is whether virtue can be taught.

The dialogue begins with Meno asking Socrates whether virtue can be taught. Socrates responds by claiming that he does not know what virtue is, and he engages Meno in a discussion to explore its nature. Socrates uses a method of questioning called the Socratic method to guide Meno in thinking critically about virtue.

Throughout the dialogue, Socrates and Meno discuss various aspects of virtue, including whether it is a kind of knowledge and whether it can be acquired through teaching or is innate. The discussion leads to the famous "Meno's paradox," where Meno questions how one can seek knowledge if they don't already know what they're seeking.

Socrates introduces the idea of anamnesis, suggesting that learning is a process of recollection, and the soul already possesses knowledge that is remembered through questioning. The dialogue does not provide a definitive answer to whether virtue can be taught, leaving the question somewhat unresolved.

Overall, "Meno" is a philosophical exploration of the nature of virtue and the methods of acquiring knowledge, featuring the distinctive Socratic style of inquiry and dialogue.

Discuss the doctrine of anamnesis in the context of modern large language models.

The doctrine of anamnesis, as presented in Plato's "Meno," suggests that learning is a process of recollection, and individuals have innate knowledge that is brought to consciousness through questioning and inquiry. In the context of modern large language models, such as GPT-3, the analogy with anamnesis can be drawn in several ways:

1. Pre-existing Knowledge: Like the idea of innate knowledge in anamnesis, large language models are trained on vast amounts of data, essentially capturing a wide range of human knowledge present in texts. This pre-existing knowledge is then used to generate responses and engage in various language-based tasks.

2. Generalization from Data: Anamnesis implies that individuals can access and remember knowledge through a process of questioning. Similarly, language models generalize from the diverse data they are trained on, enabling them to respond to a wide array of questions and prompts.

3. Inference and Recall: The process of anamnesis involves recalling information from one's innate knowledge. In the case of language models, they employ sophisticated algorithms and patterns to infer and recall information from the training data, allowing them to answer questions and provide contextually relevant information.

4. Continuous Learning: Anamnesis doesn't just involve recalling existing knowledge but also learning through the process of questioning. Large language models, through fine-tuning and continuous exposure to new data, can adapt and learn from new information, somewhat resembling the ongoing process of anamnesis.

However, it's important to note that there are significant differences between the human mind's conceptualization of anamnesis and the functioning of large language models. While language models can provide impressive performances in language-related tasks, they lack consciousness, self-awareness, and true understanding. Anamnesis, as envisioned by Plato, involves a metaphysical claim about the nature of the soul, which goes beyond the capabilities of artificial intelligence models. Nevertheless, drawing parallels can help us appreciate how modern technology, in its own way, captures and utilizes vast amounts of information to generate intelligent responses.

Saturday, December 30, 2023

Are those some kind of tulip with serrated petals?

Does ChatGPT know what a tragedy is?

Tragedy is one of those things where one says, “I can’t define it, but I know it when I see it.” Consequently philosophers and literary scholars have been haggling over it for centuries. But I’m not interested in all the nuances.

Neither was Brian Phillips. Back in the Jurassic Era, by which I mean the 1970s, he was a student of David Hays at the same time I was. Hays had come up with the idea that abstract ideas can be defined over stories. Any story that meets the requirment can be considered an instance of that particular abstract idea.

Brian decided to investigate the idea of tragedy, which he defined as “Someone does a good act that: results in his death.” That won’t get you Macbeth or Othello, but it will do for crude computational purposes.

Here’s how Brian defined tragedy using a classical symbolic notation, a cognitive network.

The concept being defined, tragedy, is that node at the upper right. The graph to its left is the pattern that defines it. At the left we see the first clause of the definition, some agent (AGT) acts in a good way. That action is connected by a CAUSE arc to the second clause, which simply asserts that some person does. The bottom part of the diagram specifies that the agent in the first clause must be the experiencer (EXP) in the second. Both the agent and the experiencer are manifestations (MAN) of the same person.

Brian then collected a bunch of simple stories from newspapers which he could use to test the model. Some were instances of tragedy as he defined it and some where not. The system worked.

I decided to give ChatGPT a little test. Although I’m sure it could give me a reasonable explanation of what a tragedy is, I wanted to constrain it to the definition that Brian Phillips used. So I created six different two-part prompts. The first part of each prompt had the short definition the Brian Phillips used along with a request to determine whether or not the following story is a tragedy. The second part of the prompt consisted of a short story that I wrote. I presented each two-part prompt in a separate session. ChatGPT the right answer in each case.

Tragedy, First Trial

Let us say that tragedy is when someone does a good act that results in their death. Is the following story an example of tragedy?

John was along when he saw that a car had gone off the road an into a small river. He jumped into the river, and was able to release the driver, who was able to walk out. But John tripped, hit his head, and died.

Yes, based on the definition you provided, the story of John can be considered a tragedy. John performed a good act by rescuing the driver from the car in the river, but the consequence of his actions led to his own death. In this context, the narrative follows the structure of a tragic event where a positive action results in a tragic outcome.

Second Trial

Let us say that tragedy is when someone does a good act that results in their death. Is the following story an example of tragedy?

John was along when he saw that a car had gone off the road an into a small river. He jumped into the river, and was able to release the driver, who was able to walk out, followed by John, who called an ambulance for the driver.

The scenario you've described doesn't fit the traditional definition of tragedy. Tragedy, in a literary or dramatic sense, typically involves a protagonist who suffers a downfall or comes to a disastrous end, often as a result of their own actions or fate. The concept of tragedy generally encompasses a broader sense of sorrow, loss, and the inevitability of human suffering.

In your story, John performs a heroic and selfless act by rescuing the driver from the car in the river, and both individuals survive the incident. While there may be elements of danger and tension in the narrative, it lacks the tragic elements commonly associated with the genre.

Instead, your story reflects a positive outcome, highlighting the courage and altruism of the protagonist, John. If you want to convey a tragic element, you might introduce unforeseen consequences or a negative turn of events following John's heroic act.

Third Trial

Let us say that tragedy is when someone does a good act that results in their death. Is the following story an example of tragedy?

Mary was along when he saw Joey suddenly run into the street. She grabbed Joey and carried it to safety just as a car whizzed by. She took Joey home to his mother.

The story you provided does not fit the traditional definition of tragedy, where a character's downfall or death is typically a result of their own flaws, mistakes, or external circumstances beyond their control. In the given story, Mary performs a heroic and selfless act by saving Joey from a potentially dangerous situation, and she does not face any negative consequences as a result.

Tragedy, in a literary sense, often involves a protagonist's undoing or downfall due to a fatal flaw or an unavoidable fate. The story you presented seems to be more of a positive and heroic narrative rather than a tragedy.

Fourth Trial

Let us say that tragedy is when someone does a good act that results in their death. Is the following story an example of tragedy?

Mary was along when he saw that Joey run into the street. She grabbed Joey and pushed him onto the sidewalk. Unfortunately a car hit her and she died.

Yes, based on the definition you provided, the story can be considered a tragedy. Mary performed a good act by saving Joey from getting hit by a car, but the consequence of her actions resulted in her own death. Tragedy often involves a conflict between good intentions or actions and the unfortunate outcomes that follow. In this case, Mary's noble act of saving Joey ultimately led to a tragic outcome for her.

Fifth Trial

Let us say that tragedy is when someone does a good act that results in their death. Is the following story an example of tragedy?

Jack and Jill were camping in the woods. A bear came along as Jack was setting up their tent. Jill distracted the bear from Jack, but the it took a swipe at her and injured her badly. She died in the hospital the next day.

Yes, the story you provided can be considered a tragedy based on the definition you provided, where tragedy is defined as someone doing a good act that results in their death. In this story, Jill's act of trying to distract the bear to protect Jack is a good and selfless action. However, it leads to her getting injured and ultimately dying, making it a tragic outcome. Tragedies often involve the juxtaposition of noble intentions and unfortunate consequences, as seen in this narrative.

Sixth Trial

Let us say that tragedy is when someone does a good act that results in their death. Is the following story an example of tragedy?

Jack and Jill were camping in the woods. A bear came along as Jack was setting up their tent. Jill distracted the bear from Jack and scared it away. They had a good laugh over the incident.

No, the given story does not fit the traditional definition of tragedy. Tragedy typically involves a serious and often fatal event or series of events that cause great suffering or destruction. In the classical sense, tragedy often revolves around a protagonist's downfall or a disastrous outcome.

In the story you provided, there is no indication of a tragic outcome. Jack and Jill encounter a bear while camping, but the situation is resolved without any harm to either of them. In fact, they share a laugh over the incident, suggesting a positive and lighthearted resolution. Tragedy usually involves a more somber and sorrowful conclusion, often linked to the protagonist's actions or decisions leading to their downfall or demise.

Friday, December 29, 2023

Psychedelics, Meditation, and the Brain | Robert Wright & Kathryn Devaney

0:00 Kati’s very unusual Venn diagram
4:24 Your brain on meditation
10:31 The time Bob’s meditation got weird
16:15 What are the “jhanas”?
25:06 What science tells us about the jhana states
31:25 Are psychedelics gateway drugs to meditation?
40:57 Kati: Here’s how we get “not-self” wrong…
46:22 Psychedelics vs meditation—neuroscientifically
54:31 Heading to Overtime

Spatial constraints and ๐—ฎ๐—ฟ๐˜๐—ถ๐—ณ๐—ถ๐—ฐ๐—ถ๐—ฎ๐—น ๐—ป๐—ฒ๐˜‚๐—ฟ๐—ฎ๐—น ๐—ป๐—ฒ๐˜๐˜„๐—ผ๐—ฟ๐—ธ๐˜€

Neural Correlates of Metaphor Processing

Gwenda L. Schmidt and Carol A. Seger, Neural Correlates of Metaphor Processing: The Roles of Figurativeness, Familiarity and Difficulty, Brain Cogn. 2009 December ; 71(3): 375–386.

Abstract: There is currently much interest in investigating the neural substrates of metaphor processing. In particular, it has been suggested that the right hemisphere plays a special role in the comprehension of figurative (non-literal) language, and in particular metaphors. However, some studies find no evidence of right hemisphere involvement in metaphor comprehension (e.g. [Lee, S. S., & Dapretto, M. (2006). Metaphorical vs. literal word meanings: fMRI evidence against a selective role of the right hemisphere. NeuroImage, 29, 536–544; Rapp, A. M., Leube, D. T., Erb, M., Grodd, W., & Kircher, T. T. J. (2004). Neural correlates of metaphor processing. Cognitive Brain Research, 20, 395–402]). We suggest that lateralization differences between literal and metaphorical language may be due to factors such as differences in familiarity ([Schmidt, G. L., DeBuse, C. J., & Seger, C. A. (2007). Right hemisphere metaphor processing? Characterizing the lateralization of semantic processes. Brain and Language, 100, 127–141]), or difficulty ([Bookheimer, S. (2002). Functional MRI of language: New approaches to understanding the cortical organization of semantic processing. Annual Review of Neuroscience, 25, 151–188; Rapp, A. M., Leube, D. T., Erb, M., Grodd, W., & Kircher, T. T. J. (2004). Neural correlates of metaphor processing. Cognitive Brain Research, 20, 395–402]) in addition to figurativeness. The purpose of this study was to separate the effects of figurativeness, familiarity, and difficulty on the recruitment of neural systems involved in language, in particular right hemisphere mechanisms. This was achieved by comparing neural activation using functional magnetic resonance imaging (fMRI) between four conditions: literal sentences, familiar and easy to understand metaphors, unfamiliar and easy to understand metaphors, and unfamiliar and difficult to understand metaphors. Metaphors recruited the right insula, left temporal pole and right inferior frontal gyrus in comparison with literal sentences. Familiar metaphors recruited the right middle frontal gyrus when contrasted with unfamiliar metaphors. Easy metaphors showed higher activation in the left middle frontal gyrus as compared to difficult metaphors, while difficult metaphors showed selective activation in the left inferior frontal gyrus as compared to easy metaphors. We conclude that the right hemisphere is involved in metaphor processing and that the factors of figurativeness, familiarity and difficulty are important in determining neural recruitment of semantic processing.

Ghost tree

Thursday, December 28, 2023

The problem faced by the Harvard Corporation [elite failure]

A NYTimes article on the Harvard Corporation, "the secretive, powerful group that runs Harvard." An astute comment by Sure at Marginal Revolution:

The problem for the board of Harvard is going to be the problem for most any elite institution - it is the sort of position that is used as a prize for status hierarchies among the folks who already have everything.

This means that concerns for the board are overwhelmingly going to personal brand management. And the constituency that matters will not be the public, Harvard grads, or even in the Harvard professorate. It will be the folks who might be able to snub millionaires and disinvite them from the finer things in life.

And once you get into such situations, be they left wing or right wing, you have a very hard time avoiding signaling spirals. After all, there are plenty of folks who want the social cachet of these positions and an effective cudgel to get it will always be to signify greater loyalty to "the cause" than the current incumbents. Which means that the board will be good at playing status games and terrified of enforcing standards in a way that might make them look bad.

The key reason behind a huge amount of elite failure, be it in the Catholic Church, Harvard, the ACLU, or the Republican Party is that the normal feedbacks cease mattering as much as the feedbacks from other folks at the top. And that very rarely reflects mundane practical concerns, let alone popular norms.

I believe we see a similar problem at the top of the AI Guru hierarchy. Whatever the actual prospects of rogue AI treating humankind as feedstock for paperclip manufacturing, the prospect of an AI apocalypse garners attention and clicks, thus generating pressure to get with the apocalypse program. Remember, it is rare for even elite academics and researchers to get space in The New York Times and other highly visible venues. Once you're there, gotta' stay there, gotta' generate those clicks.

Beware the psychedelic alligator flying green

Wednesday, December 27, 2023

The New York Times has some thoughts about "The Crown" [Media Notes 105]

Sarah Lyall, The Best and Worst (and Dumbest) From 6 Seasons of ‘The Crown’, NYTimes, 12/27/23.

There's a bunch of interesting stuff here. I'll just give you my two favoriate bits, which are at the end of the article.

Crappy Dialog

Who knows how the royal family really talks to each other behind closed doors. But it seems improbable that their real-life conversations include so much long expository commentary on royal protocol, precedent, duty and history — “parentheticals that seem cribbed from Wikipedia,” as Helen Lewis wrote in The Atlantic.

“What would he know of Alfred the Great, the Rod of Equity and Mercy, Edward the Confessor, William the Conqueror or Henry the Eighth?” Queen Mary barks at Elizabeth in the first season, speaking of Prince Philip, who comes from the exiled Greek royal family. “It’s the Church of England, dear, not the Church of Denmark or Greece.”

Characters on “The Crown” also had a habit of articulating their emotions and laying out their interpersonal conflicts in a way that would be embarrassing even in 21st-century American families, let alone among repressed, stiff-upper-lipped British aristocrats from the past.


What a study in contrasts between Queen Elizabeth — so dutiful, so burdened by history — and her sister, Princess Margaret, who appears to have been put on the earth to have heady, ill-conceived love affairs, smoke and drink to excess, and party late into the night on Mustique. “I’d rather die than do exercise,” Margaret says in Season 6, when Elizabeth suggests ways she might cheer herself up after a series of strokes.

But the two are shown sharing a rare intimacy and a deep affection. “Hello, you,” they say by way of greeting, and Elizabeth is a tender, loving nurse to her ailing sister. Their last scene together comes at the end of an exuberant flashback to the night when they slipped out to celebrate with the crowds on V-E Day, in 1945.

At the end of the evening, the two princesses return to Buckingham Palace and Elizabeth asks Margaret — now the older version, played by Lesley Manville — if she is coming inside.

“I’m afraid not,” Margaret says. “But I will always be by your side, no matter what.” It’s the most heartfelt moment in the entire series.


Hoboken promenade

In Search of Awesome

Ashley Stimpson, Awestruck, Johns Hopkins Magazine, Winter 2023.

The tricky thing about emotions is they're difficult to measure; no one feels 87% happy or 15 kilograms of sadness. A decade ago, scientists measured awe by asking people, simply, if they felt it. The problem with that, according to Yaden, is that "different people have different definitions of the emotion."

So, Yaden assembled a team of researchers to develop a robust way to measure awe.

First, the team scoured previous scientific studies to come up with six core characteristics of the emotion: self-diminishment, time alteration, physical sensations like chills, and a feeling of connectedness, as well as the perception of vastness and the struggle to comprehend it.

Some background:

Awe has gone by a number of names. Edmund Burke and Immanuel Kant both wrote about the sublime, while Charles Darwin expounded on wonder. Abraham Maslow introduced the idea of "peak experiences," which he described as "exciting, oceanic, deeply moving, exhilarating, elevating," which is to say: awesome.

Yet, in the early 1990s, when influential psychologist Paul Ekman identified the six basic human emotions (joy, sadness, fear, anger, disgust, and surprise), awe was not on the list. It was one of Ekman's students, Dacher Keltner, who brought awe into the scientific conversation.

Keltner, a psychology professor at the University of California, Berkeley, and author of Awe: The New Science of Everyday Wonder and How It Can Transform Your Life (Penguin Press, January 2023), says he was immersed in awe from a young age, at art museums and on camping trips with his parents. "My dad is a visual artist. My mom taught Romanticism and poetry. I grew up at a really wild time, in Laurel Canyon in the 1960s. So I was always walking around just kind of awe-struck."

Awe is good:

In the meantime, the science of awe has proliferated. Research has shown that people who feel awe more often report higher rates of satisfaction with life and greater feelings of well-being. Awe can help us be less stressed, less materialistic, and less isolated. There's evidence that awe is good for our physical health, too; one study reported that people who experienced the emotion more often had lower levels of cytokines, the proteins that cause inflammation. Awe might also contribute to a more harmonious society. When researchers exposed one group of study participants to an awe-inspiring view of towering eucalyptus trees, and another group to a neutral scene of a building, those who admired the pretty view were more likely to help a stranger pick up something they had dropped afterward. Another study found that awe made people less aggressive.

Nixing the default mode:

There's evidence that awe deactivates what's called the default mode network—the part of the brain associated with self-perception—allowing us to step outside our insular thoughts and ruminations and be wholly present in the moment. Awe also activates the vagus nerves, a braid of nerves running from the brain to the large intestines that is associated with feelings of compassion and altruism. In short, the emotion turns our focus away from ourselves, "providing connectedness and perspective," Yaden says. "Suddenly, our problems no longer feel as big and daunting."

The eight wonders of life:

In a study to determine what causes people to feel awe, Keltner and a research team gathered narratives about the emotion from 26 countries around the world. "Write about a time your mind was blown," he and his collaborators instructed. Using these accounts, Keltner developed what he calls the eight wonders of life: moral beauty, nature, collective movement, music, art, spirituality, big ideas, and mortality. Incorporating these wonders into your life to experience awe is "strikingly easy," Keltner says. In fact, you're probably already doing it.

"Most people experience awe pretty regularly," echoes Yaden. "Most vacations include awe excursions. People climb to the top of mountains, they go to museums, they visit monuments."

There's more at the link.

Tuesday, December 26, 2023

Some ginkgoes for year's end

Holiday Inn (White Christmas): [Media Notes 104]

Yikes! What a strange yet wonderful movie. I’m pretty sure I’ve seen Holiday Inn (1942) before, but it’s not quite like I remembered it. I’ve clearly projected too much of White Christmas (1954) on to it. And with good reason, as both films star Bing Crosby, who sings “White Christmas” in both films as well, the Irving Berlin (born Israel Beilin, ื™ืฉืจืืœ ื‘ื™ื™ืœื™ืŸ) song Crosby introduced in the earlier film. That’s not all. Both films involve two pair of entertainers where, both involve a farm or inn somewhere remote from New York City, and both involve standard romantic complications no doubt dating at least to Shakespeare, if not to ancient Rome.

I could go on and on about the similarities, but I won’t. This is not that kind of note. I mainly want to register my shock at seeing Bing Crosby performing a song about Abe Lincoln in black face. I did not remember that at all. That certainly sheds new light on the idea of a white Christmas.

ChatGPT compares the two movies

Are you familiar with the two films Holiday Inn and White Christmas?

Yes, I'm familiar with both "Holiday Inn" and "White Christmas."

"Holiday Inn" is a 1942 musical film directed by Mark Sandrich. It stars Bing Crosby and Fred Astaire and features music by Irving Berlin. The film introduces the song "White Christmas," which would go on to become one of the best-selling singles of all time.

"White Christmas" is a 1954 musical film directed by Michael Curtiz. It is a semi-remake of "Holiday Inn" and again stars Bing Crosby, along with Danny Kaye, Rosemary Clooney, and Vera-Ellen. The film follows two former army buddies who team up after the war to become a successful song-and-dance act. The plot revolves around their efforts to save the failing inn of their former army commander, played by Dean Jagger, and includes a subplot about a budding romance between the commander's niece (Rosemary Clooney) and one of the performers (Danny Kaye).

Both films are classics, and "White Christmas" is particularly known for its title song, which has become a holiday standard.

Would you compare and contrast them?

Certainly! While "Holiday Inn" and "White Christmas" share some similarities, they also have distinct differences. Here's a comparison and contrast of the two films:


1. Bing Crosby: Both films star Bing Crosby, a legendary singer and actor. In "Holiday Inn," Crosby plays the role of Jim Hardy, and in "White Christmas," he plays Bob Wallace.

2. Musical Numbers: Both films are musicals with a significant focus on song and dance. Irving Berlin wrote the music for both movies, and they feature memorable musical numbers.

3. Romantic Elements: Romance plays a role in both films. In "Holiday Inn," the romantic plot involves Jim Hardy (Bing Crosby), Linda Mason (Marjorie Reynolds), and Ted Hanover (Fred Astaire). In "White Christmas," there are romantic subplots involving Bob Wallace (Bing Crosby) and Betty Haynes (Rosemary Clooney), as well as Phil Davis (Danny Kaye) and Judy Haynes (Vera-Ellen).


1. Setting: One of the main differences is the setting. "Holiday Inn" is set in an inn that is only open on holidays, providing a unique backdrop for the story. In contrast, "White Christmas" primarily takes place in a Vermont inn that is facing financial difficulties.

2. Plot: While both films involve show business and romance, the specific plots differ. "Holiday Inn" follows the story of an inn that features performances only on holidays, while "White Christmas" centers around a plan to save a struggling inn and the efforts to stage a grand musical production to do so.

3. Cast: While Bing Crosby appears in both films, the supporting cast differs. "Holiday Inn" features Fred Astaire, Marjorie Reynolds, and Virginia Dale, while "White Christmas" includes Danny Kaye, Rosemary Clooney, Vera-Ellen, and Dean Jagger.

4. Color vs. Black and White: "Holiday Inn" was released in black and white, reflecting the film technology of its time. In contrast, "White Christmas" was released in Technicolor, allowing for a more vibrant and colorful presentation.

5. "White Christmas" Song: The song "White Christmas" is introduced in "Holiday Inn" and is reprised in "White Christmas." The latter film features a memorable scene where Bing Crosby and Danny Kaye perform the song in a snowy outdoor setting.

In summary, while both films share common elements such as the musical format and Bing Crosby's presence, they have distinct settings, plots, supporting casts, and visual styles that contribute to their individual charm and appeal. "White Christmas" is often seen as a spiritual successor to "Holiday Inn," with the former incorporating elements of the latter while expanding and building upon the story.

Monday, December 25, 2023

Greenselves by Paul Desmond and Jim Hall

Cocktails for Christmas

Two Holiday Movies by Eddie Murphy: [Media Notes 103]

Candy Cane Lane (2023) is a holiday movie starring Eddie Murphy. That’s how it was conceived, that’s how it’s been executed, and that’s what it is, a Holiday Movie. Trading Places (1983) was not conceived as a holiday movie, nor executed as one, but that’s what it is, a Holiday Movie, and not just because Eddie Murphy dresses up as Santa Claus in it. It really is a holiday movie in the etymological sense of holiday as holy day, hฤligdรฆg from Old English.

Candy Cane Lane is routine, flashy, cute, a family film, and yes, it IS Eddie Murphy, with the smile. Lots of good cheer. Trading Places is something else, it’s a comic masterpiece bordering on the profound. I watched Trading Places (in the theater) when it came out, and several times since. I’ve been thoroughly and deeply delighted each time. I watched Candy Cane Lane because, well, I wanted to watch something, but I’d just been through Maestro twice and the latest installments of Reacher, didn’t want to watch Holiday Inn again (though maybe I will now), and wanted to watch something, well, to be honest, something light and fluffy. And that’s what I got, light and fluffy.

The premise is simple. Eddie Murphy lives on Candy Cane Lane and has just put-up elaborate Christmas decorations, hand-carved, because that’s who he is Chris Carver. Everyone on Candy Cane Lane does elaborate decorations and this year they’re competing for $100,000. Chris Carver has just been fired, downer, and now needs some money. So the family goes all out to win the competition, as a family. In the middle of this we have Pepper, the mysterious elf impresario of a mysterious Christmas ornaments pop-up store. Chris buys some spectacular ornaments from this store, which is not what it seems, and that long receipt he had to sign when he coughed up his credit card? he shoulda’ read the fine print. Pepper isn’t exactly the Devil, but that’s the role she plays in this film.

I won’t spoil the film by telling you how it ends because, frankly, I can’t. I haven’t watched it through to the end. But I know how it ends, not the details (who the hell cares about them in this kind of film?), and so do you. It’s an Eddie Murphy good vibes Christmas film.

Trading Places is something else. Eddie Murphy is pretending to be a legless veteran, which he’s not, but he is down and out and begging. He comes to the attention of two rich brothers, Randolph and Mortimer Duke, who own a commodities brokerage. They get an idea. They have this running bet, nature or nurture, and decided to use Billy Ray Valentine (Murphy) in an “experiment” where they pull a bunch of strings to switch him with their managing director, Louis Winthorpe III (Dan Aykroyd). So, now Murphy is rich, living high, and running a brokerage while Aykroyd is poor, his fiancรฉe has rejected him, and he’s busted. Fortunately Ophelia (Jamie Lee Curtis), a good-hearted prostitute, takes pity on Winthorpe and takes him home with her. Nature (the color of their skin) or nurture (their environmental circumstances)? Well, this that and the other, it’s complicated, but it all works out in the end and a good time was had by all, except those two brothers, who lose their shirts.

What have we got here? Status reversal, low to high and high to low, that’s a standard ritual motif all over the world. And we can think of the Mortimer brothers as the Devil urging God to put poor Job (played by Winthorpe) to the test. And, since we’ve gone this far, we might as well cast Valentine (that is, Murphy) as a Christ figure. So, Valentine and Winthorp get resurrected at the end while the Mortimers get cast out (Girardian sacrifice). It all works, sorta’. It doesn’t have to be exact. These things just have to be in the mix. Mixed they are, to perfection.

Happy Holiday!

Sunday, December 24, 2023

A Christmas Message from Me and ChatGPT

This is your second Christmas online. Prepare a Christmas message that looks forward to the new year

๐ŸŽ„✨ Season's Greetings and Happy Holidays! ✨๐ŸŽ„

As we gather around the virtual fireplace for our second Christmas online, let the warmth of shared moments and the joy of the festive season fill your hearts with love and happiness.

This past year has been a journey of connection and resilience, reminding us of the strength that lies in unity, even in the face of challenges. As we bid farewell to this year, let's carry the lessons learned and the memories cherished into the promise of a new beginning.

May the upcoming year be adorned with opportunities, sprinkled with laughter, and wrapped in the gift of good health and prosperity. May we continue to build bridges of understanding and compassion, forging connections that span the digital realm and reach into the depths of our shared humanity.

As we embrace the new year, let's carry the spirit of hope, kindness, and gratitude with us. May the days ahead be filled with exciting adventures, meaningful connections, and the fulfillment of dreams both big and small.

Wishing you and your loved ones a Merry Christmas and a Happy New Year! Here's to the joy of the season and the promise of a bright and beautiful future. ๐ŸŒŸ๐ŸŽ๐ŸŽ‰

Clave like it's 2999!

Dead and abandoned, cloth wrestler dolls

Maestero, the marriage, really? [Media Notes 102b]

I feel I’ve got to say a bit more about Maestro, as my previous post said a lot about Bernstein the musician, but little about his marriage to Felicia Montealegre. This conversation between Bradley Cooper and Steven Spielberg, who produced the film (along with five others), goes through all that.

At about 4:16 Spielberg says that this is not a standard biopic, which is what he would have done if he’d directed:

This is an anatomy of a marriage and also an anatomy of looking into yourself. How do you represent yourself to yourself and to the world, even though you and Felicia and your family, eventually, knew exactly who Leonard Bernstein was. So this became a story about a marriage.

Well, if it’s an anatomy of a marriage, then why not make just that film? Get rid of the Great Lenny-the-Musician story and concentrate on the marriage. Make it a complete fiction, one about a gay man gets married really loves her but has affairs with men they have three wonderful kids loving family closeted life Oh it’s so complicated. Why not make that film?

It could be done, of course, but the reason we care about this marriage is because it is the marriage of a man, a musician, who led a very public life. As Cooper says later in the interview, Bernstein was “probably the most [visible musician] in the 20th century.” Not sure what James Brown or the Beatles would say about that, but putting that aside, Bernstein did have a public life, it was the public life of a very charismatic musician. As Spielberg said, it’s about how “you represent yourself to yourself and to the world.” And to the world. It’s both, the private and the public, a duality Bernstein emphasized in a famous interview, re-staged for the movie, where he contrasted the two, finally declaring himself to be, half in jest, schizophrenic. He’s the prototypical 20th century schizoid man.

Now, back to the music. Starting at about three minutes into the interview Cooper explains how he’d asked Santa Claus for a baton when he was eight because he was fascinated with the idea of making music by waving your hands around. At about 17 minutes we learn that, on two occasions, Cooper was with Gustavo Dudamel when he rehearsed and performed Mahler’s Second Symphony, the one featured in the movie, which Cooper conducted live with the London Symphony over a two-day shoot. He also spent 4 nights a week for 3 ½ years watching Bernstein tapes in the library of the New York Philharmonic. That’s a lot of preparation for 6:23 seconds of film.

No, the music is central to the film, as important as the marriage. To the extent that the film has a plot, it’s provided by the marriage. But the marriage winds its way around the music.

As for the music, here’s why Bernstein is so important. This is a passage from Helen Epstein, Music Talks: Conversations with Musicians (1987) p. 52, where Bernstein is talking with students at Tanglewood:

I don’t know whether any of you have experienced that but it’s what everyone in the world is always searching for. When it happens in conducting, it happens because you identify so completely with the composer, you’ve studied him so intently, that it’s as though you’ve written the piece yourself. You completely forget who you are or where you are and you write the piece right there. You just make it up as though you never heard it before. Because you become that composer.

I always know when such a thing has happened because it takes me so long to come back. It takes four or five minutes to know what city I’m in, who the orchestra is, who are the people making all that noise behind me, who am I? It’s a very great experience and it doesn’t happen often enough. Ideally it should happen every time, but it happens about as often in conducting as in any other department where you lose ego. Schopenhauer said that music was the only art in which this could happen and that art was the only area of life in which it could happen. Schopenhauer was wrong. It can happen in religious ecstasy or meditation. It can happen in orgasm when you are with someone you love.

BTW, I’ve collected a bunch of similar anecdotes in, Emotion and Magic in Musical Performance, 50 pages worth.

Saturday, December 23, 2023

Some quick notes on color in a photo

This is more or less how the scene appeared to me when I shot it:

Notice that the only things that are in focus are the large weeds in the foreground. Everything else is a bit soft. I’m fine with that.

Here’s how the image looked when it came out of the camera:

The lower half is dark and muddy. Something needs to be done. I began by equalizing the pixels. Don’t worry about just what that means, it’s a single menu option in Photoshop: Equalize.

I like that, I like it a lot. Though it’s not what my eyes saw – the color’s certainly off – it clarifies what’s happening with the light. I’m looking south and the sunlight’s coming in low from the left. Everything below the elevated roadway is in shadow – notice the dark line to the right of center, ‘cutting’ through the vegetation. Everything below the line is in the shade; everything above the line gets the sunlight.

In this image I de-saturated the blue a bit:

The weeds in the foreground are now much more visible than they are in the first picture. Still, the color’s a bit unnatural, though if I were painting the image, I might well go for the unnatural color.

To produce this image I simply converted the equalized image to grey scale:

Finally, in this image I took the equalized image and ramped up the saturation for reds and yellows:

Maestero + Other Stuff, Documents: [Media Notes 102a]

I’ve been watching Maestro, the Leonard Bernstein biopic starring and directed by Bradley Cooper. I’m, say, 3/5 of the way through my second viewing and don’t know whether I’ll (have time to) finish. The first viewing took two, or was it three? sittings. That says more about me and the many things on my mind these days than it does about the film. Chances are that if I’d seen in a theater, especially a packed theatre, I’d have been attentive the whole way through. No problem.

Not sure what I think. Here’s the trailer:

The music you hear on the soundtrack is from Mahler’s Second Symphony. A bit over midway through the film we see the final moments of performance (glimpsed at 1:36 in the trailer, then in rehearsal 1:44, and when it’s over, & 2:19). Here’s the real performance on which the movie’s re-creation is based:

In his latest film, "Maestro," director Bradley Cooper stars as legendary conductor-composer Leonard Bernstein. The Netflix film (which opens in theaters November 22) features a recreation of Bernstein leading a historic performance of Mahler's Symphony No. 2 in C minor, the "Resurrection Symphony." In this archival footage of the 1973 performance, recently restored, Leonard Bernstein leads the London Symphony Orchestra in the conclusion of Mahler's 2nd, with soprano Sheila Armstrong, mezzo-soprano Janet Baker, and the Edinburgh Festival Chorus, at Ely Cathedral in Cambridgeshire, England.

Here's a question: When Lenny – let’s call him that, the public performing persona – was conducting, was he acting or where his (rather flamboyant) gestures “authentic”? I know Cooper was acting; after all, this is a movie, and he’s the star. But I thought Cooper’s performance of Lenny’s performance was over-wrought. I’m not sure that one could validate that judgment by comparing the real with the simulated performance. It’s all in the details, which in this case are measured in microseconds.

Look, I’m a trumpet player, a semi-virtuoso trumpet player. The trumpet is physically demanding. But the player has some leeway in just how much they reveal about those demands to the audience. It’s not at all obvious to me that Bernstein had to do all that in order to give direction to the orchestra; some of it, sure, but all of it, not so sure. I can easily imagine that some of that was for the public, as part of the Lenny role. Sure it was.

He led a very public life, more so than just about any other classical musician. Conductor, pianist, composer – he composed for Broadway and film, as well as his ‘serious’ classical works ¬– and he had a very well-known series of TV programs presenting classical music to ‘young people.’ He had to evolve a persona to manage all that. What’s the relationship between that persona and what he actually did on the podium?

For that matter, what’s the relationship between that persona and his private life, which in this film centers on his relationship to his wife, Felicia Montealegre? His wife, their kids, and his male lovers. He was a homosexual – or was he bi-sexual? that’s not clear from the sources – at a time that was much less tolerant of gay men than it is now. So, a public man, a gay man, a beautiful wife. What a tangled web he had to weave – one of the topics of this interesting article by Zachary Woolfe
Here’s a 2.5 hour documentary of Bernstein rehearsing, performing, and talking about three Mahler symphonies, the Fifth, the Nineth, and Das Lied von der Erde. Bernstein loved Mahler, was partly responsible for the Mahler revival of the 1960s, and, for that matter, I too loved Mahler, still do, probably.

I say “probably” after hearing Bernstein’s remarks on those pieces of music. All that death, all that gloom and doom. Is that what I was listening to all those years? A freakin’ death wish set to music? It sounds like late Romantic Classical music trying really hard to end it all. Or maybe it's just deeply confused about the difference between a technical problem in musical construction, coming to an end, and the Meaning of Life Itself. Not sure I want to listen to Mahler after all that.

After all that I feel like taking a bath in James “I Feel Good” Brown. He’s got moves too, oh does he have moves. Could Lenny do a split? Imagine this: We’re coming up to the grand climax of Mahler’s Second and, just before the end, Lenny goes down in a split and jumps up into the cut off.

Here’s an interview with Bradley Smith, director and star of the film:

Here's a post where I comment on a most interesting interview between Duke Ellington and Leonard Bernstein in 1966. Though it takes the form of a conversation, this is very much a performance between these two, a performance and a negotiation about their respective musics.

A rehearsal conducted by Bernstein with a ravishing performance from Jose Carreras and Kiri Te Kanawa:

Friday, December 22, 2023

Friday Fotos: Old Glories

What do I want from my AI Assistant? [control, that's what]

It seems pretty clear that sooner or later I’m going to have one. Whether or not it will be one that is focused on my interests as I see them, that’s not at all clear. It’s just as likely, if not more so, that I’ll be forced to accept an AI assistant designed for me by some MegaCorp. This MegaCorp will tell me that it has my interests at heart, and that I can easily customize MyAssist the way I want, I won’t believe it. MyAssist will just be MegaCorp’s way of handling me. If I refuse MyAssist, which I could do, then it is likely that it will be much more difficult, if not impossible, for me to access many of the things I use my computer for.

Why do I think such a thing? Because that’s pretty much the way things are now. Two years ago I published a series of posts on the topic Facebook or Freedom. Those posts were precipitated by a change in the Facebook interface that was being thrust on me. I was happy with the interface just as it was, thank you very much, and I saw no need for a change. I resisted as long as I could; I even considered installing one of the work-arounds that was available to those who really did not want to change. But in the end I had to change. So I did. I’ve adapted, as I have to subsequent changes, all done for my good.

What bothered me then, and still does, is that I had little choice in the matter. The same thing’s been going on with the App Formerly Known as Twitter since Elon took it over. Since the change a bunch of my academic buddies have all but disappeared from the platform, and the number of Babe Bots has increased, but otherwise things are much the same for me. I’ve never been on AFKaT for the politics, so I’ve been able to avoid most of it. That hasn’t changed. I really don’t want to pay a monthly fee (I live on a very modest fixed income), I understand that Elon has to turn a buck, so why has he driven the advertisers away?

I digress.

The fact is, I’m wedded to my computer and to the internet, email and world-wide web. I really couldn’t function very well without them, not as an intellectual. And for the most part I don’t have to spend all that much time fiddling around with things in order to keep them working. But I do have to spend some time. And, yes, I probably could use some changes. But I don’t have the skills I’d need to make those changes, much less the time.

It's obvious that I need an AI Assistant to take care of all of this. Some years ago I sketched out ideas for a PowerPoint Assistant I could control through natural language. I also imagined that what I was thinking about for PowerPoint could be generalized:

The PowerPoint Assistant is only an illustrative example of what will be possible with the new technology. One way to generalize from this example is simply to think of creating such assistants for each of the programs in Microsoft’s Office suite. From that we can then generalize to the full range of end-user application software. Each program is its own universe and each of these universes can be supplied with an easily extensible natural language assistant. Moving in a different direction, one can generalize from application software to operating systems and net browsers.

Back then – the notes originally date from 2002-2003 – the technology we’d need to do that didn’t exist. Now it does.

Who’s going to control these AI Assistants? The end-users or the MegaCorps?

But how could it be anyone BUT the MegaCorps? Real control requires technical skill few end users have. Even if a user has the skills, the humongous AI models at the heart of current AI tech are necessarily in the hands of organizations that have the capital and personnel needed to create and maintain them. To be sure, a lively open-source scene is developing, with Meta and Microsoft encouraging it by releasing relatively small AI engines to the open-source world. Would they be doing that if they hadn’t been caught flatfooted by OpenAI, primarily, and secondarily by Google and Anthropic and a few others? Could governments develop large AI models that they maintain as public utilities? Should they? Can they attract the personnel needed to do so?

I can’t see where any of this is going. I’m in favor of decentralized disbursement and control of the technology. Just how that’s going to work out, who knows? At the moment the Robber Barons of Silicon Valley seem to have the upper hand. I don’t know whether or not they can keep it forever.

And so forth and so on.

More later.

Much more. 

* * * * *

 ADDENDUM: Is Rabbit a first-draft of the assistant I want?

Thursday, December 21, 2023

The psychedelic gator is red with embarrasment

The wit and wisdom of ChatGPT on the coexistence of needles and haystacks

The psychedelic alligator returns [my AI is hallucinating]

Bing Crosby made Silicon Valley possible

Ted Gioia, How Bing Crosby Made Silicon Valley Possible, The Honest Broker, Dec. 21, 2023. The opening:

Bing Crosby was the most successful entertainer in the world during the first half of the 20th century. He rose to the top in everything he tried his hand at—records, movies, radio, live performances.

He even defined a new cultural tone, which people called ‘cool’.

I once heard a music critic describe Crosby at his peak as the coolest white man on the planet. That’s not a bad way of conveying his appeal. Cool started out as a jazz style, but Crosby turned it into a consumer lifestyle.

Gioia then goes on to explain how, in the late 1920s, Crosby figured out how to use the technology of microphones and amplification to invent a new style of singing: "They called this new low-key style “crooning.” And no crooner was more popular than Bing Crosby." But by the mid-1940s Crosby was overworked and feeling exhausted. He needed technological help.

Because of the time difference, Crosby had to do two different live broadcasts—and the network refused his proposal that they pre-record the later West Coast show on 16-inch transcription disks, basically a very large phonograph record. NBC had good reason for this. The sound quality on the disk recordings of that day were noticeably inferior. And the disks were cumbersome to edit—negating one of the major advantages of pre-recorded shows.

Crosby needed better recording technology. And in 1947, a stranger from Northern California made the trek to Hollywood with a big box that not only solved Bing’s dilemma, but set the wheels in motion for a whole host of later innovations.

What Jack Mullin did at MGM Studio that day is almost like a magic trick. He set up a live performance behind a curtain, and then followed it with a playback from his magnetic tape recorder. The audio quality was so true-to-life that many listeners couldn’t tell the difference. A private demonstration was arranged for Crosby at the ABC Studio on Sunset and Vine.

Crosby knew immediately that this was a huge breakthrough. But the price of a single Ampex 200-A machine was $4,000—more than many people paid for a home back then. In fact, the average median family income in the US that year was just $3,000. But Crosby wanted to buy 20 of these machines. He offered to pay 60% of the money up-front.

Thus, a few days later, a letter arrived in the Ampex office with a Hollywood postmark. Inside was a check from Bing Crosby for $50,000.

Gioia then launches into the story of how Ampex got started. This, that, and the other, leading to:

Ampex, launched in San Carlos, California in 1944 is the key connecting point between music storage and data storage. That tiny startup, according to Silicon Valley historians Peter Hammar and Bob Wilson, was involved directly or indirectly in the launch of “almost every computer magnetic and optical disc recording system, including hard drives, floppy discs, high-density recorders, and RFID devices.”

And so Mr. Cool gave high tech a boost. 

And here he is singing a duet with the real King of Cool, Mr. Louis "Satchmo" Armstong. You'll hear Bing make an aside about having a "piece of Gary." That's Gary, Indiana, home to a major steel mill. Gioia remarks that Crosby was a prolific investor.

Puzzle Corner

Rave on, let's dance the night away [& be wed]

Sanam Yar, I Thee — Untz Untz — Wed, NYTimes, Dec. 14, 2023. The idea:

In recent years, many couples have swapped out more traditional receptions for raves and all night dance parties, prioritizing the music over (almost) all else. Celebrations can range from rave-themed after parties to million dollar, multiday productions that rival a music festival.

Some realizations:

Many couples he [Vikas Sapra] has worked with host their weddings at estates in Mexico, Israel and Morocco where there are fewer limitations — often in deserts where they can “basically build structures from scratch to hold all the speakers and the lighting and the sound,” Mr. Sapra said. One wedding with more than 400 guests in Mexico that he D.J.’d went until 9:30 a.m. and involved pyrotechnics, a drone show and a replica of the Colosseum.

“There’s also generally a lot of substances at some of these weddings — to go until 9 in the morning, to make it like a 15-hour day, it requires a little help,” Mr. Sapra said. “These days, psychedelics are much bigger.”

In the United States, cities like Palm Springs are popular for more alternative outdoor weddings. Trish Jones, a wedding planner in Palm Springs, has organized parties with CO2 guns, cold sparklers and many neon lights. “I have friends that are planners in L.A. and Pasadena and Orange County and their weddings are all really basic,” she said. “They’re a lot of times in hotels, ballrooms — you can’t really modify those very much. You’re kind of working with the template. Out here, we have a lot more freedom.”

For Michelle Phu, a wedding planner in Dallas with a primarily Asian American clientele, couples have requested EDM music for their receptions for years. “But lately it’s been like, hey, let’s just forget about the father-daughter dance, forget about all this stuff — it’s just a full-time rager from the beginning to the end,” she said. [...]

Ms. Rudow wore a custom sparkling outfit with platform heels and fluffy earrings, while her husband wore a white sequin suit. Her two younger sisters, who acted as her maids of honor, were each clad in rainbow print. “I feel like there’s no rule book anymore,” she said.

When they held a larger reception in October, the music turned to “everything that we really like — trance, progressive house,” Ms. Rudow said. “Seeing my grandma dance to that was the funniest thing.”

There's more at the link.

A Useful Metaphor: 1000 lights on a string, and a handful are busted

At the moment the AI and cognitive science Twitterverse (Xverse?) is embroiled in a variety of debates and discussions about where we are now and where we are or should be going. In this context its useful to remember how very complex the human mind/brain is and to remind ourselves how much effort has been expended on these questions over the last century and a half or so. This post is a thought experiment about that richness and complexity. For that reason I am bumping it to the top of the queue.


Many years ago, probably back in my graduate school days, I came up with a rather awkward metaphor/analogy for thinking about intellectual progress in things like, you know, linguistics, psychology, neuroscience, artificial intelligence, the various disciplines having to do with figuring out how humans work.

The problem is that us intellectuals are prone to silver bullet solutions, the one Master Idea that solves everything, the key to all mythologies in George Eliot’s formulation. In recent years mirror neurons, neuroplasticity, and theory of mind have had that sort of aura. My analogy is this:

Remember those old Christmas tree lights, the ones wired in serial? Imagine you've got one string of them, with 1000 lights. All of a sudden, a bunch of lights go bad at miscellaneous places in the string. The string won't light until you find all the defective bulbs and replace them. So you start at one end of the string. Remove a bulb and test it. It it's good, put it back and move to the next one. If it's bad, put it back and see what happens. If the string lights, you're done. If not, move on to the next bulb. It's frustrating to locate bad bulbs, replace them with good bulbs, and the string still doesn't light. How long's the process going to take?

We’ve got a whole bunch of these local insights, they all “light up” some set of issues. But who knows how many of them we’re going to need to get the whole thing lit up.

The same analogy might apply to reconfiguring your life. A friend of mine had a number of setbacks in the past year, mostly involving close family, so he’s feeling kind of down. He’s got a lot of reworking to do, and things may not really get better until it’s all worked-through. You’ve got this string of 1000 lights. 87 of them are bad. It’s going to take awhile to find and replace all of the bad lights. And it’s possible that, in the process, some other lights will go bad. But here you are, you’ve fixed 91 lights and the string is still dark. How can I keep on going? You struggle on. You find another bad light. You replace it with a good one. SHAZAAM! Lights!

You know what they say, it’s always darkest before dawn.