Thursday 6 April, 2023

Light and shade

In College the other day.


Quote of the Day

”Commerce in the 21st century is espionage for profit.”

  • Historian Jill Lepore, writing in the New Yorker.

Musical alternative to the morning’s radio news

Ray Charles | Georgia On My Mind

Link

Georgia may also be on Trump’s mind, but for a different reason.


Long Read of the Day

AI Chatbots Don’t Care About Your Social Norms

They seem to fool people into thinking they’re human, argue Jacob Browning and Yann Lecun in this essay but they are actually exceedingly alien.

With artificial intelligence now powering Microsoft’s Bing and Google’s Bard search engines, brilliant and clever conversational AI is at our fingertips. But there have been many uncanny moments — including casually delivered disturbing comments like calling a reporter ugly, declaring love for strangers or rattling off plans for taking over the world.

To make sense of these bizarre moments, it’s helpful to start by thinking about the phenomenon of saying the wrong thing. Humans are usually very good at avoiding spoken mistakes, gaffes and faux pas. Chatbots, by contrast, screw up a lot. Understanding why humans excel at this clarifies when and why we trust each other — and why current chatbots can’t be trusted.

Getting It Wrong

For GPT-3, there is only one way to say the wrong thing: By making a statistically unlikely response to whatever the last few words were. Its understanding of context, situation and appropriateness concerns only what can be derived from the user’s prompt. For ChatGPT, this is modified slightly in a novel and interesting way. In addition to saying something statistically likely, the model’s responses are also reinforced by human evaluators: The system outputs a response, and human evaluators either reinforce it as a good one or not (a grueling, traumatizing process for the evaluators). The upshot is a system that is not just saying something plausible, but also (ideally) something a human would judge to be appropriate — if not the right thing, at least not offensive…

Great essay. The authors’ conclusion ought to be printed in 95-point Helevetica Bold on every schoolroom and lecture-hall wall:

The upshot is that chatbots aren’t conversing in a human way, and they’ll never get there solely by saying statistically likely things. Without a genuine understanding of the social world, these systems are just idle chatterboxes — no matter how witty or eloquent.


Books, etc.

I’ve written for the Observer for a long time (my first piece in the paper was published in 1972, I think, and I’ve been a weekly columnist there ever since 1987).

At one stage during that time, the paper had my fellow-countryman Conor Cruise O’Brien as its Editor-in-Chief. He was a big figure in every sense of the word — an experienced diplomat and UN official (he had been the UN’s High Representative in Katanga during the Congolese civil war), the Schweitzer Professor of the Humanities at New York university, a Cabinet minister in Ireland, a distinguished author of fine books (on Camus and Edmund Burke, to name just two), and a major public intellectual.

He was also a formidable drinker, and if you went to the pub with him on a Friday night you needed to be ready for anything. One evening he said to me, “Is it true that you’re an academic as well as a journalist?”. “I’m afraid it is, Conor”, I replied. “I see,” he said. “Same as me: you have a foot in both graves.”

He liked the Observer but I think he regarded many of us as woolly-headed liberals. Still, he appreciated the ethos of the paper and occasionally told stories against himself about it.

One was about a day when he was phoning in the copy for his column from some distant land and at one point dictated as follows to the copy-taker: “the atmosphere was redolent of fin-de-siecle Vienna — that’s French – f-i—n-space-d-e-space…” At which point the copy-taker politely stopped him and said, “I think you should take it for granted, Dr O’Brien, that a copy-taker on the Observer would know what the French for ‘end of the century’ is.”

It was a good story and we all laughed at it. But although I knew the phrase at the heart of the story, I had no real understanding of what it implied.

Until now.

I’m reading — for the first time — Stefan Zweig’s The World of Yesterday, and his account of the Vienna in which he was a precocious teenager and young man is one a truly remarkable evocation of a special era. I’m finding the book unputdownable (to resort to cliché) and am retrospectively grateful to Clive James whose essay on Zweig in his collection Cultural Amnesia was what started me down this enjoyable rabbit-hole.


This Blog is also available as a daily email. If you think that might suit you better, why not subscribe? One email a day, Monday through Friday, delivered to your inbox. It’s free, and you can always unsubscribe if you conclude your inbox is full enough already!


Wednesday 5 April, 2023

Many thanks to the readers who pointed out that in the previous two editions I appeared to be confused about the month we’re now in!


Next?


Quote of the Day

”If economists wished to study the horse, they wouldn’t go and look at horses. They’d sit in their studies and say to themselves, ‘What would I do if I were a horse?’”

  • Ely Devons

Musical alternative to the morning’s radio news

Handel | Concerto grosso B flat major op. 6 No. 7 HWV 325 | WDR Symphony Orchestra

Link


Long Read of the Day

Philip K. Dick and the Fake Humans

Lovely essay in the Boston Review by Henry Farrell, arguing that we live in Philip K. Dick’s future, not George Orwell’s or Aldous Huxley’s.

This is not the dystopia we were promised. We are not learning to love Big Brother, who lives, if he lives at all, on a cluster of server farms, cooled by environmentally friendly technologies. Nor have we been lulled by Soma and subliminal brain programming into a hazy acquiescence to pervasive social hierarchies.

Dystopias tend toward fantasies of absolute control, in which the system sees all, knows all, and controls all. And our world is indeed one of ubiquitous surveillance. Phones and household devices produce trails of data, like particles in a cloud chamber, indicating our wants and behaviors to companies such as Facebook, Amazon, and Google. Yet the information thus produced is imperfect and classified by machine-learning algorithms that themselves make mistakes. The efforts of these businesses to manipulate our wants leads to further complexity. It is becoming ever harder for companies to distinguish the behavior which they want to analyze from their own and others’ manipulations.

This does not look like totalitarianism unless you squint very hard indeed. As the sociologist Kieran Healy has suggested, sweeping political critiques of new technology often bear a strong family resemblance to the arguments of Silicon Valley boosters. Both assume that the technology works as advertised, which is not necessarily true at all.

Standard utopias and standard dystopias are each perfect after their own particular fashion. We live somewhere queasier—a world in which technology is developing in ways that make it increasingly hard to distinguish human beings from artificial things….


Chart of the Day

Note, though, that there’s no graph for the compute cost, which is a proxy for the carbon footprint of all this data processing.


Orwellian metaphors in ‘Generative AI’

Long, long ago, in his essay “Politics and the English Language”, George Orwell drew attention to the way language is used to conceal awkward truths “designed to make lies sound truthful and murder respectable, and to give an appearance of solidity to pure wind”). The tech industry (and its media and academic accomplices) are singularly adept at this. Thus machine-learning suddenly became “AI” even though it has nothing to do with intelligence, artificial or otherwise. By clothing in an acronym which originally denoted a serious quest for machines that could display signs of genuine intelligence the crude planet-heating, IP-infringing technology called machine-learning can be somehow made respectable.

Now, as Rachel Metz points out in a splendid blast in Bloomberg’s Tech Daily newsletter, the idea that a Large Language Model like ChatGPT or GPT-4 can “hallucinate” has become the default explanation anytime the machine messes up.

We humans can at times hallucinate: We may see, hear, feel, smell or taste things that aren’t truly there. It can happen for all sorts of reasons (illness, exhaustion, drugs).

But…

Companies across the industry have applied this concept to the new batch of extremely powerful but still flawed chatbots. Hallucination is listed as a limitation on the product page for OpenAI’s latest AI model, GPT-4. Google, which opened access to its Bard chatbot in March, reportedly brought up AI’s propensity to hallucinate in a recent interview

“Hallucinates” is a way of obscuring what’s going on. It’s also a way of encouraging humans to anthropomorphise LLMs.

Saying that a language model is hallucinating makes it sound as if it has a mind of its own that sometimes derails, said Giada Pistilli, principal ethicist at Hugging Face, which makes and hosts AI models.

“Language models do not dream, they do not hallucinate, they do not do psychedelics,” she wrote in an email. “It is also interesting to note that the word ‘hallucination’ hides something almost mystical, like mirages in the desert, and does not necessarily have a negative meaning as ‘mistake’ might.”

Great piece. Hats off to Ms Metz.


  This Blog is also available as a daily email. If you think that might suit you better, why not subscribe? One email a day, Monday through Friday, delivered to your inbox. It’s free, and you can always unsubscribe if you conclude your inbox is full enough already!


Tuesday 4 April, 2023

Modern Irish history

Well, one shelf of it anyway.


Quote of the Day

”At times, when remonstrated with for not being ‘nice’, he would retort, ‘You don’t know how much nastier I would be if I hadn’t become a Catholic’.”

  • Tom Driberg on Evelyn Waugh.

Musical alternative to the morning’s radio news

Joni Mitchell and James Taylor | The Circle Game

Link


Long Read of the Day

ChatGPT and Virginia Woolf

Results of a frivolous experiment by yours truly.

Me: Write a diary entry by Virginia Woolf for Friday 19 March, 1926

ChatGPT:

Dear Diary,

Today has been a rather hectic day for me. I woke up early, as usual, and spent some time in my study working on my novel. I have been struggling with it lately, but today I managed to make some progress. I feel that I am getting closer to the heart of the story, and it excites me.

After breakfast, I went for a walk in the garden. The air was crisp and the sun was shining, and I felt invigorated by the fresh air. I spent some time admiring the flowers and the trees, and I thought about the beauty of nature. It’s amazing how nature can inspire us and lift our spirits.

In the afternoon, I had some visitors. My sister Vanessa came over, along with her husband Clive Bell and their children. We had a lovely time chatting and catching up on news. They are such a delightful family, and I always enjoy their company.

Later in the day, I received a letter from my friend Lytton Strachey. He is always so witty and amusing in his letters, and I found myself laughing out loud at some of his remarks. I am looking forward to seeing him soon.

As the day draws to a close, I am feeling a sense of contentment. It has been a busy day, but a productive and enjoyable one. I am grateful for the simple pleasures of life, like a walk in the garden or a good letter from a friend. It is these things that make life worth living.

Until tomorrow, Virginia Woolf.

***** 

OK, let’s try again…

Me: Write a diary entry in the style of Virginia Woolf for Friday 19 March, 1926

Chat GPT:

Dear Diary,

What a day it has been! I woke up early, as I usually do, but today the world outside my window seemed to be filled with a different light. The sun shone brighter and the birds sang louder, as if they too knew that something special was happening today.

I spent the morning writing in my study, trying to capture the essence of the character that has been haunting me for weeks. It is a struggle, as always, to find the words that will do justice to the complexity of human experience. But still, I persist.

After a light lunch, I went for a walk in the garden. The daffodils are in full bloom now, their bright yellow petals reaching towards the sky. I found myself lost in their beauty, my mind drifting away from my work and towards the simple pleasures of life.

In the afternoon, my sister Vanessa came to visit with her husband Clive and their children. It was wonderful to see them again, to hear the laughter of children and the chatter of adults. They bring a sense of joy to my life that I cannot find anywhere else.

As the day drew to a close, I found myself lost in thought. The world is changing so quickly, and sometimes it feels as though we are all rushing towards an unknown future. But in moments like this, surrounded by the beauty of nature and the love of family, I am reminded that there is still so much to be grateful for.

Until tomorrow, Virginia Woolf.

__________________ 

Now, as it happens, Woolf didn’t write anything in her diary for March 19 — hence the idea behind the prompt.

For comparison, here’s a snatch of her entry for the following day:

You get the message. ChatGPT is, no doubt, good at some things. But crassly inadequate at others. I had assumed that its training data would have included the diaries. Obviously it hadn’t. So it made up a diary entry that might have been written by an earnest teenager. Examples: “my sister Vanessa came to visit with her husband Clive and their children”. And it was, of course, “wonderful to see them again”. Vanessa is almost always “Nessa” in the actual diaries, and Woolf would never have felt the need to explain Clive’s marital status. So the whole thing reads like those family newsletters one gets at Christmas.

All of which brought to mind something that Nathan Heller wrote in his New Yorker essay, “The End of the English Major”:

“There has been much hand-wringing about ChatGPT and its ability to replicate some composition tasks. But ChatGPT can no more conceive “Mrs. Dalloway” than it can guide and people-manage an organization. Instead, A.I. can gather and order information, design experiments and processes, produce descriptive writing and mediocre craftwork, and compose basic code, and those are the careers likeliest to go into slow eclipse.”

Never mind Mrs Galloway; it can’t even imagine its author’s diary.


Books, etc.

Ulysses … I rather wish I had never read it. It gives me an inferiority complex. When I read a book like that and then come back to my own work, I feel like an eunuch who has taken a course in voice production and can pass himself off fairly well as a bass or a baritone, but if you listen closely you can hear the good old squeak just the same as ever.”

  • George Orwell, in a letter to Brenda Salkeld, September 1934.

My commonplace booklet


This Blog is also available as a daily email. If you think that might suit you better, why not subscribe? One email a day, Monday through Friday, delivered to your inbox. It’s free, and you can always unsubscribe if you conclude your inbox is full enough already!


Monday 3 April, 2023

School Trip!

King’s Parade, Cambridge.

Note the girl on the left looking snootily at the photographer. Smart kid.


Quote of the Day

”Carbon capture is currently ineffective and an extremely costly experiment, distracting from the measures that we know are effective and can implement today. The UK government should not be investing £20billion in a strategy that is essentially an ambulance at the bottom of a cliff when we could use the money to not go down the cliff in the first place.”

  • Dr Friederike Otto, senior lecturer in Climate Science at Imperial College London’s Grantham Institute, commenting on the UK government’s latest climate-catastrophe-averting ‘strategy’ — technology which will capture and store carbon dioxide in undersea caverns, thereby enabling an expansion of oil and gas extraction in the North Sea.

The Greeks were right: those whom the Gods wish to destroy they first make mad.


Musical alternative to the morning’s radio news

Mary Bergin, Cologne, Germany, 1990

Link


Long Read of the Day

Vermeer’s Daughter

Fabulous long, long read by Lawrence Weschler about a speculative theory that Maria Vermeer was not only a model for her father but also an artist who created several of the paintings attributed to him. Also, en passant, a memorable profile of the, er, unforgettable Vermeer expert whose theory this is. And, for good measure, it provides a good account of the impenetrable snootiness of the art-critic establishment.

Cheered me up no end.


Programmers, beware: ChatGPT has ruined your magic trick

Yesterday’s Observer column:

Seeking a respite from the firehose of contradictory commentary, I suddenly remembered an interview that Steve Jobs – the nearest thing to a visionary the tech industry has ever had – gave in 1990, and dug it out on YouTube.

In it he talks about a memory he had of reading an article in Scientific American when he was 12 years old. It was a report of how someone had measured the efficiency of locomotion for a number of species on planet Earth – “how many kilocalories did they expend to get from point A to point B. And the condor won – came in at the top of the list, surpassed everything else; and humans came in about a third of the way down the list, which was not such a great showing for the ‘crown of creation’.

“But then somebody there had the imagination to test the efficiency of a human riding a bicycle. A human riding a bicycle blew away the condor, all the way to the top of the list. And it made a really big impression on me – that we humans are tool-builders, and that we can fashion tools that amplify these inherent abilities that we have to spectacular magnitudes.

“And so for me,” he concluded, “a computer has always been a bicycle of the mind – something that takes us far beyond our inherent abilities. And I think we’re just at the early stages of this tool – very early stages – and we’ve come only a very short distance, and it’s still in its formation, but already we’ve seen enormous changes, [but] that’s nothing to what’s coming in the next 100 years.”

Well, that was 1990 and here we are, three decades later, with a mighty powerful bicycle…

Do read the whole thing.


Cold War 2.0 is up and running

From the Editor of the Economist in this week’s edition:

When I and some of my London colleagues travelled to Beijing last week, we arrived to find the atmosphere laced with intimidation and paranoia. The world’s most important relationship—that between China and America—has become more embittered and hostile than ever.

In the halls of government Communist Party officials were denouncing what they see as America’s bullying. They told us that the United States is intent on beating China to death and that it will never accept that any country can be as powerful as itself, regardless of whether it is communist or a democracy. America, in their view, will tolerate China only if it is submissive—in the words of one Chinese academic, a “fat cat, not a tiger”.

Meanwhile Cold War 1.1 is actively being waged in Ukraine.


Cruisin’ for a Bruisin’?

One of the strangest things about the UK’s Classic FM radio station is the incessant stream of advertisements it carries for ocean cruises.

I wonder therefore if the station’s marketing executives have seen this interesting story in Buzzfeed News.

“Hundreds Of Passengers Have Said They Were Sexually Assaulted On Cruise Ships. Their Stories Highlight Years Of Lax Security, Critics Say.”

In dozens of court documents reviewed by BuzzFeed News, cruise ship passengers say they have been dragged into cabins and raped, pushed into janitors’ closets and assaulted, and even attacked in the public corridors of ships. Likewise, parents and guardians have alleged that their children were molested by other passengers or crew members, plied with alcohol, and in some instances, abused by daycare staffers at onboard activity centers. As recently as two weeks ago, the parents of a 17-year-old passenger filed a civil suit alleging she was raped by a fitness instructor onboard a Carnival cruise ship.

In fact, sexual assaults are the most prevalent reported crime on cruise ships, according to the FBI. Since 2015, there have been 454 reported allegations of sex crimes on cruise ships. Experts believe that the actual numbers are far higher, as many sexual assaults often go unreported. (For reference, more than two-thirds of all sexual assaults in the US are not reported to law enforcement, according to the Rape, Abuse & Incest National Network.)

And many of the major cruise lines have been told — even by their own security staffers — that more could be done to protect passengers, such as installing more surveillance cameras and hiring additional security personnel. But according to court records, including a deposition from this February in a lawsuit alleging the gang rape of a minor on a Carnival Cruise ship, senior executives have opted not to implement the changes, claiming they’re too expensive.

Shiver me timbers, etc.

My idea of hell is being locked on a ship with thousands of other people.


My commonplace booklet

 Venice Is Saved! Woe Is Venice.

The New York Times has an imaginative report on Venice’s now-operational sea wall and what it might mean for the city’s future.


This Blog is also available as a daily email. If you think that might suit you better, why not subscribe? One email a day, Monday through Friday, delivered to your inbox. It’s free, and you can always unsubscribe if you conclude your inbox is full enough already!


Friday 31 March, 2023

Darwin and his masterpiece (x2)

Seen in a bookshop window yesterday


Quote of the Day

”The camera makes everyone a tourist in other people’s reality and, eventually in one’s own.”

  • Susan Sontag

Musical alternative to the morning’s radio news

Satie | Je te veux

Link


Long Read of the Day

How Will AI Transform Photography?

As artists experiment with this fast-evolving technology, they uncover creative opportunity, absurdity, and bias. So says Charlotte Kent, an arts writer and an assistant professor of visual culture at Montclair State University in a thought-provoking essay. It pulled me up short because, as a keen photographer, I initially thought that generative AI technology was a threatening antithesis to photography. The article suggests, though, that some photographers see its possibilities for augmentation.

Sample:

Due to the range of sources from which these image generators pull data—online images ranging from stock photography, news imagery, social media posts, and personal websites—the results can range from the real to the uncanny. New York–based photographer Charlie Engman believes that AI’s limited understanding of bodies stems from perceiving them through images, not lived experiences. Informed by a background in dance and performance, Engman’s work spans fashion imagery as well as collaborative portraits of his mother. His AI experiments push some of these ideas further, exploring how the technology is able and unable to articulate bodily movement.

Our physical gestures are expressive of internal, psychological states, but AI struggles to process the aesthetic of emotions. Grief or pleasure may appear on AI-generated faces but isn’t replicated in those figures’ postures or gestures. Engman has observed that the body language of performers includes subtle movement choices cultivated over time to express thoughts and feelings, but these are rarely read accurately across AI data sets. Tags associated with images don’t typically specify a relationship between affect and a particular gesture. For instance, an emotion might be determined as happy because many images with smiles are tagged “happy,” but the AI might not be prompted to discern other subtle postures or stances, such as relaxed shoulders. For Engman, this gap is a compelling reason to explore the technology…

The piece includes lots of striking images, like this one making a commentary on office life.

Interesting throughout.


Books, etc.

Travels with Charley

Browsing in David’s bookshop in Cambridge yesterday morning, I came on a battered copy of this and was reminded of the first time I read it, aeons ago. I had an audio copy of it too, and sometimes listened to it during the years when I had a long commute to work. But then I mislaid my copy and the cassette tapes of the audio version went the way of all cassette tapes. So I opened the paperback and read this…

When I was very young and the urge to be some place else was on me, I was assured by mature people that maturity would cure this itch. When years described me as mature, the remedy prescribed was middle age. In middle age, I was assured that greater age would calm my fever and now that I am fifty-eight perhaps senility will do the job. Nothing has worked. Four hoarse blasts of a ship’s whistle still raise the hair on my neck and set my feet to tapping. The sound of a jet, an engine warming up, even the clopping of shod hooves on pavement brings on the ancient shudder, the dry mouth and vacant eye, the hot palms and the churn of the stomach, high up under the rib cage. In other words, I don’t improve; in further words, once a bum always a bum. I fear the disease is incurable. I set this matter down not to instruct others but to inform myself…

…and was lost. So I paid David £2 thinking “well, that takes care of the weekend”.


My commonplace booklet

Going Solar

My friend Quentin (Whom God Preserve) decided that he would ‘go solar’ some time ago. And he did. But Quentin never does anything by halves, or without thinking things through beforehand. And he’s just released a video describing what he did and explaining the various decisions he made. It’s long (nearly 40 minutes) but if you’re seriously interested in harnessing the power of the sun for domestic reasons, then you’ll learn a lot from it. I know I did.


This Blog is also available as a daily email. If you think that might suit you better, why not subscribe? One email a day, Monday through Friday, delivered to your inbox. It’s free, and you can always unsubscribe if you conclude your inbox is full enough already!


Thursday 30 March, 2023

Tricycling for billionaires

Well, as Zero Mostel shouted in The Producers, “If you’ve got it, baby, flaunt it.”


Quote of the Day

“The past is never dead. It isn’t even past.”

  • William Faulkner

Musical alternative to the morning’s radio news

Padraig Ó Carra | An Buachaill Caol Dubh (The slender black boy)

Link

Another product of the ongoing discussion about Hammered Dulcimers. This was suggested by Joe Dunne, who lived in Galway in the 1980s and often heard Ó Carra perform.

There are some annoying clicks on the recording. Do not adjust your sets if you hear them. Blame the sound engineer who did the recording.


Long Read of the Day

Cheating is All You Need

A very perceptive blog post about LLMs (Large Language Models like Chat GPT, GTP-4, et al) by Steve Yegge, one of the most experienced software gurus around.

TL;DR summary

There is something legendary and historic happening in software engineering, right now as we speak, and yet most of you don’t realize at all how big it is.

Includes a compelling example of ChatGPT’s ability to write a good piece of functioning code from a sloppy verbal description of what was required.

Fascinating and worth a read.


Books, etc.

There’s a new issue of the journal Daedalus which is absolutely fabulous. The theme is “Creating a New Moral Political Economy”. It’s edited by Margaret Levi and Henry Farrell and has a list of terrific contributors that includes Alison Gopnik, Anne-marie Slaughter, Joshua Cohen, Rebecca Henderson, Colin Mayer, Margaret O’Mara, Marion Fourcade, danah boyd and Bill Janeway (Whom God Preserve). Like manna from heaven — and it’s free! A whole weekend’s brain-food.


DPReview, RIP

DPReview, the best source of informed reviews of photographic gear, is being shuttered by its owner, Amazon, after 25 years. It was founded in 1998 and acquired by Amazon on 2007, having built up a formidable reputation for providing us with detailed reviews of cameras, lenses, and related kit. It was originally based in London, but eventually moved its operations to Seattle to be closer to its new owner and where it continued to operate relatively independently.

It was caught up in the recent round of layoffs at Amazon. At a guess, I’d say that — given the way that smartphone photography has eroded the market for real photo kit — it was regarded by Amazon as a poor prospect for growth.

Pity. I always valued its reviews, and occasionally bought something based on them.


How to beat Trump?

Jack Shafer’s depressing advice for De Santis.

Apparently, there’s no mileage in attacking him for his innumerable failings.

Trump’s vulnerabilities reside in his positives, and that’s where DeSantis should probe for cracks and fissures. This is no independent discovery. GOP campaign strategist Karl Rove was famous for eroding an opponent’s strengths. For example, under the Rove lens during the 2004 presidential campaign, patriotic war veteran Sen. John Kerry was portrayed as something of a weakling as he challenged President George W. Bush (who, unlike Kerry, spent the Vietnam War in the Texas Air National Guard). “Sometimes people’s strengths turn out to be really big weaknesses,” Rove told Fox News in 2007. “We tend to — you know, people tend to sometimes in campaigns accentuate things that they think are big and important, and they exaggerate them.”

What are Trump’s positives? In his campaign 2016 kickoff, he promised, “I will build a great, great wall on our southern border and I’ll have Mexico pay for that wall,” and continued to praise his wall throughout the 2020 campaign. The wall turned out to be a Potemkin affair, with PolitiFact finding in 2020, “What the administration has mostly done is replace old and outdated designs with newer and improved barriers.” DeSantis could easily out-wing and out-demagogue Trump on the border (remember his airlift of asylum seekers to Martha’s Vineyard?) by savaging Trump’s wall as an illusion.

To defeat Trump, Shafer thinks De Santis could learn a thing or two from Stormy Daniels, the porn star who has won every round so far against Trump.

Daniels refused to be intimidated by Trump’s threats (ad baculum) and shrugged off his lawyer’s attempts at coercion. She didn’t let Trump reduce her to an object (reification) of scorn or hatred. And when she retaliated against him, it was with the artillery of humor, insulting his manhood. “In addition to his…umm…shortcomings, he has demonstrated his incompetence, hatred of women, and lack of self-control on Twitter AGAIN! And perhaps a penchant for bestiality. Game on, Tiny,” Daniels tweeted.

Depressing, isn’t it, when one thinks that the future of there American republic (if it has one) could be decided at this level.


This Blog is also available as a daily email. If you think that might suit you better, why not subscribe? One email a day, Monday through Friday, delivered to your inbox. It’s free, and you can always unsubscribe if you conclude your inbox is full enough already!


Wednesday 29 March, 2023

Haut Canine

We were having dinner in a nice Copenhagen restaurant one evening in 2022 when the proprietor’s dog decided to sit opposite to keep a friendly eye on these two strangers who had wandered onto his territory.


Quote of the Day

”The mistakes of the great, promulgated along with the discoveries of their genius, are apt to work havoc.”

  • Erwin Schrödinger, in “Nature and the Greeks”.

Musical alternative to the morning’s radio news

Joni Mitchell | California | BBC In Concert, 1970)

Link

Joni playing a dulcimer.

Thanks to Tom Hubbard for the link. And see Commonplace Booklet below for a trip down that particular rabbit hole.


Long Read of the Day

The RESTRICT Act 

Perceptive essay by Kevin Xu on the RESTRICT Act currently wending its unimpeded way through Congress, and on what it means for Chinese companies hoping to do business in the US.

TL;DR — it’s “game over” for them.

From time to time, I like to read the full text of a legislative bill, if only to put my past work experience at the White House and my law degree to some good use. What caught my attention recently was the RESTRICT Act, which goes after the national security implications of Chinese technologies in the US. It is getting lots of traction in DC, so I read it – all 55-pages of it.

My one-sentence conclusion: if it becomes law, the RESTRICT Act basically spells “game over” for all Chinese technology companies seeking to do business in the US.

RESTRICT stands for Restricting the Emergence of Security Threats that Risk Information and Communications Technology. (Never underestimate how much energy Congressional staffers put into a catchy acronym to help pass a bill.) It covers all the potential dangers posed by technologies affiliated with America’s foreign adversaries – namely, the PRC (including Hong Kong and Macau), Russia, North Korea, Iran, Cuba, and Venezuela under Maduro. But everyone knows the bill is squarely aimed at China and, to a much lesser extent, Russia. (No one is concerned about the threat of networking equipment made in Iran or Cuba.)

What’s surprising to me is how extremely comprehensive the technology areas that are covered under this proposal, and how much power this bill gives the executive branch to ban (or restrict) these technologies for national security purposes…

Eerie echoes of the Cold War and CoCom.


Books, etc.

John Gray’s  Feline Philosophy: Cats and the Meaning of Life is great.


My commonplace booklet

On dulcimers, hammered or not

Tom Hubbard took issue with Sheila Hayman’s theory about ‘hammered’ dulcimers.

Ooooh, you’re going to hear from a lot of indignant dulcimer aficionados about your crude description of dulcimer distinctions.

Two very different instruments. Wikipedia can help.

It does. There are hammered ones (i.e. ones you play with hammers) and Appalachian ones, which are three- or four-stringed fretted instruments, generally played on the lap by strumming. (As by Joni Mitchell above).

He also sent a link to a great interpreter of the hammered dulcimer, one John McCutcheon. Here he is.


This Blog is also available as a daily email. If you think that might suit you better, why not subscribe? One email a day, Monday through Friday, delivered to your inbox. It’s free, and you can always unsubscribe if you conclude your inbox is full enough already!


Tuesday 28 March, 2023

Stepping stones

A section of the ‘limestone pavement’ of the Burren in Co Clare. Seen from a distance the karst landscape looks completely barren (“like a moonscape” someone once said). Yet close up it’s anything but. In fact, Wikipedia says, the region is renowned for its remarkable assemblage of plants and animals, and over 70% of Ireland’s species of flowers are found there. The Burren supports Arctic–alpine and Mediterranean Basin plants side-by-side, due to the unusual environment, as well as  many rare Irish species, some of which are only found in this area. When you look more closely, you see that many of the grikes — the crevices between the limestone slabs — basically provide micro-climates in which such exotica thrive. 

We spent a lovely day there on our last trip to Ireland.


Quote of the Day

”Interpretation is the revenge of the intellect upon art.”

  • Susan Sontag

Musical alternative to the morning’s radio news

Bach | Concerto for 2 Violins Strings | BWV 1043: II. Adagio

Link

Chosen because the sun was shining when I was listening to it.


Long Read of the Day

On Writing

Wonderful reflective essay by Helen Lewis on the difficult thing that many of us do for a living.

Notice what you notice. John Lloyd, the great comedy producer, once said to me that the best comedians use the audience as an editor: the audience are the experts: they know what’s funny. Something similar is true of journalism: you are a human being encountering the world, and if you find something interesting, the chances are, so will other people. If you find your brow furrowing, don’t be afraid to ask the question that just popped into your head.

The main reason people don’t do this is that they want to seem cool, or knowledgeable, in front of their interviewees. They don’t want to risk asking a stupid questions. Always ask the stupid question. Not least because if you don’t, you might come back, write up your piece and face an editor going, “so what did she mean by saying she lost her virginity to a goat?”

Read on. It’s lovely. And the best thing I’ve read on the subject since John McPhee’s book.

Helen sometimes reminds me of Joan Didion.


Yes, it’s crazy to have TikTok on official phones. But it’s not good for any of us

My OpEd piece in Sunday’s Observer.

As of this moment, government officials in 11 countries are forbidden to run TikTok on their government-issued phones. The countries include the US, Canada, Denmark, Belgium, the UK, New Zealand, Norway, France, the Netherlands and Poland. In addition, European Commission and European parliament staff were required to delete the app. This raises two questions.

First, why were politicians and senior officials in democracies scrolling like zombies through dance crazes, daft pet videos, feeling “bonita” and things you can do with smudged lipstick?

And second, what took these governments so long?

Do read the whole thing


My commonplace booklet

“Excitement” contd.

From the Humanist daily newsletter, which is an endless source of joy to those of us who like that sort of thing (to quote Miss Jean Brodie on the subject of chemistry). There’s been an interesting thread running on the newsletter about the tendency of ostensibly mature scholars regularly to announce (usually on Twitter) how “excited” or even “delighted” they are to be giving a paper at some dreary academic conference or other. (It is, of course, just virtue-signalling on steroids.)

From: Christian-Emil Smith Ore
Subject: Re: [Humanist] 36.478: excitement everywhere all the time, but no Oscar

And also synchronic cultural differences. In USA superlative and adverbs like fantastic are more frequent than in Nordic languages. Many years ago the Swedish lexicographer Martin Gjellerstam analysed a corpus of trivial literature (novels) and accidentally observed that the novels translated from English (US) had a much higher frequency of the word ‘gud’ (God) than the rest and definitely higher than the average of Swedish texts.


This Blog is also available as a daily email. If you think that might suit you better, why not subscribe? One email a day, Monday through Friday, delivered to your inbox. It’s free, and you can always unsubscribe if you conclude your inbox is full enough already!


 

Monday 27 March, 2023

What’s in a picture?

From Noema:

Where a host meets his guests reveals the context in which he wants to be regarded. The background decor of the chosen setting is more than a telling detail. It is the writing on the wall.

In the case of Russian President Vladimir Putin and Chinese President Xi Jinping, the image of power they want to project is out of the historical realm of czars and emperors among whom they place themselves. The civilizational past portrayed on their walls suffuses their vision of the future. It is the common springboard of opposition to the liberal world order of the West they are united in resisting.

This was in splendid evidence at the Moscow summit this week when Putin hosted a banquet for Xi at the 15th-century Palace of Facets in the Kremlin where czars celebrated after their coronation and consecrated the top clergy of the Orthodox Church. The mural behind the two leaders in the photo above, which depicts Vladimir the Great and his sons, is meant to convey legitimacy conferred through continuity. Vladimir ruled what came to be called the Kievan Rus from 980 to 1015, when he unified disparate principalities into one state and converted the nation to Christianity.

It is this very history that lay behind Putin’s justification of the invasion of Ukraine. Could he have been more explicit in what he was asking Xi to endorse?

The Chinese leader may have been unaware of the message the wily namesake of Vladimir I was sending through a staged photo-op. But he would have easily understood the uses of historical continuity as a touchstone to legitimate his own rule.

If Xi was unaware of it at the time, he isn’t now. Besides, as Noema points out, he uses similar imagery himself from time to time.


Quote of the Day

“You only live once, but if you do it right, once is enough”

  • Mae West

Amen.


Musical alternative to the morning’s radio news

The Dubliners | Christ Church

Link


Long Read of the Day

On the allurements of conspiracy theory

Really astute and insightful essay by Phil Christman in the Hedgehog Review on a subject that my colleagues and I spent some years studying before it was academically fashionable. Interesting for — among other things — the way it tries to get inside a conspiracist’s head.

One day, you stumble across something—a long video, an article, a conversation (How rare those are! You must make more time for them…) with a learned friend. The same self-righteousness of authority crosses his face, the tinniness of certainty issued from his mouth too, but this time what he says sticks. It seems to explain the wrongness. Or not even explain it, really—just make it stand still. It was this thing that was wrong. The monster disclosed himself. He was something small and definable—a vaccine, a chemical—that spreads until it can’t be isolated, or he was something large and indefinable—“wokeness,” “CRT”—that terminates in many small, sharp wrongnesses. Or maybe it was the second sort of thing, but epitomized in a single image, so that it sounds like the first: The Cathedral. The cabal. But for a second, you could see the wrongness. How clarifying, simply to see it. You felt something like desire.

As you read on, as you watch more videos, as you continue to talk with your learned friend, you experience, for perhaps the first time in your life, the joy of scholarship. What was school, anyway? A punishment for being awake, a reminder that for every minute of playground, life will exact an hour of sitting still in a hot room that stinks of others’ lunches digesting. How can one doubt the existence of malign conspiracies in a world that answers the miraculous sharpening of adolescent senses with the sense-insulting colors, shapes, smells, of school? School never gave you this feeling, the feeling that “there is a world inside the world,” as Don DeLillo writes in Libra (1988), his great novel of the John F. Kennedy assassination. You start to become, as DeLillo depicts Oswald becoming, a sort of secular monk…

You read like Oswald, obsessively. You marshal for yourself the rough narrative of history that education should already have given you. You become that precious and imperiled thing, an autodidact…

It’s long but worth it.


Gordon Moore RIP

A great figure from the history of modern computing has passed away. Gordon Moore was a co-founder of Intel and the inspiration for the eponymous ‘Law’ predicting that the number of transistors that could be placed on a silicon chip would double at regular intervals for the foreseeable future, thus increasing the data-processing power of computers exponentially.

Holcomb Noble and Katie Hafner have a nice Obituary of him in the New York Times.

I met him once. He was on a visit to Cambridge, where he had endowed a beautiful science and technology library. I asked for an interview and we met in the office of the University Librarian and had a long chat about the early history of the industry and the part he had played in it. At one point I noticed that he was still wearing the ancient digital watch for which he had become famous and asked him why he still wore it. He answered that it was a peg for one of his stories — namely that, at $15 million it was the most expensive watch in the world. How come? Because that was Intel lost from trying to get into — and exiting from — the digital watch business.

Our talk was very enjoyable but after a while I started to worry about his schedule and mentioned to him that the car that the University had arranged to take him to meet the then Chancellor of the University (Prince Philip) should now be picking him up. So we went down to the Library entrance and… there was no limo in sight. He didn’t have a contact number for someone to call, but he knew where he was supposed to be heading. So we climbed into my battered Saab — littered with kids’ toys, tennis racquets and other junk — and I drove him to his destination.

After I dropped him off I drove home and told my late wife Sue about the about my role as an impromptu chauffeur. She was not amused. “What!” she expostulated. “You drove Gordon Moore in our crummy jalopy.” Then she went to her laptop, ascertained how many Intel shares Moore then owned, multiplied that by the share price and came back with the number $7B. The least I could have done, she said, was to get him to buy us a new Saab.

He was a nice and a good man. May he rest in peace.


You wait ages for an AI chatbot to come along, then a whole bunch turn up. Why?

Yesterday’s Observer column:

When, late last year, the editor asked me and other Observer writers what we thought 2023 would be like, my response was that it would be more like 1993 than any other year in recent history. Why? Simply this: 1993 was the year that Mosaic, the first modern web browser, launched and all of a sudden the non-technical world understood what this strange “internet” thing was for. This was despite the fact that the network had been switched on a whole decade earlier, during which time the world seemed almost entirely unaware of it; as a species, we seem to be slow on the uptake.

Much the same would happen in 2023, I thought, with ChatGPT. Machine-learning technology, misleadingly rebranded as artificial intelligence (AI), has been around for eons, but for the most part, only geeks were interested in it. And then out comes ChatGPT and suddenly “meatspace” (internet pioneer John Perry Barlow’s derisive term for the non-techie world) wakes up and exclaims: “So that’s what this AI stuff is all about. Wow!”

And then all hell breaks loose, because it turns out that all the tech giants, who had been obsessed with this generative AI stuff for years, realised that they had been scooped by a small US research outfit called OpenAI (cunningly funded by boring old Microsoft)…

Read on


My Commonplace Booklet

The other day, I wondered what a “hammered dulcimer” might be. (I was vaguely reminded of my undergraduate days when the term “hammered” described someone so drunk as to be incapable of independent locomotion, and I was entertaining fantasies of a inebriated musical instrument wandering the streets.)

Sheila Hayman (Whom God Preserve), whose mission in life is to protect me from my invincible ignorance, provided rapid enlightenment.

Basically, before pianos, keyboard instruments (harpsichords, clavichords, dulcimers) made their notes by plucking the strings, which meant no gradations of sound, no resonance, no long or short notes. Dual keyboard harpsichords made it possible to do loud or soft, but nothing in between. Then forte pianos and later pianofortes came along which hit the strings with hammers, which could be done more or less hard, giving more range of sound. Then dampers and the ‘loud’ pedal gave us resonance, and the ‘soft’ pedal (which just shifts the hammers along so they only hit two strings rather than three) gave an extra layer of expressiveness. Then Erard invetned the double escapement action which made it possible to repeat notes very quickly. Then Beethoven came along and showed what could be done with it. As did Fanny [Mendelssohn] about whom Sheila has made a new documentary.

So a hammered dulcimer, as I understand it, is an evolved dulcimer in which the strings are hammered, not plucked.

So now I know. And so , dear reader, do you.


This Blog is also available as a daily email. If you think that might suit you better, why not subscribe? One email a day, Monday through Friday, delivered to your inbox. It’s free, and you can always unsubscribe if you conclude your inbox is full enough already!