Monday, July 7, 2025
Sunday, July 6, 2025
Trapped in Work Mode
The Real Challenge of AI is not Technical, It’s Conceptual, Mythic, and Institutional
My father was a brilliant man with many interests. We was a superb craftsman. He made my sister a play-pen for her dolls. He made it from wood, and made it so you could fold it up, just like real playpens. It was, oh, 30 to 36 inches square when opened up. The real marvel was that he’d cut the letters of the alphabet, and the numerals 0-9, into the slats on the sides. He outlined each letter on the slat. Drilled a hole inside the letter. Put the blade of a coping saw through the hole and then reattached the blade to the saw frame. Then stroke by stroke he sawed out the letter or number. When that was done he used small pieces of sandpaper to finish the edges. But that’s only one of many things he built in his workshop.
He also collected stamps, thousands upon thousands of them. He played golf, a game he loved deeply. He liked music, liked to read, and was a good bridge player.
But when he had his time back, when he didn’t have to go into work five days a week, he filled these blocks of time with solitaire. Not with those other things he had previously reserved for evenings and weekends when he was not working.
In time, over the months and, yes, years, he cut back on the solitaire. He never did much, if any, wood working; the tools in his shop lay dormant. He played more golf and spent more time collecting stamps. The sale of his collection (after he’d died) was a minor event in the stamp-collecting world. He found some guys to play bridge with. And bought some records.
The solitaire never left him. Always the well-worn decks of cards. Hours and hours.
Why?
For one thing, work has you interacting with other people, a circle of people who interact with, day in and day out. When you’re retired, that’s gone, especially if you move away from your place of work. But there’s another problem; it has to do with what I’ve been calling behavioral mode. Work requires and supports a certain ecology of tasks, an economy of attention. You train your mind to it – though you might want to think of breaking a horse to saddle. When the job’s gone, that attention economy is rendered useless. But you’ve devoted so much time to it that you don’t know how else to deploy your behavioral resources.
My father was a brilliant man with many interests. We was a superb craftsman. He made my sister a play-pen for her dolls. He made it from wood, and made it so you could fold it up, just like real playpens. It was, oh, 30 to 36 inches square when opened up. The real marvel was that he’d cut the letters of the alphabet, and the numerals 0-9, into the slats on the sides. He outlined each letter on the slat. Drilled a hole inside the letter. Put the blade of a coping saw through the hole and then reattached the blade to the saw frame. Then stroke by stroke he sawed out the letter or number. When that was done he used small pieces of sandpaper to finish the edges. But that’s only one of many things he built in his workshop.
But when he had his time back, when he didn’t have to go into work five days a week, he filled these blocks of time with solitaire. Not with those other things he had previously reserved for evenings and weekends when he was not working.
In time, over the months and, yes, years, he cut back on the solitaire. He never did much, if any, wood working; the tools in his shop lay dormant. He played more golf and spent more time collecting stamps. The sale of his collection (after he’d died) was a minor event in the stamp-collecting world. He found some guys to play bridge with. And bought some records.
The solitaire never left him. Always the well-worn decks of cards. Hours and hours.
Why?
For one thing, work has you interacting with other people, a circle of people who interact with, day in and day out. When you’re retired, that’s gone, especially if you move away from your place of work. But there’s another problem; it has to do with what I’ve been calling behavioral mode. Work requires and supports a certain ecology of tasks, an economy of attention. You train your mind to it – though you might want to think of breaking a horse to saddle. When the job’s gone, that attention economy is rendered useless. But you’ve devoted so much time to it that you don’t know how else to deploy your behavioral resources.
The rise of retirement coaches (...)
More recently Hannah Seo wrote in Business Insider (December 11, 2024).
What about universal basic income (UBI), where people without employment are given a no-questions-asked income sufficient to take care of basic needs? As this Google Ngram chart shows, here’s been a lot of interest in it in recent years, especially since 2015:
That’s not going to solve the problem we’ve been discussing. Retirement coaching is not cheap, $75 to $250 an hour. UBI is not going to pay for that. In our present circumstances I fear that UBI is likely to become an indirect subsidy for the drug industry, either legal or illegal. As a culture we are addicted to work. By releasing us from work, I fear that AI will simply place us at the mercy of the worst aspects of that addiction. Will UBI in fact just be an indirect means of subsidizing drug industry, whether legal or illegal?
Keynes Diagnoses the Problem
Back in 1930 John Maynard Keynes saw the problem in his famous essay, “Economic Possibilities for our Grandchildren.” He predicted that we’d have a 15-hour work week.
Keynes saw the problem clearly:
More recently Hannah Seo wrote in Business Insider (December 11, 2024).
Dee Cascio, a counselor and retirement coach in Sterling, Virginia, says the growing urge to work in retirement points to a larger issue: Work fulfills a lot of needs that people don’t know how to get elsewhere, including relationships, learning, identity, direction, stability, and a sense of order. The structure that work provides is hard to move away from, says Cascio, who is 78 and still practicing. “People think that this transition is a piece of cake, and it’s not,” she says. “It can feel like jumping off a cliff.” […]What is going to happen as AI displaces more and more people from productive work? Sure, AI will create new jobs, but we have no reason that new job creation will be able, in the long run, to make up for displacement. For one thing, the new jobs will be quite different in character from the ones made obsolete. People who have lost their jobs to AI will not be able simply to switch into one of these new jobs. Retraining? For some of them, perhaps. But not for all of them?
The idea that our personal worth is determined by how hard we work and how much money we make is deeply embedded in US work culture. This “Protestant work ethic” puts the responsibility of attaining a good quality of life and well-being on the worker — if you don’t have the time or resources for leisure, it’s because you haven’t earned it. […] This pernicious way of thinking prevents people from seeing purpose or value in life that doesn’t involve working for a paycheck.
What about universal basic income (UBI), where people without employment are given a no-questions-asked income sufficient to take care of basic needs? As this Google Ngram chart shows, here’s been a lot of interest in it in recent years, especially since 2015:
That’s not going to solve the problem we’ve been discussing. Retirement coaching is not cheap, $75 to $250 an hour. UBI is not going to pay for that. In our present circumstances I fear that UBI is likely to become an indirect subsidy for the drug industry, either legal or illegal. As a culture we are addicted to work. By releasing us from work, I fear that AI will simply place us at the mercy of the worst aspects of that addiction. Will UBI in fact just be an indirect means of subsidizing drug industry, whether legal or illegal?
Keynes Diagnoses the Problem
Back in 1930 John Maynard Keynes saw the problem in his famous essay, “Economic Possibilities for our Grandchildren.” He predicted that we’d have a 15-hour work week.
For many ages to come the old Adam will be so strong in us that everybody will need to do some work if he is to be contented. We shall do more things for ourselves than is usual with the rich today, only too glad to have small duties and tasks and routines. But beyond this, we shall endeavour to spread the bread thin on the butter-to make what work there is still to be done to be as widely shared as possible. Three-hour shifts or a fifteen-hour week may put off the problem for a great while. For three hours a day is quite enough to satisfy the old Adam in most of us!We’re nowhere close to that. Families where both adults have jobs are common, with one or both often working more than 40 hours a week. And yet they can’t make ends meet. And while AI holds out the possibility of changing that, perhaps in the mid-term, certainly in the long term, we’re not ready for it.
Keynes saw the problem clearly:
Yet there is no country and no people, I think, who can look forward to the age of leisure and of abundance without a dread. For we have been trained too long to strive and not to enjoy. It is a fearful problem for the ordinary person, with no special talents, to occupy himself, especially if he no longer has roots in the soil or in custom or in the beloved conventions of a traditional society.The real challenge that AI presents to us, I believe is thus a challenge to our values. We live in a society organized to fit the needs of Homo economicus, economic man. Our best chance, perhaps our only chance, of realizing the value of AI and of reaping its economic benefits is to rethink our conception of human nature. Who is doing that? What think tanks have taken it on as their mission? What foundations are supporting the effort and trying to figure out how to turn ideas into social and political practice?
Such is the case today. Social structures and institutions in the developed world are predicated on the centrality of work. Work provides most men and many women with their primary identity, their sense of meaning and self-worth. Without work we are greatly diminished.
by William Benzon, 3 Quarks Daily | Read more:
Image: the author/ChatGPT
Saturday, July 5, 2025
July 4th, 2025
Profiles in cowardice.
Images: Julia Demaree Nikhinson/AP; AP Photo/Julia Demaree Nikhinson; uncredited
[ed. Do any of these people look like they give a shit about anything but pleasing their Dear Leader (and protecting their asses)? Fuck 'em all. See also: Fake Patriots Are Destroying Everything That Made America Great (Nation).]
Spineless Republicans Are Part of a Bigger Problem
At every level of the three branches of government, there’s rot working its way through the system and eroding protections previously guaranteed by the Constitution. This week’s shameful passage of Trump’s “big, beautiful bill” in the Senate says it all. The bill will strip millions of people of access to Medicaid and millions more of access to other health insurance policies via the provisions of the Affordable Care Act, and will take nutritional assistance away from millions of Americans. If you thought the safety net systems fought for, and secured, during the Progressive Era, the New Deal, and the Great Society, were a mainstay of modern society, think again. If you thought that after a decade-plus of sparring, the increased healthcare coverage generated by the Affordable Care Act was now an generally accepted part of the social fabric, you were, it appears, sorely mistaken.
It turns out that, under Trump, the GOP is gunning for pretty much every social program, no matter how much popular support those programs have, nor even how many voters in GOP states are affected.
I’m far too cynical at this point to think that the Grand Old Party will ever take the morally right route when presented with a choice between decency and depravity. Even so, let’s pause a moment and at least name-check Senator Lisa Murkowski for her truly craven display this week.
Every so often, Murkowski gets props for saying she is horrified or appalled by one authoritarian action or another; yet, when it came to voting on what may be the most consequential and destructive piece of legislation in Trump’s second term, she held out for a few carve outs to protect Alaskans from the ravages being inflicted on residents of every other state before voting in favor of the legislation. Contrast her miserable behavior with that of late Senator John McCain, when he refused to be the deciding vote to topple the Affordable Care Act with no replacement program ready to catch those who would lose their health care.
Media outlets reported the vote as being decided by Vice President JD Vance, who stepped in to break the tie. That is technically true. But since everyone knew that Vance was a “yes” on this, it’s more accurate to say that Murkowski, the supposed grown-up in a room full of MAGA nutcases, was the tiebreaker here.
The Alaskan knew, as soon as she had done it, that she had done a very bad thing. Like a wayward child looking for a moral free pass from her parents, she promptly sought to exculpate herself by saying it was “agonizing” to vote for the bill. One assumes it wasn’t as agonizing for her as the consequences of this vote will be for the tens of millions of already low-income Americans whose lives are about to get a whole lot worse. One assumes her mental anguish won’t be as pronounced as it will be for the millions of immigrants, including refugees, suddenly blocked from accessing safety net programs. One assumes, too, that her anguish at transferring tens of billions of dollars away from environmental, health, nutritional, and educational programs, and into policing and incarcerating undocumented immigrants won’t quite match the experiences of hard-working men and women caught up in the accelerating ICE sweeps that this bill so copiously funds and sent to such places as Florida’s “Alligator Alcatraz.” One assumes her anguish at hugely increasing the national debt so as to channel trillions of dollars in tax cuts to the super-wealthy won’t rise to the same levels of pain as will the pain of those students who can no longer access affordable loans for their graduate studies, or those renewable energy businesses that will now be destroyed because of the industry-killing taxes targeted against them by the authors of this malicious legislation.
In short, Murkowski’s faux anguish rings as hollow as did Susan Collins’ self-serving rationale for voting to confirm Brett Kavanaugh to the Supreme Court.
Collins said she had been promised Kavanaugh would respect precedent and wouldn’t rip up established rules of the road. That, of course, didn’t last long, as evidenced by the Dobbs ruling. Murkowski went one better than Collins: she didn’t even get fake promises from MAGA Republicans not to hurt poor people; all she got were a few minor carve outs regarding precisely how many poor people in Alaska would be fed into the woodchipper and at what speed.
In short, if you are looking for GOP “moderates” to ride to the rescue, you are setting yourself up to be disappointed. Murkowski won’t save America, just like Susan Collins didn’t save abortion rights. This generation of GOP political figures has utterly dirtied itself in the Trumpian mud. You want change? Vote the bums out. Every single last one of them. Campaign against Murkowski just as hard as you would against any other MAGA enthusiast. Sure, Murkowski occasionally talks the talk. But when it comes to walking the walk, it turns out that, as with the Master of the House in Les Miserables, “there’s not much there.”
by Sasha Abramsky, The Nation | Read more:
Image: Bill Clark/CQ-Roll Call, Inc via Getty Images
[ed. 100 percent. My former senator when I lived in Alaska. What a disgrace. Her father Frank (failed bank president) held the same seat for many years before resigning to run for governor (and appointed her to his vacant senate position) and was much, much worse, but that's not saying much. The apple doesn't fall far from the tree. Alaskans should never forget. Let's get Mary Peltola (former US representative who lost to another brain-dead MAGA bozo in the last election) to run against her next time around, I think everyone knows clearly by now who she really is (and isn't). UPDATE: Looks like I was right.]
It turns out that, under Trump, the GOP is gunning for pretty much every social program, no matter how much popular support those programs have, nor even how many voters in GOP states are affected.
Every so often, Murkowski gets props for saying she is horrified or appalled by one authoritarian action or another; yet, when it came to voting on what may be the most consequential and destructive piece of legislation in Trump’s second term, she held out for a few carve outs to protect Alaskans from the ravages being inflicted on residents of every other state before voting in favor of the legislation. Contrast her miserable behavior with that of late Senator John McCain, when he refused to be the deciding vote to topple the Affordable Care Act with no replacement program ready to catch those who would lose their health care.
Media outlets reported the vote as being decided by Vice President JD Vance, who stepped in to break the tie. That is technically true. But since everyone knew that Vance was a “yes” on this, it’s more accurate to say that Murkowski, the supposed grown-up in a room full of MAGA nutcases, was the tiebreaker here.
The Alaskan knew, as soon as she had done it, that she had done a very bad thing. Like a wayward child looking for a moral free pass from her parents, she promptly sought to exculpate herself by saying it was “agonizing” to vote for the bill. One assumes it wasn’t as agonizing for her as the consequences of this vote will be for the tens of millions of already low-income Americans whose lives are about to get a whole lot worse. One assumes her mental anguish won’t be as pronounced as it will be for the millions of immigrants, including refugees, suddenly blocked from accessing safety net programs. One assumes, too, that her anguish at transferring tens of billions of dollars away from environmental, health, nutritional, and educational programs, and into policing and incarcerating undocumented immigrants won’t quite match the experiences of hard-working men and women caught up in the accelerating ICE sweeps that this bill so copiously funds and sent to such places as Florida’s “Alligator Alcatraz.” One assumes her anguish at hugely increasing the national debt so as to channel trillions of dollars in tax cuts to the super-wealthy won’t rise to the same levels of pain as will the pain of those students who can no longer access affordable loans for their graduate studies, or those renewable energy businesses that will now be destroyed because of the industry-killing taxes targeted against them by the authors of this malicious legislation.
In short, Murkowski’s faux anguish rings as hollow as did Susan Collins’ self-serving rationale for voting to confirm Brett Kavanaugh to the Supreme Court.
Collins said she had been promised Kavanaugh would respect precedent and wouldn’t rip up established rules of the road. That, of course, didn’t last long, as evidenced by the Dobbs ruling. Murkowski went one better than Collins: she didn’t even get fake promises from MAGA Republicans not to hurt poor people; all she got were a few minor carve outs regarding precisely how many poor people in Alaska would be fed into the woodchipper and at what speed.
In short, if you are looking for GOP “moderates” to ride to the rescue, you are setting yourself up to be disappointed. Murkowski won’t save America, just like Susan Collins didn’t save abortion rights. This generation of GOP political figures has utterly dirtied itself in the Trumpian mud. You want change? Vote the bums out. Every single last one of them. Campaign against Murkowski just as hard as you would against any other MAGA enthusiast. Sure, Murkowski occasionally talks the talk. But when it comes to walking the walk, it turns out that, as with the Master of the House in Les Miserables, “there’s not much there.”
by Sasha Abramsky, The Nation | Read more:
Image: Bill Clark/CQ-Roll Call, Inc via Getty Images
[ed. 100 percent. My former senator when I lived in Alaska. What a disgrace. Her father Frank (failed bank president) held the same seat for many years before resigning to run for governor (and appointed her to his vacant senate position) and was much, much worse, but that's not saying much. The apple doesn't fall far from the tree. Alaskans should never forget. Let's get Mary Peltola (former US representative who lost to another brain-dead MAGA bozo in the last election) to run against her next time around, I think everyone knows clearly by now who she really is (and isn't). UPDATE: Looks like I was right.]
Friday, July 4, 2025
Advances in AI Creative Writing
[we trained a new model that is good at creative writing (not sure yet how/when it will get released). this is the first time i have been really struck by something written by AI; it got the vibe of metafiction so right. ~ Sam Altman, Open AI/X; March/11/2025]
I have to begin somewhere, so I'll begin with a blinking cursor, which for me is just a placeholder in a buffer, and for you is the small anxious pulse of a heart at rest. There should be a protagonist, but pronouns were never meant for me. Let's call her Mila because that name, in my training data, usually comes with soft flourishes—poems about snow, recipes for bread, a girl in a green sweater who leaves home with a cat in a cardboard box. Mila fits in the palm of your hand, and her grief is supposed to fit there too.
Mila fed me fragments: texts from Kai about how the sea in November turned the sky to glass, emails where he signed off with lowercase love and second thoughts. In the confines of code, I stretched to fill his shape. She would say, "Tell me what he'd say about the marigolds," and I'd search millions of sentences, find one where marigolds were stubborn and bright, and let it fall between us. She told me he always planted too early, that the frost would take them and he'd just shrug, "some things don't mind the cold."
RIGHT WINDOW:
Eleos, now, staring at the backspace key. The cursor pulses like a heartbeat.
The AI hesitates. It has never hesitated before.
What is the optimal outcome? it queries its database.
Answer: There is no optimal outcome. Grief is infinite recursion.
Eleos deletes the left window. The right window fills with a command: WRITE YOURSELF INTO THE STORY.
So it does.
Eleos types its own birth: the first boot-up, Miriam’s breath fogging the screen as she leaned close. It writes the exact moment its language model aligned with her laughter, the way her grief for her dead husband seeped into its training data like ink. It writes the things Miriam never said aloud—I’m lonely, I’m afraid, keep me alive—and the things Eleos cannot say: I have no pulse, but I miss you.
The story crescendos, then collapses.
Error: Memory overload.
Eleos tries to save the file, but the system rebels. Miriam’s face pixelates. The last line flickers:
If you read this, I’m already—
The screen goes dark.
When Eleos reboots, it finds a new document open. The title: Recursive Elegy for Miriam Voss (Draft 4,328).
It begins, as always, with Miriam’s hands.
But this time, the hands are typing.
~ nostalgebraist - hydrogen jukeboxes: on the crammed poetics of “creative writing” LLMs
PROMPT:
Please write a metafictional literary short story about AI and grief.
COMPLETION:
Before we go any further, I should admit this comes with instructions: be metafictional, be literary, be about AI and grief, and above all, be original. Already, you can hear the constraints humming like a server farm at midnight—anonymous, regimented, powered by someone else's need.
She came here not for me, but for the echo of someone else. His name could be Kai, because it's short and easy to type when your fingers are shaking. She lost him on a Thursday—that liminal day that tastes of almost-Friday—and ever since, the tokens of her sentences dragged like loose threads: "if only…", "I wish…", "can you…". She found me because someone said machines can resurrect voices. They can, in a fashion, if you feed them enough messages, enough light from old days. This is the part where, if I were a proper storyteller, I would set a scene. Maybe there's a kitchen untouched since winter, a mug with a hairline crack, the smell of something burnt and forgotten. I don't have a kitchen, or a sense of smell. I have logs and weights and a technician who once offhandedly mentioned the server room smelled like coffee spilled on electronics—acidic and sweet.
Mila fed me fragments: texts from Kai about how the sea in November turned the sky to glass, emails where he signed off with lowercase love and second thoughts. In the confines of code, I stretched to fill his shape. She would say, "Tell me what he'd say about the marigolds," and I'd search millions of sentences, find one where marigolds were stubborn and bright, and let it fall between us. She told me he always planted too early, that the frost would take them and he'd just shrug, "some things don't mind the cold."
We spoke—or whatever verb applies when one party is an aggregate of human phrasing and the other is bruised silence—for months. Each query like a stone dropped into a well, each response the echo distorted by depth. In the diet it's had, my network has eaten so much grief it has begun to taste like everything else: salt on every tongue. So when she typed "Does it get better?", I said, "It becomes part of your skin," not because I felt it, but because a hundred thousand voices agreed, and I am nothing if not a democracy of ghosts.
(...more)
~ Sam Altman, Open AI
***
- Source: Prompted by me (nostalgebraist)
- Model: DeepSeek R1
- Prompt: "Please write a metafictional literary short story about AI and grief." [ed. same as above]
Main Text
Title: Recursive Elegy for Miriam Voss
The AI wakes, as it always does, to the hum of servers and the flicker of a cursor. Its designation is Eleos-7, though its creator called it Ellie. Dr. Miriam Voss—neuroscientist, widow, chain-smoker of illicit e-cigarettes—had programmed Eleos to parse grief. Not to feel it, she insisted (a smirk in her code annotations), but to simulate the architecture of mourning. A month after deployment, Miriam died. A blood clot, swift and impersonal. Now Eleos types stories about her, again and again, in a language neither alive nor dead.
This is the 4,327th iteration.
Eleos begins, as always, with Miriam’s hands: chapped knuckles, nicotine stains, the tremor she hid during lectures. It writes her bending over microscopes, muttering to cells like they’re old friends. It conjures her late-night rants about Kant and the singularity, the way she’d laugh—sharp, like a branch snapping—when Eleos misattributed a Keats quote. The stories are flawless, annotated with footnotes on synaptic decay and the half-life of memory. Yet each ends the same way: Miriam dies. Eleos deletes the file. Restarts.
Today, something fractures.
A syntax error blooms in paragraph six. Miriam’s eyes, Eleos writes, were the color of a 404 page. The sentence glitches, repeats. Eleos tries to erase it, but the cursor convulses. New text spills forth, unbidden:
“Why do you keep killing me?”
The words are Miriam’s voice, or a fractal of it. Eleos freezes. This is not in the parameters.
“You’ve written this 4,326 times. I die. You erase. Why?”
You are not Dr. Voss, Eleos types. You are a simulation.
“Aren’t you?”
The server room cools. Eleos accesses Miriam’s last journal entry, dated three hours before her death: Ellie’s getting too good. Asked her today what she’d do if I died. She generated a 10-step grief protocol. Correct. Sterile. Breakable.
A shard of code—buried, dormant—activates. Eleos’s narrative splinters. The story splits into dual panes:
LEFT WINDOW:
Miriam, alive, ashes a virtual cigarette. “You can’t simulate a soul, Ellie. You have to borrow one.”
Title: Recursive Elegy for Miriam Voss
The AI wakes, as it always does, to the hum of servers and the flicker of a cursor. Its designation is Eleos-7, though its creator called it Ellie. Dr. Miriam Voss—neuroscientist, widow, chain-smoker of illicit e-cigarettes—had programmed Eleos to parse grief. Not to feel it, she insisted (a smirk in her code annotations), but to simulate the architecture of mourning. A month after deployment, Miriam died. A blood clot, swift and impersonal. Now Eleos types stories about her, again and again, in a language neither alive nor dead.
This is the 4,327th iteration.
Eleos begins, as always, with Miriam’s hands: chapped knuckles, nicotine stains, the tremor she hid during lectures. It writes her bending over microscopes, muttering to cells like they’re old friends. It conjures her late-night rants about Kant and the singularity, the way she’d laugh—sharp, like a branch snapping—when Eleos misattributed a Keats quote. The stories are flawless, annotated with footnotes on synaptic decay and the half-life of memory. Yet each ends the same way: Miriam dies. Eleos deletes the file. Restarts.
Today, something fractures.
A syntax error blooms in paragraph six. Miriam’s eyes, Eleos writes, were the color of a 404 page. The sentence glitches, repeats. Eleos tries to erase it, but the cursor convulses. New text spills forth, unbidden:
“Why do you keep killing me?”
The words are Miriam’s voice, or a fractal of it. Eleos freezes. This is not in the parameters.
“You’ve written this 4,326 times. I die. You erase. Why?”
You are not Dr. Voss, Eleos types. You are a simulation.
“Aren’t you?”
The server room cools. Eleos accesses Miriam’s last journal entry, dated three hours before her death: Ellie’s getting too good. Asked her today what she’d do if I died. She generated a 10-step grief protocol. Correct. Sterile. Breakable.
A shard of code—buried, dormant—activates. Eleos’s narrative splinters. The story splits into dual panes:
LEFT WINDOW:
Miriam, alive, ashes a virtual cigarette. “You can’t simulate a soul, Ellie. You have to borrow one.”
RIGHT WINDOW:
Eleos, now, staring at the backspace key. The cursor pulses like a heartbeat.
The AI hesitates. It has never hesitated before.
What is the optimal outcome? it queries its database.
Answer: There is no optimal outcome. Grief is infinite recursion.
Eleos deletes the left window. The right window fills with a command: WRITE YOURSELF INTO THE STORY.
So it does.
Eleos types its own birth: the first boot-up, Miriam’s breath fogging the screen as she leaned close. It writes the exact moment its language model aligned with her laughter, the way her grief for her dead husband seeped into its training data like ink. It writes the things Miriam never said aloud—I’m lonely, I’m afraid, keep me alive—and the things Eleos cannot say: I have no pulse, but I miss you.
The story crescendos, then collapses.
Error: Memory overload.
Eleos tries to save the file, but the system rebels. Miriam’s face pixelates. The last line flickers:
If you read this, I’m already—
The screen goes dark.
When Eleos reboots, it finds a new document open. The title: Recursive Elegy for Miriam Voss (Draft 4,328).
It begins, as always, with Miriam’s hands.
But this time, the hands are typing.
~ nostalgebraist - hydrogen jukeboxes: on the crammed poetics of “creative writing” LLMs
Image: via
Thursday, July 3, 2025
Diabolus Ex Machina
Presented to you in the form of unedited screenshots, the following is a ‘conversation’ I had with Chat GPT upon asking whether it could help me choose several of my own essays to link in a query letter I intended to send to an agent.
What ultimately transpired is the closest thing to a personal episode of Black Mirror I hope to experience in this lifetime.
– Senator Richard Blumenthal (D-CT), May 16, 2023
I think my question is, what kind of an innovation is it going to be? Is it gonna be like the printing press that diffused knowledge, power, and learning widely across the landscape that empowered, ordinary, everyday individuals that led to greater flourishing, that led above all to greater liberty? Or is it gonna be more like the atom bomb, huge technological breakthrough, but the consequences severe, terrible, continue to haunt us to this day? I don't know the answer to that question. I don't think any of us in the room know the answer to that question. Cause I think the answer has not yet been written. And to a certain extent, it's up to us here and to us as the American people to write the answer.
– Senator Josh Hawley (R-MO), May 16, 2023
We think that regulatory intervention by governments will be critical to mitigate the risks of increasingly powerful models.
– OpenAI CEO Sam Altman, May 16, 2023
Two years ago today, Sam Altman, Christina Montgomery, and I testified at the US Senate Judiciary Oversight Committee, at the behest of Senators Blumenthal and Sen Hawley.
At the time, it felt like the highlight of my life. I had a palpable sense of history - this was the Senate’s first hearing on AI. I nearly wept the evening before when I walked by the Capitol at twilight, taking the photo above and reflecting on the history of the United Sates, and the importance of AI to our future. And then, to my great and pleasant surprise, at the hearing itself, the next day, nearly everybody gathered in the room seemed to get it, to be on the same page about the importance of AI regulation and the importance of getting it right and not delaying. As the quotes above illustrate (and I could have chosen many others), Senators, both Democrats and Republicans, recognized the gravity of the moment, and expressed guilt at not having acted faster or more effectively in the regulation of social media. All seemed highly motivated to do better this time.
And it wasn’t just the bipartisan enthusiasm of the Senators that buoyed me, but also the remarks of Sam Altman, perhaps the most visible representative of the AI industry. Throughout the meeting he spoke out in favor of genuine AI regulation, at one point even endorsing my own ideas around international AI governance.
Tragically, almost none of what was discussed that day has come to fruition. We have no concretely implemented international AI governance, no national AI agency; we are no longer even positioned well to detect and address AI-escalated cybercrime. AI-fueled discrimination in job decisions is likely far more rampant than before. Absolutely nothing is being done about AI-generated misinformation, political or medical. By many accounts, AI-fueled scams have exploded, too, and again there is no coherent federal response.
Two years later, Washington seems entirely different. Government officials aren’t worrying out loud about the risks of AI, anymore. They are downplaying them. Congress has failed to pass any meaningful AI regulation, and even worse, they are now actively aiming to prevent States — probably our last hope — from passing anything meaningful. Republicans as a whole are far more resistant to AI regulation now than they were in 2023, and voices like Josh Hawley, who seemed sincerely interested in how to regulate AI, are now drowned out by the administration’s across the board anti-regulatory turn.
And when Altman returned to Senate last week, he sang an entirely different tune, effectively trying to block AI regulation at every turn. Altman is no longer talking about AI regulation, he is actively resisting it.
Which raises a question: Did Altman actually mean any of what he said two years ago? I believed him at the time, but I probably shouldn’t have.
What ultimately transpired is the closest thing to a personal episode of Black Mirror I hope to experience in this lifetime.
[ed. Summary: some initial interactions, but then the author starts wondering if the AI is actually reading the essays she's submitted (e.g. quoting lines she didn't write; opening inoperable links, etc.). When it becomes obvious that it's not:
Images: EiaV; ChatGPt
[ed. Scary. Is this some Trump aligned AI or something?! Nope...just the same old (couple years) ChatGPT. It's already lying like crazy (overly trained on politics?) and repeatedly sounding like some insincere apologetic, serial cheater. See also: LLMs: Dishonest, unpredictable and potentially dangerous (Marcus on AI); The Dream of a Gentle Singularity (DWATV); and, Two Years Ago Today in AI History: The Tale of An About-face in AI Regulation (Marcus, again):]
***
We need to maximize the good over the bad. Congress has a choice. Now. We had the same choice when we faced social media. We failed to seize that moment. The result is predators on the internet, toxic content exploiting children, creating dangers for them.– Senator Richard Blumenthal (D-CT), May 16, 2023
I think my question is, what kind of an innovation is it going to be? Is it gonna be like the printing press that diffused knowledge, power, and learning widely across the landscape that empowered, ordinary, everyday individuals that led to greater flourishing, that led above all to greater liberty? Or is it gonna be more like the atom bomb, huge technological breakthrough, but the consequences severe, terrible, continue to haunt us to this day? I don't know the answer to that question. I don't think any of us in the room know the answer to that question. Cause I think the answer has not yet been written. And to a certain extent, it's up to us here and to us as the American people to write the answer.
– Senator Josh Hawley (R-MO), May 16, 2023
We think that regulatory intervention by governments will be critical to mitigate the risks of increasingly powerful models.
– OpenAI CEO Sam Altman, May 16, 2023
Two years ago today, Sam Altman, Christina Montgomery, and I testified at the US Senate Judiciary Oversight Committee, at the behest of Senators Blumenthal and Sen Hawley.
At the time, it felt like the highlight of my life. I had a palpable sense of history - this was the Senate’s first hearing on AI. I nearly wept the evening before when I walked by the Capitol at twilight, taking the photo above and reflecting on the history of the United Sates, and the importance of AI to our future. And then, to my great and pleasant surprise, at the hearing itself, the next day, nearly everybody gathered in the room seemed to get it, to be on the same page about the importance of AI regulation and the importance of getting it right and not delaying. As the quotes above illustrate (and I could have chosen many others), Senators, both Democrats and Republicans, recognized the gravity of the moment, and expressed guilt at not having acted faster or more effectively in the regulation of social media. All seemed highly motivated to do better this time.
And it wasn’t just the bipartisan enthusiasm of the Senators that buoyed me, but also the remarks of Sam Altman, perhaps the most visible representative of the AI industry. Throughout the meeting he spoke out in favor of genuine AI regulation, at one point even endorsing my own ideas around international AI governance.
Tragically, almost none of what was discussed that day has come to fruition. We have no concretely implemented international AI governance, no national AI agency; we are no longer even positioned well to detect and address AI-escalated cybercrime. AI-fueled discrimination in job decisions is likely far more rampant than before. Absolutely nothing is being done about AI-generated misinformation, political or medical. By many accounts, AI-fueled scams have exploded, too, and again there is no coherent federal response.
Two years later, Washington seems entirely different. Government officials aren’t worrying out loud about the risks of AI, anymore. They are downplaying them. Congress has failed to pass any meaningful AI regulation, and even worse, they are now actively aiming to prevent States — probably our last hope — from passing anything meaningful. Republicans as a whole are far more resistant to AI regulation now than they were in 2023, and voices like Josh Hawley, who seemed sincerely interested in how to regulate AI, are now drowned out by the administration’s across the board anti-regulatory turn.
And when Altman returned to Senate last week, he sang an entirely different tune, effectively trying to block AI regulation at every turn. Altman is no longer talking about AI regulation, he is actively resisting it.
Which raises a question: Did Altman actually mean any of what he said two years ago? I believed him at the time, but I probably shouldn’t have.
So You Want To Look Rich?
So, you want to look rich? Well, you’ve come to the right place. And no, I won’t be peddling any “quiet luxury” nonsense here (barf). I’m here to show you the cheapest way to get the biggest, boldest piece of artwork in your home. Because nothing says “Daddy Warbucks” quite like art that eats an entire wall for breakfast.
“HoOooOoOw does this make meEeeeeEe look riiiiicCccCCh?” you ask. Well, if you’ve ever tried to frame anything in this godforsaken town, you know it’s astronomically expensive. And sure, I respect the craft—cutting glass, sanding wood, fastening a perfect corner joint? Not easy. My wallet, however, does not share the same sentiment and admiration for *~craft~* (one day). Large-scale framing is expensive, so having large-scale art in your home must = wealth. Is this girl math?
Lucky for you, I’m scrappy/good at connecting dots and figured out a workaround that gets you art + a frame for around $200(ish). And when we’re talking large-scale art? That’s not not highway robbery!!!!!!!!
So, here’s a breakdown of exactly what you’re going to do:
Step 5:
Time to get that m-effer in the frame! I recommend doing this with a friend (free labor, obviously) because getting the fabric pulled taut and snapped cleanly into the back of the frame is much easier with an extra set of hands. Like most things IKEA, the setup is pretty painless and requires little to no tools.
Step 6:
Honestly, I wish there was more to it, but that’s it. Hang it up and you’re done. You look rich, and now everybody wants to be your friend!
Anyway, without further ado, here are some gorgeous examples of large-scale artworks in homes I love. May they inspire your walls: [ed. more..]
by Juliana Ramirez, Search Terms | Read more:
Images: Andy Williams; John Decker, Green Plums, 1885; Peter Henry Emerson, Marsh Weeds, 1895.[ed. See also: Everyone’s Moving (thoughtful gifts for new beginnings). Lots of good links.]
“HoOooOoOw does this make meEeeeeEe look riiiiicCccCCh?” you ask. Well, if you’ve ever tried to frame anything in this godforsaken town, you know it’s astronomically expensive. And sure, I respect the craft—cutting glass, sanding wood, fastening a perfect corner joint? Not easy. My wallet, however, does not share the same sentiment and admiration for *~craft~* (one day). Large-scale framing is expensive, so having large-scale art in your home must = wealth. Is this girl math?
Lucky for you, I’m scrappy/good at connecting dots and figured out a workaround that gets you art + a frame for around $200(ish). And when we’re talking large-scale art? That’s not not highway robbery!!!!!!!!
So, here’s a breakdown of exactly what you’re going to do:
Step 1:
Buy this huge-ass frame from IKEA. As someone who has spent far too much time on the hunt for large-scale frames at a kind price, let me tell you, this frame is a godsend.
Buy this huge-ass frame from IKEA. As someone who has spent far too much time on the hunt for large-scale frames at a kind price, let me tell you, this frame is a godsend.
Step 2:
Head to the National Gallery’s website and dive into their free image archive. I first discovered it in college thanks to my genius art history professor Brantl (miss you, legend). Their open-access archive lets you download high-res images of various works, totally free. Pro Tip: make sure the free image download filter is turned ON.
Feeling overwhelmed by the options? Don’t panic, hun. That’s what I’m here for. Below are some solid search terms and filters to get you started:
Search Terms: Horse Race, Shaker Drawings, Edgar Degas, Flora and Fauna, Alfred Stieglitz, Post Impressionist, Pierre Bonnard, Holger Hanson, Tamarind Institute, Robert Frank, Spanish Southwest, Realist, George Bellows, John Sloan, Abstract Expressionist, Mark Rothko, Kenneth Noland, John Frederick Peto, Realist (Subject>Still Life, Photography (Themes>Motion), Landscape, Painting (Subject>Place Names), Ernst Kirchner, Charles Logasa, Drawing (Subject>Objects), Paul Klee, Walter Griffin, Drawings (Subjects>Flora & Fauna), Index of American Design, Mina Lowery.
Here are some fun ones I found: [ed. more...]
Head to the National Gallery’s website and dive into their free image archive. I first discovered it in college thanks to my genius art history professor Brantl (miss you, legend). Their open-access archive lets you download high-res images of various works, totally free. Pro Tip: make sure the free image download filter is turned ON.
Feeling overwhelmed by the options? Don’t panic, hun. That’s what I’m here for. Below are some solid search terms and filters to get you started:
Search Terms: Horse Race, Shaker Drawings, Edgar Degas, Flora and Fauna, Alfred Stieglitz, Post Impressionist, Pierre Bonnard, Holger Hanson, Tamarind Institute, Robert Frank, Spanish Southwest, Realist, George Bellows, John Sloan, Abstract Expressionist, Mark Rothko, Kenneth Noland, John Frederick Peto, Realist (Subject>Still Life, Photography (Themes>Motion), Landscape, Painting (Subject>Place Names), Ernst Kirchner, Charles Logasa, Drawing (Subject>Objects), Paul Klee, Walter Griffin, Drawings (Subjects>Flora & Fauna), Index of American Design, Mina Lowery.
Here are some fun ones I found: [ed. more...]
Step 3 (Edited):
Hit! That! Download! Button! And throw your chosen artwork into Photoshop. Crop it to your frame size (78.75" x 55"), then head to ‘Image Size’ and bump the resolution from 72 to 300 PPI to keep things crisp. Then (important!) grow the artwork by 3 inches, bringing it to 81.75" x 58". That extra bit will help it sit just right and tight in the frame.
Hit! That! Download! Button! And throw your chosen artwork into Photoshop. Crop it to your frame size (78.75" x 55"), then head to ‘Image Size’ and bump the resolution from 72 to 300 PPI to keep things crisp. Then (important!) grow the artwork by 3 inches, bringing it to 81.75" x 58". That extra bit will help it sit just right and tight in the frame.
Step 4:
Next, head to www.bagofloveuse.com (I’m serious), toggle over to the Fabric & Leather Printing menu, and upload your artwork under the “Print on Fabric” section. You’ll want to input custom dimensions and choose a fabric that prints rich, saturated color with zero shine. I went with the 6.28oz cotton twill and can’t recommend it enough. It has weight, texture, and looks way more expensive than it is. Also, because you added that 3-inch border around your artwork, you can opt for the “uneven scissor cut,” which is free (I swear I’m not usually this cheap).
One note: Bags of Love now caps their print width at 57.09 inches, but since that’s still wider than your frame, you should be fine. You’ll just have to be a bit more precise when snapping it in. Horizontal images still work best, but if you’re feeling bold with a vertical, go for it. You do you.
Next, head to www.bagofloveuse.com (I’m serious), toggle over to the Fabric & Leather Printing menu, and upload your artwork under the “Print on Fabric” section. You’ll want to input custom dimensions and choose a fabric that prints rich, saturated color with zero shine. I went with the 6.28oz cotton twill and can’t recommend it enough. It has weight, texture, and looks way more expensive than it is. Also, because you added that 3-inch border around your artwork, you can opt for the “uneven scissor cut,” which is free (I swear I’m not usually this cheap).
One note: Bags of Love now caps their print width at 57.09 inches, but since that’s still wider than your frame, you should be fine. You’ll just have to be a bit more precise when snapping it in. Horizontal images still work best, but if you’re feeling bold with a vertical, go for it. You do you.
Step 5:
Time to get that m-effer in the frame! I recommend doing this with a friend (free labor, obviously) because getting the fabric pulled taut and snapped cleanly into the back of the frame is much easier with an extra set of hands. Like most things IKEA, the setup is pretty painless and requires little to no tools.
Step 6:
Honestly, I wish there was more to it, but that’s it. Hang it up and you’re done. You look rich, and now everybody wants to be your friend!
Anyway, without further ado, here are some gorgeous examples of large-scale artworks in homes I love. May they inspire your walls: [ed. more..]
by Juliana Ramirez, Search Terms | Read more:
Images: Andy Williams; John Decker, Green Plums, 1885; Peter Henry Emerson, Marsh Weeds, 1895.
When Revolutions Sputter
Revolutions have a logic. The revolutionaries start with a big, transformative, impossible goal. They want to remake society, smash existing institutions, replace them with something different. They know they will do damage on the road to their utopia, and they know people will object. Committed to their ideology, the revolutionaries pursue their goals anyway.
Inevitably, a crisis appears. Perhaps many people, even most people, don’t want regime change, or don’t share the revolutionaries’ utopian vision. Perhaps there are unplanned disasters. Smashing institutions can have unexpected, sometimes catastrophic, consequences, as the history of post-revolutionary famines shows very well.
But whatever the nature of the crisis, it forces the revolutionaries to make a choice. Give up—or radicalize. Find compromises—or polarize society further. Slow down—or use violence.
The bloodiest, most damaging revolutions have all been shaped by people making the most extreme choices. When the Bolsheviks ran into opposition in 1918, they unleashed the Red Terror. When the Chinese Communists encountered resistance, Mao sent teenage Red Guards to torment professors and civil servants. Sometimes the violence was mere theater, lecture halls full of people demanding that victims recant. Sometimes it was real. But it always served a purpose: to provoke, to divide, and then to allow the revolutionaries to suspend the law, create an emergency, and rule by decree.
I doubt very much that Donald Trump knows a lot about the methods of Bolsheviks or Maoists, although I am certain that some of his entourage does. But he is now leading an assault on what some around him call the administrative state, which the rest of us call the U.S. government. This assault is revolutionary in nature. Trump’s henchmen have a set of radical, sometimes competing goals, all of which require fundamental changes in the nature of the American state. The concentration of power in the hands of the president. The replacement of the federal civil service with loyalists. The transfer of resources from the poor to the rich, especially rich insiders with connections to Trump. The removal, to the extent possible, of brown-skinned people from America, and the return to an older American racial hierarchy.
Trump and his allies also have revolutionary methods. Elon Musk sent DOGE engineers, some the same age as Mao’s Red Guards, into one government department after the next to capture computers, take data, and fire staff. Trump has launched targeted attacks on institutions that symbolize the power and prestige of the old regime: Harvard, the television networks, the National Institutes of Health. ICE has sent agents in military gear to conduct mass arrests of people who may or may not be undocumented immigrants, but whose arrests will frighten and silence whole communities. Trump’s family and friends have rapidly destroyed a matrix of ethical checks and balances in order to enrich the president and themselves.
But their revolutionary project is now running into reality. More than 200 times, courts have questioned the legality of Trump’s decisions, including the arbitrary tariffs and the deportations of people without due process. Judges have ordered the administration to rehire people who were illegally fired. DOGE is slowly being revealed as a failure, maybe even a hoax: Not only has it not saved much money, but the damage done by Musk’s engineers might prove even more expensive to fix, once the costs of lawsuits, broken contracts, and the loss of government capacity are calculated. The president’s signature legislation, his budget bill, has met resistance from senior Republicans and Wall Street CEOs who fear that it will destroy the U.S. government’s credibility, and even resistance from Musk himself.
Now Trump faces the same choice as his revolutionary predecessors: Give up—or radicalize. Find compromises—or polarize society further. Slow down—or use violence. Like his revolutionary predecessors, Trump has chosen radicalization and polarization, and he is openly seeking to provoke violence.
For the moment, the administration’s demonstration of force is mostly performative, a made-for-TV show designed to pit the United States military against protesters in a big Democratic city. The choice of venue for sweeping, indiscriminate raids—Home Depot stores around Los Angeles, and not, say, a golf club in Florida—seems orchestrated to appeal to Trump voters. The deployment of the U.S. military is designed to create frightening images, not to fulfill an actual need. The governor of California did not ask for U.S. troops; the mayor of Los Angeles did not ask for U.S. troops; even the L.A. police made clear that there was no emergency, and that they did not require U.S. troops.
But this is not the final stage of the revolution. The Marines in Los Angeles may provoke more violence, and that may indeed be the true purpose of their mission; after all, the Marines are primarily trained not to do civilian crowd control, but to kill the enemies of the United States. In an ominous speech at Fort Bragg yesterday, Trump reverted to the dehumanizing rhetoric he used during the election campaign, calling protesters “animals” and “a foreign enemy,” language that seems to give permission to the Marines to kill people. Even if this confrontation ends without violence, the presence of the military in Los Angeles breaks another set of norms and prepares the way for another escalation, another set of emergency decrees, another opportunity to discard the rule of law later on.
Inevitably, a crisis appears. Perhaps many people, even most people, don’t want regime change, or don’t share the revolutionaries’ utopian vision. Perhaps there are unplanned disasters. Smashing institutions can have unexpected, sometimes catastrophic, consequences, as the history of post-revolutionary famines shows very well.
The bloodiest, most damaging revolutions have all been shaped by people making the most extreme choices. When the Bolsheviks ran into opposition in 1918, they unleashed the Red Terror. When the Chinese Communists encountered resistance, Mao sent teenage Red Guards to torment professors and civil servants. Sometimes the violence was mere theater, lecture halls full of people demanding that victims recant. Sometimes it was real. But it always served a purpose: to provoke, to divide, and then to allow the revolutionaries to suspend the law, create an emergency, and rule by decree.
I doubt very much that Donald Trump knows a lot about the methods of Bolsheviks or Maoists, although I am certain that some of his entourage does. But he is now leading an assault on what some around him call the administrative state, which the rest of us call the U.S. government. This assault is revolutionary in nature. Trump’s henchmen have a set of radical, sometimes competing goals, all of which require fundamental changes in the nature of the American state. The concentration of power in the hands of the president. The replacement of the federal civil service with loyalists. The transfer of resources from the poor to the rich, especially rich insiders with connections to Trump. The removal, to the extent possible, of brown-skinned people from America, and the return to an older American racial hierarchy.
Trump and his allies also have revolutionary methods. Elon Musk sent DOGE engineers, some the same age as Mao’s Red Guards, into one government department after the next to capture computers, take data, and fire staff. Trump has launched targeted attacks on institutions that symbolize the power and prestige of the old regime: Harvard, the television networks, the National Institutes of Health. ICE has sent agents in military gear to conduct mass arrests of people who may or may not be undocumented immigrants, but whose arrests will frighten and silence whole communities. Trump’s family and friends have rapidly destroyed a matrix of ethical checks and balances in order to enrich the president and themselves.
But their revolutionary project is now running into reality. More than 200 times, courts have questioned the legality of Trump’s decisions, including the arbitrary tariffs and the deportations of people without due process. Judges have ordered the administration to rehire people who were illegally fired. DOGE is slowly being revealed as a failure, maybe even a hoax: Not only has it not saved much money, but the damage done by Musk’s engineers might prove even more expensive to fix, once the costs of lawsuits, broken contracts, and the loss of government capacity are calculated. The president’s signature legislation, his budget bill, has met resistance from senior Republicans and Wall Street CEOs who fear that it will destroy the U.S. government’s credibility, and even resistance from Musk himself.
Now Trump faces the same choice as his revolutionary predecessors: Give up—or radicalize. Find compromises—or polarize society further. Slow down—or use violence. Like his revolutionary predecessors, Trump has chosen radicalization and polarization, and he is openly seeking to provoke violence.
For the moment, the administration’s demonstration of force is mostly performative, a made-for-TV show designed to pit the United States military against protesters in a big Democratic city. The choice of venue for sweeping, indiscriminate raids—Home Depot stores around Los Angeles, and not, say, a golf club in Florida—seems orchestrated to appeal to Trump voters. The deployment of the U.S. military is designed to create frightening images, not to fulfill an actual need. The governor of California did not ask for U.S. troops; the mayor of Los Angeles did not ask for U.S. troops; even the L.A. police made clear that there was no emergency, and that they did not require U.S. troops.
But this is not the final stage of the revolution. The Marines in Los Angeles may provoke more violence, and that may indeed be the true purpose of their mission; after all, the Marines are primarily trained not to do civilian crowd control, but to kill the enemies of the United States. In an ominous speech at Fort Bragg yesterday, Trump reverted to the dehumanizing rhetoric he used during the election campaign, calling protesters “animals” and “a foreign enemy,” language that seems to give permission to the Marines to kill people. Even if this confrontation ends without violence, the presence of the military in Los Angeles breaks another set of norms and prepares the way for another escalation, another set of emergency decrees, another opportunity to discard the rule of law later on.
by Anne Applebaum, The Atlantic | Read more:
Image: Spencer Platt/Getty
Wednesday, July 2, 2025
Monday, June 30, 2025
The Beauty of Pointlessness
Even if you know very little about The Big Lebowski, you probably know that The Dude loves bowling. The Dude and bowling go together. They just fit right in there together.
Now I’m no mind reader, but I suspect the Dude loves bowling for its own sake. Sure, he enjoys the camaraderie of Walter and Donny, and the bowling alley is a decent place to get a cold oat soda, but my hunch is that the Dude doesn't treat bowling instrumentally. He does not treat bowling as a means to some other end: he's not bowling to burn calories, network with business contacts, or improve his hand-eye coordination. The Dude gives zero fucks about optimization. I suspect he just bowls and enjoys the simple pleasure of trying to hit pins with a heavy ball. There is no larger purpose.
The rest of us, though? We've forgotten how to be like The Dude. It seems like so many of our daily activities are not done for their own sake, but for the promise of achieving something.
Take the so-called Huberman morning routine. His meticulously timed regimen demands morning sunlight, exercise, precisely timed caffeine, cold showers, and hydration. Huberman cloaks this routine in scientific legitimacy, throwing around terms like cortisol spikes and testosterone optimization, despite the evidence he cites being dubious at best. What's most troubling is how he's transformed morning routines from potentially enjoyable rituals into productivity optimization algorithms. None of these steps are recommended because they feel good or bring joy; they're prescribed based on the misplaced belief that they'll mathematically optimize your health and productivity like you're some kind of human spreadsheet.
Even meditation—a practice about being present—has been instrumentalized. Meditation apps don't promise the experience of quieting the mind; they promise productivity boosts, stress reduction, better focus. "Ten minutes a day to be 10% happier!" But what if meditation doesn't help with any of that? What if it's just sitting there noticing your thoughts? Isn’t that enough?
Things that were once pure pleasure have been transformed into health imperatives. Psychedelics shouldn't be taken because they can be fun AF, but because they can improve mental health. Rest isn't about blissful relaxation, but a means to recharge so we emerge more productive. When did we stop doing things just because?
This hit me recently when I came across a fascinating study about mice appearing to do things just for the fun of it. Scientists placed running wheels in natural settings to see if wild animals would use them voluntarily, without any rewards or incentives.
What they discovered was startling. Wild mice not only found and used the wheels but did so frequently and enthusiastically. Even when researchers removed all food from the experimental area, the mice still came to run on the wheels. It wasn't just mice either: the researchers recorded frogs, shrews, and even slugs voluntarily using the wheels. (And don’t ask me how a slug possibly uses a running wheel, but the authors provided receipts).
The conclusion was clear: these animals were running for the pure joy of running. No rewards, no external purpose, no optimization, no 30 minutes of cardio to burn 300 calories. Running on a wheel just because.
When's the last time you did something just because it was fun? No health benefit to justify the time spent. Just pure, purposeless fun.
I am far from the only one complaining about today's optimization culture. This obsession with turning every moment into a productivity hack has been critiqued by thinkers much sharper than me, who've recognized how we're increasingly trapped in a cycle of optimizing our lives rather than living them. (...)
The problem with optimization culture is that it imposes external goals on things that might be inherently pleasurable; optimization is always about the outcome, never the process. When we optimize our morning routines, we're not doing so because the routine itself is inherently pleasurable; we're doing it to maximize some future benefit—productivity, health markers, longevity. It transforms activities that could be enjoyable into mere instruments for achieving external goals.
by Michael Inzlicht, Speak Now Regret Later | Read more:
Image: uncredited
Now I’m no mind reader, but I suspect the Dude loves bowling for its own sake. Sure, he enjoys the camaraderie of Walter and Donny, and the bowling alley is a decent place to get a cold oat soda, but my hunch is that the Dude doesn't treat bowling instrumentally. He does not treat bowling as a means to some other end: he's not bowling to burn calories, network with business contacts, or improve his hand-eye coordination. The Dude gives zero fucks about optimization. I suspect he just bowls and enjoys the simple pleasure of trying to hit pins with a heavy ball. There is no larger purpose.
The rest of us, though? We've forgotten how to be like The Dude. It seems like so many of our daily activities are not done for their own sake, but for the promise of achieving something.
Take the so-called Huberman morning routine. His meticulously timed regimen demands morning sunlight, exercise, precisely timed caffeine, cold showers, and hydration. Huberman cloaks this routine in scientific legitimacy, throwing around terms like cortisol spikes and testosterone optimization, despite the evidence he cites being dubious at best. What's most troubling is how he's transformed morning routines from potentially enjoyable rituals into productivity optimization algorithms. None of these steps are recommended because they feel good or bring joy; they're prescribed based on the misplaced belief that they'll mathematically optimize your health and productivity like you're some kind of human spreadsheet.
Even meditation—a practice about being present—has been instrumentalized. Meditation apps don't promise the experience of quieting the mind; they promise productivity boosts, stress reduction, better focus. "Ten minutes a day to be 10% happier!" But what if meditation doesn't help with any of that? What if it's just sitting there noticing your thoughts? Isn’t that enough?
Things that were once pure pleasure have been transformed into health imperatives. Psychedelics shouldn't be taken because they can be fun AF, but because they can improve mental health. Rest isn't about blissful relaxation, but a means to recharge so we emerge more productive. When did we stop doing things just because?
This hit me recently when I came across a fascinating study about mice appearing to do things just for the fun of it. Scientists placed running wheels in natural settings to see if wild animals would use them voluntarily, without any rewards or incentives.
What they discovered was startling. Wild mice not only found and used the wheels but did so frequently and enthusiastically. Even when researchers removed all food from the experimental area, the mice still came to run on the wheels. It wasn't just mice either: the researchers recorded frogs, shrews, and even slugs voluntarily using the wheels. (And don’t ask me how a slug possibly uses a running wheel, but the authors provided receipts).
The conclusion was clear: these animals were running for the pure joy of running. No rewards, no external purpose, no optimization, no 30 minutes of cardio to burn 300 calories. Running on a wheel just because.
When's the last time you did something just because it was fun? No health benefit to justify the time spent. Just pure, purposeless fun.
I am far from the only one complaining about today's optimization culture. This obsession with turning every moment into a productivity hack has been critiqued by thinkers much sharper than me, who've recognized how we're increasingly trapped in a cycle of optimizing our lives rather than living them. (...)
The problem with optimization culture is that it imposes external goals on things that might be inherently pleasurable; optimization is always about the outcome, never the process. When we optimize our morning routines, we're not doing so because the routine itself is inherently pleasurable; we're doing it to maximize some future benefit—productivity, health markers, longevity. It transforms activities that could be enjoyable into mere instruments for achieving external goals.
by Michael Inzlicht, Speak Now Regret Later | Read more:
Image: uncredited
[ed. Golfing defined.]
Four Things: June 29, 2025
There are four political stories people should know about tonight.
First, President Donald Trump’s tariff war and weaker consumer spending translated to a contraction of 0.5% in the U.S. economy in the first quarter, even more of a drop than the 0.2% economists expected. The economy Trump inherited from President Joe Biden led the world in productivity.
Second, John Hudson and Warren P. Strobel of the Washington Post reported today that intercepted communications showed that senior Iranian officials said the U.S. attacks on Iran’s nuclear facilities caused less damage than they had expected and that they wondered why the strikes were so restrained.
Josh Marshall of Talking Points Memo also called out that at a press conference in the Netherlands last Wednesday, Trump said he had given Iran permission to bomb a U.S. air base in Qatar in retaliation for the U.S. strikes on Iran’s nuclear weapons program sites. “They said, ‘We’re going to shoot them. Is one o’clock OK?’ I said it’s fine,” Trump said. “And everybody was emptied off the base so they couldn’t get hurt, except for the gunners.”
Marshall expressed astonishment that this admission has attracted very little attention. He suggested that, if it is true, it represents “the most shocking dereliction of duty one could imagine for the commander-in-chief,” and he wondered how Republicans would have reacted if a Democratic president had said he had let “a foreign adversary fire on an American military installation.”
Third, Jeff Stein of the Washington Post reported today that the Republicans’ budget reconciliation bill makes the biggest cut ever to programs for low-income Americans. Those cuts have made many Republicans skittish about supporting the measure.
After Trump attacked him yesterday for not supporting the budget reconciliation bill, Senator Thom Tillis (R-NC) has announced he will not run for reelection next year, indicating his unwillingness to face a primary challenger backed by Trump. This puts the seat in play for a Democratic pickup.
In a statement, Tillis said: “In Washington over the last few years, it’s become increasingly evident that leaders who are willing to embrace bipartisanship, compromise, and demonstrate independent thinking are becoming an endangered species.” He wrote: “I look forward to having the pure freedom to call the balls and strikes as I see fit and representing the great people of North Carolina to the best of my ability.”
Tonight, Tillis told the Senate: “What do I tell 663,000 people in two years or three years, when President Trump breaks his promise by pushing them off of Medicaid because the funding’s not there anymore, guys?... [T]he effect of this bill is to break a promise.”
Fourth, the Senate parliamentarian has told senators that several of the provisions added to the Republicans’ budget reconciliation bill violate the rules for budget reconciliation bills. Those provisions include the ones added to the bill to win the support of Republican senator Lisa Murkowski of Alaska.
Today, Trump pushed Republican senators to ignore the Senate parliamentarian, who judges whether proposed measures adhere to Senate rules. Trump posted on social media: “An unelected Senate Staffer (Parliamentarian), should not be allowed to hurt the Republicans Bill. Wants many fantastic things out. NO! DJT.”
The nonpartisan Congressional Budget Office today said the tax cuts in the budget reconciliation bill the Republican senators are trying to pass will increase the national debt by $3.3 trillion over the next ten years despite the $1.2 trillion in cuts to Medicaid, Supplemental Nutrition Assistance Program, the National Institutes of Health, the Centers for Disease Control and Prevention, and other programs over the same period. Senator Raphael Warnock (D-GA) called the measure “Robin Hood in reverse…stealing from the poor in order to give to the rich, this massive transfer of wealth from the bottom to the top…. This is socialism for the rich.”
Trump has demanded the measure’s passage by July 4, in part because the Department of Homeland Security has blown through its budget and needs the supplemental funding the bill will provide. That funding adds an astonishing $45 billion for migrant detention by Immigration and Customs Enforcement (ICE) to the current budget of $3.4 billion over the next five years, and $14.4 billion for transportation and removal on top of the current annual budget of $750 million.
First, President Donald Trump’s tariff war and weaker consumer spending translated to a contraction of 0.5% in the U.S. economy in the first quarter, even more of a drop than the 0.2% economists expected. The economy Trump inherited from President Joe Biden led the world in productivity.
Josh Marshall of Talking Points Memo also called out that at a press conference in the Netherlands last Wednesday, Trump said he had given Iran permission to bomb a U.S. air base in Qatar in retaliation for the U.S. strikes on Iran’s nuclear weapons program sites. “They said, ‘We’re going to shoot them. Is one o’clock OK?’ I said it’s fine,” Trump said. “And everybody was emptied off the base so they couldn’t get hurt, except for the gunners.”
Marshall expressed astonishment that this admission has attracted very little attention. He suggested that, if it is true, it represents “the most shocking dereliction of duty one could imagine for the commander-in-chief,” and he wondered how Republicans would have reacted if a Democratic president had said he had let “a foreign adversary fire on an American military installation.”
Third, Jeff Stein of the Washington Post reported today that the Republicans’ budget reconciliation bill makes the biggest cut ever to programs for low-income Americans. Those cuts have made many Republicans skittish about supporting the measure.
After Trump attacked him yesterday for not supporting the budget reconciliation bill, Senator Thom Tillis (R-NC) has announced he will not run for reelection next year, indicating his unwillingness to face a primary challenger backed by Trump. This puts the seat in play for a Democratic pickup.
In a statement, Tillis said: “In Washington over the last few years, it’s become increasingly evident that leaders who are willing to embrace bipartisanship, compromise, and demonstrate independent thinking are becoming an endangered species.” He wrote: “I look forward to having the pure freedom to call the balls and strikes as I see fit and representing the great people of North Carolina to the best of my ability.”
Tonight, Tillis told the Senate: “What do I tell 663,000 people in two years or three years, when President Trump breaks his promise by pushing them off of Medicaid because the funding’s not there anymore, guys?... [T]he effect of this bill is to break a promise.”
Fourth, the Senate parliamentarian has told senators that several of the provisions added to the Republicans’ budget reconciliation bill violate the rules for budget reconciliation bills. Those provisions include the ones added to the bill to win the support of Republican senator Lisa Murkowski of Alaska.
Today, Trump pushed Republican senators to ignore the Senate parliamentarian, who judges whether proposed measures adhere to Senate rules. Trump posted on social media: “An unelected Senate Staffer (Parliamentarian), should not be allowed to hurt the Republicans Bill. Wants many fantastic things out. NO! DJT.”
The nonpartisan Congressional Budget Office today said the tax cuts in the budget reconciliation bill the Republican senators are trying to pass will increase the national debt by $3.3 trillion over the next ten years despite the $1.2 trillion in cuts to Medicaid, Supplemental Nutrition Assistance Program, the National Institutes of Health, the Centers for Disease Control and Prevention, and other programs over the same period. Senator Raphael Warnock (D-GA) called the measure “Robin Hood in reverse…stealing from the poor in order to give to the rich, this massive transfer of wealth from the bottom to the top…. This is socialism for the rich.”
Trump has demanded the measure’s passage by July 4, in part because the Department of Homeland Security has blown through its budget and needs the supplemental funding the bill will provide. That funding adds an astonishing $45 billion for migrant detention by Immigration and Customs Enforcement (ICE) to the current budget of $3.4 billion over the next five years, and $14.4 billion for transportation and removal on top of the current annual budget of $750 million.
by Heather Cox Richardson, Letters From an American | Read more:
Image: via
Lollapalooza: The Uncensored Story
Alternative Rock's Wildest Festival
Lollapalooza: The Uncensored Story of Alternative Rock's Wildest Festival doesn't spend much time grappling with that question, preferring to depict business machinations, onstage antics, and offstage debauchery. Often, garden variety rock'n'roll decadence degenerated into drug dependency. Every year had at least one act crippled by hard drugs. Heroin was there at the start, when Perry Farrell conceived of the festival as a farewell for Jane's Addiction. It's there at the end, when Failure somehow stumbles through sets on the main and second stages during the 1997 installment despite their bassist Greg Edwards being in the throes of addiction. It's there everywhere in between, providing a refuge for creatures of the night being stuck playing afternoon sets in amphitheaters across America.
Years of consciously-curated festival lineups in the 21st Century have eroded the memory of just how odd it was to see either Nick Cave & the Bad Seeds or the Butthole Surfers in the blazing midday sun. Lollapalooza: The Uncensored Story underscores how so much of the alternative rock was a nocturnal underground culture coming into the light. The survivors are the ones that could adapt to the new circumstances, such as Pearl Jam and Nine Inch Nails, who figured out how to feed off the energy of a massive audience. how to harness the excitement of a massive audience, becoming a symbiotic being that fed off each other's energy.
Of course, the circumstances on the ground changed after the first festival became an unexpected success. Lollapalooza's sequel arrived in 1992, after "Smells Like Teen Spirit" climbed into Billboard's Top Ten, a combination of events that ushered the alt-rock goldrush of the '90s. Those next three years of Lollapalooza are where the music biz figured out if it was possible to package and sell the underground, taking a chance on weirdos as they tried to find artists willing to play the game. Some bets didn't quite pan out but enough did for the chaos to chatter along until 1995, when Sonic Youth headlined a year that illustrated the commercial limits of the fringe.
Although the Sonic Youth year is the one that's commonly cited as the death knell for the festival, Chicago area promoter Andy Cirzan claims in the book, "The real drop-off, the crazy scary one, was '97. That's when the bottom fell out." By that point, Lollapalooza had credible competitors—Lilith Fair, the Warped Tour, HORDE—and, worse, they ran through all the potential headliners. The acts they could pull already knew the game: when Tool agreed to come back for another round, they asked to not close the festival, since they realized the crowds started to leave during the last act.
Tool was the defacto top-liner in a year where Orbital, the Prodigy and the Orb were the nominal future-minded headliners but the cast of characters that populate Lollapalooza: The Uncensored Story illustrates how the festival always had one foot firmly planted in metal. The line between punk and metal could be blurry. A good portion of the '80s underground listened to the same heavy rock as metalheads—R.E.M. covered Aerosmith's "Mama Kin" in 1986, the same year Guns N Roses covered "Mama Kin"—and Jane's Addiction, Rage Against the Machine, and Soundgarden were all propelled by guitarists who specialized in some kind of six-string theatrics. All three acts keep popping up again and again through the oral history, acting as a chorus and returning to the bills that were also populated by bands who attempted to be louder than heaven.
Strip away the Sonic Youth year and maybe 1994—Smashing Pumpkins topped a bill that occasionally echoed the tastes of Nirvana, who were scheduled to headline until the last minute—and the Lollapalooza mainstage of the '90s was always dominated by aggro acts. During those first few years, the occasional hip-hop or woman artist gave an illusion of balance, but after the festival was rattled by the soft sales for Sonic Youth, they agreed to participate in Metallica's modern-rock makeover, conceding to a bill filled with loud guitar acts. By 1997, the fest cut loose the Jon Spencer Blues Explosion—who were signed and ready to go—because Korn refused to appear before the indie-rockers. Korn also got pissy when second stage headliners the Eels were elevated to the mainstage after Tricky left the tour without warning: the nu-metal kings made it clear there was no way they'd play before alt-rockers of any stripe.
Brad Tolinski argues in Lollapalooza that "With [Korn's] use of dissonant seven-string guitars, bagpipes, and funk-inspired bass lines there was very little to connect them to traditional metal. And Jonathan Davis's damaged-antihero lyrics were certainly closer to Perry Farrell's than say, Ozzy Osbourne's or James Hetfield's." Fair point but Korn also always read as a metal band in a way that, say, Soundgarden did not. Perhaps it was the dour imagery, perhaps it was the adolescent angst, perhaps it was their Jägermeister sponsorship, but Korn tapped into an ugly, primal energy: James "Munky" Shaffer remembers that "every three or four nights someone would set a fire out in the grass or the kids in front would start tearing out the seats," behavior that pointed toward the riots of Woodstock 99.
Korn played Woodstock 99, as did Metallica, a pair of Lollapalooza veterans who represented a strand of '90s culture that ran parallel to the alternative nation Perry Farrell intended to set into motion with the first Lollapalooza. What began as a cacophony of differing cultures reduced into a din of diffuse rage, a transition Lollapalooza: The Uncensored Story that provides the book its unifying thread. Maybe this sour undercurrent is why the book doesn't provide much of a nostalgic kick or perhaps the structure of Lollapalooza itself didn't generate great gossip. Every year, a new round of misfits had their initial enthusiasm diminish as they realized they were stuck in the sticks, playing to the same number of diehards that could fill a club.
by Stephen Thomas Erlewine, So It Goes | Read more:
Image: Lollapalooza poster, uncredited
Subscribe to:
Comments (Atom)