For several years now I’ve had readers ask me from time to time about my opinion of the current media and investment frenzy surrounding so-called Artificial Intelligence (AI). The first thing I’ve had to explain in each of those cases is that the label is a misnomer; generative large language models, to give these bloated creations of the software industry their proper name, are certainly artificial but they’re not intelligent in any meaningful sense of the term.
Generative LLMs churn out statistically likely sequences of words, pixels, or computer code. That’s what they do, and it’s all they do. They differ in complexity but not in principle from those amusing programs that generate pirate talk or postmodernist academic papers on demand. Influential computer scientist Emily Bender, in an important 2021 paper, labeled generative LLMs “stochastic parrots,” and the label’s an accurate one; for those who don’t speak the jargon, “stochastic” means “producing a statistically random output.” (I hope I don’t have to explain to anyone what a parrot is.) There’s nobody home in these so-called AIs, just a program that churns out sequences that imitate the material on which they are trained.
That isn’t useless, by a long shot. Quite a bit can be accomplished by generating statistically likely but unpredictable sequences of words or pixels or computer code. Yet the gap between this and the expectations that have been loaded on the AI phenomenon is at least as significant as the actual potentials of the technology. Listen to the promoters and true believers of AI hype and you can count on hearing claims that LLMs will be conscious, self-aware beings in a matter of months, that they will soon be far more intelligent than human beings, and that once this happens AIs will usher in Utopia if they don’t decide to exterminate us all first.
In point of fact, all of this is hogwash. Outside of a narrow range of uses, generative LLMs perform very poorly. Loud predictions of vast economic payoffs to companies that adopted them have turned out to be so much hot air, and the best LLMs on the market still perform very poorly indeed when confronted with genuinely new challenges—the sort of thing that human intelligence takes easily in its stride. A recent study, one of many, thus showed that LLMs can handle less than 3% of business tasks in the real world.
The same issues have become notorious in the publishing field. One of my publishers noted the other day that his firm fields plenty of LLM-written manuscripts. They are instantly recognizable as such; they are also unpublishable garbage. (The publisher has a snappy rejection email for these saying, “We publish people, not robots.”) Yet money keeps on pouring into the AI phenomenon, yielding a vast buildout of the gargantuan, expensive, energy- and water-hungry data centers that are needed to deploy LLMs at scale.
It’s quite a spectacle, and has led many commenters to wonder if we’re in the middle of another delirious speculative bubble on the scale of the one that popped so disastrously in 1999. The parallels are striking: the internet boom that burst a quarter century ago was set in motion by a genuinely transformative shift in technology, but that reality was buried in vast amounts of hype and a cascade of malinvestment that paid no attention to economic reality. Inevitably, the bubble popped, thousands of businesses and millions of investors went broke, and the frantic attempts by governments to paper over the mess led to the real estate bubble and bust of 2004-2009.
That could still happen. Still, I’ve come to think that there may be something far more important going on in the current frenzy over AI than the sort of common or garden variety speculative boom that so reliably separates fools from their money. To understand what I think may be going on here, however, we’re going to need to talk about catabolic collapse.
Longtime readers of my blog posts know about that, or at least have heard of it. Those without that background will want to know that it’s the subject of a paper I wrote in 2004, “How Civilizations Fall,” which you can read online here. Behind the paper lay years of research into the way that civilizations unravel. Despite the usual assumptions, this isn’t a fast process. It unfolds over one to three centuries of repeated crisis periods separated by intervals of stabilization and partial recovery. The question I wanted to explore was why this happens.
The answer’s actually quite simple. Civilizations always build more stuff than they can afford to maintain. By “stuff” I mean anything that an economist would call capital: buildings, roads, trading systems, social networks, educational institutions, transport technologies, ideologies that encourage people to contribute to the system, you name it. If it’s produced by human labor and has to be maintained by inputs of labor and resources, it’s capital—or, as I like to call it, stuff. Different civilizations fixate on different kinds of stuff, but every civilization produces a lot of stuff: usually as much as its resource base will allow.
The difficulty, of course, is that once built, stuff has to be maintained, which uses up labor and resources. Meanwhile there’s always a demand for new stuff, which also uses up labor and resources. Sooner or later, depending on how big your civilization’s resource base is, the demands on your labor force and resource base rise high enough that you can’t keep doing both. That’s when crisis arrives.
I borrowed terms from biology to provide labels for these stages. In any living body, including yours, the process by which new tissues are produced is called anabolism. (Think of anabolic steroids, which build muscle mass.) The corresponding process by which old tissues are broken down is called catabolism. The crisis that comes when a society no longer has the available labor and resources to meet the need for new production, and still maintain all its existing stuff, is a catabolic crisis. As the term suggests, what happens in that crisis is that a lot of old stuff gets torn down or just abandoned, so that the labor and resources that once went into maintaining it can be freed up for other uses.
You might think that civilizations, like living bodies, would simply balance catabolism against anabolism and keep things from going into crisis. Some human societies do this, but the kind of complex urban societies we call civilizations aren’t good at it. In particular, they reliably use the old stuff as infrastructure and build new stuff on top of it, and then more new stuff on top of that. This is why, for example, New York City still relies on a water system that was already obsolete in 1950. It’s also why the United States still relies on New York City as a port, marketplace, and population center when it’s been falling apart for many decades, and costs far more to maintain than it returns in terms of value to our society.
Of course politics, ideology, and other human factors come into play and make things even more complex. The smart thing to do with New York City in the 1950s would have been to tear it down one borough at a time, haul away the rubble, replace the decrepit infrastructure, and then rebuild. That was actually discussed, but it never got beyond the talking stages for political and cultural reasons. Instead, New York City will continue to be a crumbling, dilapidated, absurdly expensive mess until it’s abandoned, stripped of metal and other valuable resources, and left to the slowly rising oceans a century or two from now.
This isn’t a new story. Rome was a city with vast public buildings and apartment blocks twenty stories high in 300 AD; by 600 AD the Forum at the center of the city was a goat pasture and the apartment blocks were distant memories. Plenty of other great cities of the past went exactly the same way, for the same reasons: the civilizations that built them kept pouring labor and resources into maintaining them, until they couldn’t.
It’s possible for a civilization can go through a catabolic crisis without collapsing. A lot of capital gets converted to waste, some of it abandoned, some stripped of raw materials for other uses. The United States went through a catabolic crisis of that kind in the 1970s and 1980s, and you can still find the dilapidated remnants of old factories and the former rights-of-way of disused rail lines all over the country. It was a wrenching transformation and ruined a lot of lives, but the nation survived it. It takes certain other factors to turn a catabolic crisis into the opening round of catabolic collapse, the process by which civilizations fall.
That’s not what I want to discuss here, however. Here we’re talking about the ordinary sort of catabolic crisis, the kind in which it stops being possible to keep covering the maintenance costs of unproductive capital, and so a lot of that capital is allowed to become waste so that labor and resources can be redirected to more productive uses. Yes, I’m suggesting that one of these is imminent in the United States and throughout the Western industrial nations.
There are very good reasons to think this. The global economy that funneled vast amounts of unearned wealth to the United States and its inner circle of allies is breaking apart into separate economic blocs; the status of the US dollar as default reserve currency is waning, though in the usual way this is happening a little at a time, not all at once. Other factors even less fashionable to discuss these days are placing sharp burdens on the available supply of labor and resources. Those will wait for a later post; what matters now is that something has to give.
This is where my deliberately broad definition of “stuff”—if you prefer, capital—is crucial to keep in mind. Stuff doesn’t have to consist of buildings, or roads, or New York City. It can also be organizational capital. An army is capital in this sense; so is a school, whether or not it meets in a building; so is a religion. So, finally, is a bureaucracy.
Here in the modern industrial West, we have far and away the largest bureaucratic sector in the recorded history of the planet. Our governments, local, regional, and national, are crammed to the bursting point with bureaucrats. What’s more, so are the office towers of our corporations and the headquarters of our nonprofits and nongovernmental organizations. These are so close to identical that personnel constantly move from one to another without the least disruption, and all can be seen as part of a single gargantuan bureaucratic structure, the most distinctive creation of industrial society over the last three quarters of a century or so.
It’s a very expensive creation. Here it’s crucial to remember that “stuff” isn’t just material objects such as office buildings, computer networks, yellow sticky notes, and all the other impedimenta that play roles in a modern bureaucracy. The ample salaries and benefits paid to bureaucrats are another part of the cost. So is the entire system of modern higher education, which abandoned most of its previous commitments to become a factory for manufacturing bureaucrats. So are the regulatory burdens loaded by government bureaucrats on more productive economic activities, and the costs of the pervasive corruption and graft that runs all through all these systems, from casual pilfering of company property to the multimillion-dollar bribes that routinely change hands at the upper end of the pyramid.
What makes all these costs even more galling than they would otherwise be is that the bureaucratic systems contribute so little and place so many burdens on productive economic activity. There is certainly such a thing as too little bureaucracy, but the United States left that behind by 1936 or so and has never looked back. My late wife, a bookkeeper during most of her working life, used to come home day after day with stories of the absurd regulations and heavy financial burdens loaded by city, county, state, and federal governments on the small businesses whose books she handled. In a post here two years ago I talked about lenocracy, literally “rule by pimps,” in which every activity is loaded with fees to the breaking point by corporate and government middlemen who contribute nothing but take an ever-increasing cut of the proceeds. That’s the standard strategy of bureaucracies these days.
In addition, these days our bureaucracies are not merely expensive and burdensome, they’re also stunningly incompetent. There’s a reason why NASA has to hire private contractors to put people into orbit; despite more than ample budgets, the bureaucracy that once put bootprints on the Moon hasn’t been able to design and build a working spacecraft in more than a quarter century. This is typical. Corporate and nonprofit bureaucracies are no better; need I cite Hollywood, which has completely lost the ability to make movies that audiences can enjoy?
None of this is accidental. As privileged classes become comfortable and decadent, they always try to shield their members from having to deal with the consequences of their own actions. That’s why you hear so much talk these days about “failing up:” no matter how miserably bad a job you do, if you belong to the bureaucratic class, you don’t have to worry about your career. Even if the firm you run crashes into ruin as a result of your idiocy, you’ll inevitably find a well-paying post elsewhere. The downside, of course, is that people thus sheltered never learn from their mistakes, and the institutions that shelter them end up mired in hopeless incompetence.
Bring all these factors together with the potential for catabolic crisis and the implications are obvious. Of all the ways to cut maintenance costs in today’s society without doing any significant damage to productive economic activity, far and away the most effective is to gut government, corporate, and nonprofit bureaucracies, freeing up the billions upon billions of dollars a year they cost (and the corresponding inputs of labor and resources) so that these can be put to genuinely productive uses, while unburdening the economy of the countless petty rules and fees that today’s bureaucracies load on them.
The one thing that makes this otherwise straightforward project difficult is that power is very diffuse in today’s industrial nations, and much of it resides in exactly those same bureaucracies that most need to be pruned. It’s indicative that the relatively modest steps the Trump administration has taken to trim the size of the federal bureaucracy and stop the wholesale looting of federal funds by corrupt politicians and nonprofits have unleashed shrieking rage and bloodcurdling threats of vengeance from leading members of the bureaucratic class. Carrying out comparably modest decreases in the corporate and nonprofit worlds, not to mention the much more extensive layoffs and shutdowns that will likely be needed, would be politically very difficult, unless it can be done in a way that seems inevitable, impersonal, and praiseworthy.
This is where the AI phenomenon enters the picture.
Our society has made a surrogate religion out of faith in progress. No matter how unsatisfactory something is, if you can convince people that it’s the wave of the future, a surprising number of them will accept it without quibbling. If you want an example, compare the frankly lousy sound quality on a phone playing streaming music with the vivid clarity of sound you get from a fifty-year-old stereo playing vinyl records. The step from records to CDs involved one sharp loss of sound quality, the step from CDs to streaming audio on computers a much greater one, but only a few eccentrics refused to make those changes. Even now, as vinyl records are resurgent, a vast number of people still put up with flat, tinny sound from phone speakers when a very modest investment would give them the chance to enjoy music much more. Why? Because they’ve been conned by the myth of progress.
The hoopla around AI, I’ve come to think, is intended to exploit that same reaction. Business media is full of stories these days about the vast number of white-collar jobs that will be going away forever in the near future as LLMs hit their stride. There’s a certain amount of fussing, to be sure, but nothing like the violent rage and hatred the Trump administration has gotten by making modest cuts in the federal bureaucracy. Most of the people who are likely to be affected are staring at AI-related stories like deer at the headlights of an oncoming truck. My guess is that this is no accident.
Ironically, it doesn’t matter in the least that LLMs can’t actually accomplish most of the tasks that human employees do. An immense share of the work done by today’s bureaucrats doesn’t need to be done at all, and an even larger share can be done quite well by machines that can produce statistically likely sequences of words that imitate human thought. Such work as is actually needed can be quietly outsourced to cheaper human labor, and of course this is already happening; a sour joke in today’s computer scene has it that AI actually stands for “Additional Indians,” because several companies have been caught using boiler rooms in Mumbai and Kolkata to do work that was supposedly being handed over to LLMs.
If I’m right, over the months and years immediately ahead, we can expect to see any number of triumphalist pieces in the mass media announcing that this or that department of this or that government, corporate, or nonprofit bureaucracy has been replaced by a shiny new AI. Governments at various levels will doubtless make various pro forma gestures in the direction of retraining the surplused bureaucrats, but those of us who remember how laid-off factory workers were treated forty years ago know better than to believe a word of it. Meanwhile, an entire world of businesses that supported themselves by providing services to cubicle inmates, from Pilates coaches to baristas and more, will also be left scrambling for survival.
Those bureaucrats I know who have a clue are already getting themselves retrained for jobs that produce real goods and services; they’re getting ready to become electricians, farmers, small business owners, and the like. Too many others are doing nothing to get ready for the wrenching changes ahead. I would encourage all my readers to assess the work they do to support themselves, remembering that if that job can be done by a stochastic parrot, they may not have a job five years from now. I would also encourage them to see what skills and talents they have that might be suited to small businesses. Once the leaden weight of excess bureaucracy gets lifted, there may be a great deal more room for small businesses than there has been in living memory. Still, we’ll just have to wait and see how it all plays out.
Hello JMG,
Thank you for your post , it is an interesting insight that makes sense: I saw many mainstream articles years ago about how ai would replace a high percentage of jobs , before ai become the thing it is today. I was wondering why the elite was pushing for that .
I have these comments:
1*The ai specialist I am following says that LLMs are only one section of AI in Computer Science and its current usage is brute force . Yann Lecun for example has said that it should be configured in a different way so that it is far less energy intensive and smarter for the algorithms . Other aspects of Computer Science receive much less attention and are just valuable
2* I remember ten years ago when the big IT corporations’ executives came out and said the future was in the cloud instead of on-premise. Then we discussed it with other IT professionals and we agreed this would create vast security issues, unnecessary complexity , and data loss for companies. Nevertheless the decision was made for strategic, investment and political purposes and we got the good , the bad and the ugly of cloud technology. It seems the same is happening now with AI data centers on an even bigger scale – whether we like it or not, and businesses and workers will have to live with the consequences.
4* there has been a few vast data theft in european government administrations this year. I thought this showed a level of incompetency compared to the level of responsibility they have with our personal and health data.
5*Regarding inefficiencies in organizations like corporations and bureaucracies, I have heard people say that most of the work is done by 20 per cent of people, and I agree. The thing is that it would not work with just those people because it is like trying to be an athelete with a very lean body, only eats healthy things and train rigorously. How long can groups of humans realistically behave like athetes in their lives ? What other parts of their lives will be neglected too much ?
Even the most dedicated groups become ‘ out of shape after some years ‘ . That level of performance is not sustainable . My explanation is not perfect but my intuition is that removing all the inefficient people from society is not going to work .
An exemple of a society that is under permanent stress, overwork at 80 hours per week, and high performance is South Korea . Their source of stress may be North Korea, but do we want to live like that for decades ? I had an American friend who was married to a South Korean woman, and he said ‘ it was hell ‘ .
I would rather live with less stuff and not have to live like a stressed-out zombie my whole life .
Just a critique of the current push to have everyone maintain living standards at all costs.
Good article. I only have a thought having to do with “The step from records to CDs involved one sharp loss of sound quality”.
Not really true, there was no loss in the quality of the sound, though there certainly is an argument between people who miss the crackles in the old vinyl and those who don’t (I’m often in the first camp precisely because I think there is such a thing as too much perfection in the arts), but provided you played both platforms in a good hifi system CDs perform better than records.
The following is true though, “the step from CDs to streaming audio on computers [involved] a much greater [loss]”, but again, the reason for this it’s not on the streaming part of the equation but on using the computer for reproduction.
I used to agree with this second half of the paragraph until a friend of mine who works in a high-end hi fi shop played me some music through a system in the shop (equal in price to a large family car) and I noticed he was playing vinyl, CDs and directly from Spotify with no difference in quality.
Often though, people who’ve been risen on the music of the 50s to 90s era will find some modern music unlistenable for reasons of their sound but that has to do with signal compression practices at the mixing and mastering stages in the recording studio which prioritise reproduction through tiny speakers and then sound awful on a hi fi or good headphones. But that’s a conscious decision.
If anyone doubts what I’m saying they only have to hear musicians of the analogic era commenting on the advent of digital music, for instance David Gilmour talking to Rick Beato, “when I listened to Pink Floyd’s first mix with digital means I never looked back”.
Wow, this is pretty much off topic, sorry!
This is an interesting essay.
I’m curious though, why you feel the weight of bureaucracy will be lifted. Surely the artificial bureaucrats can churn out just as many regulations as the living ones. If anything, more as they have no need for sleep and other human constraints.
While I would very much like to see the catabolism minus crisis, it is hard for me to see a good outcome here.
California and Colorado just passed a law requiring all operating systems to require age verification. How the **** are they going to get old Windows XP / Windows 7 running in random hospitals or mainframes like z/OS running in banks to comply with their age verification law? Let alone the millions of random Linux and BSD distributions sitting in servers and the cloud and in embedded / IoT systems? Just another example of clueless government bureaucrats making things impossible for everybody. If the California and Colorado politicians who passed the law succeed at enforcing the law, most businesses will be forced to abandon their computers and go back to pen and paper.
It seems like replacing most of today’s bureaucrats with LLMs won’t even require massive builds of data centers powered by new nuclear plants/perpetual motion machines. The Internet will become less usable due to AI slop but most people will quit using the Internet unless they absolutely have to over the coming years so it won’t matter that much. However, a lot of printed media will be LLM-generated so it might be a good idea to avoid most nonfiction books written after 2021.
You had to pick this topic, of all the topics out there.
>The hoopla around cocaine, I’ve come to think, is intended to exploit that same reaction. Business media is full of stories these days about the vast number of white-collar jobs that will be going away forever in the near future as cocaine use hits its stride. There’s a certain amount of fussing, to be sure, but nothing like the violent rage and hatred the Trump administration has gotten
https://inv.nadeko.net/watch?v=O6yeLNNVa4A
Thank you for this article John. Perhaps useful to fellow writers, the Authors Guild has launched a Human Authored Certification program. If you are a guild member you can get the certification on your books / works free, but it’s a modest fee for non-members.
https://authorsguild.org/human-authored/
The artisans, craftsman and workers who know how to do and make things from their own imagination will be in need!
On another note, as all of this decline and chaos continues to accelerate the second religiosity, I have looked at the hippie Jesus Freak group, The Trees Community in my latest article. Unlike other Jesus People groups of the seventies, after they came down from the acid, they got involved in liturgical Christianity at the Cathedral of St. John in NYC where Edward Nason West, spiritual advisor to Madeline L’Engle, became their abbot when they took formal vows and created a monastic community. L’Engle was also the “mother” to this group as West was their “father.” James Parks Morton also played a role, and through all this, I look at the roots of West and L’Engle’s universalism, and Morton’s work in the interfaith movement and what effect this all had on the group, who already been explorers of the worlds religions before their conversion. I contrast that with the Jesus People who went the way of premillenial dispensationalism. I really love the music of the Trees Community, wanted to share their alternate tour through the realm of Christianity with others.
Interested readers can check it out here:
https://www.sothismedias.com/home/freaking-out-with-jesus-in-the-trees-community
and here:
https://justinpatrickmoore.substack.com/p/freaking-out-with-jesus-in-the-trees
JMG,
Your post is so understated, so well put, so spot on, so true. Thank you for this one!
JCR
Hi John,
Great post. I have a few comments to make:
1) In regard to white collar work – and in particular dysfunctional public service bureaucracies – I wholly agree that much of what they do is irrelevant or downright negative for what remains of our productive economy.
This is a UK example today but what is clearly a smart guy got so disillusioned with the utter incompetence of the British state he has decided to resign. The Foreign Office isn’t interested anymore in actually implementing and executing effectively whatever the British interest is but rather is woke, dysfunctional and ineffective.
https://www.thetimes.com/article/uk-foreign-policy-is-choked-by-lawyers-says-departing-diplomat-vpg22fpmz
I have personal knowledge from people close to me who work in government just how useless most civil servants are. Scope for massive reductions are clear to me.
2) Now, AI is an interesting one. I do use AI apps and they have improved their capabilities over the last 6 months or so. Overall logic and reasoning have improved a lot and where their data set is limited and high quality they make things far more effective.
Examples include using a regulatory chatbot to search their local rules and guidance. Before I would need to try and locate a specific clause on the website, now I can use the chatbot. I have also used Gemini AI for some personal research recently on areas that I have extensive knowledge over. I was quite impressed in parts and at its best its like chatting to a very clever friend.
However, I have also experimented with it in areas where I specifically ask for things (e.g. events locally) or what is going on in that country and it hallucinates things. A silly example was I had a spare 30 minutes and asked AI for local art exhibitions. It told me about one on landscape art. I didn’t check it and went to the art centre and it turned out that this exhibition is only starting in April! Not a big deal but this specific hallucination shows the fundamental weaknesses of the AI.
Yes, it had picked up an exhibition but couldn’t tell me that its not on at the moment.
I see a future with AI on AI with very specific and clean data points and/or AI tools that can find pattern recognition and reasoning leaps in industries with huge amounts of data to be tapped. Finance, healthcare, coding, insurance and so on.
Within the limitations of AI I’m sure some AI agentics will work and help automate tasks done by humans to now.
However, my playing around with AI tools hasn’t convinced me it can take over the really challenging and complex work done by white collar workers.
A couple problems more critical than your (correct) observation that LLMs won’t ever be able to achieve what industry hype has been claiming. The industry’s business model totally depends on achieving human-like AGI by 2028, which is the only way it can achieve trillion-dollar magnitude revenues increases needed to repay trillion-dollar magnitude data center capex spending. Previous bubbles (1870s railroad, fiber-optics 2008 housing) involved mistimed/premature investments in proven technologies, while the LLM bubble is a much larger one-way bet on a non-existent technology (imminent AGI). Add to this an even bigger political bubble. Every major political interest—the Tech Industry, the financial industry and the entire Washington establishment—has placed a one-way bet that an AGI-driven productivity boom will be the magic bullet that drives their desired programs (increased Tech Industry political power, equity markets “numbers always-go-up”, funding for lower taxes, higher military spending, etc). No previous bubble had this powerful array of forces dedicated to preventing the bubble from bursting and avoiding any accountability for the massive misallocation of capital.
Fair to speculate about hypothetical future impacts on different jobs/industries from LLMs, but the path from here to there is likely to be a lot uglier than your post suggest.
“Understanding the LLM Bubble” American Affairs Journal, Spring 2026, p. 122.
https://horanaviation.com/publications-llm%2Fuber
Synchronicity has struck, here is the opposing viewpoint.
“At Mobile World Congress, Cristiano Amon of Qualcomm argued that the coming 6G networks will power an AI-driven “agent economy,” where devices and AI assistants constantly communicate across the network. “AI will fundamentally change our mobile experiences,” Qualcomm chief executive, Cristiano Amon says. “It’s going to change how we think about our smartphones. Think about our personal computing. Think about and interact with a car. The car is now a computing surface. If you actually believe in the AI revolution, 6G will be required. Resistance is futile.””
“The traffic that we expect on 6G is way different than what we had before,” says Palkhiwala. “Before, it was all about consumer traffic. We expect 6G to be driven by [AI] agent traffic. Think about all these use cases where there are AI agents sitting on various devices — your glasses, your watch, your phone, your PC. These agents are going to be talking back and forth across the network to other agents and services. “The traffic completely changes. 6G is being built with this idea that the traffic that goes on the network is not just going to be consumer voice calls or downloading videos, we’re going to have agents talking to each other, so the reliability of the network becomes very important.”
https://tech.slashdot.org/story/26/03/04/0033216/qualcomm-ceo-resistance-is-futile-as-6g-mobile-revolution-approaches
I’ll be giggling about that for the rest of the day.
And then there was this lament from the Administrative State; “Dec 24, 2025 — With fewer than 40 bills signed into law as of Monday, the House and Senate set a modern record for lowest legislative output in the first year ”
The full article in the Washington Post is paywalled, but if you google fewest new laws passed you’ll find similar laments.
Tony A,
The cloud is unsustainable in the long run. It is hugely vulnerable to disruptions such as war, with Iran bombing AWS cloud data centers and taking down the entire AWS Middle East region with significant negative effects on businesses in that region being a very recent example.
I have to give credit to a YouTuber, Whatifalthist, actual name Rudyard Lynch, for putting a bug in my head to think about wrt catabolic collapse. He said something along the lines that after World War II the West in general was burning through its “social capital.” This would be things like the old unspoken social contract that a university would not only provide you an education, but also almost guarantee that you would be able to find a job after graduation that would bring you into the middle class. Or that divorce is really high these days in that both parties do have some incentive to defect from the marriage and there is little community or family cohesion that would encourage a couple to stay together. Basically, its the transformation of a high trust society to a distrustful society. Curious where this fits into the scheme of catabolic collapse.
Also, the thing I found that will correct the thin, tinny sound of streaming music is either to buy an instrument and make your own music or go to a live show. No digital compression loss there!
I was a kid when CDs came out, a teen when they really caught on. Records played on a halfway descent rig have always sounded better than CDs and most audiophiles I know agree. What I remember at the time that CDs caught on was that most of us late gen Xers were listening to audio cassettes at the time, which sounded horrible, and deteriorated over time rather quickly (I remember it being a badge of honor to the fandom of a band to have worn out your cassette, but I digress), so when CDs came out they sounded like progress incarnate compared to cassettes which is what my peer group were comparing them to, but scratched easily and at least at first played poorly on smaller players.
I went back to vinyl in my mid to late 20s right when the mp3/iTunes era had just started. I was at my mother’s house and found an old record of mine from childhood. Threw it on her player and realized records sounded better than anything that’s come out since, and if cared for lasted a lifetime and more. My mother has since passed, but I have about 100 of her 45’s from the 50s and 60s and most of them still sound great! Only problem in the last few years is that due to folks starting to go back used record prices (mostly classic rock stuff) has skyrocketed, but isn’t too bad, still much much cheaper than buying stuff new digitally. There’s a lot of smaller record presses coming out with real high quality/fidelity stuff as well, it’s a really cool time for vinyl.
need I cite Hollywood, which has completely lost the ability to make movies that audiences can enjoy?
****
They still can make movies that people could enjoy. Too many, however, are only making movies for themselves and their little clique of admirers. They’re contributing to catabolization in that they are using resources that could be making money. This eventually leads to fewer productions going forward due to lack of returns from the previous productions.
John,
Thanks for this great wake-up call of an essay. In January, I graduated from the bureaucrat factory (college) and got my job at a bureaucratic organization. The first thing I’ve learned is that I hate the cubicle. I got my college degree at the insistence of my parents and went the route of least resistance. Now I realize that working indoors is just not what I want to do.
I have experience working as a landscaper and for an arborist. I’m going to look into the trades and see what I can do. I enjoy working outside in the sun and the trees.
Tony, thanks for this. These are points worth considering.
CC, yes, I’m familiar with that claim, which was pushed heavily by the mass media while CDs were replacing vinyl records. May I offer a counterpoint? I have a stereo system that will play records, cassette tapes, and CDs, and I listen to all three. Analog recording has a richness of sound that digital recording cannot match. No, it’s not just “crackles;” it’s a distinct qualitative difference, noticeable as a “flat” quality on digital media. What I’ve noticed, though, is that not everyone seems to be able to register it; I’m not sure if people like you don’t hear it or simply have learned not to notice it. That said, for those of us who do perceive it, it’s a major difference — and it explains why vinyl records are resurgent nowadays.
Paul, human bureaucrats have multiple motives for increasing the regulatory burden — it makes them feel like they’re accomplishing something, it justifies hiring more subordinates, and it sharply increases the potential for bribery. LLMs are not subject to these motivations. I freely grant that the people who run then will be just as corrupt as their bureaucratic predecessors, but if it’s a matter of bribing one employee rather than a whole office building of them, the burden is noticeably less.
Richard, what’s already happening, of course, is that businesses are abandoning overregulated states. Smaller firms are moving elsewhere, larger firms are simply shutting down their California stores and offices, because it isn’t worth their while to do business there. California in particular is making a cascade of massive mistakes that will turn it into the Rust Belt of the 21st century; I confidently expect that by 2050 or so, SF and LA will look like Detroit, complete with much less than half their current population.
Patrick, ah, but it’s easy to tell a nonfiction book written by an LLM from one written by a human being. My guess is that LLM books will turn into a major money-loser, and be abandoned before most other LLM products.
Other Owen, keep snorting away! 😉
Justin, interesting. I may need to give the Authors Guild another look.
John, thank you, but we’ll see if it’s spot on as things unfold.
Forecasting, as I noted in the post, I think there are definitely many things that a well-trained stochastic parrot can do, and do profitably. Replacing overpaid bureaucrats is certainly one of them! The problem, as with the internet bubble that popped in 1999-2000, is that a genuine advance is being overinflated to the point of absurdity.
Hubert, fascinating. That makes sense, and it feeds into my take, still tentative but developing, that we’re going to see a serious economic and political crisis across the Western industrial nations by the end of this decade. If everyone in power is counting on humanlike AGI as their “Hail Mary” strategy to pull out of the power dive, that becomes even more likely. Thank you for the link, btw — if you know of other resources that someone without a tech background can use to follow up on this, I’d appreciate hearing about them.
Siliconguy, thank you. I needed a belly laugh. As for Congress, good. Lots of new laws are not necessarily an advantage!
Watchflinger, excellent. Social structures are also capital, and we spent the second half of the 20th century subjecting them to ruthless catabolism. As for live music, well, that’s even better!
Dean, oh, I know. My stereo has a cassette tape deck but I use it only when I can’t find something in any other format. As for vinyl, it’s always a crapshoot, but many thrift stores have record sections where you can find astonishing things for reasonable prices. I can also point you to a great used record store here in Silver Spring…
Clarence, they could theoretically do so, but they’ve forgotten how. The quality of acting has also gone sharply downhill in recent decades. Watch the acting in an old classic like Casablanca sometime and compare it to what passes for acting these days; the deterioration in technical skill is very striking.
Nephite, all I can say is “move fast.” If you send your parents some articles about how AI is going to replace all the cubicle inmates, they might not argue as much.