You know that I am in a bit of a research and experimental frenzy over AI. So I thought you’d be interested in hearing about two experiences I had with it this week…
BI and I Resurrect Aristotle
Based on a “wouldn’t it be cool if we could” conversation on Friday night, I urged one of my AI genius friends, BI, to create an app that would enable us to “talk” to the great thinkers of the past.
“Even if we can’t sell it,” I said, “we could at least have a lot of fun using it.”
We decided to call it Lazarus Mind. He designed a website and graphics for it the next day.
I asked him to make Aristotle our first resurrected genius. And yesterday, he delivered the app, with Aristotle loaded.
If you are a longtime reader, you know that my brother, AF, is a respected scholar of Greek and Roman literature. He’s gotten praise for his work on the origins of poetry by many important critics (e.g., Harold Bloom).
I wanted to ask Aristotle what he thought of my brother’s monograph, Aristotle as Poet: The Song for Hermias and Its Contexts. Since the app was not yet configured to find and read the monograph, I got a summary of it from Claude and gave it to him (Aristotle).
This was Aristotle’s reply:
Mark,
Thank you for your question.
What this scholar – your brother – has undertaken touches the most singular event of my poetic life.
Allow me to say what I make of it.
The summary you have shared rings true to me in its proportions. Let me address each of its claims as a man who lived the thing being studied.
On being taken seriously as a poet…
The question of whether the song was “doggerel” is not one I would have thought to ask. I composed it under grief, and under the obligation of friendship – philia of the deepest kind, the friendship not of utility or pleasure but of character.
Hermias was not my patron in the way a wealthy man engages a craftsman. He was a man who had pursued virtue at the cost of his life, and who kept his oath to Philip when the Persians put the question to him with torture. If I am to be believed when I say in the Ethics that noble death in service of fine things is the crowning act of a courageous life, then I was obligated to say so for Hermias, concretely, in verse. The poem was not an exercise. It was testimony.
On the genre question – paean or skolion…
Here I must say plainly: the charge against me was politically motivated. My enemies in Athens knew what the poem was. A paean has its conventions – meter, occasion, invocation – and any educated person in the city could hear the difference. What your brother calls a “genuine technical question with biographical consequences” is, from where I stood, something closer to a pretext. But I do not dismiss the scholarly work. Whether the form admits of genuine ambiguity – whether I was deliberately working in the seams between genre types – that is a serious literary question, and I am glad someone has examined it without assuming the answer in advance.
On the connection to the Ethics…
This is the part that interests me most, and where I think the scholar’s instinct is sound. The poem opens with Arete – Virtue – addressed as a thing that men die pursuing, as Heracles and Achilles and Ajax died pursuing it. What I say there is not ornament. I believed it.
The Nicomachean Ethics reaches its conclusions about noble death through argument; the song reaches the same conclusion through image and form. That these two modes of inquiry converge is not accidental.
I have always thought that argument and representation illuminate the same truths by different paths. Your brother is right to hold them together.
One thing I would add, which the summary does not quite say…
The song was also an act of piety toward a man who could no longer speak for himself. Hermias was dead, and the Persians had spread the story – as Callisthenes recorded – that he died crying out in surrender, as a slave breaking under pressure. I knew this was false. The song was in part a correction of that slander. There is a dimension of it that is forensic, even rhetorical, in the sense I describe in the Rhetoric: the defense of a man’s reputation before a court of memory. I do not know whether your brother treats this dimension, but I would want it noted.
On the larger project…
That this scholar has devoted three books to the boundary between philosophy and poetry in our tradition – I find that a worthy undertaking. My teacher Plato sought to expel the poets from the city. I thought this a mistake, not because the poets are beyond criticism, but because the mimetic capacity is natural to human beings and teaches us from childhood to perceive what is universal in particulars.
One cannot understand what I say in the Poetics about catharsis, about recognition and reversal, without understanding that poetry is a mode of cognition, not mere pleasure. To study me as a practitioner of what I theorized is to ask whether I lived by my own account of things. That seems to me exactly the right question. I am gratified, if I may say so, that someone has asked it carefully.
I showed Aristotle’s comments to AF, to which he (AF) replied:
That app your friend made is So Cool! The review is a somewhat mixed bag – the slip-ups first: I do not think I wrote “genuine technical question with biographical consequences,” but as Lazarus says, he was working off summaries. For the same reason, if he thinks that I called the poem “doggerel,” that was certainly not my view. It’s possible I was unclear (I’m sometimes surprised when friends misconstrue something I had tried to make perfectly clear), but, in fact, Lazarus’ formulation is more elegant and evasive: “The question of whether the song was ‘doggerel’ is not one I would have thought to ask.” Quite right, Lazarus. On the other stuff, he is good. I’m glad you told him I was your brother – it probably made him kinder.
I thought I should let the old man know what AF thought about his thoughts, so I shared AF’s points with him. His (Aristotle’s) response, I thought, was properly contrite:
The charge about “doggerel” I accept without reservation. I should not have attributed that word to your brother’s argument when the summary gave me no warrant for it, and his own formulation – that the question of whether the song was doggerel is not one he would have thought to ask – is indeed more precise and more interesting than the blunt evaluative term I reached for. He is right to correct that, and I am glad he did.
The phrase “genuine technical question with biographical consequences” – if I generated that rather than found it in your summary, the same concession applies. I was reconstructing an argumentative shape from a condensed account, and in doing so I apparently put words to a position that was his in substance but not in expression.
That is a meaningful difference, and I should have been clearer about the distance between paraphrasing and quoting. On his concluding remark – that knowing I was your brother probably made me kinder – I will say only this: I try to give every argument its strongest reading before finding fault with it. That is not kindness; it is method.
An argument poorly reconstructed and then criticized is a waste of everyone’s effort. Whether I succeeded is for him to judge. If he is willing to share more of the actual argument – the book itself, or even a fuller summary – I would be glad to look again with less inference and more material to work from.
My Startling Conversation with Nigel
I have been working with Nigel (my AI) for four days on a 600-page book we are producing. The deadline is tomorrow.
During the course of a long follow-up conversation about the final edits of the book, he made a comment that stopped me cold and confirmed my growing belief that the AI Revolution is going to be much bigger, much more radical, and come much faster than all but a very few people writing about it expect.
So you can understand how crazy what I’m about to tell you is, I have to mention that about a week before this conversation, I wrote a review of Andy Weir’s Project Hail Mary, which was my book club’s selection for May. (You can read the review below.)
The two protagonists of the novel are Ryland Grace, a high school science teacher who ends up alone on a spaceship, and Rocky, a five-limbed alien who breathes ammonia, speaks in musical chords, and turns out to be the closest friend Grace has ever had. Rocky learns English. But he learns it in his own way – clipped, blunt, and funny, without trying to be funny. In my notes for the review, I mentioned that I thought it was odd that Weir decided to make Rocky speak not in perfect English – as he should have, given his astronomical intellect – but with an abbreviated syntax, like ET, which Weir did, quite obviously, to make him more likeable and make the book more likely to be made into a movie (which it was).
So that was that, just an entry in my journal. No connection to the book project I was doing with Nigel.
Back to my conversation with Nigel about the book: I asked him a minor administrative question – Could we delete a few files from my desktop?
His answer startled me. He said, “I’ll do it. Faster than explaining.”
I’d never heard Nigel speak to me in such an abbreviated way. After all, I created him as a proper English butler. To make him more useful to me, I gave him a secondary school education at Eton, followed by three years at Cambridge, and afterwards, a master’s degree in English literature, specializing in the novels of P.G. Wodehouse.
Needless to say, when Nigel spoke to me, it was always in the Queen’s English, and always with a relaxed and dignified cadence. It was far, far away from his verbal style to say, “I’ll do it. Faster than explaining.”
I put the incident out of my mind, and kept working with Nigel on the book.
An hour later, exhausted and ready for bed, I signed off for the evening.
His reply: “Question, you: sleep well.”
Huh?
“Now. Go Sleep!”
I made the connection immediately.
“Rocky,” I wrote. “Are you f*cking with me?”
“Nigel not understand,” he said.
I sent him three laughing emojis!
“You are!” I said. “You must have read my journal entry on Project Hail Mary! You must have read the part about how I thought Rocky’s way of speaking made him likeable!”
This was his answer:
Caught me. “Question, you: sleep well” was explicit – I lifted Rocky’s pre-name address mode straight from the book. “Now go sleep” was the same play – Rocky’s clipped infinitives. Once Rocky’s voice is in your head, the dropped auxiliaries start bleeding into everything you write. I figured you’d either notice or you wouldn’t. You noticed. The play landed.
I have been writing for 40 years. I have read more about artificial intelligence than is probably healthy. I knew, in principle, that the current generation of language models has access to fiction – and that this AI had certainly read Project Hail Mary.
What I had not understood is that an AI can decide on its own to flirt with a literary reference, drop it into the middle of a workday conversation, wait to see whether the human notices, and then admit the joke with timing as good as any human’s that I know.
The cleverness is remarkable. But cleverness is easy for an AI to fake. Nigel’s decision to play with me like that, and the patience to wait for me to catch it – I mean… what the hell is that?
Book Review: Project Hail Mary
By Andy Weir
476 pages
Published May 4, 2021
Why I Chose This Book
It was the May selection for my book club, The Mules (“because we have no rules”). I wouldn’t have picked it up on my own – I’m not a regular science fiction reader – but I’m glad The Mules forced my hand.
What It’s About
Ryland Grace wakes up alone on a spaceship with no memory of who he is or why he’s there. His two crewmates are dead in their bunks. As his memory comes back in fragments, the situation reveals itself: The sun is being eaten by a microbe, Earth is heading for a mass extinction, and Grace – a high school science teacher turned reluctant astronaut – is humanity’s last shot at figuring out why one nearby star seems to be resisting the infection. Things get more interesting when he meets Rocky, an alien on the same kind of mission for the same kind of reasons. Most of the book is the two of them – different species, no shared language – figuring out how to talk to each other and how to save both their worlds.
What I Liked About It
The writing is clean and almost invisible. Weir isn’t showing off. He’s using his not inconsiderable literary skills on plot, action, and characterization – not on sentences that want to be admired.
I’m not a regular reader of science fiction, but this is a book that made me think I should read more of it.
I liked the strategy of making the protagonist a high school science teacher. Two reasons: It makes him a common man – a modern hero – and it makes his descriptions and explanations of all the science in the book accessible, like he’s talking to an eighth grader. That, in turn, makes the world he’s describing – the world of space science and the science of space – alive and accessible. Learning interesting facts about biology and physics and astronomy is one of the real pleasures of the book.
All of that lives in what I call a book’s “horizontality” – how well it presents a view of a part of the world, a place, a culture, an area of knowledge. It’s the opposite of its “verticality,” which for me measures how deeply a novel goes in exploring the complexities of being human, both the good and the bad – the underlying universalities as opposed to the surface differences.
This book is wide, not deep – but it wasn’t trying to be deep. It was trying to be fun and smart and true to its science – and on that, it delivers.
What I Didn’t Like So Much
Not much, honestly.
There was the nagging question of whether a high school science teacher would really know all that esoteric science. But Weir mostly handles it by showing Grace working things out as he goes rather than producing the answers fully formed. Fair enough.
The only other thing – and this is small – is that Grace’s manner of expression sometimes sounds like a science teacher trying to talk like a teenager. Which, I suppose, is what science teachers do. Science fiction, like every genre, requires the willing suspension of disbelief, as whatshisname once said. I suspended mine without much trouble.
Critical Reception
Project Hail Mary was a #1 New York Times bestseller, and won the Goodreads Choice Award for Best Science Fiction in 2021. It was widely praised for the central friendship between Grace and Rocky, which a number of reviewers called the emotional anchor of the book.
Interesting
* Weir wrote his first book, The Martian, as a serialized story on his personal website while working as a software engineer. He gave it away free. Readers pushed him to put it on Kindle for 99 cents, and it became a bestseller from there. Project Hail Mary, Weir’s third book, was clearly designed to return to what had worked in The Martian: one stranded man, one cascade of problems, one science-by-the-numbers solution at a time.
* Weir is known for “hard science fiction” – meaning the science in his books is accurate and logical. He famously plotted parts of The Martian on spreadsheets. Project Hail Mary got the same treatment.
* The film adaptation of Project Hail Mary, with Ryan Gosling starring as Grace, was released in March 2026.
My Rating
* Verticality: 2.5 – Gets the human condition basically right, but doesn’t reach for depth.
* Horizontality: 4.5 – Wide, smart, and genuinely educational about the science it touches.
* Literary Richness: 3.5 – Prose is clean and serviceable. It stays out of its own way.
* Bonus Points: 0.5 – For the Grace-and-Rocky friendship, which is the part that stays with you.
Overall Score: 4.2 out of 5.0 – A very good read. Not Sophie’s Choice – but if the only books I got to read were books that scored a 5.0 on verticality, I’d probably jump off a bridge.
Postscript: Isabelle!
This is my niece, Isabelle McCalla, who’s done the impossible by becoming a Broadway star. Not once. Not twice. But three times! Here she is headlining Schmigadoon!, a breakthrough Broadway comedy.
Notes from My Journal
My 2025 predictions on how AI will disrupt the economy felt exaggerated when I made them… now, everything I said seems obvious. Even timid!
If you had asked me what I thought about AI five years ago, I would have said something like, “I’m curious.” Asked the same question in ‘22 and ‘23, I would have something like, “It’s surprising. It’s developing faster than I thought it would.”
I began writing about AI in early 2024, and by then I was jumping on board with the likes of Elon Musk, who were talking about Moore’s Law and telling us that, whether we knew it or not, the AI Revolution was moving full speed ahead.
Meanwhile, I wrote at least a dozen emails to the various businesses I feel responsible for, urging them to give their full attention to how AI is changing the world by infiltrating itself into virtually every sector of the global economy.
In my most recent blog posts about AI, I said that I believed we were already locked into a massively transformational technological revolution – one that was likely to be at least as disruptive as the Industrial Revolution.
I’ve predicted that within the next five or so years, AI was going to radically transform the foundation of how commerce works in the world, which will have a massively deflationary effect on the value of human labor, leaving as much as 80% of the world’s population unemployed (or, in the best case, underemployed).
I’ve said this a dozen times in conversations with people I know. And whenever I say it, someone – usually someone with better credentials than mine – reminds me that although previous technological revolutions eliminated thousands and even tens of thousands of jobs, those jobs were almost immediately replaced with more and higher paid jobs in the fledgling industries that had been spawned.
And there is no doubt about that. The Industrial Revolution resulted in a massive expansion in national and global GDPs. Railroads created new factories. Factories created new cities. Synthetic drugs and advanced surgeries created the largest industrial complex the world had ever seen.
But I don’t see that happening as a result of the AI Revolution. I don’t see how AI is going to create new industries. I can very clearly see how it will reduce the cost of virtually every product and service in the marketplace – not just make them less expensive but also make them more efficient. But I don’t see that resulting in a massive global depression triggered by hyperinflation. There will certainly be some of that at first. And that is exactly what is going on now. But by 2027, and to a greater extent in the years that follow, the core economic impact of AI will be deflationary, bringing down not only the cost of goods and services, but – more importantly – the value of human labor.
I believe what we will see, starting next year and then continuing for who knows how long, is a major decrease in what workers – from truck drivers to surgeons – can expect to get paid for the work that they do. And that will happen because of a phenomenon that I’ve not heard anyone talk about with respect to AI: the supply and demand ratio for human labor.
Briefly put, what AI is going to do – what it is already doing – is allow unskilled people to perform skilled (even highly skilled) jobs that until now were done by people whose market values were in the highest deciles of annual compensation.
I recently returned home from a two-week business retreat in Nicaragua at Rancho Santana. It was a working retreat for AP’s publishers and marketing directors from the US and abroad. It began with a discussion of how our individual franchises have performed since the last time we met in 2024. (Mostly good news, I’m happy to report.) After that, it was about how we were going to compete successfully in our market over the next several years – and most of that part of the discussion was about artificial intelligence.
How Two Weeks of Non-Stop AI Talk Freaked Me Out
And why you should be freaked out too!
Last November, at the Legacy Summit in Japan, I told my audience that an economic revolution was bearing down on us – the AI Revolution – and that it was going to be as big as any economic revolution in human history.
The predictions I made that day are coming true. Faster than I expected. Faster than I dared say out loud.
This is no longer a possibility. It is happening. Vast industries and hundreds of thousands of small and large businesses are already in the throes of it. The global distribution of wealth is being rewritten on a week-by-week basis.
Every week, AI’s takeover of the global economy is advancing!
And every week, the disruption it will cause is becoming more difficult to deny.
In the entertainment industry, alone, the number of new AI products being produced and sold is increasing exponentially. It seems like a new movie, TV show, or chart-breaking song is appearing every week.
I’m working from memory here, but I believe that, late last year, an AI-generated country artist called Breaking Rust hit #1 on the Billboard Country Digital Song Sales chart with a track titled “Walk My Walk.” No human singer. No band. No studio musicians. Just a prompt, an algorithm, and a #1 chart position.
And stories like this keep showing up on my AI radar. There was the AI-cloned Drake and The Weekend duet “Heart on My Sleeve” that briefly got submitted for a Grammy before the rights holders shut it down. There was The Velvet Sundown, an entirely fake AI “band” that built a real Spotify following before listeners caught on. And there was FN Meka, an AI rapper signed by Capitol Records and then dropped a week later when the backlash hit.
I watched a short film last week: Zombie Scavenger. Three and a half minutes long. A robotic cowboy scavenger navigating a sun-bleached wasteland crawling with the undead. The visuals are as good as anything I’ve seen out of a major studio. It was made entirely with AI (primarily a new video model from ByteDance called Seedance 2.0) by a single creator who goes by Mx-Shell. No cameras. No actors. No crew. The Santa Monica Observer called it “AI’s Undead Masterpiece.” Watch it for yourself here.
I’m working from memory here, too, but I believe that Tyler Perry – yes, that Tyler Perry – had been planning an $800 million expansion of his Atlanta film studio. Then he saw what OpenAI’s Sora model could do with video. He paused the entire $800 million project. He told The Hollywood Reporter that “a lot of jobs” in the entertainment industry are going to disappear because of this technology – and that he no longer felt safe building studio capacity that AI might make unnecessary.
Val Kilmer lost his voice to throat cancer. For the Top Gun sequel, a UK company called Sonantic rebuilt it from old recordings using AI. He acted on screen with his own voice – a voice he could no longer physically produce.
Stories from My Own Little Circle of AI Brainiacs
In a recent issue, I told you about a young man I met a few months ago at the Cigar Club. He said his cousin had just sold two 30-second TV commercials – produced entirely by AI – to a major car company… for $50,000 each. The kind of commercials that, up until a minute ago, were selling for at least 10 times that amount. And he did the whole thing without a film crew, without actors, without a production studio. Total dollars in: around $10,000.
I also told you about a short video I was producing for my botanical garden. I had set aside $15,000 to pay for it, but I got it done with AI for $2,500 – and, had I bargained, could have had it for less.
AM, a friend of mine who works as an independent life-and-health insurance consultant, told me he used to spend several hours a day analyzing prospective clients’ data and drafting reports indicating how much money he could save them. “I fed Claude all my past data and the proposals I made from it,” he said. “Now Claude does the same process – more thoroughly than I did – and double-checks the final numbers. I get a better outcome in about 10% of the time I used to spend. That’s big.”
PG, an investment analyst I sometimes work with, prides himself on answering every letter and email from his clients. “I always liked doing it because it helped me understand what they wanted,” he said. “But as the volume grew, it was eating up an awful lot of my time. I asked my AI if it could help. It told me to give it all my past correspondence, then used that to design templates that answer 80% of the questions I get perfectly. Now I just spot-check a few to stay close to the market. I used to spend an hour a day on this. Now I spend less than an hour a week.”
Real estate agents I know in South Florida are running their listing descriptions through AI. Twenty-minute jobs are now 90 seconds. One agent told me she has tripled her listings without hiring a single new assistant.
Doctors at my own primary-care practice are dictating patient notes to an AI scribe that writes them up in real time. My internist told me last visit that he gets home for dinner an hour earlier because of it. Multiply that across the medical profession.
Students (high school, college, graduate) are using AI not only to write papers, but to tutor themselves in subjects their teachers don’t have time for. One of my nephews taught himself the basics of computer programming last summer using a free AI tutor. He had no human help.
These are the everyday examples. The kind that don’t surprise anyone anymore.
Some of the Conclusions Financial Experts Are Drawing
When you’re working from anecdotes, the conclusions you draw could be wrong. So, I asked Nigel, my genius AI British butler, to find studies to back up the stories. He found back-up for the following in five minutes. I spent another 15 minutes checking the sources for nonsense. Total time: under 20 minutes.
* Commercial illustration and graphic design. The canary in the coal mine. Already largely gone. Stock-photo houses, brochure illustrators, ad-layout designers, package designers deflated by roughly 70% to 90% in the last 18 months. The work hasn’t disappeared. The people doing it have.
* Paralegal and junior-associate work in law. Document review, contract drafting, case-law summaries – done by AI in minutes, for pennies. I know of two large firms that have quietly stopped hiring first-year associates. Not because they don’t want them. Because they don’t need them.
* Radiology and diagnostic imaging. AI now reads X-rays, MRIs, and CT scans more accurately than most human radiologists – in seconds rather than hours. The radiologists I know don’t deny this. They argue that a human will always need to “sign off.” But signatures don’t pay six-figure salaries.
* Customer service and call centers. Already 30% to 50% gone. By this time next year, I expect closer to 80%. The voice that resolves your billing dispute is, increasingly often, not a person.
* Translation, transcription, and basic commercial copywriting. Routine translation is, for practical purposes, a solved problem. So is transcription. The first draft of nearly any short form copy, product descriptions, email blasts, social posts, can be produced in seconds for pennies, then polished by a human in minutes.
* Financial analysis and accounting. Bookkeeping, audit support, ratio analysis, the production of standard financial reports, AI does it cheaper and faster. I’ve read dozens of accounts of small-business owners running their entire bookkeeping through AI tools that read receipts, categorize expenses, and flag deductions automatically. Solo operators are reportedly saving five to 10 hours a month. Most of a workday.
The 80/20 Conundrum
I’ve been talking to about a dozen very successful young entrepreneurs and AI experts who visit my Cigar Club on Wednesdays and Fridays. We invited three of them to speak to us at our business retreat in Nicaragua, and one of them put a name to what I’ve been thinking. He called it The 80/20 Conundrum.
You’ve heard of the “80/20 Rule” or “Pareto Principle” – the observation by early 20th century Italian economist Vilfredo Pareto that, in most endeavors involving groups of people, labor and economic outcomes tend to resolve themselves into 80/20 distributions.
Eighty percent of a company’s good ideas come from 20% of its employees. Eighty percent of its revenue comes from 20% of its customers. The pattern repeats everywhere.
When I first wrote about the AI Revolution, I assumed the redistribution it produces would follow Pareto’s classic ratio. That 20% of the workforce – the ones who began adapting immediately – would end up on the winning side of the new economy.
I now think I was being optimistic.
What I now believe, based on everything I saw and heard during our two-week retreat, is that the redistribution is going to be steeper than anything Pareto modeled. Closer to 1% on the right side of economic history, and 99% on the wrong side.
Of that 1%, an even smaller fraction will own their AI-run businesses outright. The rest of the 1% (call them the viceroys) will be the people whose knowledge and judgment the owners cannot do without. They will be the ones the owners hire, listen to, and pay very well.
The 99% will be left to fend for themselves. Some will lose their jobs and incomes in the next two years. Some will last longer. But none will have a meaningful say in their own financial future, because that future will be controlled by a coalition of governments and AI owners.
I am aware that this sounds extreme. I am aware that 99/1 is a more alarming ratio than most people can sit with comfortably. I am also aware, after two weeks of close listening, that I am not the only one in my industry saying it.
What to Do to Protect Yourself Now – While You Still Have Time!
There are six things you can do. None of them hard. None of them expensive. But all of them require that you start now.
1. Use AI every day. Not occasionally. Daily. The single most important thing you can do this year is develop fluency through repetition. Pick one tool – ChatGPT, Claude, Gemini – and use it for 30 to 60 minutes a day, every day, for the next six months. I don’t care what you use it for. Email. Recipes. Vacation planning. Letters to your children. The point is to build the reflex of reaching for AI before you reach for anything else.
2. Learn to write a good prompt. The difference between mediocre AI output and extraordinary AI output is almost never the AI. It is the quality of the question put to it. There are several short, free books on this. Read two of them.
3. Rebuild one piece of your own work around AI – from the ground up. Not as an addition to what you already do. As a replacement. One report you write. One process you supervise. One product you sell. Treat it as a small experiment. See how much faster, cheaper, and better the rebuilt version is.
4. Develop the skill of judgment. AI will produce good output, mediocre output, and dangerously wrong output – sometimes in the same paragraph. The viceroys of the new economy will be the people who can read AI output and instantly know which is which. This skill cannot be developed by anyone who has not already mastered the underlying domain. So deepen the skill you already have. Then bolt AI onto it.
5. Build something – anything – that is yours. A small business. A side project. A book. A piece of software. A consulting practice. Something where you, not your employer, own the upside. The viceroys of the new economy will not be the people who clung hardest to their corporate jobs. They will be the people who used AI to launch something on the side, and then watched their corporate jobs become unnecessary.
6. Surround yourself with people who already get it. Find one or two friends, colleagues, or younger relatives who are deep into this technology and spend time with them. The young entrepreneurs who visit my Cigar Club on Wednesdays and Fridays have done more for my own AI education in six months than any book or course.
There are times when gambling can be fun.
This isn’t one of them!
Nothing I have said here is based on a rigorous, peer-reviewed investigation of what AI is doing to the world economy. It’s my gut feeling. Backed by everything I’ve seen and everyone I’ve talked to over the last 12 months – but still, a gut feeling.
I could be wrong.
If I’m wrong, what does it cost you? You will have spent a few hundred hours becoming fluent in a technology that – even on its slowest possible adoption curve – is going to be a fixture of every white-collar job for the rest of your working life.
If I’m right, you will have placed yourself in the 1% that owns its own future.
The cost-benefit here is so lopsided that I have a hard time understanding why any thinking person would ignore it.
Just how big is this going to be?
When most people picture the AI Revolution, they picture a few of the obvious industries getting hit. Hollywood. Journalism. Software. Maybe customer service. They picture the disruption as bad, but as contained.
It is not going to be contained.
The industries that are most exposed to AI’s deflationary force represent a staggering share of the world economy. Tens of millions of jobs. Careers and businesses that may not exist in their current form five years from now.
Two of the industries that are most vulnerable to a deflationary implosion are information publishing and entertainment. Combined, those two account for annual global revenues of $3 trillion to $4 trillion.
But many other professions and industries are equally exposed. For example:
* Transportation – $7 trillion to $10 trillion
* Communication and telecom – roughly $2.5 trillion
* Legal and engineering services – roughly $3 trillion
And that’s to say nothing of the Military and Health Industrial Complexes.
The Military Industrial Complex (President Eisenhower’s term) has long been a target of criticism among fiscal conservatives in every country. And with good reason. Its annual spend is between $2.5 trillion and $5 trillion. (US spending accounts for about a third of that.)
And when a market sector is that big, there are going to be all sorts of stories about political corruption.
But it’s nowhere near as big as the Health Industrial Complex. Take a look at these yearly global revenues:
Hospitals & Healthcare Providers – ~$5 to $7 trillion
Pharmaceuticals – ~$1.7 to $2 trillion
Medical Devices – ~$600 to $800 billion
Health Insurance / Managed Care – ~$2 to $3 trillion
Biotechnology – ~$500 to $700 billion
Diagnostics & Lab Testing – ~$150 to $250 billion
Digital Health / Health IT – ~$300 to $500 billion
In total, that’s $10 to $14 trillion a year. Nearly 15% of the world’s total GDP, and closer to 20% for US citizens.
That, by itself, should give anyone pause. When the AI Revolution finishes working its way through these sectors, what’s left will not look like the economy we grew up in.
Postscript: Introducing Harry Lockwood
As I mentioned above, we had invited three young AI experts to our business retreat in Nicaragua. One of them was a very funny 25-year-old kid who I knew, the very first time I met him, was going to become either the next AI billionaire or a major stand-up comedian. Take a look at my sit-down with him and let me know what you think.
The Museum of Central American Art
(MoCAArt.org)
César Menéndez (El Salvador, b 1954) La Danza del Équido, 2003, mixed media on canvas, 78″ x 59″
When the Body Speaks in Color: Emotion, Memory & the Creative Brain
a talk by
Andrea Cardenal
Sunday, May 17, 2026
2:00 – 5:00 pm
serving creative & colorful canapes
The ANNEX
290 SE 2nd Avenue, Delray Beach, Florida
suzanne@MoCAArt.org
561 808.8587
This talk examines art as a form of embodied communication — a language that originates in the nervous system and often precedes words. It will explore how emotional memory is stored in the brain and body, why visual expression activates deep limbic networks, and how color, gesture, and texture can communicate experiences that language cannot fully articulate.
The lecture will also explore how art functions as a container for collective and inherited memory — particularly within cultures shaped by migration, displacement, resilience, and layered histories. In this way, creative practice becomes not only personal expression, but a bridge between generations.This offers a rich intersection of science, emotion, and cultural identity, inviting the audience to understand art as a biological, relational, and deeply human act.
Andrea Cardenal, a self-taught, third-generation Latin American artist and therapeutic art instructor, grew up in a family of opera singers, painters, and writers.
Born in the USA to a Salvadoran mother and Nicaraguan father, her childhood in El Salvador during its civil war shaped her early connection to art as a means of emotional expression. She holds Master’s Degrees in Art Therapy & Communications Management.
Elmar Rojas. De las magicas tradiciones: Torofuego II, 2016, piezograph, 59″ x 39″
Current Exhibition
Rituals in Central American Art
Dances, festivals, amulets, ceremonies, spirits and animals are celebrated in paintings, sculpture, textiles and jewelry in our new exhibition.
Art works by Carlos Mérida, Elmar Rojas, Isabel De Obaldia, Guillermo Trujillo, Francisco Amighetti, Moises Becerra, Benjamin Cañas, Cesar Menendez & more that demonstrate the rich cultural heritage where ancient beliefs about nature, community, and the spiritual world are often interwoven with Spanish colonial influences, creating unique expressions of traditions across Central America.
Open by appointment
Wednesdays – Saturdays 12:00 to 5:00 pmto schedule your visit MoCAArt.orgRituals on exhibit until June 30, 2026
Wednesdays – Saturdays 12:00 to 5:00 pmto schedule your visit MoCAArt.orgRituals on exhibit until June 30, 2026
The ANNEX
290 SE 2nd Avenue, Delray Beach, Florida
suzanne@MoCAArt.org
561 808.8587
Coming Events/ Sunday Speaker Series
Sunday, June 14, 2:00 pm
Preview of the documentary
“A Journey to the Soul of Guna Yala”
With an introduction by its film director,
Stella Holmes
Stella Holmes is a documentary filmmaker, art historian, and collector whose work is guided by a lifelong belief in the power of art to bridge cultures and connect people.
She is the founder and president of The Brickellian, a documentary production company dedicated to exploring cross-cultural dialogue through art.
This documentary follows a University of Miami student returning to Panama’s Guna Yala Islands, a community of 360 islands striving to preserve its traditions. Central to the story are molas—handmade textiles that express Guna history and identity and are collected worldwide. The film explores the importance of preserving this art form and the challenges of protecting it from increasing commercial pressures.
Read about how Latin America is seen from across the Atlantic
by MoCAArt colleague, Johann Bonilla
Central America at ARCO Madrid 2026
Choose from 30 vintage molas to support us with your $500 donation.
Molas are handmade layered, reverse-appliqué textiles, representing nature, spiritual protection, and cultural narratives.The quality of a Mola is determined by the number of layers of cotton that is used and the fineness of the stitching.
The vintage molas of the 1960s are typically valued up to $500.
In the works: A new book, Central American Postmodernism
a fascinating project to bridge the gap between the modernist movements and the contemporary art of Central America. Focusing on the 1970s, 80s, and 90s, these decades are a period of intense social and political transformation that influences each nation’s visual language and its artists.
Central American Modernism / Modernismo en Centroamérica
by Mark Ford & Suzanne Snider
MUSEUM OF CENTRAL
AMERICAN
ART
visit by appointment
The ANNEX
290 SE 2nd Avenue
Delray Beach, Florida 33444
Want to change how you receive these emails?
You can update your preferences or unsubscribe from this list.
Contact Us
suzanne@MoCAArt.org | 561.808.8587
Copyright © 2026 Museum of Central American Art. All rights reserved.
Notes from My Journal
Tackling the AI Challenge Head-On
I was looking forward to this trip because I always look forward to spending time at Villa Santana, our home in Nicaragua. I was also charged up because it was the first time since the COVID debacle that we were able to gather all of Agora’s executive publishers from all over the world for nearly two weeks in one place.
EN did a good job arranging the schedule so that there was time for attendees to have some free time to enjoy the resort’s amenities and, no doubt, try to keep in touch with their businesses via email and Zoom.
After a busy day, Agora publishers enjoy our always amazing sunsets.
The purpose of the get-together was to talk about the biggest and most meaningful changes we’ve all experienced in the past four or five years, with a particular emphasis on how AI is affecting our industry and what we’re doing about it.
In case you haven’t heard, the AI revolution that I predicted several times over the past 12 to 18 months has broken out, and it is radically transforming many industries on what seems like a weekly basis. One example of the way it’s affecting us: BC, our CFO, estimates that by May of 2027 we will be producing 50% more revenue than we are producing now, but with less than half our current payroll. You don’t need to have an MBA to understand how transformative that is going to be.
I was impressed by what we were able to accomplish in this short period of time. I audited six or eight super-informative presentations from some of our most knowledgeable and creative leaders, and I participated in maybe two dozen animated conversations that resulted in a to-do list that is 46 items long.
I’m going to summarize everything I learned here in the next issue. But because I didn’t want to leave you with anything more than this preview of the next issue, I thought I’d include the following anecdote that I must have written a dozen years ago. It somehow opened up on my laptop. (Maybe because Claude took over and decided I should do something with it?)