Music compensation fact of the day

The Kanye West and Jay-Z song “No Church in the Wild,” for instance, sampled a single instrumental line from a failed solo album recorded in the late 1970s by the Roxy Music guitarist Phil Manzanera; the licensing proceeds provided Mr. Manzanera with “the biggest payday he had in the course of his entire career.” Or there is Mr. Hepworth’s revelation that some crazed fan supposedly paid more than $160,000 for a seat at Led Zeppelin’s 2007 reunion.

Here is more from the WSJ review of David Hepworth’s Hope I Get Old Before I Die, reviewed by D.J. Taylor.

What I’ve been reading

1. Florian Illies, The Magic of Silence: Caspar David Friedrich’s Journey Through Time.  An excellent book, usually I am allergic to art history books that attempt to charm, but this one works.  Excerpt: “A question posed to the philosopher Peter Sloterdijk: ‘What makes the Monk by the Seashore so unprecedented?’ His answer: “It is the first picture of the dissolution of the subject in the substance.””  I had not known Friedrich also was an expert canary breeder.

2. Elsa Morante, Lies and Sorcery.  The kind of long novel that women on average will like much more than men do?  If someone said to me they thought it was excellent, I would not feel they had bad taste.  For me the narrative strayed too far from anything I cared about, other than fineries about the characters.

3. John Ferling, Shots Heard Round the World: America, Britain, and Europe in the Revolutionary War.  A good and well-detailed book for putting the Revolutionary War and its battles into a broader perspective, explicable to both American and British perspectives.

4. Nick Land, The Dark Enlightenment.  There is plenty one can say about this book and these views, but most of all I am struck how negative “the new Right” is about American institutions.  Even at whatever you might think is their most decrepit state (which year is that again?), they are some of the best institutions the world has seen.  Call that a low standard if you wish, but it is not an irrelevant standard.  Here are some other examples of people becoming far, far too pessimistic about the American status quo ex ante.  As personality types, they are simply way too much a bunch of sourpusses.  Things just have not been that bad!

5. John Cassidy, Capitalism and its Critics: A History: From the Industrial Revolution to AI.  John Cassidy of course is the New Yorker writer on economics.  Comprehensive and clearly written, I predict this book will find its audience, and no it does not discuss Nick Land.

*The German Empire, 1871-1918*

By Roger Chickering, this is so far the best book I have read this year, and I knew that within the first fifty pages (or less).  It is everything one could want from a book on this very important country and time period.  Likely I will report more on it as I read more, for the moment here is one excerpt:

Together, the new smelting techniques had driven the price of crude steel in Europe down nearly 90 percent by the end of the nineteenth century.  In Germany, the results of this trend registered in a thirty-fold increase in the annual production of steel between 1879 and 1913.  Thanks in great part to the iron fields of Lorraine, German output overtook British annual production in 1893; by 1913, German mills produced more steel than their British, French, and Russian counterparts combined.  Much of this steel was poured into the German railways.  Rail networks were extended; primarily at the insistence of the army, trunk lines were enlarged to two, in some cases four tracks.  Iron rails were replaced with more durable steel.  Wheels, axles, couplings, and wagons were modernized into steel, as were bridges.  These substitutions not only made railroads faster but also increased their capacity.  Meanwhile, palaces of rail travel emerged out of metal and glass as the great train stations of Leipzig, Frankfurt am Main, Hamburg, and Germany’s other main cities.  Late in the century travel along the steel rails also expanded in the form of tramways onto the streets of the cities themselves.

It is wonderful on the politics of the time as well, for instance tracing out the rise of Bismarck, or how the rivalries between Prussia and Austria shaped so many issues at the time.  You can buy the book here.

Thursday assorted links

1. Jerome Powell on stablecoins.

2. Hollis Robbins on o3 and higher education.

3. Google has started hiring for “post-AGI research.”  If you want one, here is a straightforward definition of AGI.  I believe o3 passes that test, including for the one hour of human labor mark.  I hear lots of complaining, but I don’t hear people, even the small-minded men who occupy one tiny corner of this debate, arguing it fails that test.  Here is Derya on o3 and immunobiology.  Here is Pablo on o3 and the law.  Here is the strawberries guy.  Also Greg Brockman comments.

4. Biosignatures on a habitable planet? (NYT)  And WaPo on the same.

5. Market-based mechanisms for AI agents.

6. Dean Ball, formerly of Mercatus and with excellent taste in music: “I am pleased to announce that as of this week, I have taken on the role of Senior Policy Advisor for AI and Emerging Technology at the White House Office of Science and Technology Policy.”

7. Delays for full Novavax authorization.

A note on o3 and AGI

Basically it wipes the floor with the humans, pretty much across the board.

Try, following Nabeel, why Bolaño’s prose is so electrifying.

Or my query why early David Burliuk works cost more in the marketplace than do late Burliuk works.

Or how Trump’s trade policy will affect Knoxville, Tennessee.  (Or try this link if the first one is not working for you.)

Even human experts have a tough time doing that well on those questions.  They don’t, and I have even chatted with the guy at the center of the Burliuk market.

I don’t mind if you don’t want to call it AGI.  And no it doesn’t get everything right, and there are some ways to trick it, typically with quite simple (for humans) questions.  But let’s not fool ourselves about what is going on here.  On a vast array of topics and methods, it wipes the floor with the humans.  It is time to just fess up and admit that.

My Conversation with the excellent Ian Leslie

I loved his new book on John and Paul, of the Beatles, and I am delighted to see it doing so well on the UK bestseller lists, and now also on the US lists.  Here is my audio, video, and transcript with him.  Here is the episode summary:

In this deep dive into one of music’s most legendary partnerships, Ian Leslie and Tyler unpack the complex relationship between John Lennon and Paul McCartney. Leslie, whose book John & Paul: A Love Story in Songs examines this creative pairing, reveals how their contrasting personalities—John’s intuitive, sometimes chaotic approach and Paul’s methodical perfectionism—created a unique creative alchemy that neither could fully replicate after the Beatles split.

They explore John’s immediate songwriting brilliance versus Paul’s gradual development, debate when the Beatles truly became the Beatles, dissect their best and worst covers, examine the nuances of their collaborative composition process, consider their many musical influences, challenge the sentiment in “Yesterday,” evaluate unreleased tracks and post-Beatles reunions, contemplate what went wrong between John and Paul in 1969, assess their solo careers and collaborations with others, compare underrated McCartney and Lennon albums, and ultimately extract broader lessons about creative partnerships.

Here is one excerpt:

COWEN: Do you think Paul’s song, “Yesterday,” is excessively sentimental?

LESLIE: No, I don’t. First of all, it’s not really sentimental in any way. I think it acquired this reputation because it does seem to come from a different tradition, perhaps a more easy-listening tradition in the first instance, although, I can hear echoes of music going far back from that in history.

But as a song about this person, this woman has left me and I have no idea why, it doesn’t then go on to describe how wonderful this girl is. Just says she’s gone and I don’t know why. It’s bleak. [laughs] The way he sings it is clipped, it’s brusque, it’s northern. It’s almost this northern folk sound to the way he sings it.

The string arrangement — he made sure that it wasn’t sentimental. He said to George Martin explicitly, “We’ve got to find a way of not making this sound saccharine.” So, George Martin asked the players not to play with vibrato or to play with very little vibrato. I think it’s very unsentimental, and in a way, it’s not that far off from “For No One,” which is an anti-sentimental song, where there’s very little hope.

COWEN: Or “Another Girl” even, right? The girls were leaving all the time in that song. It’s quite brutally about something very particular.

LESLIE: It’s interesting because I think in that year, 1965, with “Another Girl” and “I’m Looking Through You,” he is really soaking up, I think, from John. Or “The Night Before.” He’s leading into his Johness in the sense of he’s finding some anger and some hostility.

COWEN: You Won’t See Me,” most of all.

The only topic was the Beatles, plus a bit on artistic collaboration more generally.  In any case this was one of the most fun episodes for me.  Definitely recommended, and again I am a big fan of Ian’s book John & Paul: A Love Story in Songs.

o3 and AGI, is April 16th AGI day?

I think it is AGI, seriously.  Try asking it lots of questions, and then ask yourself: just how much smarter was I expecting AGI to be?

As I’ve argued in the past, AGI, however you define it, is not much of a social event per se.  It still will take us a long time to use it properly.  I do not expect securities prices to move significantly (that AI is progressing rapidly already is priced in, and I doubt if the market cares about “April 16th” per se).

Benchmarks, benchmarks, blah blah blah.  Maybe AGI is like porn — I know it when I see it.

And I’ve seen it.

Here is the OpenAI LiveStream.  And they tell us o3 pro is on the way.  Here is a good Dan Shipper review.  Here is Alexandr Wang.

My Blind Spots

“Based on everything I’ve ever asked you, what do you think my biggest blind spots are?” ChatGPT replies:

Here’s a speculative, analytical take based on your past questions and style of interaction:

1. Underestimating Non-Market Frictions in Implementation
You’re extremely sharp on incentives, regulation, and institutional design, especially in economic theory and historical analysis. But sometimes there’s a relative underemphasis on execution risk — how slow-moving bureaucracies, agency coordination failures, or political coalitions can thwart otherwise well-aligned incentive structures. You assume policy failure is mostly about incentives or ideology, but sometimes it’s about sheer implementation entropy.

Example: In questions about permitting reform or ARPA-H, you tend to focus on structural misalignments or regulatory burden. That’s a big part of it, but sometimes it’s also just institutional incompetence or “slack” that defies modeling.

2. Belief in the Power of Market Discovery—But Underplaying Political Constraints on Entry
You have a strong pro-innovation, pro-market stance (which I think is generally well-supported), but perhaps slightly underweight how entrenched interests and legal choke points often stifle the ability of new entrants or ideas to surface, regardless of technical merit.

Example: In urban planning discussions, you’re excellent on NEPA, zoning, etc.—but some of the constraints (e.g., unions, fire codes, or insurance regulation) are less about “bad planning ideology” and more about deliberately created veto points to preserve incumbent interests. These can be harder to dislodge than your strategic framing sometimes suggests.

3. Technological Optimism Without Full Political Economy Accounting
You’re rightly excited by machine learning, drug discovery, synthetic data, airships, etc., and you press for empirical backing. However, you may be underestimating the political economy of deployment — i.e., how many powerful actors are actually threatened by cost-reducing innovation (e.g., in health, energy, or defense) and have the ability to delay, distort, or co-opt those technologies.

Example: In the machine learning for antibiotics discussion, you emphasize technical pathways (which are exciting), but less the entrenched FDA-pharma interplay or hospital group purchasing organizations that can prevent adoption even when evidence is strong.

4. Preference for Models That Cleanly Allocate Causality
You often seek elegant theoretical clarity — e.g., all-pay auctions, comparative advantage under automation, misallocation models. But the real world often features multiple overlapping distortions (e.g., taxes, zoning, union rules, insurance, etc.) that interact nonlinearly. Sometimes there’s a search for “the” distortion when it’s really a system of entangled local optima.

5. Policy-First Lens vs. Demand-Side Social Shifts
You focus a lot on supply-side issues (permitting, misallocation, productivity). This is correct and important. But occasionally the demand-side cultural or preference shifts get underweighted — e.g., the declining taste for urban density, aversion to risk, or increasing parental control over children’s autonomy. These may not be fixable through supply-side tweaks alone.

Hat tip: Aashna Doshi.

Subterranean sentences to ponder

But the fact that it’s commonplace is precisely why Earth’s subsurface biosphere is so compelling.  Mud is everywhere, which means it is important.  If you add up the total amount of mud underneath all the worlds’s oceans, you come up with a volume equivalent to about the entire Atlantic Ocean.  And, per cubic meter, there are 100 to 100,000 times more microbial cells in mud than there are in seawater.  That means that there’s so much intraterrestrial life in the subsurface that it’s hard to even fathom it.  The total amount of microbial cells in the marine sediment subsurface is estimated to be 2.9 x 10 [to the 29th] cells.  This is about 10,000 times more than the estimated number of stars in the universe.  But that’s not the whole subsurface.  You’d have to at least double this number to include the microbial cells living deep underneath the land.  And some of these cells may have found pockets where the food is more abundant than the average location, so more cells can live there than our models predict.  For these reasons, the actual number of microbial cells in the subsurface biosphere is certain to be much higher than our current estimates.

That is from the new and interesting IntraTerrestrtials: Discovering the Strangest Life on Earth, by Karen G Lloyd.

Is China the ultimate free-rider?

With a Trump-induced decline of American alliances n the works, is Chinese global ascendancy going to result? It would seem so. Matt Yglesias tweeted that “America may be cooked and it’s gonna be the Chinese century.” Thomas Friedman recently wrote a column suggesting that the future is to be found in China, not America.

In the realm of technology, China’s advances are impressive. BYD has the best and cheapest electric vehicles, the CCP is pulling out all stops to attain high-quality chips and lithography capabilities. Chinese AI, in the form of DeepSeek and Manus, has shocked many Westerners with its inventiveness.

Yet Western and most of all American hegemony is not over yet. These advances by China are real, but they rest on a foundation of Western values and institutions more than it might appear at first.

Consider global economic growth over the last few decades. China has risen in import, relative to most of the poorer nations it was once bunched with. America too has risen in economic influence, widening the gdp gap with Western Europe. The lesson is that economies with scale have prospered more than average, which is hardly surprising in a world where tech and also big business are ascendant. America and China are thus likely to prosper jointly under broadly common conditions.

The inconvenient truth, for China, is that its scale relies upon American power and influence. The Chinese export machine, for instance, requires a relatively free world trading order. The recipe to date has been “mercantilism for us, free trade for everybody else.” Yet Trump threatens to smash that framework. If the world breaks down into bitterly selfish protectionist trading blocs, China will be one of the biggest losers. After all, where will the Chinese sell the rising output from their factories?

The Chinese growth and stability model also requires relatively secure energy supplies. For that it relies on the United States and its allies, as the Chinese programs for nuclear and solar power remain far from their final goals. If the Western alliance system collapses, who is to keep the Middle East relatively stable, at least stable from the point of view of procuring fossil fuels? China hardly seems up to that task, as the country has neither the means, the inclination, the experience, nor the allies to do the job.

Furthermore, China relies more on American hard and soft power more than it likes to let on. The leading role of America makes both Western Europe and also Latin America a bit “soft” when it comes to self-defense and martial spirit and also nationalistic pluck. After all, many countries are outsourcing their defense and also parts of their intelligence-gathering to the United States. That makes them relatively easy pickings for Chinese infiltration, whether it be economic infiltration, pulling up alongside as an easy “extra friend” to boost bargaining power with America, or spying and surveillance. If Trump scuttles our current multilateral commitments and trust, China will find most other countries harder to penetrate, not easier.

Another risk on the horizon is nuclear proliferation, which could result from any number of events, ranging from an Israeli attack on Iran, the partial fall of Ukraine, or a Chinese invasion of Taiwan. The more nuclear powers inhabit the world, the more China is hemmed in with its foreign policy ambitions. That outcome may not be good for the United States either, but again we are back to the scenario where the US and China have some fundamental common interests, rather than the narrative where China displaces America as world leader.

There is much to rue in the first few months of Trump’s foreign and economic policy, but China is far from being able to take the baton. They are running second, and doing a great job of that, precisely because we Americans – in spite of all our mistakes — still have the lead.

Tuesday assorted links

1. Scott Sumner on who is rising and falling in status.  Mostly I agree.

2. New personalized dating form for STEM men and women, here is the link for women.  The previous link I put up for men already is generating matches and perhaps a marriage as well.

3. Michael Nielsen wants to reconsider AI alignment as the goal.

4. Musa al-Gharbi on Harvard’s decision.

5. For a brief moment, Harvard tweets libertarian, pre-1964 stuff.  And Alex retweets Will Stancil, and justifiably so.