A selection of longer posts originally published on X.
2026-06-20 · X post
I just visited Paris. The city seemed to be in particularly radiant shape this time.
• It got me thinking about how many of the nicest built environments in the world standardize materials rather than form. Jerusalem's stone regulation makes it much prettier than Tel Aviv. Similarly, rules in the Charleston, the Cotswolds, and Sea Ranch leave a lot of flexibility in shape, but tightly restrict materials in a way that yields cohesion. In Paris's case, there are of course also some rules around form, but the consistency of the limestone (and zinc) is very pleasant.
• I hadn’t before internalized that central Paris is unique for the fraction of its building stock that is traditional. There are of course some modern buildings, such as Centre Pompidou and the new facade at La Samaritaine, but they are rare and typically dramatic. Most pleasant old cities (such as London) contain more of a mixture.
• Relatedly, is Haussmannian Paris the finest example of the central planning that Scott decries? "By 1870 one-fifth of the streets in central Paris were his creation." And is the late 19th century the last time you could have done this well, immediately before the corruptions of modernism? I guess Chicago was later, but Paris certainly comes close.
• From a book I picked up: In a letter of 1886 to the Ministry of Public Works, Charles Garnier, architect of the neo-Baroque Paris Opéra, wrote, “The Metropolitan Railroad, in the eyes of most Parisians, will only be excused if it rejects absolutely all industrial character so as to be completely a work of art. Paris must not be made into a factory, it must stay a museum.” Are there elites anywhere in the world today who would reject something in the physical world unless it was a work of art? One artist recently commented to me that late 19th century France had the most educated visual culture among its elites in human history. This observation struck me a few times as I traveled around.
• I am curious what those who defend modern architecture say about central Paris. Do they think that one could in principle have a place built of modern architecture that people would find as attractive and that would bring joy to so many? Do they think that such a place exists in actuality today? If not, why not? Or is the goal of having somewhere pretty and attractive in their eyes itself ignoble and saccharine? To me Paris feels like a challenge of the whole project.
• Walking past the Louvre at night, I was struck by its austerity and severity. It made me reflect on how Parisians in 1700 might have felt as they took it in, and the subjugation that has been associated with social structures of prior eras. (Maybe this is on my mind partly as a result of reading Charles Taylor.) It made me wonder if I should be slightly more sympathetic to modernism for embodying a sense of individual freedom and joy. The Hilma af Klint exhibition at the Grand Palais was quite a contrast.
• Perhaps heretical, but Notre Dame is just not especially impressive as a cathedral, especially inside, though the restoration seems to have been excellently done, and is a terrific achievement. Overall, Lincoln cathedral (say) is much more attractive in my view. Maybe I need to read Hugo to appreciate it better. (Hugo apparently was responsible for much of the resurgence of interest in Gothic architecture. A good example, I guess, of art driving life.)
• The Renoir exhibition at the Musée d’Orsay was interesting for its emphasis on egalitarian and open relations between men and women, not something observed everywhere in the world at the time. "At the same time delicate and modest – neither moralising nor Dionysian." I thought of @_alice_evans and her work.
• There are now so many bikes in Paris. It means you have to pay very active attention as a pedestrian, but is overall a big improvement. Rue de Rivoli is now dominated by the pleasant whirr of bicycles. I mostly got around this way.
• The Musée Quai Branly is very interesting – it’s the best tour of the world in a single compressed space that I know of. Most of the works are not impressive as such, but the concentrated breadth is great. The Ethiopian illustrated Gospels were very charming.
• Maybe my imagination, but there seemed to me to be a third fewer brasseries than on prior trips. Overall, the food was good, but not better than what you get at good restaurants in the US. The median in Paris is definitely still better, though.
• The Matisse exhibition at the Grand Palais was pleasant. It mostly reminded me of the observation that it is difficult to rank artists but easy to rank the work of a given artist. The Blue Nudes and The Sheaf are just very obviously among Matisse’s best work.
• The Michelangelo x Rodin exhibition at the Louvre was excellent, most of all for making clear how direct the artistic lineage is. Given the 300 year interlude, we should probably be more optimistic about the prospects for revival of the best of the visual arts. I hadn't before realized that Michelangelo's career spanned 74 years. It’s easy to focus on youth and prodigious genius, but maybe enduring genius should be more central. May we all aim to be useful and productive for a large majority of a century! In this vein, David Hockney, RIP, also just cleared the 70 year career mark.
• The Louvre is quite hot; far hotter than an American museum would be. Presumably because of EU/French air conditioning laws? (26 degree regulatory minima, supposedly.)
• Overall, central Paris feels like it's in very good shape. Things are generally quite clean and well-maintained. Not too much graffiti (though some buildings, such as the Louvre, are very overdue for power washing.) Nowhere felt unsafe. (Given that it’s been ruled continuously by socialists since 2001, one wonders why it has fared better than many coastal cities in America. The LLMs claim that it's because much of the funding is central and because the police report centrally, not to the mayor.)
Overall, is central Paris the greatest single artistic achievement in the world? That is what I came away wondering.
Pictured: Ethiopian gospels; Iranian qalamkari; Renoir; af Klint.
2026-05-25 · X post
Tyler and I just published a list of the recipients of the New Aesthetics grants: https://newaesthetics.art/grants.
Thank you very much to all who applied. There were far more applications than we expected. We funded 28 grantees and are excited to see what they create.
My reflections on the whole thing:
• Though there are clearly selection dynamics afoot, figuring out some route beyond the current aesthetic moment seems to be of wider interest in the art community than I would have guessed. Many applicants described their dissatisfaction with the status quo, some in strong terms. We had to close applications after a few weeks because there were so many.
• It's too early to call it, but it seems that both beauty as an unapologetic goal (contra much that is in modernist and contemporary approaches), and ways to channel pre-modern styles into something new for the present era, are of growing interest.
• The awards made me reflect on the perhaps obvious issue of how hard it must be for an artist to persistently do something new: schools, galleries, buyers, etc., all have structurally embedded preferences as well. These individual awards made me wonder what form supporting new clusters could take.
• Architecture seems to me like the discipline most ripe for new ideas. One correspondent observed: "American architects are somewhat constrained by the association with the academy, in addition to the well known regulation issues. There is a tendency to overthink things so that the designs are formally interesting to someone deep in the conversation, but lacking poetry and magic. There are more firms in Europe, South America and beyond that “just do things” (especially in places where it is easier to build)." This was evident in the submissions.
• AI seems to be making people rethink things in a quite fundamental way, just as urbanization/industrialization/popularization of photography did at the end of the 19th century. For some that will mean interesting new forms of AI-augmented art, but the effects of the rethinking will likely be wider.
• Arts funding is clearly as precarious and scarce as ever. That's unfortunate, but it probably also means that individual actors can have meaningful impact, and I encourage others to get involved if interested.
• There's a lot to know that is not written down, and I'm very grateful to those who have helped and advised me along the way.
2026-05-16 · X post
Detroit impressions:
• The downtown is full of beautiful buildings. All of them seem to have been built specifically in the 1920s. I guess that is after the city had accumulated enough auto wealth but before the twin hits of Modernism and the Depression. (I hadn't known that the GM Renaissance Center, built as a revitalization project, was at the time the largest private development in US history, and also at the time the world's tallest hotel. It may be large, but it is not pretty.) The downtown is surprisingly depopulated -- both the streets and the sidewalks feel empty. That said, it didn't feel at all unsafe. There are lots of great homes in the suburbs.
• The Henry Ford Museum of American Innovation is amazing, and it's worth visiting Detroit for it alone. Among many (many) other things, it contains the oldest known surviving steam engine in the world, the actual Montgomery bus on which Rosa Parks refused to give up her seat, a deconstructed Model T, a deconstructed Eames Chair, and many great cars, agricultural equipment, locomotives, industrial specimens, and more. (They have the Lincoln Continental that JFK was riding in when assassinated -- which, apparently, was returned to service and used by several subsequent presidents.)
• The museum made me wonder why American car design peaked in the mid-60s. (This fact is very evident at the museum.) The LLMs blame the 1966 National Traffic and Motor Vehicle Safety Act. (Not quite https://wtfhappenedin1971.com/, but close.)
• Good food exists but it is hard to find.
• The Heidelberg Project also exists and is unique.
• We stayed at the Dearborn Inn, which is wonderful, and contains cottages modeled after the homes of significant American figures. Dearborn (and Hamtramck) are now predominantly Muslim, apparently for reasons that go back a century to Henry Ford's $5 wage. Dearborn felt noticeably prosperous (we stopped for coffee at a fancy Japanese cheesecake cafe); Hamtramck did not.
• https://michigan.gov/ says that the Hispanic population of Michigan is just 6%. Coming from California, the absence is very striking.
• The Detroit Institute of Arts is remarkable, particularly the room with the American landscapes and the section with the Dutch masters (especially The Visitation). An obvious question is why there is nothing quite like it in the Bay Area given how much richer the latter is than Detroit ever was -- we techies are just so uncultured by comparison. The Diego Rivera murals are amazing (and quite strange; you can see why they were controversial).
• Detroit is full of historic plaques -- they are truly everywhere. This is presumably due in part to the fact that Detroit has a lot of history, but it still has many more than places with comparable historical depth. Some research suggests that it might be related to generous tax credits for historic preservation. Whether or not that is true, Detroit persuades me that other places should engage in more plaquemaxxing.
• I recommend a visit! You overall leave with some sense for how exciting America must have felt in the early 20th century.
2026-04-26 · X post
Which are the most humane (empathetic, compassionate) Arab / Middle Eastern novels?
Thought behind the question: I read a bunch of these novels last year -- my selection algorithm was to sample widely among the award-winning works from the region (Egypt, Sudan, Iran, Palestine, Jordan, among others) -- and, overall, I was very struck by the darkness and violence. (Abundant rape, murder, violence, and so forth.)
In trying to figure out why the outlooks are so consistently bleak, I don’t think it’s only a matter of colonialism. For example, The Blind Owl is often ranked as the best novel to come out of Iran, which was never colonized as such, but nonetheless describes an obsessive madman who kills and dismembers his partner. In Season of Migration to the North, the colonizer -- Britain -- is described as being quite benevolent at least at the object level (granting a scholarship to the protagonist; treating him unreasonably justly during his murder trial). Men in the Sun is similarly grim while taking place in a post-colonial Arab world. Even books that are sometimes described as heartwarming (such as Mahfouz’s Cairo Trilogy) centrally feature rape and female oppression (that Amina is not permitted to leave the home is a core plot issue).
One guess is that it is a function of award selection algorithms: gritty despair is seen as high-status and structurally celebrated.
Another theory would be the period: there are lots of humane novels in the Western canon (Dickens, Tolstoy, Eliot…), but those are more likely to be from the nineteenth century, whereas the Arab / Middle Eastern novelistic canon didn’t emerge until the twentieth. I’m not sure this explains it, however. In Search of Lost Time, Great Gatsby, Ulysses, Midnight's Children are all critically-acclaimed 20th century novels, close to the top of almost any list, that one would not describe as macabre.
It’s possible that I just read the wrong books and got unlucky. So: which authors from the region can best be compared to Faulkner, Eliot, Fitzgerald, or Rushdie? (And if they haven't won major awards, does that indicate that the awards have a negative bias?)
2026-04-17 · X post
I'm lucky enough to have a great doctor and access to excellent Bay Area medical care. I've taken lots of standard screening tests over the years and have tried lots of "health tech" devices and tools.
With all this said, by far the most useful preventative medical advice that I've ever received has come from unleashing coding agents on my genome, having them investigate my specific mutations, and having them recommend specific follow-on tests and treatments.
Population averages are population averages, but we ourselves are not averages. For example, it turns out that I probably have a 30x(!) higher-than-average predisposition to melanoma. It turns out that there are both specific supplements that help counteract the particular mutations I have, and of course I can significantly dial up my screening frequency. So, this is very useful to know.
I don't know exactly how much the analysis cost, but probably less than $100. Sequencing my genome cost a few hundred dollars.
(One often sees papers and articles claiming that models aren't very good at medical reasoning. These analyses are usually based on employing several-year-old models, which is a kind of ludicrous malpractice. It is true that you still have to carefully monitor the agents' reasoning, and they do on occasion jump to conclusions or skip steps, requiring some nudging and re-steering. But, overall, they are almost literally infinitely better for this kind of work than what one can otherwise obtain today.)
There are still lots of questions about how this will diffuse and get adopted, but it seems very clear that medical practice is about to improve enormously. Exciting times!
2026-03-21 · X post
Just discovered Ruskin's The Nature of Gothic. Remarkable essay: https://www.gutenberg.org/files/30755/30755-h/30755-h.htm#page151.
"The charts of the world which have been drawn up by modern science have thrown into a narrow space the expression of a vast amount of knowledge, but I have never yet seen any one pictorial enough to enable the spectator to imagine the kind of contrast in physical character which exists between Northern and Southern countries. We know the differences in detail, but we have not that broad glance and grasp which would enable us to feel them in their fullness. We know that gentians grow on the Alps, and olives on the Apennines; but we do not enough conceive for ourselves that variegated mosaic of the world’s surface which a bird sees in its migration, that difference between the district of the gentian and of the olive which the stork and the swallow see far off, as they lean upon the sirocco wind. Let us, for a moment, try to raise ourselves even above the level of their flight, and imagine the Mediterranean lying beneath us like an irregular lake, and all its ancient promontories sleeping in the sun: here and there an angry spot of thunder, a grey stain of storm, moving upon the burning field; and here and there a fixed wreath of white volcano smoke, surrounded by its circle of ashes; but for the most part a great peacefulness of light, Syria and Greece, Italy and Spain, laid like pieces of a golden pavement into the sea-blue, chased, as we stoop nearer to them, with bossy beaten work of mountain chains, and glowing softly with terraced gardens, and flowers heavy with frankincense, mixed among masses of laurel, and orange and plumy palm, that abate with their grey-green shadows the burning of the marble rocks, and of the ledges of porphyry sloping under lucent sand. Then let us pass farther towards the north, until we see the orient colors change gradually into a vast belt of rainy green, where the pastures of Switzerland, and poplar valleys of France, and dark forests of the Danube and Carpathians stretch from the mouths of the Loire to those of the Volga, seen through clefts in grey swirls of rain-cloud and flaky veils of the mist of the brooks, spreading low along the pasture lands: and then, farther north still, to see the earth heave into mighty masses of leaden rock and heathy moor, bordering with a broad waste of gloomy purple that belt of field and wood, and splintering into irregular and grisly islands amidst the northern seas, beaten by storm and chilled by ice-drift, and tormented by furious pulses of contending tide, until the roots of the last forests fail from among the hill ravines, and the hunger of the north wind bites their peaks into barrenness; and, at last, the wall of ice, durable like iron, sets, deathlike, its white teeth against us out of the polar twilight. And, having once traversed in thought its gradation of the zoned iris of the earth in all its material vastness, let us go down nearer to it, and watch the parallel change in the belt of animal life: the multitudes of swift and brilliant creatures that glance in the air and sea, or tread the sands of the southern zone; striped zebras and spotted leopards, glistening serpents, and birds arrayed in purple and scarlet. Let us contrast their delicacy and brilliancy of color, and swiftness of motion, with the frost-cramped strength, and shaggy covering, and dusky plumage of the northern tribes; contrast the Arabian horse with the Shetland, the tiger and leopard with the wolf and bear, the antelope with the elk, the bird of paradise with the osprey: and then, submissively acknowledging the great laws by which the earth and all that it bears are ruled throughout their being, let us not condemn, but rejoice at the expression by man of his own rest in the statutes of the lands that gave him birth. Let us watch him with reverence as he sets side by side the burning gems, and smoothes with soft sculpture the jasper pillars, that are to reflect a ceaseless sunshine, and rise into a cloudless sky: but not with less reverence let us stand by him, when, with rough strength and hurried stroke, he smites an uncouth animation out of the rocks which he has torn from among the moss of the moorland, and heaves into the darkened air the pile of iron buttress and rugged wall, instinct with work of an imagination as wild and wayward as the northern sea; creations of ungainly shape and rigid limb, but full of wolfish life; fierce as the winds that beat, and changeful as the clouds that shade them."
2025-12-19 · X post
The @Stripe Atlas team just published their year in review. Because Atlas now incorporates so many startups (23,000+ thus far in 2025), it's an interesting snapshot of broader ecosystem trends. Some of the findings that I thought were interesting:
• Atlas incorporations grew 36% Y/Y. More than 20% of Delaware C Corporations are now started with Atlas. (Delaware corporations are started for lots of reasons, obviously -- large companies creating subsidiaries, etc. -- so Atlas represents some larger fraction of overall startup creation.)
• Founders of Atlas companies can come from anywhere and Europe was the fastest-growing region (+48% Y/Y). My speculative hypothesis is that this is because dealing with incorporation is very annoying and bureaucratic in many European countries, and the knowledge that you can just use a US corporation is becoming more widespread. A lot of European leaders are aware of these issues and I'm hopeful that they'll act.
• Multinational founding teams are 79% more common (among multi-founder teams) than they were in 2017. This feels like a straightforward dividend of remote work, but the effect size is surprising to me.
• Time-to-revenue is accelerating. Remarkably, the median Atlas startup that incorporated in 2025 generated 39% more revenue in its first 6 months than its 2024 counterpart. And while there were more incorporations than ever this year, it is also true that a growing fraction of companies reached $100k of revenue within 6 months. That is, both quantity and some kind of quality (at least in revenue terms) are increasing. I'm not exactly sure how to explain this. I think the null hypothesis is simply that AI and stablecoins have opened the aperture of possibility, a vast surge of startups is mobilizing, and customers are eagerly flocking.
• The variance is increasing. While the median company generated 39% more revenue than last year, the 90th percentile company generated 52% more, and the 99th generated 67% more. Again, this is a year-over-year change -- pretty striking. This trend aligns with the anecdotes: startups like @cursor_ai and @Lovable (both of which incorporated with Atlas) are posting truly unprecedented revenue growth figures.
One of my favorite aspects of Stripe is getting to see trends like these play out in real time. If you're interested in building tools that directly enable this entrepreneurship and innovation, you should get in touch.
2025-12-15 · X post
War and Peace is a honking doorstopper. The explanation appears to involve a heartwarming tale of vertical integration. With the confidence provided by early career literary success, and spurred by the indifferent response to early serialized excerpts, Tolstoy decided to self-publish War and Peace, contracting a printer, and adopting the financial risks as his own. In so doing, he excised the role of “external editor”, and asserted independence from meddling oversight. In fully liberated auteurship, we get multiple epilogues, multi-chapter philosophical asides, and a ludicrously sprawling cosmos of characters. Like a Substacker unshackled from tyrannical newspaper restrictions on length and form, Tolstoy wallows delightedly in his prolix freedom.
War and Peace combines history, novel, and philosophical treatise. The philosophy, however, is wrong: Tolstoy attempts a misguided refutation of the heroic conception of history. Instead of, say, granting Napoleon’s European success as an interesting exception to a general tendency, Tolstoy unapologetically adopts a tendentious and implausibly maximalist position. “Napoleon’s influence on the course of these events is purely external and fictitious.”
It certainly seems possible that the importance of history’s heroes tends to be overstated relative to structural factors and the deliberate effects of single individuals, but “purely external and fictitious” is stretched beyond credibility. How exactly does one deterministically derive events which occurred under Lenin, Hitler, Atatürk, Mao from the broad tenor of the masses?
Tolstoy immodestly adopts the robes of Newton and even the infinitesimals of calculus as analogs for his case, but his position is of course the antithesis of anything the scientific revolution represents, and his “science of history” is de facto the opposite. Where Newton enabled specific prediction, and rendered supernatural explanations unnecessary, Tolstoy places us in the position of mystics: whatever ensues is structurally determined by unknowable forces far larger than us. His famous religious transformation was not announced for some years to come, but in War and Peace we already see his sympathies.
He was only 35 when he started to work on War and Peace, and he was supposedly irritated by hagiographic histories, such as that of Adolphe Thiers. Maybe he was just too young.
–
Tyler agrees that the philosophy is wrong, but argues that War and Peace best reflects just how much detail can be in a single grain of history. (The novel arguably even contradicts the treatise.) Even though Tolstoy’s explicit argument is that humanity as a whole is a kind of teeming hive (“history, that is, the unconscious swarmlike life of mankind, uses every moment of a king’s life as an instrument for its purposes”), the novel demonstrates the infinite intricacy of society and relations, integrating both private and the public domains. When asked which major novel has the most named characters, ChatGPT ranks In Search of Lost Time ahead of War and Peace, but places it nonetheless in the top 5.
The obvious comparison for War and Peace is Grossman’s Life and Fate. Both span multiple families, military conflict, personal relationships, and major figures of the age, with Grossman’s work of course explicitly modeled on Tolstoy’s. As works of fiction, they're somewhat comparable: sprawling and compelling tapestries. As evocations of the human condition, however, Grossman quite clearly gets the better of Tolstoy. Grossman understands the moral and spiritual significance of freedom, and he uses Tolstoy’s architecture to contest Tolstoy’s outlook.
Tolstoy purports to show that enlightenment comes from acceptance. Pierre’s valiant efforts (to free his serfs, to assassinate Napoleon) come to nought; his peace arrives when he encounters Karataev, who simply accepts the larger forces that determine our outcomes. Prince Andrei, similarly, seeks worldly achievement (military glory, reform), but instead achieves happiness on his deathbed by viewing death as an awakening and transcending the idea of specific love in favor of something more diffuse. (Again, we can already see Tolstoy the mystic.)
For Grossman, this acceptance is in error, for human agency is the flame. Ikonnikov, the prisoner, refuses to build the gas chamber. This is an act of self-assertion that costs his life, but for him there can be no meek submission, and even totalitarianism can’t extinguish the ability to choose. Grekov, commanding House 6/1, cuts the line connecting him to his superiors, so that he may execute his own autonomous strategy. Again, a rejection of the swarm. In signing the letter of denouncement, Shtrum does accede to larger forces of history. Where Pierre finds serenity in capitulation, it is catastrophic for Shtrum: an irreconcilable fracturing of the soul.
Grossman acknowledges this disparity. In the book, we encounter the comment: “Chekov brought Russia into our consciousness in all its vastness—with people of every estate, every class, ever age… More than that! It was as a democrat that he presented all these people—as a Russian democrat. He said—and no one had said this before, not even Tolstoy—that first and foremost we are all of us human beings.”
Tolstoy misses the importance of human agency in the macro and devalues it repeatedly in the micro.
–
If we had to steelman the Tolstoy position in a contemporary context, maybe we could look at AI. It’s not a war, but it’s consuming a lot of society’s resources these days. Here, it’s not clear how much heroic individuals exercise meaningful control. Nick Land wrote (in 1993, no less) that “what appears to humanity as the history of capitalism is an invasion from the future by an artificial intelligent space that must assemble itself entirely from its enemy’s resources.” Despite the stated desire of many to avoid race dynamics, has there ever been a more vivid demonstration of the machinic determinism of “techno-capital” than 2025’s perfervid sprint?
Tolstoy venerates Kutuzov for his humility amidst the sweeping tides. Kutuzov nudges and adjusts, but lacks the hubris to attempt control. As Napoleon retreats from Russia, he simply follows, and in such restraint Tolstoy’s approbation is established. Early attempts to control AI's development have not really worked, and those arguing that we must avoid the race, pause, or first solve safety have been mostly swept away by the tide. At least thus far, the AI Kutuzovs seem to have fared better.
–
Unlike Karenina, War and Peace is definitively too long.
2025-10-20 · X post
Maybe a very prosaic observation, but I've been reflecting on just how much the pandemic changed the world in ways that are completely unrelated to the pandemic itself. I think I've underestimated it 'till now.
In a recent interview, I was struck by the comment that so many of the shops that we associate with the best of France—the poissonneries and the fromageries—closed during the pandemic, to be replaced by take-out pizza shops and the like.
College professors almost uniformly describe big changes in student behavior: lecture attendance and willingness of students to complete reading assignments are both way down.
A UK government official recently told me that British economic statistics have become much less reliable since the pandemic: data on trade, employment, and population is suspect. (The true GDP per capita figures are probably worse than what is indicated by the published data, since the 2021 census is believed to be an undercount.)
In the West, there are far fewer bustling workplaces than there used to be. In recent conversation with a well-traveled friend, he bemoaned how so many cities—places like Madrid, Buenos Aires, and Bali—have lost so much of their erstwhile vibrant nightlife.
Immigration accelerated enormously across many countries, including the US, the UK, Canada, and Australia.
In China, I hear descriptions of how fear, caution, and conservatism have persisted since the COVID lockdowns. (And Western travel to China remains massively depressed.)
Lots of the changes are neutral, or even good. Retail participation in the US stock market almost doubled overnight, say, and has persisted at that elevated rate. Firm creation in the US increased by around 50%, which is probably a very good thing.
Overall, the number of time series (either literal or figurative) that jumped discontinuously during COVID and then didn’t return to baseline is just very striking.
Which are the best historical analogs? Are there any apart from major wars?
I want to read this book!
2025-10-11 · X post
After Titan, I decided to stick with the theme of oil entrepreneurs, and at the same time rectify an important omission in my US civics education. I happened to read Moby Dick alongside Shakespeare, specifically Richard II, and it's clear that Melville was quite directly inspired. “So man’s insanity is heaven’s sense”, “the greater idiot ever scolds the lesser”, “I wonder, Flask, whether the world is anchored anywhere; if she is, she swings with an uncommon long cable, though.” I would have guessed Shakespeare if asked to speculate on the origin of many of the apothegms that Melville casually scatters. With hamartic compulsion, Ahab is obviously a tragic figure in the mold of Lear or Hamlet, and the Pequod serves as a kind of stage (complete with directions as prelude to many chapters). Soliloquies abound.
Melville is a post-industrial revolution author, though, writing from the other side of modernity’s threshold. Where Shakespeare’s preoccupation is in human relations and the psyche, Melville recognizes that we are in a time of discovery and change, and he is just as intently interested in society, the economy, biology, and the wider planet. Even when telling the history of a country, Shakespeare’s worlds are small; Melville’s, despite being substantially hemmed to a boat, is somehow large. Maybe Shakespeare in some way captured all there was to be captured at the time; if so, in Melville we can see how much larger humanity has become: industry, trade networks, energy, science, anthropology, firms with multinational labour, knowable continents beyond great seas.
It’s well known, or at least widely speculated, that VC economics are based on those of the whaling industry. As such, we presumably ought to reflect on Ahab as Silicon Valley hero: the cetacean anticipates the unicorn. Ahab recruits, he strategizes, he inspires, he exhorts, and he fully adheres to the doctrine that the captain’s fate must remain inexorably coupled with the ship’s. The most important imperative for a founder, of course, is to identify the right goals; here Ahab, in his fulminating single-mindedness, falls short. Much lore valorizes those who persist in dogged pursuit of their original mission no matter the impediments and the haters. Was Melville the first to illustrate this archetype? He doesn’t seem fully persuaded of its merits, however. Moby Dick perhaps serves to show that the founder’s zeal can exist in excess, and that, while no doubt flawed and liable to error, the signals provided by the market are a helpful check on frail human reason. Ahab himself reflects in a moment of self-awareness: “Here’s food for thought, had Ahab time to think; but Ahab never thinks; he only feels, feels, feels; that’s tingling enough for mortal man! to think’s audacity. God only has that right and privilege.” Do we think? We assuredly imagine so, but maybe we should all listen to Starbuck: “I came here to hunt whales, not my commander’s vengeance. How many barrels will thy vengeance yield thee even if thou gettest it, Captain Ahab? it will not fetch thee much in our Nantucket market.” One should sometimes sell to Google, shut the company down, go try anew.
—
The 19th century Anglosphere is the time of the cathedralesque Victorian pumping stations, of Dickens, of Turner, of Romanesque Revival, Gothic Revival, Beaux-Arts. When @culturaltutor (check out his new documentary!) calls for a retvrn, it is to the nineteenth century more than any other. And at the same time, it is the century of the full-throated destruction of California’s redwood forests, previously one of the great majesties of the planet. It is the century of the slaughter of the American bison (tens of millions to fewer than a thousand) and of the elimination of the passenger pigeon (extinct by the early 20th century). Our post-60s culture is incapable of designing an appealing government building, but it does feel a revulsion at the unbridled extirpation of a species or of an ecosystem. “Just be more Victorian” does not feel like the right blanket prescription.
The 19th century seems to have been possessed by the imperative to both forge and to debase grandeur; some kind of dialectic between the awesome and the awful. Did they merely happen to coincide or were they actually linked? Moby Dick is a novel about the counterpoise.
It is unsparing in its description of the realities: “At the instant of the dart an ulcerous jet shot from this cruel wound, and goaded by it into more than sufferable anguish, the whale now spouting thick blood, with swift fury blindly darted at the craft, bespattering them and their glorying crews all over with showers of gore, capsizing Flask’s boat and marring the bows. It was his death stroke. For, by this time, so spent was he by loss of blood, that he helplessly rolled away from the wreck he had made; lay panting on his side, impotently flapped with his stumped fin, then over and over slowly revolved like a waning world; turned up the white secrets of his belly; lay like a log, and died. It was most piteous, that last expiring spout. As when by unseen hands the water is gradually drawn off from some mighty fountain, and with half-stifled melancholy gurglings the spray-column lowers and lowers to the ground—so the last long dying spout of the whale.”
And yet the next chapter breezily (is that the point?) commences: “The more I dive into this matter of whaling, and push my researches up to the very spring-head of it so much the more am I impressed with its great honorableness and antiquity.” Ishmael is not just ambivalent in the aftermath of the suffering; he is more impressed.
How Melville himself felt about the industry is not made clear, but I see no particular reason to doubt his enthusiasm. He did, after all, himself work as a whaler. (Take that, MFA-ification of the novelist.)
So, the question: does the psychological impulse that undergirds a Victorian desire to monumentalize and to elevate—the self-confidence and the narcissism—somehow also beget the attendant cruelty? Eureka’s Carson Mansion, one of the extravagant high points of American architecture of the period, was built by the clearcutting local lumber magnate. As far as I can tell, the presence of injury isn’t just incidental. Walt Whitman, who surely embodies the late 19th century’s numinous aspiration as well as anyone, hymns in Song of the Redwood Tree to the “crackling blows of axes, sounding musically, driven by strong arms” yielding “the falling trunk and limbs, the crash, the muffled shriek, the groan”. Rather than be appalled (or at least discomfited), he is enraptured: “I see the Genius of the modern, child of the real and ideal, Clearing the ground for broad Humanity, the true America”. The true America! Now, there’s an obvious alternate view. Maybe all cultures are just imbued at the outset with malignity and blindness, with Victorian progress simply uneven. Perhaps their advancement in the aesthetic domain was simply not yet matched in the moral domain. But Melville, Whitman, Kipling, and others make me suspect that there is in fact a connection. In Gast’s American Progress, the bison are being driven into the darkness. As with all Nietzschean tendencies, spiritual self-regard is double-edged.
—
I hadn't previously know anything about the economics of whaling. Moby Dick was published in 1851. (Melville was, remarkably, just 31.) As with Liar’s Poker, he captured a sector in its heyday: whaling reached its peak in 1845, whereupon declining whale populations started to constrain. Oil was discovered in Pennsylvania in 1859, and domestic petroleum extraction surpassed oil derived from the whaling industry pretty much immediately. By 1870, US whaling had declined by about 75%. (The decline also accelerated by the Norwegian invention and adoption of the explosive harpoon, rendering US fleets less competitive.)
Whale oil was never the US’s primary energy source or source of oil and never amounted to even 1% of US GDP. Camphene (from alcohol) was the main lamp fuel, with annual production more than tenfold greater than peak whale oil. Lard oil, tallow, and vegetable oils were also used. Our whaling was in this sense a luxury undertaking: whale oil smelled better and burned more cleanly.
While American whale oil use declined precipitously in the 19th century, it did not abate entirely. I had no idea that sperm oil was widely-employed until relatively recently. Wikipedia: “Prior to 1972, over 30 million lb (14 million kg) of sperm whale oil was used annually in lubricants because of its exceptional lubricity and heat stability. In 1972, the sperm whale was listed as an Endangered Species. The following year, the US Congress amended the Endangered Species Act, outlawing the killing of whales and the use of their oil. The loss of sperm oil had a profound impact in the automotive industry, where for example, transmission failures rose from under 1 million in 1972 to over 8 million by 1975.”
One of the two last whaling stations in the US was active in the San Francisco Bay until 1971. “The station’s boats hauled in an average of 175 finbacks, humpbacks, and sperm whales a year.”
It seems that the Western Pacific gray whale and the North Atlantic right whale may not survive the already-imposed population declines. While we rue the safetyism, proceduralism, and risk-aversion that took hold in our culture starting in the 60s (of all years, it is noteworthy that the last whaling station closed in 1971…), and see that cultural turn as a fulcrum for our whole world, whaling is perhaps as good example as any of its necessity: we were in fact careering towards acts of annihilation.
—
I listened to much of the book, and thought the narration by William Hootkins was just fantastic.
2025-10-07 · X post
Read a few interesting posts on the Faroe Islands recently. My trip report from visiting a few months ago.
--
The landscape is improbably three-dimensional and rough-hewn: rugged, jutted, serrated, cragged. In being fully denuded – the peaty soil, the Atlantic winds, the centuries of overgrazing – it feels like an exaggerated, hyperreal version of the west of Ireland. It also reminds of a Patagonia stripped of the Andean backdrop.
Torshavn now boasts numerous excellent restaurants. It is a town of only 14,000 people: what’s going on? As far as I can tell, this is fully a story of cultural contingency: in 2011, “chef Leif Sørensen ended up essentially inventing Faroese haute cuisine all by himself”, opening the restaurant Koks. This is in a tradition of Norsemen defining new gastronomic cultures through force of will. In 2004, Claus Meyer and Rene Redzepi organized the Nordic Kitchen Symposium (supported by the government, it is interesting to note) and put forth the Nordic Kitchen Manifesto, setting in motion the forces that rendered Copenhagen the culinary capital it is today.
Little of note grows in the Faroes. They raise sheep; most of the rest they scavenge from the sea. Fermented lamb is a specialty. I ate it. I would not call it bad, but I won't rush to consume it again.
Over dinner, I chatted with a young couple from Liechtenstein. (Liechtenstein being the only other comparably-sized country in Europe, this seemed appropriate.) The woman worked as a diplomat in Brussels. She told me that the city was often unsafe and that there were many places she couldn’t go. That concept felt a far cry from Torshavn. Her boyfriend mentioned the heatwave back home; I asked about their thoughts on air conditioning. “It’s too energy intensive… one has to consider the greater good.” I point out that California’s abundant air conditioning is mainly powered by solar. “Yes, but still… it’s not good to use so much energy.” My optimism about Europe was not enhanced.
There are a lot of undersea tunnels in the Faroes, connecting the islands, with plenty of additional projects underway. As a Californian, these are a mystical luxury. How can a nation of 55,000 people (Petaluma has more), and poorer per capita than my home state, possibly afford them? Per-unit length costs appear to be almost 30x lower than California’s. For example, the 11km Eysturoyartunnilin opened in 2020, and was evidently constructed for $14M per km.
The bookstore contains many Faroese-language works. Approximately 200 new books are published each year; one for every 275 people. Ireland’s annual production is one for every 2,000 people or so.
What does one learn from the Faroes? It feels clearly to the betterment of the world that they exist. Some of this is in the natural splendor, but some is also in seeing what a micro-nation is capable of. Are the Faroes an example of how clearly-defined polities are a bottleneck for the advancement of the world? To the extent that cultures establish the preconditions for anything, and to the extent that appreciation for and consumption of humanity’s creations are among the most durable sources of welfare, should we want more Faroes? Do the Faroes, with isolation enforced by maritime tyranny, hint at what is lost in global integration? Did Patrick Leigh Fermor encounter a new Faroe Islands every day? There were around 27 different languages spoken in France in 1900. How does one like the Faroes and like globalization?
2025-09-28 · X post
Given its status as one of the great American business biographies, I decided to read Titan, on Rockefeller, a couple of months ago. (I also paired it with a little of Tarbell’s history.) Titan is an impressive work, clearly the product of prodigious research. Assorted points that jumped out to me:
• Certain periods seem more propitious for the rise of noteworthy figures, at least in business: Carnegie, Morgan, and Rockefeller were all born in a four year span. (Steve Jobs and Bill Gates were also born in the same year.) I wonder how much of this is about the culture vs the business opportunities. More generally, I hadn’t appreciated the fervor (as perceived at the time) of the late 19th century. Thomas Mellon: “It was such a period as seldom occurs, and hardly ever more than once in anyone’s lifetime.”
• Chernow: “Many people in the mid-nineteenth century kept such journals to enforce thrift and also objectify their moral performance. Adolescents kept diaries larded with pep talks, exhortations, inspirations, and warnings. Andrew Carnegie wrote hortatory memos to himself, while William C. Whitney kept a small notebook of little homilies. A contradictory impulse was at work: people were spurring themselves to excel but also trying to curb their insatiable appetites in the new competitive economy.” I find myself wondering whether this earnestness is foreign today, or whether it is fully present and has simply taken a different shape, with hustle culture, lifestyle influencers, self-help, and so forth.
• Rockefeller sold candy to other kids as a child. I find this specific detail funnily common in the origin stories of magnates. (Warren Buffett, Sheldon Adelson, Thomas Edison, for example.)
• Chernow emphasizes the importance of his being given freedom and responsibility from an early age. I’m also struck by how frequently one hears this in similar stories. Bill Gates, for example, mentions in an interview that the freedom he was afforded as an early teenager (sneaking out of the house late at night, etc.) was influential in shaping who he became. (Though he acknowledged that he didn’t parent his own kids that way.)
• “One notes that Rockefeller’s earliest memory was associated with caution and that he edited out the absentee father and inebriated grandfather while retaining the strong, enduring mother and grandmother. He always possessed an unusual, self-protective capacity to suppress unpleasant memories and keep alive those things that fortified his resolve.” This reminds me of the point about “suppression” in the Harvard Grant Study (see the 2009 Atlantic article[1]). I often wonder whether suppression (vs “processing emotions”) is underrated.
• I don’t understand the whole rebate controversy that was so defining for Standard Oil. It’s extremely common for businesses to receive discounts of some sort in return for significant demand. Is Rockefeller’s name thus unfairly besmirched by this controversy?
• In contrast with the “decisive leader” archetype, it’s interesting that the book emphasizes so much his practice of consensus-based decision-making. The obvious question is to what degree that characterization is actually true. Maybe his views tended to be discernible, and he was imbued with sufficient stature and credibility that his perspective carried without comity being disturbed. (On the other hand, the delayed acquisition of the oilfields in Ohio suggests that this at least wasn’t always the case.)
• I found the description of Standard Oil as being both a first- and a second-generation company, and Rockefeller as a first- and second-generation manager, to be thought-provoking. (First-generation: being able to innovate in a very messy and open-ended space; second-generation: being able to scale with tight operating discipline.) Rockefeller was in this frame both Steve Jobs v1 and v2.
• Chernow describes how Rockefeller was influenced by Carnegie's Gospel of Wealth essay. I went and read it, and found it to be more complex in its views than the straightforward exhortation to philanthropy that I had understood it to be. "In bestowing charity, the main consideration should be to help those who will help themselves; to provide part of the means by which those who desire to improve may do so; to give those who desire to use the aids by which they may rise; to assist, but rarely or never to do all. Neither the individual nor the race is improved by almsgiving." [...] "He is the only true reformer who is as careful and as anxious not to aid the unworthy as he is to aid the worthy, and, perhaps, even more so, for in alms-giving more injury is probably done by rewarding vice than by relieving virtue." [...] "The rich man is thus almost restricted to following the examples of Peter Cooper, Enoch Pratt of Baltimore, Mr. Pratt of Brooklyn, Senator Stanford, and others, who know that the best means of benefiting the community is to place within its reach the ladders upon which the aspiring can rise—parks, and means of recreation, by which men are helped in body and mind; works of art, certain to give pleasure and improve the public taste, and public institutions of various kinds, which will improve the general condition of the people; in this manner returning their surplus wealth to the mass of their fellows in the forms best calculated to do them lasting good." It is interesting that the adverse effects of charity were so prominent for Carnegie. For him, artworks that “improve the public taste” are to be prioritized over mere “alms” (which may cause injury). Rockefeller appears to have agreed: “It is a great problem to learn how to give without weakening the moral backbone of the beneficiary.” On this topic, Frederick T Gates’s philanthropy tips, mentioned in passing and which I managed to track down, now make for entertaining reading[2].
• The idea that the air quality in some of the environs of the refineries was so poor that it ruined beer and milk was arresting. As far as I can tell, the noxious quality of urban air is one of the first things that would strike us if we traveled back in time.
• Chernow describes how Cleveland’s Euclid Avenue was “the most beautiful in the world”. Sadly, it seems to have been fully demolished. I’d love to understand why: any individual might err in tearing down a beautiful home, but for all of them to be razed requires a structural change. Were staff too expensive in the face of the city's economic decline? Did property taxes rise to unsustainable levels? Is this simply a story of changing tastes? Of course, there are many Euclid Avenues across the US.
• Miscellaneous small facts that stood out: both the panics of 1873 and 1893 were at the time called “great depressions”. There were 17 attorneys in the Department of Justice at the time of Teddy Roosevelt. James Joyce was supported by Edith Rockefeller. John D. Rockefeller Jr. didn’t like modern art, but Abby Rockefeller helped start MoMA. I hadn’t known that the first prognostications of Peak Oil had occurred so early! “In 1875, Henry E. Wrigley, the head of the Pennsylvania Geological Survey, issued a doomsday warning that the state—and hence the world—production of oil had peaked.”
• My main reflection, and I suppose critique of the book, is that there’s so little about the business of Standard Oil. Extensive time is spent on the acquisitions of competitors that Rockefeller engaged in, but there’s no explanation of how he could afford them. Why was Standard Oil able to do this vs having other competitors buy him out? How did Rockefeller manage dilution through this period? Did he purchase at cyclical lows? The book claims that he tended to buy at fair prices, but was there in fact sub rosa coercion? How much did capital costs and tariffs matter in determining the international market structure? The LLMs haven’t helped me much on these kinds of questions. In general, business biographies have far too little structural analysis for my taste. In an ideal world, I’d really like some combination of the human biography and HBS case studies/Goldman Sachs analyses: stories about the subject’s relationship with their parents, sure, but also figures, tables, and charts. Perhaps this is challenging in practice given the disparate skills required to produce such a thing, though maybe the LLMs of the future will be able to produce them on demand. (Is this an eval?) Which are the books that come closest to doing this today?
2025-09-25 · X post
Over the past week, @arcinstitute published three new discoveries that I’m very proud of.
• The world's first functional AI-generated genomes. Using Evo 2 (the largest biology ML model ever trained, which Arc released in partnership with @nvidia in February), Arc scientists took advantage of the fact that Evo 2 is a generative model to produce completely new sequences for complete phage genomes. That is, they used AI to produce wholly new, never-before-seen-by-nature genomes. They experimentally synthesized these genomes and showed that these AI-generated phages actually work, killing E. coli bacteria with high efficacy.
• Germinal, an AI system for creating new antibodies. Antibody design is one of the great problems of medical biology given their obvious importance and usefulness for creating therapeutics. (Antibodies are tiny particles that help the immune system identify pathogens and other harmful intruders. See also the recent Works in Progress article on this topic: [1].) Today, designing effective antibodies is very expensive and slow. Germinal is a cheap and fast way to produce drug candidates, with success rates of up to 22%. This means that one can go from having to screen thousands of candidates in the lab to screening perhaps a few dozen. It's early, but I suspect that better methods for designing antibodies will be a very big deal for disease treatment in the coming years.
• Today, we published a paper showing that “bridge editing”, which Arc scientists first introduced last year, can make precise edits in human cells that are up to 1 million base pairs long, and without relying on intrinsically unpredictable cellular repair machinery (which CRISPR requires, often leading to editing mistakes). They showed that it’s possible to use this editing to cut out the DNA repeats that cause Friedreich’s ataxia (a neurological disease), an approach which should also be relevant to Huntington’s and other similar disorders. One particularly cool thing about it is that it’s possible to specify every nucleotide within the extended editing window, meaning that recursive bridge edits could potentially be a powerful way to reprogram even biological traits that are caused by many genetic mutations. (Genetic therapies today target single mutations.)
Arc is pretty new. Its doors opened in mid 2022, and it's now 300 people. I’m excited about these discoveries because they show that a number of our hopes in starting Arc are starting to pay off:
• AI/ML and computation are at the center of all three. That is obviously true for the first two, but the mobile genetic element behind bridge editing was also discovered as a result of a complex computational search. One of our premises in starting Arc was the belief that the intersection of software/AI and experimental wet lab biology should enable great things. (And besides requiring great computational work, all three of these also required strong wet lab work, tightly coordinated under a single physical roof.)
• We’ve been toying with the idea that a handful of technologies are enabling a new kind of “Turing loop” in biology: sequencing advances (including single-cell sequencing) give us new ways to read; transformers and AI gives us new ways to think; and functional genomics (such as bridge editing) give us new ways to ways to write. This trio of discoveries span each part of this loop, and we’re hopeful that there’ll be compounding returns in improving each part.
• Arc is a non-profit, which we hoped would make collaborating with others easier, since we can avoid worries about financial return. This is indeed proving important, and all three of these projects involved close partnership with others. Germinal was done in partnership with @SynBioGaoLab at Stanford; Evo 2 was trained in partnership with Nvidia. Bridge editing was jointly published with a structure from the @HNisimasu Lab at the University of Tokyo. Arc tries to make its discoveries useful (see the Evo 2 Designer[2]) for others, and the code behind the computational projects is open source, hopefully making it easy for others to spot new opportunities for collaboration and partnership in the future. Most of all, Arc itself is an ongoing collaboration with @UCSF, @UCBerkeley, and @Stanford.
• With Arc, we wanted to enable better bottom-up and top-down work. With the fully flexible, no-strings-attached funding that we provide to investigators, we want to enable completely unexpected discoveries and avenues of investigation. With our institute initiatives (around creating a virtual cell and curing Alzheimer’s), we want to bring to bear a scale and level of coordination that’s usually difficult in basic science. Germinal is a “surprise” discovery that didn’t involve top-down coordination, whereas Evo 2 is the result of ambitious high-level planning and funding.
• Humanity has never cured a complex disease (a category that includes most neurodegenerative diseases, most cancers, and most autoimmune diseases), and my hope is that Arc can help change this. It’s also clear that AI will revolutionize biology, and I hope that Arc can effectively aggregate the ingredients needed to fully capitalize on its promise. I’m biased, but I think some of the coolest biology in the world is currently being done at Arc. (They’re always hiring if you’re interested.)
While I’m a cofounder of Arc, I spend almost all my time on Stripe, where we spend our time building economic infrastructure for the internet. All credit for Arc’s progress should go to the remarkable scientists and staff who’ve made Arc their home or who’ve chosen to collaborate with us. (You can read more about these particular discoveries in these threads: [3], [4], [5].) I’m also very grateful to the amazing Stripe employees who’ve built the company that makes Arc’s ongoing work possible, and to the millions of customers who’ve chosen to partner with Stripe. John and I feel fortunate to be able to support Arc’s work to the extent that we do.
Maybe this is reading too much into it, but I sometimes feel that there’s a commonality between @arcinstitute and @stripe. Both biology and economic infrastructure involve reasoning about complex systems with many levels of emergent effects, and in both cases building the right tools can have almost unboundedly large benefits. Even though progress in both tends to take a long time, it also feels like the next five years in both will be some of the most interesting in living memory.
(If economic infrastructure is your jam, we have a whole slew of fantastic announcements coming up at Stripe Tour in New York next week. Tune in!)
2025-09-21 · X post
A recent reflection, based on conversations with policy leaders, is that there are two superficially similar but importantly different perspectives one can hold with respect to US manufacturing:
* Affinity for manufacturing and physical production is an anachronistic fetish, embodied by populists with outdated attraction to hard hats and clanging forges. A great deal of manufacturing has departed the US, which is certainly fine and probably even quite good. It's unpleasant labor, and countries ought to each specialize in their respective comparative advantages.
* Manufacturing is the ultimate network effects and economies-of-scale business. As services are substituted by AI, and as datacenter deployment accelerates, the relative importance of manufacturing is likely to grow. To think that one can pick and choose sectors in which one will excel ("let's win in drones but not in dishwashers") is a fallacy. Manufacturing is hence of paramount strategic importance. However, we don't know how to make the US the world's preeminent manufacturing power (given its cost base and given the current center of gravity in China) -- indeed, we don't know whether it's even possible -- and this is a significant strategic problem for the country.
I have zero direct expertise here, but my outside view is closer to #2 than #1: it seems that the ecosystems and supply chains create strong gravity across the board. I also asked @elonmusk, who has clearly done more over the past decade to advance sophisticated US manufacturing than anyone else, and this appears to be his view. Most economists, on the other hand, are much closer to #1, and I don't think that the economics profession considers the absence of good ideas for reviving US manufacturing to be a problem of particular significance. (There are lots of snide epithets about the efficacy of industrial policy.) It seems to me that there's even some amount of backwards reasoning happening, where, because we don't know how to do #2, #1 is subconsciously a much more comfortable position to hold.
Talking about winning particular manufacturing sectors feels to me a bit like talking about winning individual biological research sectors or winning particular software sectors. That is: it seems that the strong default assumption should be that "the place that is best at biology research sector X will also be best at sector Y", and similarly in software, because the skills and inputs needed are so transferable. As such, my guess is that if the US seeks meaningful sovereignty or preeminence in any of drones, robotics, solar, batteries, pharma, etc., we need to bite the bullet, and win at manufacturing across the board.
Overall, I'd love to read more arguments for and against these perspectives, particularly from those with direct expertise.
2025-09-14 · X post
Observing some people close to me with chronic health conditions, it's striking how useful Reddit frequently ends up being. I think a core reason is because trials aren’t run for a lot of things, and Reddit provides a kind of emergent intelligence that sits between that which any single physician can marshal and the full rigor of clinical trials.
Why aren’t trials run for a lot of things? Well, they’re of course slow and expensive (median cost of $19M for a pivotal trial in 2015[1]; after adjusting for inflation and other phases, maybe that corresponds to a total of $40M today?). But they’re also hard to fund when the intervention in question lacks IP protection since the ensuing knowledge can’t be monetized. As such, trials for diet, over-the-counter supplements, and lifestyle interventions are under-pursued. To give one prosaic example, lots of people think that magnesium improves sleep, but, as far as I know, no trial has ever been run assessing its ability to improve sleep in non-elderly adults without sleep disorders.
So, Reddit — in a pretty unstructured way — makes a limited kind of “compounding knowledge” possible. Best practices can be noticed and can imperfectly start to accumulate. For people with chronic health problems, this is a big deal, and I’ve heard lots of stories between “I found something that made my condition much more manageable” all the way to “I found a permanent cure in a weird comment buried deep in a thread”. (Of course, one also sees this outside of medical conditions. I’ve enjoyed the recommended routine in the BodyWeightFitness subreddit, as a comparable kind of distilled practical wisdom[2].)
An interesting and somewhat more formalized example of this approach was recently used for long COVID and published earlier this year[3]. After surveying 3,900 individuals, the paper analyzes patient-reported outcomes for 150 different treatments, yielding the figure reproduced below. There are evidently no silver bullets, but it is striking that, say, about half of people find that antihistamines are helpful. I know a number of people who found the learnings from this study to be impactful in improving their daily quality-of-life.
Seeing this paper and the Reddit experience makes me wonder whether the approach could somehow be scaled: is there a kind of observational, self-reported clinical trial that could sit between Reddit and these manual approaches? Should there be a platform that covers all major chronic conditions, administers ongoing surveys, and tracks longitudinal outcomes?
I don’t really know what the best way to go about this would be, but it feels to me that there could be something important here. There’s a lot of latent data in patients’ subjective experiences that is not today being properly gathered or analyzed.
2025-09-08 · X post
I have a couple of times come across the idea of “The Irish Enlightenment”. What exactly was it? I’ve wondered this for quite some time.
In the early 18th century especially, there existed a cluster of thinkers in or from Ireland whose ideas seem important by modern standards: Francis Hutcheson, Richard Cantillon, Jonathan Swift, George Berkeley, and Edmund Burke probably rank first among them. William Petty, the early statistician, should maybe be mentioned as well.
These individuals don’t feature very prominently in contemporary Irish culture or Irish education: one rarely hears about Hutcheson or Cantillon. I think this is significantly because they didn’t accord with the Irish self-conception that emerged in the late 19th and early 20th centuries. They are emphatically not Gaelic revival figures and fit awkwardly beneath the nationalist palimpsest. All except Cantillon are Protestant and many lived or worked in the UK. Trinity had a Berkeley library but “denamed” it in 2023. In school, the great Irish thinkers were from the late 18th and 19th centuries: Wolfe Tone, Daniel O’Connell, and Charles Parnell.
What can we say about these earlier Irish intellectuals?
Hutcheson was “probably the most influential and respected moral philosopher in America in the eighteenth century”, according to Norman Fiering. In Original of Our Ideas of Beauty and Virtue, he introduced the concept of “unalienable rights”, with the collective right to resist oppressive government, which was used at Harvard as a textbook as early as the 1730s. Benjamin Franklin, Thomas Jefferson, and John Adams were among his fans. In Inventing America, Garry Wills argues that these authors of the Declaration of Independence drew most of all on Hutcheson. He corresponded with David Hume and taught Adam Smith. While better known as a philosopher, he wrote extensively about economics: he emphasized the importance of private property and the division of labor. He repeatedly condemned slavery.
Richard Cantillon introduced was the first person to use “entrepreneur” in its modern sense. Reading his Essai, one is struck by the clarity of its thought and its modernity. In a sense, what is noteworthy is how little there is to say about it: it feels quite contemporary and basically correct. He prefigures Malthusian population reasoning and recognizes that risk and uncertainty are central forces in economics. By separating intrinsic value from market pricing, he adumbrates subjective valuation concepts later emphasized by the Austrians. His description of the emergent order arising from the decentralized market forces coordinating landowners, farmers, tradespeople, and workers sounds downright Hayekian. Schumpeter: “Cantillon was the first to make this circular flow concrete and explicit, to give us a bird’s-eye view of economic life.”
Swift is best known as an irascible satirist. However, he was principally a pamphleteer: a hectoring intellectual activist. In this he was remarkably prodigious. His complete works is a 19 volume collection. He saw that “Ireland is the poorest of all civilized countries in Europe, with every natural advantage to make it one of the richest”, and was preoccupied with practical questions pertaining to this goal. He successfully advocated for monetary reform (in Drapier’s Letters) and thought extensively about how to stimulate both manufacture and industry in Ireland as well as a culture conducive to prosperity. He spends a great deal of time on import substitution, the balance of trade, and the stimulation of manufacture. His views are very mercantilist by today’s standards, but always in service of the question: how to develop. He composed his own epitaph: he sought to be seen as “a strenuous champion of liberty.”
Berkeley is maybe the most directly economically-relevant and in my view the most underrated. Like Hutcheson, he’s best-known as a philosopher, but, in The Querist (1735), he writes what is probably the first work of development economics. It is composed in an unusual form – 895 questions, culminating in one ultimate question: “whose fault is it if poor Ireland still continues poor?” In this, he assesses that Ireland has little excuse. After describing a vision of prosperity, he asks “whether Ireland be not as well qualified for such a state as any nation under the sun?” Like Swift, he’s disgusted by vanity and indulgence. He has a sophisticated understanding of concepts like the velocity of money. Most of all, he sees culture and human capital as being as closely linked with economic development as more conventional trade, monetary, and fiscal matters, and, unusually for a work of economics, he spends a great deal of time on the former. The Irish, in his eyes, are indolent: we need to become more skilled and more industrious. In his emphasis on culture and human capital, his outlook reminds me of Park Chung-hee and Lee Kuan Yew. Perhaps even Deng Xiaoping.
Burke is usually considered a political thinker, but his economic writings are substantial and important. He advocated for free trade (leading to the removal of restrictions on the grain trade), denounced colonial extraction (particularly in India, with some influence), and made a powerful case for market pricing and laissez-faire policy in Thoughts and Details on Scarcity. In emphasizing the cultural and institutional foundations of markets, he anticipates arguments later made by Karl Polanyi.
(As an aside, in rereading Reflections on the Revolution in France, I was surprised at how unpersuasive I found it. Unlike Berkeley, he gives almost no attention to economic outcomes, and his implicit theory just can’t explain which ruptures and revolutions one should support. If we accept his arguments, how should we feel about the formation of the Irish state, the creation of UAE or Singapore, and the fall of the Soviet Union? I was left wondering why Reflections is the most famous of his works. Is it because of the somewhat clickbaity title?)
In surveying these thinkers, one is reminded that Ireland was an oppressed polity. Hutcheson, Burke, and Cantillon all did much of their work outside of Ireland; in publishing their work at home, Swift and Berkeley resorted to unusual forms (satire, rhetorical propositions) and, often, anonymity. (Both The Querist and Drapier’s Letters were first published without their names.)
How should we view the movement as a whole? Well, the timing is important: Cantillon published his Essai in 1755, Swift Drapier’s Letters in 1724, and Berkeley The Querist in 1735. It seems to me that, before 1750, the Irish thinkers have a strong claim to leading the world in the field of economics and to having collectively sketched out much of the core of the field in broadly correct terms. In Petty you have economic statistics; in Cantillon you have risk, market pricing, and much else; in Berkeley, you have a theory of national banking plus development economics; in Swift you have proto-monetarism. The claim is not that they figured everything out or were right on all points, but which other school or group could you rank ahead of them? Smith published Wealth of Nations in 1776 and The French physiocrats, who were very important, came later: Quesnay’s first piece wasn’t published until 1756.
Smith surely instigated economics as a proper discipline with his main work. The full title is An Inquiry into the Nature and Causes of the Wealth of Nations, which is a very “Irish school” framing. And, sure enough, Smith studied under Hutcheson in Glasgow (recalling that he was “the most acute, the most distinct, and the most philosophical of all my teachers”) and explicitly cites Cantillon. In his letters, he refers to Swift’s work. He owned a copy of The Querist. He was friends with Edmund Burke. None of this should detract from Smith’s own intellectual achievement, but the ties to the Irish Enlightenment are strikingly strong.
While the group may have influenced Smith and many others, part of what is striking about the Irish Enlightenment is how influential it wasn’t at home. Irish poverty endured for over 200 subsequent years of unwise and destructive governance. Much of this policy was obviously the fault of the British (and indeed deliberately so, as in the Penal Laws), but De Valera’s autarkic protectionism in the early days of the Irish Free State kept Ireland destitute as late as the 1960s, until a liberal turn was eventually instigated by Lemass and others.
Most of all, the Irish Enlightenment seems to me an instance of small group theory. I’m fond of the thought that between great man and structuralist theories of history there lies an intermediate position: the small group, a colocated cauldron for iconoclastic thinking, can as a collective pioneer a novel direction. The romantics in Jena, the founders of Silicon Valley, the musicians behind punk. Unsurprisingly, the early Irish thinkers are closely connected. Swift and Berkeley attended the same school and were good friends. Hutcheson and Berkeley debated publicly, while Burke’s work is clearly downstream of Hutcheson’s.
It highlights the importance of simply asking the right question. Berkeley did not comprehensively diagnose why Ireland was poor, or what to do, but he did realize that “what are we doing that makes us poor?” is the key lens.
There is probably something in it about the value of being an outsider. One gets the sense that Swift and Berkeley would have been less novel had they been absorbed into the English power structure.
The Irish Enlightenment certainly shows the fragility of good ideas and of auspicious movements. Ireland did not adopt their perspective, and inasmuch as their program was intended to remedy the plaintive Irish economic situation, it did not succeed on the kind of timeframe they would have hoped.
But for me it also shows the endurance of good ideas. Ireland itself may not have been particularly influenced, but Smith was, as were the American founding fathers, Voltaire, Kant, Hume, de Tocqueville, and, eventually, the Austrians and the free market movement. (Hayek repeatedly cites Burke as a model and wrote an introduction to a reprint of Cantillon.) In 1958, 223 years after The Querist, TK Whitaker published Economic Development, a landmark report that set forth an open and trade-led vision for Irish economic growth. The report was enacted by the Lemass government and set the foundations for Ireland’s economic boom over the subsequent decades. It's hard to precisely attribute Whitaker’s intellectual influences, but he describes West Germany’s social-market policies as a model (Walter Eucken, who led the Ordoliberal school in Germany, was alongside Hayek a founding attendee of the Mont Pelerin Society), and he was surely familiar with the work of the Institute of Economic Affairs in London, established to promote liberal Austrian ideas. That is all to say, in a very roundabout way, the intellectual program catalyzed by the Irish Enlightenment thinkers in the early 1700s endured, and did, eventually, with a few century delay and no small number of digressions, lead to the remarkable melioration of Ireland’s economic circumstances.
2025-04-06 · X post
Having now spent about half my life in each (and loving both), herewith the pros and cons of Europe and the US in everyday life:
Better in Europe
• Bike lanes and bike infrastructure. London, Paris, and Amsterdam are all excellent these days. (As are many other European cities.) Made even better by easy-to-rent e-bikes—now almost always the fastest way to get around.
• The urban walking experience generally. Partly for density reasons, and partly because of...
• Late-night cafe, brasserie culture. Is there an economic reason for this or is it just climate and contingent zoning?
• Architecture. Around 1920, we forgot how to make nice buildings. European cities tend to have more construction from before the Great Forgetting, and it makes the built environment much more pleasant.
• Pedestrianized streets. Often with cobblestones.
• In general, European cities are just more pleasant. Given how hard it is to build a good city (or indeed to retrofit one), this feels like a big deal.
• Cured and pickled food.
• Bread. Obviously varies by country, but it’s generally true.
• Voltage. What are Americans doing waiting so long to boil kettles?
• Beauty in the mundane. I find that you’re more likely to find tasteful touches in prosaic places in Europe.
• Motorway design and signage. Standardized, clear, and easy-to-use. The US is a mess by comparison.
• Bathroom doors. That is, in Europe, they’re proper doors. Why does America make us see others’ feet?
• The clangor of church bells on Sunday.
• Trains. Enough said.
• Pharmacies. I'd love to understand why they're so much nicer in Europe.
• Cheese. Again, lots of cross-country variation, but true in general.
• I'm not sure why, but European regulation on many everyday items seems better. Sunscreens in Europe are better, as are bike helmets.
• Wine.
• Languor, joie de vivre, hygge, gemütlichkeit, craic. I think Europeans are better at unwinding. Drawing contrast with what he found in the US, De Tocqueville observed that in Europe "idleness is still held in honor". This difference remains apparent.
• Road density. Europe generally has many more roads per square mile, which makes it easier to find nice places to run, walk, and cycle.
Better in the US
• Air conditioning. Consistently bad in Europe. (Partly for silly degrowth-related reasons?)
• Coffee. Opinions will differ, naturally, but third wave coffee has seen much more enthusiastic adoption in the US.
• Cookie banners. That is, the lack of them. (Well, there are some, but it’s not as bad as the fusillade one is subjected to in Europe.)
• Internet speeds. European wifi often reminds me of my dialup youth.
• Capital markets. If you need money (as a consumer, a small business, or a startup), it’s much easier to get it in the US.
• Being able to buy groceries on Sunday. Inexplicably challenging on the continent.
• Showers. Like the tepid air conditioning, daily ablutions in Europe are conducted beneath parsimonious trickles.
• Urban air quality. Maybe surprisingly, it is, on average, better in the US. The unpleasant whiffs of diesel exhaust is part of the reminder that one is back in Europe.
• Government efficiency. In general, things happen faster in the US.
• Labor laws. As covered in Stripe's annual letter this year, people are more likely to work in high productivity sectors in the US (and thus to earn more). Rigid rules impede this reallocation in Europe.
• Culture of general aviation with many thousands of small airports. There are around 700,000 pilots in the US—far more than there are in Europe.
• Hospitals. A controversial claim, perhaps, but I find that those who have received care in Europe and the US prefer the US.
• Beer. The microbrewery revolution of the US means that it’s clearly the better place for it.
2024-12-27 · X post
This year, I read ten important historical novels: Jane Eyre, Middlemarch, To The Lighthouse, Bleak House, Portrait of a Lady, Anna Karenina, Life and Fate, Heart of Darkness, Madame Bovary, and The Magic Mountain.
Reflections:
• Four of these are more than 800 pages long. The Magic Mountain and Portrait of a Lady, while shorter, are not short. Of the ten, 5 are British, 2 are Russian, and there was one from each of France, Germany, and the US.
• For me the clear standouts are Middlemarch, Bleak House, Karenina, and Life and Fate. I would enthusiastically reread any of them. If I had to choose just one to go to again, I would probably select Middlemarch. There's something memorably compelling in Eliot's affection and empathy for almost all of her characters. If Succession is a show with no likable personalities, Middlemarch is the opposite. Bleak House is a close second. Life and Fate is quite different to the others: it’s not exactly entertaining (or even notably well-written), but it is true and profound. (Most works designated “important” are not, but Life and Fate surely merits that as well.) If kindness is one of the core adjurations of Life and Fate, Eliot is the author that most embodies it.
• I'd underestimated Dickens's lyricism. I had thought of him as a master of the plot (contra Nabokov), but he is just as accomplished in prose itself. “Chesney Wold is shut up, carpets are rolled into great scrolls in corners of comfortless rooms, bright damask does penance in brown holland, carving and gilding puts on mortification, and the Dedlock ancestors retire from the light of day again. Around and around the house the leaves fall thick, but never fast, for they come circling down with a dead lightness that is sombre and slow. Let the gardener sweep and sweep the turf as he will, and press the leaves into full barrows, and wheel them off, still they lie ankle-deep. Howls the shrill wind round Chesney Wold; the sharp rain beats, the windows rattle, and the chimneys growl. Mists hide in the avenues, veil the points of view, and move in funeral-wise across the rising grounds. On all the house there is a cold, blank smell like the smell of a little church, though something dryer, suggesting that the dead and buried Dedlocks walk there in the long nights and leave the flavour of their graves behind them.”
• Three of these four were written by authors in their 50s (Eliot, Tolstoy, and Grossman). Dickens was a mere 41 -- and this shows. The plot is very entertaining, and immensely intricate, but the characters are somehow flatter. So, maybe one lesson from the set is simply that wisdom is real, and that skill in the domain of fiction compounds for quite some time.
• Russian literature puzzles me. Why did it suddenly become so good in the 19th century, and why did it decline so much in the 20th? I don't think the latter answer can just be a story of oppression, since we got many great works during Stalin’s reign. But what's the best Russian novel since Master and Margarita? On the issue of the rise, I often encounter explanations claiming that it was related to Russian intellectuals being excluded from political influence and consequently retreating to the artistic domain -- but this feels obviously inadequate. Again, how does this explain the post-Bulgakov decline? And where are the great, say, Saudi works of the past 50 years?
• Whatever happened to the novel around the turn of the century (Conrad, Woolf, Mann in my reading) was not obviously salutary. All three are interesting works, and there is something very distinctly modern in Woolf's in particular, but they simply don't compel -- at least for this reader -- the way their predecessors do: maybe it's just the particular selection, but I was generally looking forward to finishing the early 20th century works, and a bit disappointed when completing those dating from before 1900. The dislocation that Blom describes in Vertigo Years is clearly manifest. Woolf's “Mr. Bennett and Mrs. Brown” essay, and her claim that “human character changed” in 1910, is consistent with the turn in the novels. She was speaking of different works, but her assessment rings true in a broader way: “Yet what odd books they are! Sometimes I wonder if we are right to call them books at all. For they leave one with so strange a feeling of incompleteness and dissatisfaction.”
• I should note that some of Woolf’s descriptions are great, even if her brooding interiority leaves me ultimately unenthralled. “The house was left; the house was deserted. It was left like a shell on a sandhill to fill with dry salt grains now that life had left it.” “He lay on his chair with his hands clasped above his paunch not reading, or sleeping, but basking like a creature gorged with existence.”
• Tom Wolfe attributes modern architecture and the international style to a post-1917 sympathy for the proletariat and a desire to strip indulgent bourgeois ornament from our construction, and, yes, Schoenberg explicitly motivated atonality in egalitarian ideals, but this set of novels makes me doubt the political explanations. You can clearly see the embrace of some kind of disharmony in the books, and I don’t think Conrad was trying to make any Marxist point. I still struggle to explain what happened, but I think I would reverse some of the standard causality, and it seems to me that the coopting of communist ideals is probably itself downstream of the broader social unease that also gave rise to these artistic tides. Blom’s description of the rise of various mental disorders -- neurasthenia and the like -- seems relevant. (All of this does make me want to better understand 1848.)
• The railway, and its attendant social upheaval, features repeatedly, and maybe most memorably in one chapter of Middlemarch. I hadn't appreciated just how significantly disruptive a force it was perceived as being even at the time. (Given the scale of the construction that was entailed, maybe this shouldn't be surprising.) More broadly, there is some sense of a society in transition through most of these works: these aren't neat and timeless tales. You have the rise of the bourgeois and broader urbanization in Bovary, the emerging social consciousness in Bleak House, the exposure of the shabbiness of Victorianism and its gender expectations in Lighthouse, and the postwar shell shock of Magic Mountain.
• The works written before 1900 are primarily about romance (Bleak House the exception, with romance only a subplot), and those written afterwards (Conrad, Mann, Grossman, Woolf) are emphatically not. I don’t know what to make of this. Perhaps just an accident of the selection.
• Ruxandra Teslo points out that there’s a moral gravity in the 19th century works that seems foreign today: people treat their own characters as important constructions in their own right. In a similar vein, I was struck by Grossman’s conception of freedom: he perceives it more as the right to self-define than a more typical liberty of action. Perhaps because actions were so circumscribed in Victorian societies (for women) and Soviet societies (for everyone), the seriousness of being weighed heavily.
* Money and its mechanics get extensive treatment in the pre-1900 novels. The details of Bovary’s debt were made famous by Piketty, but Eliot also spends time on Lydgate’s financial struggles, and Tolstoy on Levin’s agricultural economics. Pecuniary considerations are absent in the later works. Again, maybe just happenstance stemming from the particular selection, but I don’t get the feeling that it’s just that: I think something about authors’ attitudes to the topic changed.
• Today’s scientific papers are far harder to read, and jargon-replete, than those of 1960. However, the novels of the 19th century use significantly more sophisticated construction (and vocabulary) than those of today. What should we make of the countervailing trends? To me, both seem suboptimal.
• Pleasure aside, should one read these books? Does one derive moral betterment from doing so? I'm not sure. Probably not in any narrow sense. Ethicists are supposedly no more ethical than regular people -- if deliberate study doesn't help, what hope does mere fiction have? And, anecdotally, I don't consider the humanities majors to be the moral betters of the STEM students. I do think they've helped with my understanding of history, though. This year, I reflected on how the major historical moments that I've lived through -- the weeks after 9/11, the aftermath of Trump's 2016 election victory, March of 2020 -- cannot really be understood in terms of particular events, and must instead be apprehended through the vibes that prevailed. Rather than trying to assemble a logical causal chain, I think it's more helpfully explanatory to see many happenings as simply arising from a mood. History books struggle to capture such sentiments, and understandably so: the historian usually wasn't there; even if they were, vibes are ethereal things, and they feel out-of-place in a work that aspires to footnoted rigor and exactitude. As such, complements are required, and these novels have definitely helped me. This view also makes biography and autobiography seem of greater importance in developing such comprehension. The small details -- that Herbert Hoover's parents used to attend lectures and debates in a nearby town since that was the only entertainment available, that both died before age 35, or that Hoover himself once walked 80 miles in 3 days to join a geology class trip -- say a lot about a period, and are rarely captured in the grand sweep of events. I feel like I gained much more understanding of historical Vienna and of the emotions around WWI from reading Zweig's memoir than from any direct history of the period.
• Another argument made for reading these works is to simply better understand humanity and the human experience. There is almost certainly some extent to which this argument is valid, though I always wonder: do they help you better understand humanity, or better understand the kind of people who write books like these? Is Isabel Archer actually reflective of someone in that kind of position, or merely of the kind of hyper-intellectual James family? Karenina is ultimately a kind of demented obsessive (as was Tolstoy) – in learning about her, do we learn about love and its travails, or simply about unusually unstable personalities?
• There’s clearly some value in reading them for somewhat tautological reasons: they're worth reading because they are the books that we’ve decided are worth reading. They form part of our cultural context, and other works probably make somewhat more sense and are more memorable when interpreted through their lens. They are intellectual capital cities: you sorta have to go to Paris and New York in order to understand the rest of the world, and whether you “enjoy” them isn’t really the operative question.
• Ultimately, a utilitarian case for better understanding history or even humanity would not be my primary argument for why one might choose to read them, though. With self-consciousness about the platitude, they are simply some of the finest intellectual achievements of humanity, and worthy of engagement for that reason alone: a deeper appreciation for excellence is itself a valuable thing.
2024-09-09 · X post
Mario Draghi's new report on EU competitiveness doesn't mince words.
"Across different metrics, a wide gap in GDP has opened up between the EU and the US, driven mainly by a more pronounced slowdown in productivity growth in Europe. Europe’s households have paid the price in foregone living standards. On a per capita basis, real disposable income has grown almost twice as much in the US as in the EU since 2000."
"First – and most importantly – Europe must profoundly refocus its collective efforts on closing the innovation gap with the US and China, especially in advanced technologies. Europe is stuck in a static industrial structure with few new companies rising up to disrupt existing industries or develop new growth engines. In fact, there is no EU company with a market capitalisation over EUR 100 billion that has been set up from scratch in the last fifty years, while all six US companies with a valuation above EUR 1 trillion have been created in this period. This lack of dynamism is self-fulfilling."
"There are not enough academic institutions achieving top levels of excellence and the pipeline from innovation into commercialisation is weak. [...] However, while the EU boasts a strong university system on average, not enough universities and research institutions are at the top. Using volume of publications in top academic science journals as an indicative metric, the EU has only three research institutions ranked among the top 50 globally, whereas the US has 21 and China 15."
"Regulatory barriers to scaling up are particularly onerous in the tech sector, especially for young companies. Regulatory barriers constrain growth in several ways. First, complex and costly procedures across fragmented national systems discourage inventors from filing Intellectual Property Rights (IPRs), hindering young companies from leveraging the Single Market. Second, the EU’s regulatory stance towards tech companies hampers innovation: the EU now has around 100 tech-focused laws and over 270 regulators active in digital networks across all Member States. Many EU laws take a precautionary approach, dictating specific business practices ex ante to avert potential risks ex post. For example, the AI Act imposes additional regulatory requirements on general purpose AI models that exceed a pre-defined threshold of computational power – a threshold which some state-of-the-art models already exceed. Third, digital companies are deterred from doing business across the EU via subsidiaries, as they face heterogeneous requirements, a proliferation of regulatory agencies and “gold plating” of EU legislation by national authorities. Fourth, limitations on data storing and processing create high compliance costs and hinder the creation of large, integrated data sets for training AI models. This fragmentation puts EU companies at a disadvantage relative to the US, which relies on the private sector to build vast data sets, and China, which can leverage its central institutions for data aggregation. This problem is compounded by EU competition enforcement possibly inhibiting intra-industry cooperation. Finally, multiple different national rules in public procurement generate high ongoing costs for cloud providers. The net effect of this burden of regulation is that only larger companies – which are often non-EU based – have the financial capacity and incentive to bear the costs of complying. Young innovative tech companies may choose not to operate in the EU at all."
More: https://commission.europa.eu/document/download/97e481fd-2dc3-412d-be4c-f152a8232961_en.
2024-06-26 · X post
This morning, Nature published two papers on bridge editing, the new genome engineering technology from @ArcInstitute: https://www.nature.com/articles/s41586-024-07552-4, https://www.nature.com/articles/s41586-024-07570-2. I'm quite excited about its potential!
Since the whole thing is pretty arcane, I fed the blog post (https://arcinstitute.org/news/blog/bridge) to Claude 3.5, and asked it to write an introduction. Below is the rather impressive (unedited) result.
Genome Design: The Bridge to Our Biological Future
I.
Imagine you're trying to edit a document, but instead of a cursor, you have a pair of scissors. You can cut out words you don't like, maybe paste in a few new ones, but precise editing? Forget about it. Now imagine someone hands you a pen. Suddenly, you can write whatever you want, wherever you want. This is the kind of leap we're seeing in the world of genome editing.
For the past few decades, we've been snipping away at genomes with tools like CRISPR, making impressive progress but always constrained by the fundamental nature of our tools: they cut DNA. But what if we could write directly into the genome, inserting whatever we want, wherever we want, without ever making a single cut?
This isn't just a "wouldn't it be nice" daydream anymore. Researchers at the Arc Institute have discovered a new system that does exactly that. They're calling it "bridge recombination," and it might just be the biggest revolution in genetic engineering since CRISPR.
II.
To understand why this is such a big deal, we need to take a quick tour through the history of genetic manipulation.
In the late 1990s, we discovered RNA interference (RNAi). This was our first real taste of programmable biology. We could use short RNA sequences to target and shut down specific genes. It was like having a universal remote control for gene expression. Cool, right?
Then came CRISPR in the early 2010s. Suddenly, we could not just turn genes off, but edit them directly. It was like upgrading from a remote control to a basic text editor. We could cut out bad genes and paste in good ones. But there was always a catch: CRISPR works by cutting DNA, and cells don't always repair those cuts exactly the way we want them to.
Both of these systems were revolutionary, but they shared a common limitation: they were destructive. They worked by breaking things – either the RNA transcripts of genes (in the case of RNAi) or the DNA itself (in the case of CRISPR).
III.
Enter the bridge recombination system.
The researchers at Arc Institute, led by Dr. Patrick Hsu, were poking around in the genomes of bacteria, looking at transposable elements. These are sometimes called "jumping genes" because they can cut themselves out of one part of a genome and paste themselves into another.
They were particularly interested in a group called IS110 elements. These are about as minimalist as you can get while still being functional – just a gene for the enzyme that does the cutting and pasting, plus some mysterious flanking DNA segments.
What they found was surprising. When an IS110 element cuts itself out of a genome, those mysterious flanking segments join up to form an RNA molecule. This RNA folds into two loops, one that binds to the IS110 element itself, and another that binds to the target DNA where the element will insert itself.
This RNA – which they've dubbed "bridge RNA" – is the key to the whole system. It's like a set of instructions, telling the enzyme exactly where to insert the DNA and what DNA to insert.
IV.
Now, you might be thinking, "Okay, that's neat, but how is this different from CRISPR?" The key is in how the insertion happens.
CRISPR works by making a cut in the DNA and then relying on the cell's repair mechanisms to insert the new DNA. It's effective, but it's also a bit like performing surgery with a chainsaw. Sometimes you get exactly what you want, but often you end up with small errors or unwanted insertions or deletions.
The bridge recombination system, on the other hand, doesn't cut the DNA at all. It unzips a small section, inserts the new DNA, and zips it back up again. No broken DNA strands, no relying on error-prone repair mechanisms. It's precise in a way that CRISPR can only dream of.
But the real magic is in the programmability. Remember those two loops in the bridge RNA? They can be programmed to recognize any DNA sequence. This means you can tell the system to insert any piece of DNA into any location in the genome. It's like having a word processor for DNA.
V.
The implications of this are staggering. Here are just a few possibilities:
• Gene Therapy 2.0: Current gene therapy approaches often rely on somewhat random insertion of therapeutic genes. With bridge recombination, we could insert corrective genes exactly where they need to go, without risking disruption of other important genes.
• Synthetic Biology: Want to give an organism a completely new capability? Just design the gene and insert it precisely where you want it.
• Evolutionary Biology: We could insert reporter genes at specific locations across the genome, allowing us to watch evolution happen in real time.
• Agricultural Improvements: We could insert beneficial genes into crops with unprecedented precision, potentially revolutionizing our ability to create drought-resistant or nutrient-enhanced plants.
• Bioengineering: Imagine being able to design and build entire genetic circuits, inserting each component exactly where it needs to be for optimal function.
VI.
In the grand scheme of things, the discovery of bridge recombination feels like a pivotal moment. It's as if we've been trying to write the book of life with a typewriter, and someone just handed us a word processor.
The researchers at Arc Institute have opened a door to a new era of genome design. As with any breakthrough of this magnitude, it's hard to predict exactly where it will lead. But one thing is certain: the future of biology just got a lot more interesting.
As we stand on the brink of this new frontier, I'm reminded of a quote from Arthur C. Clarke: "Any sufficiently advanced technology is indistinguishable from magic." With bridge recombination, we're not just editing the genome anymore. We're writing it. And that, my friends, is pretty close to magic.
2013-08-21
Over the last two decades, tension between government and the changes caused by the internet has been a recurring theme. Today, they’re almost seen as opposing forces. This is somewhat strange when you think about it. Most technologies don’t cause so much ongoing upheaval.
Why is the internet so challenging? I decided to make a list of reasons and came up with 11. Though none of them are very novel, I found the catalog interesting. (For one thing, I expected fewer.)
1. Better communication tools mean that events simply happen faster. The Arab Spring would probably have been less problematic for incumbent governments if things had happened more slowly. They’d have had more time to react. But governments still operate on timescales of days and weeks while it’s becoming easier for events to play out hour-by-hour.
2. Communication and publication can no longer be censored. Wikileaks, the Arab Spring, and Snowden’s revelations all depend on governments being unable to prevent mass dissemination of information.
3. Individuals can now cast a spotlight on government action. (That is, publication isn’t just uncensorable; it’s also decentralized.) With the internet, we can rapidly rewire our communication networks when a node becomes an important source of information. (This is most noticeable during live events, when people rapidly figure out which Twitter users are worth paying attention to.) If a government does something wrong, and even if the mainstream publishers ignore it, the information can still be rapidly broadcast to millions.
4. In a global community, local aberrations stick out more. Because online news and social structures don’t pay much attention to national boundaries, laws and government actions are increasingly held to international standards. People are more likely to know when they’re being screwed over by their governments.
5. It’s harder for governments to broadcast directly to their citizens. Fifty years ago, it was easy: just run a prime-time TV segment. You can still do that today, but many fewer people will pay attention.
6. Governments are more fragile and hence weaker. It’s almost as easy to leak a database as it is a file. It’s much harder for governments to maintain secret structures, and they must contend with the omnipresent risk of a calamitous leak.
7. Governments are more powerful and hence more likely to overreach. Because it’s now far easier to eavesdrop on communications, maintain intrusive databases, etc., it’s much more tempting to do it. Thirty years ago, you needed to adopt extreme GDR-style tactics to eavesdrop on everyone. It was logistically prohibitive, and most governments would probably reconsider when they realized what doing so would actually entail. Today, technology improvements mean that it takes much less effort—and evidently that it feels much less wrong.
8. Because a lot of internet activity is oblivious to national borders, jurisdictional questions are now much murkier. Internet companies and services aren’t so much proactively global as casually global: the default is to be available everywhere. As a result, internet services don’t consider the legal implications of expansion into each jurisdiction. They don’t really expand into jurisdictions at all. They’re just there. We don’t have a good framework for regulating these entities. Should a US website be subject to Australian libel law? (To the union of all libel laws?) The most obvious solution is to have an internet company be subject only to the laws of the country in which it resides, but even this doesn’t work: companies can easily operate from multiple countries. And, of course, countries affected by a non-resident service aren’t likely to be satisfied by this solution.
9. A lot of laws make less sense today. Remix culture, Airbnb, YouTube, Lyft, and Bitcoin challenge existing regulation. The harm of bad laws is often invisible, which makes weighing the trade-offs difficult. (How many good things aren’t happening and how good would they be?) It’s hard to argue against regulation before the potential of a new technology has been realized—the possibilities are, by definition, merely hypothetical.
10. Since a lot of industries are being reshaped by technology, more incumbents are seeking regulatory protection. Goverments sometimes acquiesce and enact bad laws (DMCA), which in turn angers citizens.
11. Legislators lack the conceptual framework to reason effectively about internet and software issues. I think this might be the biggest problem of all. As industry insiders, we have an advantage: we know it’s inane to talk about "getting data back"; we know that metadata and data are often distinctions without differences; we know that large datasets are very hard to anonymize; we know that a large dataset will rarely be used only for its originally intended purpose. We know this simply because we’ve watched these issues play out many times before. Politicians haven’t, and when policy questions hinge on understanding technology, they don’t tend to fare well.
Looking back over these, the main thing that strikes me is that it’s very hard to imagine any of them going away or being resolved any time soon. The internet was an epochal jolt and our governing structures have yet to catch up. We’re now twenty years in; given the pace of change, I expect these issues to persist for most of my life.
I find it interesting that the internet is still politicians’ example of choice when they need to show how the future is exciting. The US is today, in Obama’s words, “the nation of Google and Facebook.” The problems don’t simply stem from obliviousness. Even leaders who recognize the internet’s importance and value are stuck in an edifice almost guaranteed to yield a dissonant relationship.
2012-10-22
I’m sometimes asked whether Stripe could have been started in Ireland. It’s impossible to really know the counterfactual, but I suspect not.
Stripe wasn’t easy to get off the ground. It required convincing banks to work with us, and to take a bet on an unproven startup. I actually spoke to some banks in Ireland when we were starting out, and it was pretty clear that getting them to work with us would have been a very tough battle. I doubt we’d have been able to pull it off.
But I’m not sure that asking whether Stripe could have been started in Ireland is the right question. Most technology start-ups don’t have to convince banks to work with them. The interesting question is probably “how hard is to start a successful start-up in Ireland compared to doing so in Silicon Valley?” (I’m not claiming that Stripe itself is yet successful—it's still very early days.)
The answer is almost definitely “substantially harder”. Among the reasons:
- While improving, the investment climate still isn't very strong. There are far more investors in the US, particularly once you look beyond the seed stage. More importantly, all investors aren’t created equal, and the investors a start-up is likely to want are much more likely to be in the US. It still makes sense for most Irish start-ups to raise money outside Ireland, and over the last few years, it seems that the most notable technology start-ups with Irish founders have chosen this path.
- The talent pool here is much smaller than that of Silicon Valley. The single most important aspect of Silicon Valley is that it’s where many great people choose to live. Stripe’s employees come from Honduras, Kenya, India, Sweden, Canada, Austria, and more—but they’ve all chosen to live in Silicon Valley. Because Ireland has fewer of these immigrants, Irish start-ups are forced to either hire from a much more limited group, or to try to convince people to move here. (A third option is to have a geographically distributed team from the start; this route is also quite tough.)
- There aren’t many acquisitions happening, reducing the expected outcome of a start-up. In Silicon Valley, a failed start-up with good founders will often be bought by one of the tech giants; In Ireland, that same start-up is likely to simply fail. This matters not only because founders are less likely to want to start companies, but also because it’s harder to attract capital and to convince employees to join.
Despite these issues, I’m struck by how things seem to be improving every time I come back to Ireland. Dogpatch Labs recently opened in Dublin, and Eamon Leonard has been organizing a successful tech events series. Conferences like the Web Summit, f.ounders, FunConf, and Úll have substantially increased Dublin’s profile. Thanks to firms like Atomico, Accel, Index, DST, and others, the European investment scene generally looks much better than it did five years ago. Early stage tech companies like Hubspot and Zendesk have opened offices in Dublin. In general, things appear to be moving in the right direction. Given its size, Dublin compares surprisingly favorably to Berlin or London as a tech hub.
It also goes without saying that it’d be a mistake to look at any of the problems identified in this post as immutable, and it’s worth keeping in mind that they apply to most areas of the world that aren’t Silicon Valley. The first two issues mentioned above have gotten better since we started a company in Ireland in 2007. But given how much effort is (rightly!) being put into making Ireland a better place to start a start-up, it’s probably worth being clear about what should be improved.
