Viktor Orbán, who has governed Hungary for the past 16 years, turning the small Central European country into an international model for (as he himself proudly put it) “illiberal democracy,” just suffered a crushing defeat at the polls. According to preliminary results, the main opposition party, Tisza, will win over two thirds of the seats in the National Assembly. The victory by Péter Magyar is so unequivocal that Orbán conceded his defeat within hours of the polls closing, congratulating his likely successor on his victory.

This victory is such a big achievement in good part because Orbán has for the past decades proven extraordinarily effective at dominating Hungarian public life. He has built up a huge network of clients whose wealth depended on his goodwill. He has anointed himself an effective spokesperson for the conservative values shared by a large part of the country’s voters. And he has proven extremely adept at portraying himself as the only politician who can protect Hungary against its enemies.

Subscribe now

These enemies kept changing according to the needs of the moment. They variably included George Soros, who was raised in Hungary and paid for Orbán to attend Oxford University; the European Union, which grew vocal about Orbán’s blatant abuses of power after initially tolerating them for a shamefully long period; and Ukraine, which according to the most extreme claims in the latest election campaign had plans to invade Hungary. What never changed was Orbán’s insistence that the threat was existential, and that he alone was able to protect the Hungarian nation.

But after many years in office, leaders tend to be judged on their record rather than their rhetoric. And Orbán’s record increasingly looked abysmal.

Once one of the most affluent countries in Central Europe, Hungary is now the poorest in the European Union; over the last years, the standard of living of a typical Hungarian has fallen behind that of countries that had historically been much poorer, such as Romania and Bulgaria. Corruption runs so deep in Hungary that it started to affect the lives of ordinary citizens; the evident impunity enjoyed by Orbán allies who broke serious laws was a big part of the reason why erstwhile allies distanced themselves from him in droves over the last months. And on the international stage, a country that suffered brutal domination by the Soviet Union for half a century—most notably in 1956, when a reforming government was violently quashed by tanks sent by the Kremlin—found itself more aligned with Moscow than with Brussels, a development many Hungarians came to resent.

Subscribe now

The man who was able to seize upon these failings has himself for most of his adult life been an Orbán loyalist. Magyar rose to prominent political positions, running a public student loan program and sitting on the board of state-owned corporations, thanks to his close ties to the government. His break with Orbán did not come until 2024. When a presidential pardon for an accomplice in a child sex abuse scandal drew widespread outrage, Magyar broke with his political allies by giving an interview to a independent YouTube channel that went hugely viral. Within weeks of the interview, he was leading mass rallies; within months, the new party he put together had won 30 percent of the vote in elections for the European Parliament. Magyar has since positioned himself on the center-right, allying his newly founded party with Christian Democratic parties like Friedrich Merz’s CDU.

The victory of the opposition gives Hungarians a crucial opportunity to heal their ailing democracy and return their country to economic growth. It will make it much easier for the European Union to act with a united voice, especially regarding the ongoing war in Ukraine. And it is a humiliating defeat for the many American conservatives who have over the last years chosen Hungary as the projection screen for their political fantasies. (Evidently, it was so important to JD Vance to boost Orbán’s chances at reelection that he made a remarkable stopover in Budapest amid his negotiations with Iran.)

All of these are reasons for genuine joy. But to this expression of joy, I want to add a few more sober observations from the perspective of a political scientist.

Hungary has such outsized importance in part because it has long been seen as a test case for the stability of democratic institutions. Political scientists once believed that countries which are as affluent and have as long a democratic tradition as Hungary should not be vulnerable to sliding into dictatorship. Orbán’s ability to undermine key democratic institutions like a free press thus seemed to suggest that even countries in the traditional heartlands of democracy might be vulnerable to serious “democratic backsliding.” This makes it remarkable that the opposition was able to oust Orbán at the ballot box, and that he conceded defeat rather than trying to rig the elections. The outcome of Sunday’s vote should thus make us a little more optimistic about the prospects for democratic resilience in other countries in which demagogues are daily attempting to circumvent constitutional limits on their power, including the United States.

The stakes of politics have risen sufficiently high that, from Hungary to the United States, it is widely said about every major election that it is “the most important of our lives.” But the opposition’s success at ousting Orbán on its fourth try reminds us that the process of demagogues trying to win office and consolidating their power is very lengthy. A single election rarely allows them to concentrate power in their own hands. Despite all of his attempts at entrenching his rule, Orbán evidently failed to do so over the last 16 years.

Subscribe now

Conversely, a single defeat rarely banishes the danger such movements pose. In the United States, a demagogue who had been widely written off after his first electoral defeat succeeded in returning to power. In Brazil, a demagogue who had been widely written off—and even put in jail—after an electoral defeat could soon help his son ascend to the presidency. The fight for democracy is a marathon, not a sprint.

For similar reasons, it would be premature to conclude that the threat to Hungarian democracy has now been banished. Magyar has won a commanding victory, and the fact that he enjoys a two-thirds majority will make things much easier for him. But the impressive coalition he put together is so diverse that it will struggle to agree on how to govern, and he himself remains in many ways an ideological cipher.

Even if Magyar proves to be sincere in his commitment to govern in a way that is more respectful of the rule of law, he will face what I’ve come to call the “post-populist dilemma.” Orbán has put so many of his own people in so many positions of power that, even with his party reduced to a small rump in parliament, he will retain the ability to torpedo the work of the government in a million ways. This means that Magyar faces two equally unappetizing choices. He can choose to play completely by existing rules; but if he does, he is leaving many of Orbán’s corrupt appointees in key positions in the administration and the state media, making his work all but impossible. Or he can fire anybody who appears more loyal to Orbán than to the constitution; but if he does, he will effectively normalize the idea that each new prime minister simply fires anybody appointed by their predecessor. The difficulty of navigating the post-populist dilemma is one reason why even a big setback for demagogues doesn’t always spell the end of their political career.

Finally, there is a delicious irony to how lop-sided Magyar’s victory is. During his 16 years in power, Orbán repeatedly changed the electoral system to tip the balance in his party’s favor. Because the opposition was divided and he counted on always retaining the most votes of any single party, he adopted an electoral system which strongly boosts parliamentary representation for the numerical victor. Now that Hungarian voters have finally turned on Orbán, he is a victim of his own machinations. Despite winning about 40 percent of the vote, his party will hold less than a third of seats in parliament.

Demagogues always try to manipulate political institutions in their own favor. But as Orbán’s crushing defeat illustrates, doing so successfully is very hard. Again and again, tomorrow’s electoral arithmetic turns out to be vastly different from today’s. And so the frequency with which attempts at manipulating the electoral system backfire is one of the small ways in which democratic institutions have proven to be more resilient than we might have expected a few years ago.

Over a decade into a political era defined in large part by the threat that demagogues pose to democratic institutions, it is time to recognize that some of the simplest narratives conceal more than they reveal. Most countries are neither perfect democracies nor outright dictatorships; they fall on some point along the messy continuum between the two.

For that reason, the most likely threat for most countries is not that they are about to slide into outright dictatorship. It is that incumbents severely tilt the playing field without quite being able to banish the opposition.

This implies an important lesson for those of us worried about the state of democratic institutions in our own country. The real risk for the United States today is not that the country will soon resemble the world’s most extreme dictatorships. It is that America turns into a “dirty democracy,” in which those in power are able to rewrite the rules of the game in their own favor without ever quite rendering democratic elections meaningless.

Subscribe now

Whether in Hungary or in the United States, a clear view of the situation requires us to adopt a more messy model of how democracies rise and fall. The fate of longstanding democracies is unlikely to consist either in a full victory or in a full defeat for the forces of freedom; and it is determined by choices made over the course of decades, not days.

But such a refined understanding of the complexities of this political era should not impede our ability to celebrate when there is a rare piece of genuinely good news. And anybody who cares about basic values like the rule of law should welcome Orbán’s defeat as a big step in the right direction. Sunday’s election was a good day for Hungary and a good day for democracy.

Follow Persuasion on X, Instagram, LinkedIn, and YouTube to keep up with our latest articles, podcasts, and events, as well as updates from excellent writers across our network.

And, to receive pieces like this in your inbox and support our work, subscribe below:

Subscribe now

It is sometimes hard to know which pieces will attract wider interest and which won’t. For whatever reason, last week’s article did. And among the many interesting responses to it, there was one by one of my favorite writers: Michael Lind.

In the article, I argued that we are living amidst a strange “Paradox of Infinite Voices and Narrow Minds.” On the one hand, the social media revolution has vastly increased the ease of expressing our opinions, leading to a much more variegated public sphere (in ways both good and bad). On the other hand, those of us who are in some sense members of the professional class are part of a milieu in which the breadth of acceptable opinion is much more narrow than it was in the past. Part of the reason for this paradox, I argued, is a process I called the “Brooklynization of the Bourgeoisie.” The affluent, credentialed class has shifted sharply leftward over the past decades. And since they hold outsized sway over the culture as a whole, this has opened up a cultural representation gap between this milieu and the rest of the country.

Lind’s response, which I am sharing with you today, makes a strong point: that we should, really, be distinguishing between two different segments of the middle class. The first segment includes lawyers, doctors, academics, and others who have advanced to their positions by accruing formal meritocratic credentials; the German term for it is the Bildungsbürgertum (roughly: the bourgeoisie of the educated). The second segment includes business owners and prosperous artisans who have advanced to their positions by competing more directly in the free market; the German term for it is the Besitzbürgertum (roughly: the bourgeoisie of the owners). Without preempting Michael’s fire, I will just note that the way in which I used the term “bourgeoisie” in last week’s essay was primarily meant to refer to the first group, since that—perhaps to the detriment of our collective conceptual clarity—is how that term now tends to be used in the United States.

While I am at it, I should also own up to another synecdoche of which I was rightly found guilty by some thoughtful correspondents last week. When I wrote about the “Brooklynization of the Bourgeoisie,” I of course had in mind the parts of Brooklyn that are home to the Bildungsbürgertum; everything I wrote should be taken to apply to Brooklyn Heights or Park Slope but not to Brighton Beach or Sheepshead Bay; I formally apologize for unduly bringing the latter neighborhoods into disrepute.

One last note: If you have not yet added The Good Fight to your favorite podcast app, now is the time to do so. And if you are (or become!) a paying subscriber, you will have access to full versions of all recent episodes—from my conversation about the war in the Middle East with Francis Fukuyama, to my occasionally contentious interview with Ibram X. Kendi to my abortive attempt at a conversation with Klaus Schwab.

But now, without further ado, here is Michael Lind’s response to last week’s piece.

Thanks, as ever, for reading.

—Yascha

Set up podcast

The Two Bourgeoisies

Yascha Mounk’s essay “The Bourgeoisie Has Switched Sides” is as insightful as his phrase “the Brooklynization of the bourgeoisie” is memorable. His analysis could be elaborated by acknowledging that there is more than one bourgeoisie in the contemporary West.

In Germany, there has long been a distinction between the “educated middle class,” or Bildungsbürgertum, which includes lawyers, doctors, academics, clerics, and civil servants, on the one hand, and the “propertied” middle class, or Besitzbürgertum, which includes business owners and independent bankers (large and small), and prosperous, self-employed artisans, on the other.

This social division, if not the terminology, is familiar in the United States. The politics of “expert progressivism” has been based in America’s educated bourgeoisie, who since the 1900s have favored variants of would-be enlightened technocratic government as an alternative to the dreaded extremes of mob rule and plutocracy. Meanwhile, for a century, American businessmen and the politicians and pundits they have funded have denounced “meddling bureaucrats” and “long-haired professors” in pseudo-populist campaigns to delegitimize rival non-capitalist elites.

The growth of giant corporations run by managers rather than founders, and the bureaucratization of higher education and philanthropy in the United States and Europe, has greatly expanded the offices that can be filled by professionals educated and credentialed as members of the Bildungsbürgertum. These meritocratic managers can easily circulate among the bureaucracies of business, banking, government, and the nonprofit sector, and they tend to share common values instilled in them by prestigious universities.

Today’s propertied bourgeoisie is made up both of small business owners and of entrepreneurs who found companies that grow to immense size. Big and small owner-operators alike tend to share the view that their firm is their personal property. They feel attacked and insulted by government regulators, tax authorities, and workers who try to organize unions or simply demand higher wages.

Subscribe now

Right-wing populists on both sides of the Atlantic claim to represent “the people” against “the elites,” when in fact they merely represent the propertied bourgeoisie in its century-long battle against the managerial-professional overclass. A model for today’s anti-intellectual, anti-tax, anti-state demagogic populism can be found in postwar poujadism—the revolt of small proprietors in France in the 1950s led by Pierre Poujade. While demagogic populists like Donald Trump and Nigel Farage can win over working-class voters upset with immigration or alienated by cultural progressivism, their core constituents and donors are the petty bourgeoisie as well as super-rich tycoons who answer only to themselves, like oil men and tech-company founders, as opposed to the CEOs and other temporary, professional managers of bureaucratic corporations and megabanks with many stakeholders.

If I am right, the pattern that Mounk has described so well can be described as a clash of the two bourgeoisies. On one side, technocratic professionals in large organizations of all kinds appeal to science and reason as they define them. On the other side, small capitalists and big entrepreneurs hire demagogic politicians to represent them while posing as anti-system populists. Except in the run-up to elections when they need working-class voters, both of the two bourgeoisies tend to ignore working-class majorities in the West.

Michael Lind is a contributor to Unherd and author of “Hell to Pay: How the Suppression of Wages is Destroying America.”

That book is now out. It includes contributions by great writers—and Persuasion regulars—from Jonathan Haidt to Jesse Singal and from Eboo Patel to Henry Louis Gates, Jr. Here is a lightly edited version of my contribution to it; I hope you’ll enjoy reading it.

—Yascha

P.S: I had a rather memorable experience interviewing—or rather, trying to interview—Klaus Schwab, the founder of the World Economic Forum, a few weeks ago. If you have not yet listened to one of the more memorable episodes of The Good Fight, set up the podcast here (or read the transcript)!

The year 2026 is a strange time to worry about viewpoint diversity. In the palm of my hand, I am holding a smart phone which gives me access to a greater diversity of views than has perhaps ever before been available to humans. On social media apps, in podcasts followed by millions of people, and increasingly even in traditional media, I can follow people who argue for communism and for fascism, listen to them making the case for social justice or for Islamic theocracy, or seek out those who will urge me to become a Catholic monk or a Hasidic Jew.

Since the large-scale deployment of artificial intelligence, I can even ask ChatGPT or Claude or DeepSeek to state whatever argument I choose in the tones and the style of any moral tradition that takes my fancy. John Stuart Mill famously argued that it is crucial to hold our beliefs as living truths rather than dead dogmas, something that would only be possible if we were exposed to a genuine diversity of views. “If opponents of all important truths do not exist,” he suggested, “it is indispensable to imagine them and supply them with the strongest arguments which the most skillful devil’s advocate can conjure up.” Today, that devil’s advocate is accessible to any human with an internet connection.

And yet, the unprecedented diversity of viewpoints that is now available to—and to some extent inescapable for—the citizens of modern democracies coexist with a greater homogeneity of thought in key spheres of civil society than has been characteristic of life in the West in any historical epoch since the Victorian period. If you are an artist or an academic or a social worker or a psychologist—or, increasingly, a journalist or doctor or lawyer or civil servant—you likely operate in a social milieu in which the range of respectable opinion is strikingly narrow.

Oddly, that adherence to a narrow band of opinion is largely self-imposed. There are (at least in the United States—the story is sadly rather different in much of Europe) no formal legal constraints on expressing a different point of view. The modes of censorship that leading social media companies, in clandestine cooperation with the state, imposed for the past decade have largely disappeared. There is even a good living in refusing to toe that line: You can accumulate a lot of fame and perhaps ascend to the highest echelons of political power by assailing those respectable nostrums, turning yourself into an angry pundit. But if you happen to be a normie professional who simply wants to enjoy a good career and a peaceful life, the incentive to pay lip service to a list of narrow articles of faith remains overwhelming.

Subscribe now

Homogeneity breeds conformity. Because many of these professions are now so dominated by people with one point of view, the rising generation of professionals tends to share the same outlook. And where the conformity isn’t genuine, coercion can create its appearance. Surveys reveal that an astonishing share of people in a broad range of professions regularly engage in self-censorship.

I have come to think of this strange coexistence between an unprecedented variety of opinions that are strongly represented in the public square and the rigid worldview that constrains the beliefs of the most influential people in our society as the paradox of infinite voices and narrow minds. Never before have so many opinions been at our fingertips—and never before have so many professionals felt unable to voice theirs. What explains this paradox, why does it matter, and what can we do about it?

The Brooklynization of the Bourgeoisie

It is impossible to understand the recent politics of the Western world without considering a giant sociological transformation—one that, inevitable though it may seem in retrospect, nearly nobody predicted: The bourgeoisie has switched sides.

For much of the nineteenth and twentieth centuries, the proletariat was the political stronghold of the left. The bourgeoisie was the stronghold of the right. Indeed, the assumption that affluent professionals would tend to be conservative is reflected in the most famous political treatises and pieces of art that the period produced.

Karl Marx called on the workers, not on the lawyers or freelance illustrators, of the world to unite. The origins of Germany’s Social Democratic Party, of Britain’s Labour Party, and even of the modern-day Democratic Party in the United States lie with factory workers and trade unionists. In Jacques Brel’s song “Les Bourgeois,” three young men mock the conservative pieties of their elders by mooning the notaries of a small French town; when, by song’s end, the protagonists, themselves now middle-aged notaries, respond in anger to being mooned in turn, the obvious implication is that they too have turned into conservatives.

But of late, these realities have started to shift, with huge impacts on contemporary politics. It is astonishing, for example, that according to The Economist, the socio-economic profile of the coalition assembled by Kamala Harris, the Democratic presidential candidate in 2024, most closely resembles the socio-economic profile of the coalition assembled by Bob Dole, the Republican presidential candidate, in 1996. (Unsurprisingly, both lost.)

This transformation is even visible in the realm of popular culture. Take, as an example, the most famous American cartoon of the last decades. When The Simpsons first aired, Homer Simpson was likely a Democrat, his pious neighbor Ned Flanders definitely a Republican. But over the three decades that the show has been on air, the nature of America’s partisan divide has shifted so much that any politically astute viewer would now assume these characters to have rather different loyalties. Flanders may be sufficiently alienated by the coarseness of the populist right to vote for the Democrats; Homer would undoubtedly support Donald Trump.

This transformation has been called by a variety of names. Thomas Piketty has described it as the rise of the Brahmin left. David Brooks has written about the rise of the Bobo. Matthew Yglesias has lamented the rise of The Groups. I propose to call it the Brooklynization of the Bourgeoisie: New York’s wealthy used to live on the Upper East Side, to pride themselves on their old family ties, to value markers of high culture like the opera, and to vote conservative; today, they live in Brooklyn, believe that they have earned their place in the upper echelons of society thanks to succeeding in a meritocratic competition, are more likely to care about rock bands or microbrews, and think of themselves as progressive.

Subscribe now

That same transformation also helps to explain the Paradox of Infinite Voices and Narrow Minds. The population of the United States, and of many other Western democracies, is now deeply stratified by educational achievement. The affluent and highly credentialed are mostly on the political left. The working class is increasingly drifting to the political right. And that has deeply transformed the composition, the values, and even the actions of the professional class.

Plumbers are right wing but lawyers are left wing. Cab drivers are right wing but university professors are left wing. Police officers are right wing but civil servants are left wing. And though many professions claim to be apolitical, the plumbers and cab drivers and police officers increasingly suspect that the lawyers and professors and civil servants are letting their political values influence their work. The decline in respect for “experts” is in part owed to the blatant lies spread on social media; but it also has its roots in the real ways in which the consensus within these professions has increasingly come to adhere to a narrowly progressive—and often lamentably erroneous—set of assumptions about the world.

The Brooklynization of the Bourgeoisie also has another side effect. Lawyers, university professors, and civil servants have outsized influence on the rules, norms, and decisions that structure a lot of day-to-day life. And that leaves many less-affluent and less-educated citizens feeling that the democracy they were promised is a sham. “We are the majority,” they complain, “but no one listens to us.”

The resulting state of affairs leaves both sides equally unhappy. Many citizens feel ignored, besieged, and detested by a professional class which believes that it is entitled to rule, and finds the views of many of their compatriots intolerably bigoted. That is of great political significance because, even in highly affluent countries, there are more tradespeople, cab drivers, and police officers than there are lawyers, university professors, and civil servants. Meanwhile, members of the professional class feel bewildered at the lack of respect for their expertise, and fearful that the barbarians at the political gates will soon come for their heads.

What one side perceives as flagrantly unjust domination by the well-credentialed, the other interprets as the perils of revanchist demagoguery.

Barbarians Inside the Gate

There is one group of professionals that I have so far omitted to mention: elected officials. These officials differ from other upper middle-class professionals because voters ostensibly select them for their political views. But in sharp contrast to the past, when many of them, especially on the left, had working-class backgrounds, nearly all of them have also undergone an extensive process of socialization as middle-class professionals. With few exceptions, elected officials in the United States, the United Kingdom, and most of continental Europe, have attended universities, spent long periods of time living in big urban centers of economic opportunity, perhaps worked in fields like the law, media, or academia, and now make upper middle-class wages. If it looks like a professional, talks like a professional, and earns like a professional, then it is probably a professional—with all the cultural and ideological accoutrements that nowadays come with that status.

It should, then, come as no surprise that, as a recent paper by Laurenz Günther shows, a significant gap has formed between the views of elected officials and those of the voters they are supposed to represent. In Germany in 2013, at a time when right-wing populists had not yet made it into the national parliament, for example, the average politician was much more likely than the average voter to say that it should be easier to immigrate to the country. In fact, even the average member of the Bundestag for the Christian Democrats, the most right-leaning party to be represented in that body at that time, was well to the left of the median voter on this question.

Similar gaps of political representation, Günther shows, also held in other countries and for other topics. They are evident in questions about how severe the sentences for violent criminals should be; in questions about whether schools should teach students to obey social authorities; and in questions about whether politicians should prioritize the fight against climate change over economic growth.

Subscribe now

There are many partial explanations for the astonishing success of populist parties over the past decade. The rise of the internet and of social media, for example, clearly made it easier for outsiders to storm the political stage and intensified the public’s tendency to see the world in unremittingly negative terms. But as Günther suggests, the big gap in views about cultural topics between most voters and most of their representatives surely played an important role: The most straightforward reason why right-wing populists have gained so much in vote share of late “is that they fill the cultural representation gap.”

The lack of viewpoint diversity in important professions does real harm to their ability to deliver on their mission. A psychologist who prioritizes the abstract demands of social justice over the well-being of the patient sitting in front of him in his office fails to live up to his duty of healing patients. A social scientist who is so afraid of what her colleagues might say about her latest study if its findings happen to run counter to some sacred article of faith fails to live up to her duty of advancing human knowledge. But these kinds of harms only capture the most immediate impact of the Brooklynization of the Bourgeoisie. Its ultimate harm stems from the representation gap that has opened up between ordinary citizens and those calling the shots in society—and the counterproductive rebellion it inspired.

How Not to MAGA

Populists are able to win power in good part because they promise their voters that they will do what they can to close this representation gap. Legislators, they say, will finally start listening to the views of the people. Professions that have been captured by ideologues enforcing a narrow orthodoxy will be forced to become more representative. Institutions which once had disdain for ordinary people will finally feel their wrath.

There are real reasons why these promises have proven so enticing. Anybody who completely dismisses the fact that this anger is based in real failings of the professional elite is refusing to grapple seriously with this political moment. And yet, the record of populists in India and Turkey, in Hungary and Venezuela suggests that these promises are rarely fulfilled—and the first year of Donald Trump’s second administration in the United States only serves to reinforce that suspicion.

When populists rise to power, they tend to assail institutions that have lost the trust of the population. In the United States, for example, Donald Trump has exploited the unpopularity of universities like Harvard and Columbia by subjecting them to an unprecedented assault from the federal government. The ostensible purpose of this assault was to right the ways in which they had become inhospitable to opinions which violated rigid campus orthodoxies. And in certain particulars, those complaints really were well-founded. It is now, for example, well-documented that the mandatory diversity statements which many universities used in their hiring processes over the course of the past decade in practice forced applicants to pay lip service to the mantras of critical race theory (with anybody who refused to comply excluded from serious consideration).

Subscribe now

But it has also quickly become obvious that the White House was never truly interested in broadening the range of views which would be permissible, or even those that would be commonly represented, on the nation’s most prestigious college campuses. Instead, it seems to have two goals, which may stand in slight tension with each other, but are equally inimical to the true cause of viewpoint diversity.

To the extent possible, recent executive orders and other administrative actions by the White House have sought to replace one set of dogmas with another. Instead of pushing back against the forms of ideological coercion which do persist, they have simply created a new set of do’s and don’ts. If it was previously taboo to criticize the nostrums of critical race theory, a raft of new laws, executive orders, and administrative fiats attempt to stifle academics who teach these ideas. And instead of mandating that virtually all research must in some way promote the cause of diversity, public funding bodies have indiscriminately cut grants which commit the faux pas of mentioning such terms in any way—in the most absurd cases, even if they used them in a wholly unpolitical context.

At the same time, the White House also seems to have recognized that no amount of pressure from the federal government will transform the ideological leanings of most faculty at leading universities. And so, its recent activity appears to aim as much at weakening as at transforming these institutions. The point is not to change the culture at institutions which populists rightly recognize as hostile to their worldview; increasingly, it is to weaken the power bastion of their ideological adversary at any cost.

From a purely partisan standpoint, this is probably a shrewd judgment. The cynics in the White House who have concluded that the cause of the MAGA movement is better served by besieging than by reforming universities may be right about how difficult it would be for legislative fiat to undo the long-term effects of a much deeper sociological transformation of the professional class. But anybody who cares about preserving institutions that actually allow a broad range of people to do science, to argue about the world, and to criticize the powerful in honest and intelligent terms should be appalled by what is being sacrificed in the process. To undermine the great contributions that the United States has made in fields from computing to neuroscience in the service of undermining the department of comparative literature is both bad for humanity and for anybody who genuinely aspires to make America great again.

Diversity of Institutions (Within and Between)

It is hard to see a quick way out of the Paradox of Infinite Voices and Narrow Minds. This political moment increasingly resembles a Greek tragedy whose protagonists, unable to grasp the larger forces that determine their actions, are quickly gaining ground on the abyss. The professionals whose values are so far out of keeping with those of the rest of the population and the populists who are promising to use all the power they can amass to let the will of the people prevail see each other as mortal enemies; what neither seems to grasp is that they are actually one another’s biggest assets. And whoever ends up winning, it is the goal of viewpoint diversity—and the deeper values, like freedom of speech and freedom of conscience, with which it is intimately intertwined—which is likely to perish as a result.

The technological forces which have allowed such a great variety of viewpoints to enter the public square are unlikely to subside. The sociological transformations which have created a professional class beholden to an ideologically narrow set of nostrums are unlikely to reverse. And the populists who have been empowered by the resulting gap between the actions of key social institutions and the views of ordinary people are, despite their promises, likely to keep limiting true diversity of viewpoints in their own ways. It’s easy to see how things could go from bad to worse.

For the most part, the solution to this narrow problem hinges on the solution to a much broader set of problems. Institutions that want to sustain broad legitimacy must recall that they should be more beholden to their founding missions than to the ideological predilections of their members. This applies to institutions from Harvard to NPR and from the Ford Foundation to Coca-Cola. It also, of course, applies to political parties: If mainstream parties cared deeply about basic constitutional values, and were able to close the cultural representation gap, they would leave much less oxygen for demagogues who blithely reject those commitments.

Subscribe now

There is, however, one more direct change that advocates of viewpoint diversity can try to bring about in the meantime: One of the reasons why a diversity of viewpoints could so quickly have eroded within the professional world has to do with the fact that there has been a concerted attack on the ability to express different opinions in places like Harvard or Columbia. But another big reason is that there is so little true diversity between institutions, with many colleges and law firms and corporations adopting increasingly similar cultures, policies, and operating procedures. And this suggests that one of the partial solutions lies in establishing new institutions that differ radically from the old.

There are over two thousand colleges in the United States. At the lower end of social prestige, there is a great variety of such institutions, from community colleges serving heavily immigrant communities to religious schools preaching the Good News about Jesus. But all the schools at the top range of prestige have over the past decades come to resemble each other to a remarkable degree. However much their respective college tour guides may wax lyrical to visiting high school seniors about their idiosyncratic local traditions, Harvard and Princeton, Yale and Stanford, Duke and Columbia are all examples of what biologists call “convergent evolution.” It is not just in the substance of their prevailing views that they constantly copy and emulate each other; it is also in the design of their curricula, in the way they finance their institutions, and in the criteria they use to select their undergraduate classes.

The same holds true in many other realms. There are tens of thousands of law firms in the United States. But the culture at the most prestigious, from Cravath to Skadden to Wachtell, is much more similar than that variety might suggest to a naive observer. Even the mainstream press suffers from the same malady, especially when it comes to proudly progressive publications. A few decades ago, there were distinctive differences in style and content between Dissent, The Nation, and The New Republic; a well-versed reader could probably have guessed with a high degree of accuracy which article had appeared in which of these publications. Today, these magazines have largely lost their distinctive identities; just about any article which appears in one of these publications could just as easily appear in another.

The situation is, of course, even worse in those areas in which one or two institutions hold outsized sway. Top-level researchers in the natural sciences need to plan their research, more or less, in such a way that it meets with the approval of the National Institutes of Health or the National Science Foundation. Psychologists must abide by the dicta of the American Psychological Association. And researchers in global health better make sure that their proposed work fits the agenda of the biggest private philanthropists in the field, such as the Gates Foundation.

It is this tendency towards convergent evolution which makes it so hard to sustain a genuine variety of thought and opinion within the professional class. If one prestigious university applied different standards for admission and hiring than another, if the culture of one law firm radically diverged from that of another, if the journalistic enforcers of ideological orthodoxies still had genuine debates among themselves, if scientists were not beholden to a tiny number of funding bodies, and if professional associations were less quick to impose their ideological certainties on their members, professionals with dissident—or merely diffident—views would find it much easier to sustain thriving careers and speak their minds.

Subscribe now

Thankfully, there are some incipient signs that those professionals who have grown uncomfortable within mainstream institutions, or been cast out for daring to speak up, are starting to organize. Across the country, new universities and alternative media outlets and rival professional associations are forming. It is too early to know whether they will succeed in establishing genuine alternatives to existing structures, and even whether they will actually stick to their ostensible mission of promoting viewpoint diversity. But they are a small green shoot amidst a devastating drought.

The cause of viewpoint diversity remains much imperiled. One of the best ways to serve this embattled cause is to widen our understanding of what its success will require, both now and when the political constellation shall change: true diversity, both within and between institutions. If we want viewpoint diversity, we must not only protect dissenting voices—but also cultivate dissenting institutions.

This essay originally appeared in “Viewpoint Diversity: What It Is, Why We Need It, and How to Get It,” co-edited by John Tomasi and Bernard Schweizer, and published by Heresy Press.

A couple of months ago, I received an official letter from the District of Columbia with the words JURY SUMMONS printed atop the envelope in big, intimidating letters.

I have been an American citizen since 2017. But so far I have never been called upon to perform this particular duty bestowed by American citizenship. The historical purpose of the right to a trial by a jury of one’s peers was to ensure that an out-of-control executive could never turn the criminal justice system into a tool to augment its own power; at a time when the Department of Justice, adorned with a giant banner of Donald Trump’s face, is attempting to prosecute a number of his critics on spurious grounds, the relevance of this tradition feels far from abstract.

Subscribe now

So, one Wednesday morning in February, I dutifully trudged to the Superior Court of the District of Columbia at nine in the morning. It was the first mild day after a few brutal winter weeks. As the sun was rising high into the sky, the snowbanks that still marked the city’s streets were starting to melt. In the distance, I could make out the cupola of Congress.

It was hard to know what to expect. As a political scientist, I know all kinds of facts about the jury system but have never seen a jury in action. Would I serve as a juror on some minor civil case or some spectacular murder trial? And would they even want me to serve? Both prosecutors and defendants can strike a number of potential jurors from the pool simply because they have a hunch that they may not be favorable to their case—and professors, suspected by the prosecution of being overly progressive and by the defense of being overly smartalecky, are often among the first to be voted off the island.

At the entrance to the courthouse, I joined the first of many lines I would be standing in that day. As I made my way through an airport-style security check, I spotted one well-worn sign noting that the wearing of masks was no longer mandatory and another which exhorted visitors to the court not to wear gang insignia or expose their underwear.

Once inside, I made my way up to the fourth floor and caught the first glimpse of my peers: a long line of people waiting to prove their identity and receive their juror cards. There is something strange about seeing a statistical average manifest in the flesh. I realized that I had, in my life, looked at countless polls and sat through numerous focus groups. But never before had I actually been part of that statistical abstraction: a group of average Americans.

It turned out we all had something in common: young and old, dressed in the grey suits favored by the city’s well-heeled lobbyists or the sneakers and sweatshirts worn by its poorer residents, most (but not all) of us were staring at our phones. A long-faced Asian woman wearing a bright pink shirt was one of the few to raw-dog reality, staring into space without any form of entertainment. A single prospective juror, a white lady in her late 50s, was reading, her paper copy of The New Yorker turned to a short story called “The Heat of the Moment.”

Subscribe now

A short video, based on the findings of the “implicit bias test” (which has, I couldn’t help grumble to myself, been widely debunked) was playing on loop. “It’s pretty well settled that most biases happen at an unconscious level,” the chief justice, Milton C. Lee Jr., an elderly black man with a fastidiously trimmed grey beard and a benevolent tone of voice, explained.

“At the beginning of this video we all saw the chief justice,” a chipper young woman seconded in the cadence of the devout. “The truth is that we all immediately judged him.” What judgment, I wondered, had I unwittingly passed on the chief justice? That he takes pride in his appearance and, after a long day at the courthouse, likes to sit back in a large armchair with a small tumbler of fine whiskey?

When it was finally my turn to enter the office, a court clerk checked my ID, then handed me a lanyard with a sign that read Petit Juror and bore the number by which I’d be known for the remainder of the day. The next stop was the “juror’s lounge,” which turned out to be a giant waiting room, with about ten rows of forty chairs, all facing towards the front.

After an hour, a court official announced over a tinny intercom that a jury was about to be convened. She would call some of us by our names and the last three digits of our juror numbers. After a couple dozen other people, I finally heard something resembling my name: “Moo… Mou… Muuunk? 063.” I looked at my card to verify that she meant me, picked up a new piece of paper which had the number 23 written on it, then lined up along the back wall, wedged between jurors 22 and 24.

When our little troupe of fifty or so would-be jurors was complete, we were marched, single-file, into a windowless courtroom. The AV system was playing a loud background hum of static. The defendant, a young black man accused of driving without a license and fleeing the police, and his wizened defense lawyers, sat to the right. The prosecutors, a man and a woman, both fresh-faced and surprisingly young, sat to the left. Jurors one through 14 took a seat in the jury box; the rest of us, still arranged by number, sat in the public gallery.

Subscribe now

For ten long minutes, the whole courtroom was silent. Then the static suddenly cut out; the judge composed his face into a benevolent smile and turned towards us. Judge Jason Park, an Asian-American man in his mid-forties who had (I later learned) been nominated for his position by Donald Trump, explained that the American justice system is founded on the “belief that regular folks in the community have the experience and intelligence to make these judgments and make them well. This truly is government of the people, by the people, and for the people. Whether you are selected or not, I hope you leave today with a sense of having served your civic duty.”

Judge Park administered an oath to us, then started to read a long list of numbered questions. Had we heard anything about this case? Had we ever been arrested for a felony? Did we have any relatives who had been to jail? If the answer was yes, we were supposed to write its number on our juror card. Like me, Juror 24, an elementary school teacher in her twenties who was sitting to my right, handed in a blank sheet. Juror 22, a black woman in her forties with a friendly demeanor and a tired face who was sitting to my left, had, I saw out of the corner of my eye, written down three or four numbers.

Judge Park asked Juror 1 to step forward to a microphone positioned in front of his dais. The lawyers put on headphones, and the static noise returned. We all watched as one juror after another was called up to give answers we couldn’t make out to questions we couldn’t hear. I glanced at my phone and realized it was well past noon.

Some jurors spent ages answering questions about themselves before returning to their seats. Others were up there for a grand total of sixty seconds. Juror 22, the woman who had written various numbers on her card, answered questions for at least five minutes. Finally, it was my turn. By this stage, I had endured so many earnest lectures about the importance of jury service that my ambivalence had disappeared: I really wanted to be picked.

Was there, Judge Park asked in his benevolent demeanor, any reason why I wouldn’t feel able to consider this case without prejudice? “No, your honor,” I said, the customary honorific feeling strange in my mouth, as though I were reciting lines in a movie.

Subscribe now

“What do you do for a living?” the judge asked. How, I wondered, could I answer this question in an honest way without inspiring either the defense or the prosecution to blackball me? “I’m a professor of political science,” I said.

“What is your work about?” the judge asked.

“Um, I have written a lot about democracy in the past,” I said, groping for words that would be accurate yet sound innocuous. It occurred to me that it would be rather ironic if being a scholar of democracy should get me excluded from this most democratic of traditions. “My current project is about artificial intelligence,” I added, tentatively.

“Thank you very much,” the judge said. “You may take a seat.” I had barely been up there for thirty seconds.

A few more people were called up to answer questions about themselves. Then the static cut out again, and the judge told us that we would need to come back after lunch.

The elementary school teacher and I got lunch together at a nearby deli. “I really hope I don’t have to serve,” she told me over pastrami sandwiches. “The kids would be really upset if I’m not in school for Valentine’s Day.” But, she said, she wouldn’t be picked anyway: “My colleagues told me that they never select teachers.”

When we returned to the courtroom, all trial’s protagonists were already inside, standing in a show of respect for us as we returned to our earlier seats. The static cut out again. Everybody who was still in the room, Judge Park explained, had been found constitutionally eligible to serve. Now, both the prosecution and the defense would be allowed to strike ten potential jurors from the pool for any reason other than protected characteristics such as their race or religion. “Please don’t take it personally if you are struck. I myself have never been selected to serve on a jury.”

There was much passing of papers between the defense and the judge, and between the judge and the prosecution. Finally, Judge Park’s voice cut back through the static: “Juror number 4. Please vacate your seat and stand at the back of the room.” One by one, the judge asked five of the people seated in the jury box to get up from their seats. Evidently, they had been blackballed.

Subscribe now

Then he started to go through the first people seated in the gallery. “Juror number 16, please take the fourth seat in the jury box.” I did some quick math in my head and realized that my juror number would likely be low enough to be promoted to the jury if neither the defense nor the prosecution had nixed me. To my surprise, I felt my heart starting to pound. “Juror 22, please take seat 11.” The lady sitting to my left stood up and took a seat in the jury box. She had no visible reaction to being selected, but her face looked to me a little more tired than it had before.

If I were to be chosen, they’d have to call me next. “Juror 26, please take seat 12.” I had not been chosen. Nor had the elementary school teacher. We looked at each other, and I tried to match her smile of relief. But all I felt was a pang of disappointment.

Then I remembered what Judge Park had said earlier: Even though I wouldn’t actually help to decide the fate of the defendant, I had still served my civic duty. Earlier, that had sounded a bit hokey; now, it rang true.

The whole day had, in a sense, been a waste of my time. I had stood in a never-ending succession of lines, and spent hours playing on my phone, only to be dismissed for reasons that would never be explained to me.

But that is not the main lesson I took away from the experience. When I first arrived in America, I was in awe of the country’s institutions, from its courts to its universities. Today, it can feel as though many of these institutions are in a state of terminal decline—failing to do their jobs, run by incompetent loyalists, increasingly distrusted by the general public.

A deeply ordinary day in a deeply ordinary court reminded me that this collapse is not yet total: There are still judges who perform their duties with great professionalism; lawyers and clerks and security guards who take genuine pride in their jobs; and ordinary Americans willing to take upon themselves the awesome responsibility to sit in judgment of their peers. While the civic fabric is rotting rapidly, it is made of ample and sturdy cloth. As I emerged back into the sunshine and took a walk down the National Mall, trying to dodge the puddles of melted snow, I looked upon the glistening cupola of Congress with a little more optimism about my adoptive country than I had been able to muster that morning.

There has long been a divide between those who believe that artificial intelligence is an enormously transformative technology and those who believe that it is hopelessly overhyped. Never has that divide been more enormous than in the last weeks.

Most people who have regularly used the technology in the recent past believe that the rate at which the state-of-the-art models progress is extremely rapid. They are now capable of engaging in long chains of reasoning that dramatically increase their problem-solving abilities in areas from financial analysis to molecular biology. Their ability to one-shot practical tools, from data visualizations to websites, is astonishing. They have become so good at coding that some of the most accomplished computer programmers in the world now say they barely write any of their own lines anymore. And just the other day, leading scientists presented a genuinely new finding in astrophysics, one that corrected long-held assumptions in the field, that was produced by a large language model.

And yet, many people I know, especially in the humanities, continue to be in deep denial about the state of this technology. Perhaps the most common way in which they dismiss the importance of this technology is to claim that AI models are not intelligent or creative. Sure, they say, these stochastic parrots can do some impressive things like summarize an email or write boilerplate corporate language; but they are congenitally incapable of making a genuine intellectual or artistic contribution.

Subscribe now

A lot of the time, the people who make this argument are not very clear on what they mean by intelligence or creativity, and keep shifting ground when you push them on their definition. If you manage to pin them down, it usually becomes evident that their argument is circular: they believe that AI systems cannot be intelligent or creative because only texts or works of art produced by humans are instances of intelligence or creativity.

I don’t want to get consumed by a futile semantic debate about how to use those words. What I do know is that I consider the ability to make a novel, interesting, and plausible argument about politics to be one important indicator of intelligence and creativity, and that I devoted a long stretch of my early adult life to developing the ability to do so at a high level. So when, still jet-lagged from a recent trip to Europe, I woke up well before the crack of dawn a few days ago, I decided to see whether the newest AI models would be capable of writing a competent academic paper in my field of study, political theory. The result both elated and depressed me.

I spent the better part of a decade primarily devoting my intellectual energy to the study of political theory. That required me to master some of the most influential texts in the history of political thought; to make careful distinctions between different ideas and follow the premises of an argument through to their logical conclusion; and (the part I always struggled with the most because I found it so boring) to learn the conventions of academic publishing, developing a sense of the implicit norms which govern what you do and don’t do in a “publishable” academic paper.

Though little of either my academic or my public work now falls squarely into the category of political theory, narrowly understood, this training has deeply shaped how I write, and I am immensely grateful for it. Years of thinking about the nature of political arguments taught me how to understand the structure of all kinds of questions about the social world, to spot the logical inconsistencies in both scholarly articles and social media posts, and to turn a nascent idea into a cohesive argument at rapid speed. The core skills imparted by a rigorous study of political theory provided the intellectual foundation for much of my work, whether I was engaged in trying to understand the conditions under which democracies might come to be more vulnerable to demagogues than was widely believed at the time in The People versus Democracy, or to explain and critique the rise of a new ideology on the American left in The Identity Trap.

In fact, it is, I think, hardly a coincidence that political theorists tend to punch above their weight in public debate in the United States. The list of prominent thinkers and commentators who are at least partially trained in political theory is surprisingly long, especially given the field’s tiny size: to name but a few, it includes George Will, Andrew Sullivan, Michael Sandel, Bill Galston, Danielle Allen, and Patrick Deneen.1

In some ways, it should be easier for artificial intelligence to crack political theory than some other fields. After all, political theory doesn’t require collecting or analyzing new datasets, and many of the field’s canonical texts are likely to be strongly represented in the training data for AI. But in other ways, it is a high bar: Making an original argument in the field requires both a demanding mix of interpretative and argumentative skills, and a new idea on a topic people have argued about for thousands of years. The ability of large language models to create a convincing work of political theory thus seems to me a good test case for the debate about whether artificial intelligence is or is not intelligent.

(Claude’s opinion of the field, I must admit, is a little less flattering. Referencing my desire to disprove that AI is “merely a stochastic parrot,” Claude told me that “political theory may be the one field where ‘stochastic parrot’ is actually a compliment, since the whole discipline consists of creatively recombining things Tocqueville and Mill already said.” Ouch.)

Subscribe now

I started by asking Claude Opus 4.6, with extended thinking enabled, to help me write a political theory paper that could be published in a top journal in the field. After consulting recent publications in top journals, it came up with five different ideas, some better than others. One, for which I later asked Claude to write a summary for general readers,2 reproduced here, felt to me like it held promise:

Political theorists have spent the last decade asking whether big corporations are like mini-governments—whether your boss is a kind of dictator, whether tech companies should be democratized. That’s the right instinct, but it’s looking in the wrong place. The real power that Google, Meta, and OpenAI exercise isn’t over your choices—it’s over the conditions under which you think. They don’t tell you what to believe; they shape what you encounter, what feels plausible, what questions seem worth asking, and increasingly, through generative AI, they produce the very material out of which your beliefs are formed. Tocqueville had a phrase for this: the “formidable circle drawn around thought.” Mill feared the same thing—that when a society loses the friction of genuinely competing ideas, even its true beliefs decay into “dead dogma,” held by rote and understood by no one. Both were responding to the communications revolutions of their own eras. Ours is more radical than anything they imagined, because for the first time in history, a handful of private companies control not just which ideas circulate, but the infrastructure of cognition itself—and they do so with no democratic mandate, minimal transparency, and almost no accountability. I call this epistemic domination, and I argue it’s the single greatest untheorized threat to self-governance in the twenty-first century.

In the next step, I uploaded two recent papers in Political Theory, a top journal, and asked Claude to give me an outline of the paper which follows the field’s conventions. After that, we went section by section, with me giving one round of high-level feedback on each. To give an example, I worried that the section it had written on John Stuart Mill spent too much time rehashing the arguments in favor of free speech from Chapter 2 of On Liberty, which would be very familiar to political theorists, tasking Claude with incorporating quotations from more obscure texts such as published letters.

Subscribe now

The human feedback involved in this process certainly drew on my training in the field, but it was very minimal. Including the time it took Claude to generate the text, and the rather longer time it took me to read what Claude had written, it took less than two hours from when I had the idea to run this experiment to when the draft was finished.

The draft could certainly be improved in a few respects. There are certainly a few places in the argument where reviewers could come up with clever objections. Claude explicitly urged me to check the page numbers in some of the references for the quotations it used against canonical editions of the works by Tocqueville and Mill. It also asked me to double-check the wording of some of the quotes from less canonical texts, such as the correspondence between Mill and Tocqueville. (Since I wanted to present Claude’s output to you in its original form, I did not do this. The few references I looked up seemed to be correct, but I expect that there are some mistakes that would need to be corrected before the paper could be submitted to an academic journal.) But on the whole, the outcome was depressingly good: I am confident that it could, with minor revisions, be published by a serious journal.

The power of motivated reasoning is immense. If this little experiment should happen to draw a bit of wider attention, a lot of people will quickly claim that this paper is deeply flawed or outright stupid, and that it could never have been published in a serious journal. The way to definitively disprove this would have been to do a version of the Sokal Hoax, getting this paper accepted at a good journal under false pretenses before sharing it publicly.

I briefly thought about doing this. But since the ethics of submitting work to journals under false pretenses is contested, and institutional review boards of universities tend to frown upon the practice, I decided not to do so. Suffice it to say that I am convinced that someone with basic knowledge in political theory could pull such a feat off with ease. If you are a political theorist who is deeply convinced of the contrary, why don’t you give it a good-faith try?

But the comparison to the famous hoax by Alan Sokal, as well as the follow-up by Helen Pluckrose, James Lindsay and Peter Boghossian, is in any case misleading. Both of these efforts targeted journals in academic subfields that had gone deeply awry; they were a deliberate reductio ad absurdum. The paper produced by Claude, by contrast, is hardly absurd. While it has its shortcomings, and is not exactly earth-shatteringly original, nobody can seriously call it a reductio. Had a fellow student submitted it to my department’s graduate student workshop when I was doing my PhD, my respect for them would have gone up rather than down.

Subscribe now

This is not meant to be a gotcha about political theory, a field I continue to admire greatly. It is a wake-up call about the future of the humanities. Even if you put aside the extent to which some fields in the humanities have been captured by ideology in recent years, the whole enterprise has started to look a little askew. Professors at top universities are—in good part because of what it now takes to get a good job in the field—more focused on publishing erudite contributions to niche debates in scholarly journals which only a handful of their colleagues will ever read than on teaching and mentoring the ever-dwindling ranks of their students.

This was always absurd. But once artificial intelligence is able to write these contributions in the stead of humans—not just in political theory but also in theology and art history and comparative literature—it is totally indefensible.

In some ways, the Age of AI will make the humanities more important than ever. Disciplines from literature to philosophy are needed to help us answer questions about how we can find a place in the world when we are much less needed than before, and what it is to be human when we are no longer the only ones capable of doing some of the things of which our species was once uniquely capable. But at a time when artificial intelligence can jump through the hoops that have over the past decades come to define an academic career in the humanities with growing ease, a radical reimagination of how we pursue and impart meaningful knowledge in these fields is desperately in order.

Don’t believe me that the AI-induced crisis of the humanities is upon us? Take a look at the political theory paper Claude wrote up in a couple of hours for yourself:

The Oligarchy of Scale: Epistemic Domination and the Conditions of Self-Governance

Abstract

Political theorists have increasingly turned their attention to corporate power, asking whether firms exercise authority, coercion, or governance in ways analogous to states. I argue that this framing, while productive, generates a characteristic blind spot. The most consequential form of private power in contemporary societies operates not through the direct exercise of authority over identifiable subjects but on the epistemic conditions under which citizens form their beliefs, preferences, and political judgments. Recovering two underappreciated strands of the liberal tradition — Tocqueville’s analysis of the democratic mind in Democracy in America and Mill’s theory of epistemic infrastructure in On Liberty — I show that both thinkers theorized precisely this form of power, though neither possessed the conceptual vocabulary to name it. Drawing on their insights and on recent work in postcolonial and feminist epistemology, I develop the concept of epistemic domination: the arbitrary capacity of an actor to shape the epistemic conditions under which a political community reasons and judges. I distinguish this concept from republican domination, epistemic injustice, and ideological hegemony, and argue that the rise of artificial intelligence corporations represents its most complete contemporary realization. Democratic theory, I conclude, has been operating with an incomplete account of what self-governance requires.

Keywords: epistemic domination, Tocqueville, Mill, corporate power, artificial intelligence, democratic theory

Political theorists have recently rediscovered the corporation. After decades in which concentrated private power received relatively little attention from the discipline, a growing literature now insists that the authority exercised by firms over workers, consumers, and communities demands the same scrutiny that political theorists have long directed at the state.[^1] Elizabeth Anderson’s account of the workplace as a site of “private government” has been particularly influential, revealing the extent to which employers exercise arbitrary, unaccountable authority over the daily lives of those they employ.[^2] Isabelle Ferreras and Hélène Landemore have extended this line of argument to ask whether democratic principles require the democratization of the firm itself.[^3] David Ciepley has urged political theorists to recognize the corporation as a distinctive political entity — chartered by the state, endowed with legal personhood, yet governed by neither democratic nor market principles alone.[^4]

These contributions share an important structural feature. Each models corporate power on categories drawn from the analysis of political authority: governance, coercion, domination, legitimacy. The question they pose is, in essence, whether firms exercise something sufficiently like political power that the normative frameworks we apply to states should be extended to them. This is a productive line of inquiry, and the answer is plainly yes. But it also generates a characteristic blind spot. By asking whether corporations govern, coerce, or dominate in ways analogous to states, this literature tends to look for corporate power where we have already learned to look for state power — in the direct exercise of authority over identifiable subjects.

I want to suggest that the most consequential form of private power in contemporary societies operates differently. It does not principally work through the direct exercise of authority over employees or the coercive imposition of terms on consumers, though it does these things too. It works, rather, on the conditions under which citizens form their beliefs, interpretations, and political judgments — on the epistemic environment that democratic self-governance presupposes but that democratic theory has largely taken for granted. When a handful of corporations control the infrastructure through which information is produced, curated, and encountered — when they shape not merely what people know but the frameworks within which they interpret what they know — they exercise a form of power for which our existing theoretical vocabulary is not well equipped.

This is not an entirely new anxiety. The concern that concentrated control over the conditions of thought might prove more dangerous to self-governance than the direct exercise of coercive power has deep roots in the liberal tradition, though those roots have not been adequately traced. In what follows, I recover two largely underappreciated strands of this concern. The first runs through Tocqueville’s analysis of intellectual life under democracy in Democracy in America, where his account of the “tyranny of the majority” extends well beyond social conformism to theorize how democratic conditions can narrow the very range of what he calls “thinkable thought.” The second appears in Mill’s On Liberty, where the celebrated defense of free expression rests on a less frequently examined argument about the structural conditions that a society requires in order to maintain its collective capacity for sound judgment.

Reading Tocqueville and Mill together in this way reveals that both were theorizing a form of power that contemporary political theory still lacks adequate resources to name. Both recognized that self-governance can be undermined not only by coercion, censorship, or the direct suppression of dissent, but by subtler transformations in the epistemic environment — transformations that operate below the threshold of any individual’s freedom being visibly curtailed. Both were responding, crucially, to communications revolutions in their own eras that threatened to concentrate influence over public opinion in new and unprecedented ways. Drawing on these historical resources, I develop a concept I call epistemic domination: the arbitrary capacity of an actor to shape the epistemic conditions under which a political community forms its beliefs, preferences, and judgments. This concept is related to, but distinct from, several neighboring ideas in contemporary theory — Philip Pettit’s republican domination, Miranda Fricker’s epistemic injustice, and the Marxist tradition of ideological domination — and I take care below to specify the differences.

The contemporary form of private power that most fully realizes the anxieties Tocqueville and Mill articulated is the large artificial intelligence corporation. Companies such as Google, Meta, and OpenAI do not merely distribute information, as newspapers and broadcasters have long done. They increasingly shape the conditions of cognition itself: the questions users encounter, the answers that appear plausible, the framings that feel natural, the alternatives that remain thinkable. Through the design of recommender systems, the training of large language models, and the curation of search results, these firms exercise an ongoing, infrastructural influence over the epistemic lives of billions of citizens — an influence that is largely unaccountable, frequently opaque, and concentrated in remarkably few hands. If epistemic domination names a real and distinctive form of power, then the rise of AI corporations represents not merely a new chapter in the familiar story of corporate concentration, but a qualitative transformation in the relationship between private power and democratic self-governance.

My primary purpose in what follows, however, is not to offer a policy agenda or a regulatory framework for addressing this transformation. It is to argue that democratic theory has been operating with an incomplete account of what self-governance requires — and that Tocqueville and Mill understood this more clearly than we have generally recognized.

Tocqueville and the Democratic Mind

The most familiar element of Tocqueville’s analysis of democratic culture is his account of the “tyranny of the majority.” In its popular reception, the phrase names a straightforward political danger: that a democratic majority can vote to oppress minorities, concentrating power as effectively as any despot.[^5] In more careful scholarly treatments, the concept is understood to describe something subtler — a form of social conformism in which democratic citizens, eager for the approval of their equals, suppress dissenting views out of a desire to belong.[^6] Neither reading is wrong. But both, I want to suggest, capture only the outer layers of Tocqueville’s concern. Beneath the political danger and the sociology of conformism lies a more unsettling argument about the epistemic consequences of democratic life — an argument about how equality of conditions reshapes not merely what citizens are willing to say, but what they are equipped to think.

The key texts are not the celebrated chapters on majority tyranny in the first volume of Democracy in America, but the less frequently examined opening sections of the second volume, where Tocqueville turns from democratic institutions to democratic habits of mind.[^7] He begins with a paradox. Democratic peoples, precisely because they recognize no natural intellectual authority among their equals, are driven to seek authority in the only source that remains available to them — the aggregate opinion of the many. In aristocratic societies, Tocqueville argues, individuals defer to the intellectual authority of particular persons or classes whose superior judgment they acknowledge. Democracy dissolves this deference. No citizen in a democracy regards any other citizen as inherently more competent to judge: “as citizens become more equal and more similar, the tendency of each blindly to believe a certain man or a certain class decreases.”[^8] The result, however, is not intellectual independence. It is a transfer of cognitive authority from identifiable individuals to an anonymous and overwhelming collective. “Not only is common opinion the sole guide that remains for individual reason among democratic peoples,” Tocqueville writes, “but also it has among these peoples an infinitely greater power than among any other.”[^9]

The mechanism of this transfer is worth attending to closely, because it is here that Tocqueville moves beyond anything that can be captured by the language of conformism or political oppression. The authority of the majority over the democratic mind does not operate through persuasion, nor through force. It operates through a kind of cognitive saturation:

The public among democratic peoples has a singular power the idea of which aristocratic nations would not even be able to imagine. It does not persuade, it imposes its beliefs and makes them penetrate souls by a kind of immense pressure of the mind of all on the intelligence of each.[^10]

The phrase is remarkable. An “immense pressure of the mind of all on the intelligence of each” is not a description of social disapproval or political coercion. It is a description of an epistemic condition — a condition in which the sheer weight of shared opinion reshapes the individual’s capacity for independent judgment, not by punishing dissent but by making it cognitively unavailable. The majority, Tocqueville continues, “takes charge of providing individuals with a host of ready-made opinions, and thus relieves them of the obligation to form for themselves opinions that are their own.”[^11] The language of “relief” is pointed: citizens do not experience this as constraint. They experience it as convenience — the comfortable delegation of cognitive labor to a source that feels, by its very ubiquity, authoritative.

This transformation matters because it changes the character of intellectual constraint. Under aristocratic conditions, the obstacles to free thought are visible and personal: a censor, a patron, a church. One can identify the source of constraint and, at least in principle, resist it. The cognitive authority of the democratic majority operates differently. It does not suppress particular opinions by force. It renders them implausible — not by refuting them but by depriving them of the social conditions under which they could be taken seriously. In the first volume, Tocqueville captures this in a passage that deserves more attention than it has received:

In America, the majority draws a formidable circle around thought. Inside those limits, the writer is free; but woe to him if he dares to leave them. It is not that he has to fear an auto-da-fé, but he is the butt of mortifications of all kinds and of persecutions every day.[^12]

The passage is typically read as a description of social penalties for dissent — ostracism, career closure, reputational damage. But the metaphor of the “formidable circle” suggests something more fundamental. A circle drawn around thought is not a punishment imposed after the fact of dissent; it is a prior constraint on the space within which thought operates. What falls outside the circle is not merely dangerous to express. It ceases, over time, to be genuinely available as a live intellectual option.

Sheldon Wolin’s magisterial study of Tocqueville captures part of this dynamic. Wolin reads Tocqueville as a theorist of the “total culture” of democracy — a thinker who understood that democratic power operates not primarily through institutions but through the pervasive shaping of mores, habits, and dispositions.[^13] This is right as far as it goes. But Wolin’s emphasis on democratic culture can obscure the specifically epistemic dimension of Tocqueville’s concern. The problem is not merely that democracy produces a distinctive culture of conformity. It is that democratic conditions tend to produce a distinctive epistemology — a set of default assumptions about where authoritative knowledge resides, what counts as a credible claim, and which questions are worth asking — that systematically narrows the range of perspectives available to the democratic community.

It is in the closing passages of the chapter on democratic belief that Tocqueville states this concern in its most radical form. Having traced the transfer of cognitive authority from individuals and classes to the majority, he pauses to take stock of what has been gained and lost:

I see very clearly in equality two tendencies: one that leads the mind of each man toward new thoughts and the other that readily reduces him to thinking no more. And I notice how, under the dominion of certain laws, democracy would extinguish the intellectual liberty that the democratic social state favors, so that after breaking all the obstacles that were formerly imposed on it by classes or men, the human mind would bind itself narrowly to the general wills of the greatest number.[^14]

The passage is devastating in its precision. Democracy simultaneously liberates and extinguishes — it breaks the old constraints of class and caste, but replaces them with a new and in some ways more thorough form of intellectual closure. The human mind, having freed itself from the particular wills of aristocratic masters, “binds itself narrowly” to the general will of the majority. Tocqueville is fully aware of the echo of Rousseau, and fully aware of the irony: the general will, that great emancipatory concept, here becomes the instrument of epistemic confinement. His final verdict is unsparing: “Men would not have found the means to live independently; they would only have discovered, a difficult thing, a new face of servitude.”[^15]

It is in the famous final chapters of the second volume that Tocqueville draws these threads together in his portrait of “soft despotism.” The passage is routinely cited in discussions of paternalistic government, but its epistemic dimension is rarely foregrounded. Tocqueville describes a form of power that “does not destroy, it prevents things from being born; it does not tyrannize, it hinders, compromises, enervates, extinguishes, dazes.”[^16] The verbs are revealing. This power does not “destroy” or “tyrannize” — it “prevents things from being born,” it “extinguishes” and “dazes.” These are verbs of epistemic foreclosure, not coercion. What soft despotism eliminates is not freedom of action in any conventional sense but the generative capacity of a society — its ability to produce new ideas, new interpretations, new ways of understanding its own condition.

Two features of Tocqueville’s analysis deserve emphasis. The first is that the epistemic threat he describes is structural, not intentional. No individual or institution sets out to narrow the range of thinkable thought. The narrowing is an emergent consequence of democratic conditions themselves — of equality, of the cognitive authority of the majority, of the displacement of individual judgment by collective opinion.

The second is that Tocqueville was writing in response to a specific transformation in the infrastructure of public communication. The 1830s and 1840s saw the rapid expansion of the mass-circulation press in both France and the United States — the “penny press” that for the first time made newspapers available to a broad democratic public.[^17] Tocqueville does not discuss the press extensively in these chapters, but his analysis is intelligible only against this backdrop. The “immense pressure of the mind of all on the intelligence of each” is not an abstraction; it is mediated and amplified by new communications technologies that, for the first time, made it possible for a single set of framings to reach a genuinely mass audience.

Tocqueville, then, offers something more than a sociology of conformism and something deeper than a warning about majoritarian despotism. He provides the elements — though not the finished form — of a theory of epistemic compression: the process by which the conditions of democratic life, mediated by the infrastructure of mass communication, progressively narrow the range of interpretations, framings, and questions available to citizens. The threat to self-governance he identifies operates not at the level of what citizens are permitted to think, but at the level of what they are equipped to think. This distinction will prove essential in what follows.

Mill and the Ecology of Opinion

If Tocqueville theorizes the demand side of epistemic compression — how democratic citizens come to delegate their cognitive authority to the majority — Mill theorizes the supply side: what happens to a society’s collective capacity for judgment when the conditions under which opinions are formed, tested, and revised become impoverished. The standard reading of Chapter 2 of On Liberty treats it as a defense of individual expression — the ur-text of the liberal free speech tradition, grounding the right to speak in the autonomy and dignity of the speaker.[^18] This reading is not wrong, but it understates the radicalism of what Mill is doing. His argument is not primarily about the rights of individuals. It is about the epistemic needs of the community. The question that organizes the chapter is not “What does the individual have a right to say?” but “What conditions must obtain if a society is to maintain its collective capacity for sound judgment over time?”

Mill had been developing this question long before On Liberty. In his 1836 essay “Civilization,” he offered a remarkably direct analysis of the relationship between the expansion of mass communication and the degradation of public intellect. The essay observes that as the instruments for forming and circulating opinion grow more powerful, they do not — as optimists expected — elevate the quality of public discourse. They tend instead to flatten it. The growth of the reading public and the proliferation of cheap print do not produce a more discerning citizenry; they produce a citizenry more thoroughly saturated by a narrower range of ideas. “The individual becomes so lost in the crowd,” Mill writes, “that though he depends more and more upon opinion, he is apt to be attached less and less by any well-grounded opinion — less and less to have, properly speaking, any opinions of his own.”[^19] The problem is not ignorance. It is a specific form of epistemic dependence in which citizens are surrounded by more information than ever before, yet possess less genuine understanding — because the conditions for forming independent judgment have been eroded by the very institutions that supply them with ready-made conclusions.

Mill was also in direct correspondence with Tocqueville during this period, and their exchange reveals how closely the two thinkers were tracking the same anxiety from different national vantage points. In an 1840 letter responding to the second volume of Democracy in America, Mill wrote to Tocqueville that the great danger of the modern age was not political tyranny but the erosion of independent thought under conditions where the instruments of opinion-formation had grown overwhelmingly powerful.[^20] The letter confirms what the published works suggest: Mill understood himself to be engaged in a shared intellectual project with Tocqueville — the project of theorizing a form of power that operated not through coercion but through the structural transformation of the conditions under which citizens think.

On Liberty, published two decades after “Civilization,” represents the mature and systematic statement of this concern. Chapter 2 advances a series of arguments for the liberty of thought and discussion that are typically summarized as variations on a single theme: truth is best served by open debate.[^21] But this summary flattens what is in fact a carefully sequenced argument about the conditions under which a community maintains its epistemic health. Mill’s central insight is that even true beliefs degrade when they are not regularly tested against serious challenge. A belief held without understanding of the grounds on which it rests becomes what Mill calls “dead dogma” — mechanically repeated, poorly understood, and incapable of guiding action in new circumstances.[^22] “Both teachers and learners go to sleep at their post,” he warns, “as soon as there is no enemy in the field.”[^23] The concern here is not with the silenced individual but with the community’s relationship to its own convictions. A society in which true beliefs circulate as dead dogma has lost the capacity to understand why it believes what it believes.

Mill extends this argument in a direction that has not been sufficiently appreciated. Dissenting opinions, even mistaken ones, serve what we might call an ecological function: they preserve perspectives, framings, and partial insights that the dominant view has absorbed incompletely or not at all. When they are eliminated, the community does not simply lose a wrong opinion. It loses the corrective pressure that the wrong opinion exerted on the right one — the friction that kept the prevailing view honest, precise, and responsive to its own limitations. What Mill describes functions less like a marketplace and more like an ecosystem: a complex environment in which the health of the whole depends on a diversity of elements, including elements that are individually deficient. When the ecosystem is degraded — when dissenting views are eliminated or starved of the conditions in which they can survive — the result is not simply the loss of particular opinions but the slow atrophy of the society’s collective cognitive capacity. The meaning of received doctrine “is in danger of being lost, or enfeebled, and deprived of its vital effect on the character and conduct.”[^24]

What emerges from these arguments is not primarily a theory of individual rights but a theory of epistemic infrastructure — an account of the structural conditions that a society must maintain if it is to preserve its collective capacity for sound judgment. Those conditions include, at minimum: the active circulation of competing interpretations; the regular testing of prevailing convictions against the strongest available objections; the preservation of dissenting perspectives even when they are unpopular; and the maintenance of institutional spaces in which intellectual friction is not merely tolerated but actively sustained.

Mill, like Tocqueville, locates the primary danger not in state action but in structural conditions that operate below the threshold of any identifiable act of repression. The “tyranny of prevailing opinion” does not require a censor. It requires only the absence of countervailing pressure — an absence that can be produced as effectively by the sheer homogeneity of available opinion as by the deliberate suppression of dissent. What Mill fears is not persecution in its crude forms but the quiet disappearance of intellectual alternatives: not the burning of books but the failure to write them; not the imprisonment of dissenters but the slow erosion of the social conditions under which dissent remains a live possibility.

This concern was inseparable from the material transformation of the press that Mill witnessed over his lifetime. The mid-Victorian period saw a dramatic consolidation of British journalism. The repeal of the so-called “taxes on knowledge” — the advertisement duty in 1853, the stamp duty in 1855, and the paper duty in 1861 — had been championed by liberals as a blow for intellectual freedom, opening the press to new voices and broader participation.[^25] The actual result was more ambiguous. Cheaper production costs enabled the rise of mass-circulation newspapers, but the capital requirements for launching and sustaining a publication at national scale simultaneously concentrated ownership in fewer hands. The Daily Telegraph, founded in 1855, became the first British penny daily and reached a circulation that dwarfed its predecessors; by the 1860s, a small number of large-circulation papers exercised an influence over public opinion that would have been unrecognizable a generation earlier.[^26] Mill does not name these developments in On Liberty, but the essay “Civilization” had already identified the mechanism with uncomfortable clarity: the same technologies that distribute opinion more widely also tend to homogenize it, because the economics of mass communication reward breadth of reach over depth or diversity of perspective. The paradox — more readers, fewer genuinely independent sources of judgment — is precisely the structural condition that On Liberty‘s arguments are designed to address.

Read together, Tocqueville and Mill are theorizing the same phenomenon from complementary directions. Tocqueville traces how democratic equality generates an irresistible gravitational pull toward cognitive uniformity — the “immense pressure of the mind of all on the intelligence of each.” Mill traces what is lost when that uniformity goes unchecked: not merely the rights of individual dissenters, but the epistemic infrastructure on which the community’s collective intelligence depends. Tocqueville describes the force; Mill describes the damage. Both understood — with a clarity that has not been adequately recognized — that self-governance requires not merely the formal liberty to speak and vote, but the maintenance of background epistemic conditions that no account of rights, however generous, is sufficient to guarantee. Neither, however, possessed the conceptual vocabulary to name this form of power precisely. It is to the construction of that vocabulary that I now turn.

Epistemic Domination

Tocqueville and Mill were reaching for a concept that neither quite possessed. Both identified a form of power that operates on the conditions of thought rather than on thought itself — that shapes not what citizens conclude but the epistemic environment within which they reason. Both recognized that this power is more dangerous to self-governance than overt coercion precisely because it is harder to perceive: it does not suppress particular opinions but narrows the range of opinions that a community is equipped to form. Both observed that it is amplified by, and in important respects inseparable from, the material infrastructure through which opinion is produced and circulated. Yet neither developed a precise conceptual vocabulary for naming it. Tocqueville gestured toward it through metaphor — the “formidable circle around thought,” the “immense pressure of the mind of all on the intelligence of each.” Mill theorized its consequences — dead dogma, intellectual atrophy, the slumber of decided opinion — without isolating it as a distinct category of power. The concept I propose here is an attempt to complete what they began.

I call it epistemic domination — a term I adapt from recent work in postcolonial and feminist epistemology, where it has been used to describe the imposition of dominant knowledge systems on marginalized communities.[^27] In that literature, epistemic domination names the process by which colonial or hegemonic epistemic frameworks displace alternative ways of knowing — what Bethwell Ogot has described as the denial of intellectual agency to colonized peoples, and what Kristie Dotson and others have theorized as a structural form of epistemic oppression that goes beyond the interpersonal wrongs identified by Fricker.[^28] I retain the term because it captures something that these scholars have recognized more clearly than the mainstream of political theory: that control over the conditions of knowledge is a distinctive and irreducible form of power. But I redeploy it in a different register. Where the postcolonial usage centers on the displacement of one epistemic tradition by another — Western over indigenous, dominant over subaltern — I use the term to name a structural condition in which a single actor controls the infrastructure through which an entire political community encounters, evaluates, and interprets information, regardless of which epistemic tradition is at stake. The domination I describe is not the triumph of one way of knowing over another. It is the concentration of control over the conditions under which all knowing takes place.

More precisely: epistemic domination, as I use the term here, denotes the capacity of an actor to arbitrarily shape the epistemic conditions — the available information, the operative framings, the range of interpretations that appear plausible, the questions that are treated as worth asking — under which a political community forms its beliefs, preferences, and judgments. The emphasis on capacity is deliberate. Like Pettit’s republican domination, epistemic domination is a structural condition, not an event. It obtains whenever an actor possesses the ability to reshape the epistemic environment at will, whether or not that ability is exercised on any given occasion. A community subject to epistemic domination may, at any particular moment, enjoy a rich and diverse informational environment. The domination consists in the fact that this condition is contingent on the will of another — that the actor who controls the epistemic infrastructure could, if it chose, narrow, distort, or redirect the flow of information, interpretation, and framing on which the community’s judgment depends.

The emphasis on arbitrarily is equally important. Not all shaping of epistemic conditions constitutes domination. Editors exercise judgment about what to publish; teachers select curricula; governments fund some research programs and not others. These activities shape the epistemic environment, but they do so under constraints — professional norms, institutional accountability, democratic authorization, competitive pressures — that limit the arbitrariness of the shaping. Epistemic domination obtains when the shaping is not subject to adequate constraints of this kind: when the actor who controls the epistemic infrastructure is not meaningfully accountable to the community whose epistemic conditions it shapes, and when no institutional mechanism exists through which that community can contest, check, or redirect the shaping.

Four existing bodies of work approach the phenomenon I am describing. Each illuminates an aspect of it, but none captures the whole.

The postcolonial and feminist epistemology literature from which I draw the term comes closest to recognizing epistemic domination as a structural condition rather than an interpersonal wrong.[^29] Irfan Ahmad has usefully emphasized the temporal dimension of epistemic domination — the way in which dominant knowledge systems naturalize particular conceptions of historical time and progress, rendering alternative temporalities unintelligible.[^30] This structural orientation is essential to the concept as I develop it here. But the postcolonial usage is primarily concerned with asymmetries between epistemic communities — with the domination of one tradition of knowledge by another. The form of epistemic domination I identify operates within a single political community and affects all its members, including those whose epistemic traditions are dominant. When a handful of corporations control the infrastructure through which information is encountered and interpreted, the resulting domination is not a matter of which cultural tradition prevails. It is a matter of who controls the background conditions against which all traditions — dominant and marginalized alike — must operate.

The second neighboring concept is Philip Pettit’s republican conception of domination as arbitrary interference.[^31] Pettit’s account has the right structural form: domination is a condition of vulnerability to arbitrary power, not a discrete act of oppression, and it can obtain even when the dominating party is benevolent. But Pettit’s framework is oriented toward interference — toward acts that constrain the choices available to the dominated agent. Epistemic domination does not primarily constrain choices. It shapes the conditions under which choices are conceived. A citizen subject to epistemic domination may face no interference whatsoever in the Pettitian sense: no one restricts her options, penalizes her decisions, or coerces her behavior. What is shaped, rather, is the informational and interpretive environment within which she identifies her options, understands their significance, and forms her preferences among them. This is a form of power that operates upstream of the domain in which Pettit’s domination does its work — not at the point of decision but at the point where the materials for decision are assembled.[^32]

The third neighboring concept is Miranda Fricker’s epistemic injustice, which identifies two forms of wrong done to individuals in their capacity as knowers: testimonial injustice, in which a speaker’s credibility is unfairly deflated due to prejudice, and hermeneutical injustice, in which a gap in collective interpretive resources prevents someone from making sense of their own experience.[^33] Fricker’s framework is illuminating, particularly her recognition that epistemic wrongs can be structural rather than merely interpersonal. But her account is oriented toward injustices suffered by particular knowers — individuals or groups who are disadvantaged in specific epistemic transactions. Epistemic domination, by contrast, is a condition that affects the entire community, including those who benefit from it in the short run. The domination is not a matter of who is believed or whose experience can be articulated. It is a matter of who controls the background conditions against which all believing and articulating takes place.

The fourth neighboring concept is the Marxist and Gramscian tradition of ideological domination — the claim that ruling classes maintain their power in part by shaping the beliefs, values, and interpretive frameworks of subordinate classes.[^34] This tradition captures something essential: that power can operate through the constitution of the taken-for-granted, not merely through force or institutional authority. But ideological domination, in both its classical and Gramscian forms, presupposes a relatively coherent ideological content — a set of beliefs or values that serves the interests of the dominant class and is propagated, deliberately or through structural mechanisms, to the dominated. Epistemic domination need not operate through the imposition of any particular ideology. It can operate through fragmentation as readily as through false consciousness — through the production of confusion, the erosion of shared epistemic standards, the flooding of the informational environment with noise, or the algorithmic amplification of engagement over accuracy. An actor who dominates a community’s epistemic conditions need not persuade that community of anything in particular. It is sufficient to control the infrastructure through which persuasion, inquiry, and interpretation take place.

The concept of epistemic domination thus occupies a distinctive position in the theoretical landscape. What Tocqueville described as the narrowing of “thinkable thought” and Mill theorized as the atrophy of society’s capacity for independent judgment is, I am suggesting, best understood as a problem of domination — of arbitrary, unaccountable control over the epistemic conditions on which self-governance depends.

One feature of this concept deserves special emphasis. Epistemic domination represents a threat to democratic self-governance that is in a critical sense prior to the concerns that occupy most democratic theory. Theories of deliberative democracy presuppose citizens who arrive at deliberation with beliefs, preferences, and interpretive frameworks that are, in some meaningful sense, their own.[^35] Theories of aggregative democracy presuppose that the preferences expressed through voting reflect the authentic judgments of voters.[^36] Theories of representation presuppose that constituents are capable of evaluating the performance of their representatives against some standard of their own devising.[^37] Epistemic domination threatens each of these presuppositions at its root. If the conditions under which citizens form their beliefs, preferences, and interpretive frameworks are themselves subject to arbitrary control by an unaccountable actor, then the outputs of deliberation, aggregation, and representation are compromised at their source — not because any particular stage of the democratic process has been corrupted, but because the epistemic inputs on which every stage depends have been shaped by a power that is neither democratically authorized nor democratically accountable. This is the sense in which democratic theory has been operating with an incomplete account of what self-governance requires: it has attended carefully to the procedures through which collective decisions are made, while largely taking for granted the epistemic conditions that make those procedures meaningful.

The Contemporary Realization

Every communications revolution generates new possibilities for epistemic domination — and new theoretical vocabularies for understanding them. Tocqueville wrote in the shadow of the mass-circulation press; Mill watched the consolidation of Victorian journalism concentrate opinion-formation in fewer hands. Each identified a structural threat to the epistemic conditions of self-governance that the previous generation’s theoretical vocabulary was inadequate to name. We are living through an analogous moment, though the transformation underway differs from its predecessors not merely in scale but in kind.

The difference can be stated precisely. The mass-circulation press that Tocqueville and Mill confronted was a technology of distribution. It determined which opinions, interpretations, and framings reached a broad public, and it concentrated that determination in a relatively small number of editors and proprietors. But it operated on finished epistemic products — articles, editorials, arguments — that were composed by identifiable authors, subject to professional norms, and available for public scrutiny. The epistemic environment was shaped, but the mechanisms of shaping were legible.

The infrastructure controlled by contemporary technology corporations operates at a different level. Companies such as Google and Meta do not merely distribute finished epistemic products to a mass audience. Through the design of search algorithms, recommender systems, and content curation mechanisms, they shape the conditions of epistemic encounter itself: the process by which individuals come to be presented with information, the criteria by which some claims are rendered salient and others invisible, and the framings within which new events are interpreted. The distinction matters because it marks the difference between controlling a channel and controlling an environment. A newspaper editor decides what to print. A search algorithm determines what it is possible to find. A recommender system shapes not merely which opinions a citizen encounters but the sequence, context, and affective framing in which she encounters them — conditions that cognitive science has shown to be at least as consequential for judgment as the propositional content of the opinions themselves.[^38] Shoshana Zuboff’s influential account of “surveillance capitalism” captures important dimensions of this transformation, particularly the extraction of behavioral data and its deployment for purposes of prediction and modification.[^39] But Zuboff’s framework is oriented toward the economic logic of data extraction and the threats it poses to individual autonomy. It does not theorize the specifically political dimension of the problem — the way in which corporate control over epistemic infrastructure undermines the conditions of democratic self-governance as such. The concept of epistemic domination names a political condition, not merely an economic practice.

Three features of this infrastructure make it a qualitatively new site of epistemic domination, rather than simply the latest chapter in the familiar story of media concentration.

The first is opacity. The editorial judgments of a newspaper proprietor are, at least in principle, recoverable. One can read the paper, compare it with rivals, and form a reasonably accurate picture of how the proprietor shapes the epistemic environment. The algorithmic systems that curate search results and populate news feeds are not recoverable in this way. They are proprietary, complex beyond the interpretive capacity of individual users, and frequently beyond the full understanding of the engineers who designed them.[^40] Citizens subject to this form of epistemic shaping cannot, even in principle, identify the mechanisms by which their informational environment has been constituted. The circle drawn around thought is invisible to those inside it. This opacity does not merely make epistemic domination harder to resist; it makes it harder to perceive. Under the conditions Tocqueville described, citizens could at least recognize the social pressure to conform, even if they lacked the resources to withstand it. Under conditions of algorithmic opacity, the shaping of the epistemic environment presents itself not as pressure but as the natural order of available information — as simply what there is to know.

The second is personalization. Mass media, for all its concentrating effects, at least imposed a common epistemic environment. Citizens reading the same newspaper inhabited a shared informational world, even if that world was partial and curated. This commonality had a paradoxical benefit: precisely because the distortion was shared, it was in principle detectable. Algorithmic systems eliminate this possibility by producing individuated epistemic environments — news feeds, search results, and recommendation streams tailored to each user’s inferred preferences and behavioral profile. The result is not a single “formidable circle around thought” but millions of individually drawn circles, each shaped by the same infrastructure yet enclosing different informational worlds.[^41] Mill’s fear that the disappearance of intellectual friction would reduce living truth to dead dogma finds its most efficient realization in recommender systems that maximize engagement by presenting users with increasingly refined variations of what they already believe — precision instruments for producing the “deep slumber of a decided opinion.”

The third is generativity, and it marks the sharpest discontinuity — not only with the press that Tocqueville and Mill confronted, but with the social media platforms and search engines that have dominated discussion of technology and democracy over the past decade. Previous concentrations of communicative power, including the platform-based concentrations that currently preoccupy scholars and regulators, operate on human-produced content. They curate, amplify, or suppress, but the underlying epistemic material is composed by identifiable human agents with their own intentions and commitments. Large language models and generative AI systems introduce a genuinely novel element: the capacity to produce plausible text, argument, and interpretation at scale, without an identifiable author and without the constraints — accountability, reputation, professional norms — that have historically operated as checks on the production of public speech.[^42]

This last feature deserves particular emphasis because it distinguishes the emerging form of epistemic domination from the one that has occupied most critical attention thus far. The epistemic domination exercised through search engines and social media platforms is primarily a domination of selection: it determines which human-produced claims, arguments, and framings are made visible or invisible to which audiences. This is a serious form of power, and the analysis of opacity and personalization applies to it fully. But it remains parasitic on a substrate of human epistemic production. The form of epistemic domination that generative AI makes possible is qualitatively different. It is a domination not merely of selection but of production — the capacity to generate plausible epistemic material at a scale and speed that can flood public discourse, simulate the texture of genuine argument, and erode the distinction between inquiry and fabrication. A corporation that controls both the generation and the curation of the epistemic material on which a political community relies does not merely shape which existing opinions citizens encounter. It shapes what there is to encounter.

Existing regulatory and theoretical frameworks are inadequate to this phenomenon. Antitrust doctrine addresses market concentration, and recent proposals to apply it to technology companies have gained significant traction.[^43] But antitrust has no vocabulary for epistemic concentration. Its remedies — breaking up dominant firms, preventing anticompetitive mergers, imposing interoperability requirements — operate on market structure. A technology conglomerate can be divided into smaller units that collectively exercise the same epistemic domination, because the domination derives not from market share as such but from control over the epistemic infrastructure through which citizens form their judgments.

Rights-based approaches fare no better. The liberal rights tradition offers powerful protections against identifiable acts of interference with individual expression — censorship, prior restraint, penalties for speech. But epistemic domination does not interfere with anyone’s expression. It shapes the background conditions against which expression takes place. A citizen whose epistemic environment has been constituted by algorithmic curation and generative AI has suffered no violation of her rights in any standard sense. She has not been silenced, censored, or coerced. She has been subjected to conditions that compromise her capacity for independent judgment without any of her formally recognized rights being engaged.[^44]

Platform regulation — the most rapidly developing area of policy response — treats technology corporations as media companies: publishers or distributors of content subject to obligations of accuracy, fairness, or transparency.[^45] This framing captures something real. But assimilating the power of AI corporations to the familiar category of media power misses the deeper structural transformation. A media company operates within an epistemic environment that it did not create and does not fully control. A corporation that designs the search algorithms, curates the information feeds, and deploys the generative models through which citizens encounter the world does not operate within the epistemic environment. It constitutes that environment.

What Tocqueville described as the emergent consequence of democratic equality and Mill theorized as the structural decay of intellectual life under conditions of homogeneity has, in the space of two decades, become the designed product of privately controlled infrastructure. The epistemic conditions of self-governance — the diversity of available interpretations, the friction between competing perspectives, the capacity of citizens to form judgments on the basis of an informational environment they can scrutinize and contest — are now contingent on the decisions of a remarkably small number of corporate actors who are neither democratically authorized nor democratically accountable. This is epistemic domination in its most complete contemporary form. The question it poses for democratic theory is not how to regulate a new kind of media company, but how to ensure that the epistemic conditions on which self-governance depends are not subject to the arbitrary will of any actor — public or private.

Conclusion

I have argued that democratic theory has been operating with an incomplete account of what self-governance requires. The tradition has attended carefully to the procedures through which collective decisions are made — to the design of deliberative institutions, the aggregation of preferences, the authorization of representatives — while largely taking for granted the epistemic conditions that make those procedures meaningful. Tocqueville and Mill understood, more clearly than we have generally recognized, that these conditions are neither natural nor self-sustaining. Both theorized a form of power that operates not on what citizens are permitted to think but on what they are equipped to think — a power that narrows the range of available interpretations, erodes the friction on which sound collective judgment depends, and does so without engaging the categories of coercion, censorship, or rights-violation through which political theory has traditionally identified threats to freedom.

The concept of epistemic domination is an attempt to give this form of power a precise name and a precise location in our theoretical vocabulary. It is not reducible to republican domination, epistemic injustice, ideological hegemony, or the postcolonial critique of dominant knowledge systems, though it draws on and learns from each. It identifies a structural condition — the arbitrary, unaccountable control of the epistemic infrastructure on which a political community depends — that is prior to and more fundamental than the procedural questions that have occupied most democratic theory. If the epistemic inputs of democratic life are themselves subject to domination, then no procedural reform, however well designed, can be sufficient to secure self-governance.

This paper has been primarily diagnostic rather than prescriptive, and deliberately so. The construction of institutional responses to epistemic domination — responses that might secure what we could call epistemic non-domination as a condition of democratic life — is a task that exceeds the scope of a single article.[^46] But the shape of such responses can at least be gestured toward. They would need to address not merely the content that circulates within the epistemic environment but the control of the infrastructure itself. They would need to ensure that no single actor — public or private — possesses the arbitrary capacity to reshape the conditions under which citizens form their judgments. They would need, in short, to extend the democratic demand for non-domination from the domain of political decision-making, where it has long been recognized, to the domain of epistemic conditions, where it has not. What Tocqueville and Mill understood, and what we have been slow to remember, is that the greatest threats to self-governance are often invisible precisely because they operate on the conditions of thought itself.

[^1]: For an overview of this turn, see [PT corporations piece, Vol. 53, Issue 4 — citation to be completed].

[^2]: Elizabeth Anderson, Private Government: How Employers Rule Our Lives (and Why We Don’t Talk about It) (Princeton: Princeton University Press, 2017).

[^3]: Isabelle Ferreras, Firms as Political Entities: Saving Democracy through Economic Bicameralism (Cambridge: Cambridge University Press, 2017).

[^4]: David Ciepley, “Beyond Public and Private: Toward a Political Theory of the Corporation,” American Political Science Review 107, no. 1 (2013): 139–58.

[^5]: This reading is prominent in constitutional theory and Federalist political thought. See, e.g., the invocations of Tocqueville in discussions of countermajoritarian institutions in Alexander M. Bickel, The Least Dangerous Branch: The Supreme Court at the Bar of Politics (New Haven: Yale University Press, 1962).

[^6]: For representative versions of this reading, see Jon Elster, Alexis de Tocqueville: The First Social Scientist (Cambridge: Cambridge University Press, 2009), 149–55; Larry Siedentop, Tocqueville (Oxford: Oxford University Press, 1994), 67–73.

[^7]: Alexis de Tocqueville, Democracy in America, trans. Harvey C. Mansfield and Delba Winthrop (Chicago: University of Chicago Press, 2000), Volume II, Part 1. All subsequent citations refer to this edition.

[^8]: Tocqueville, Democracy in America, II.1.2, 409.

[^9]: Tocqueville, Democracy in America, II.1.2, 409.

[^10]: Tocqueville, Democracy in America, II.1.2, 409.

[^11]: Tocqueville, Democracy in America, II.1.2, 410.

[^12]: Tocqueville, Democracy in America, I.2.7, 244.

[^13]: Sheldon S. Wolin, Tocqueville Between Two Worlds: The Making of a Political and Theoretical Life (Princeton: Princeton University Press, 2001), especially chapters 9–12.

[^14]: Tocqueville, Democracy in America, II.1.2, 410.

[^15]: Tocqueville, Democracy in America, II.1.2, 411.

[^16]: Tocqueville, Democracy in America, II.4.6, 663.

[^17]: On the transformation of the American press in this period, see Paul Starr, The Creation of the Media: Political Origins of Modern Communications (New York: Basic Books, 2004), 125–52.

[^18]: For a representative treatment, see Frederick Schauer, Free Speech: A Philosophical Enquiry (Cambridge: Cambridge University Press, 1982), 15–34.

[^19]: John Stuart Mill, “Civilization,” in Essays on Politics and Culture, ed. Gertrude Himmelfarb (Garden City, NY: Doubleday, 1962), 51. The essay was first published in the London and Westminster Review in April 1836.

[^20]: Mill to Tocqueville, 1840. The Mill-Tocqueville correspondence is usefully discussed in H. O. Pappé, “Mill and Tocqueville,” Journal of the History of Ideas 25, no. 2 (1964): 217–34. The specific phrasing should be verified against The Collected Works of John Stuart Mill, Vol. XIII, ed. Francis E. Mineka and Dwight N. Lindley (Toronto: University of Toronto Press, 1963).

[^21]: This is the standard pedagogical summary. See, e.g., Jonathan Riley, Mill on Liberty (London: Routledge, 1998), chapter 3.

[^22]: John Stuart Mill, On Liberty, ed. Elizabeth Rapaport (Indianapolis: Hackett, 1978), 34. All subsequent citations refer to this edition.

[^23]: Mill, On Liberty, 38.

[^24]: Mill, On Liberty, 39.

[^25]: On the “taxes on knowledge” and their repeal, see Martin Hewitt, The Dawn of the Cheap Press in Victorian Britain: The End of the ‘Taxes on Knowledge,’ 1849–1869 (London: Bloomsbury, 2014).

[^26]: Aled Jones, Powers of the Press: Newspapers, Power and the Public in Nineteenth-Century England (Aldershot: Scolar Press, 1996), chapters 4–5; see also Stefan Collini, Public Moralists: Political Thought and Intellectual Life in Britain, 1850–1930 (Oxford: Clarendon Press, 1991), chapters 1–2.

[^27]: The term appears with increasing frequency in postcolonial and feminist epistemology. See especially Kristie Dotson, “Conceptualizing Epistemic Oppression,” Social Epistemology 28, no. 2 (2014): 115–38; Bethwell A. Ogot, “Rereading the History and Historiography of Epistemic Domination and Resistance in Africa,” African Studies Review 52, no. 1 (2009): 1–22; and Vrinda Vaditya, “Social Domination and Epistemic Marginalisation: Towards Methodology of the Oppressed,” Social Epistemology 32, no. 4 (2018): 272–85.

[^28]: Dotson, “Conceptualizing Epistemic Oppression,” 115–20; see also Gaile Pohlhaus Jr., “Epistemic Oppression,” in The Oxford Handbook of Feminist Philosophy, ed. Kim Q. Hall and Ásta (Oxford: Oxford University Press, 2021), who recommends “epistemic domination” as the more encompassing term.

[^29]: Kiefer Roberts Harris, “Epistemic Domination,” Thought: A Journal of Philosophy 11, no. 1 (2022): 42–52, develops the concept in a broadly feminist epistemological framework, with attention to the structural conditions under which epistemic agency is compromised.

[^30]: Irfan Ahmad, “The Time of Epistemic Domination,” ReOrient 6, no. 2 (2021): 171–97.

[^31]: Philip Pettit, Republicanism: A Theory of Freedom and Government (Oxford: Oxford University Press, 1997), especially chapters 2–3; see also Pettit, On the People’s Terms: A Republican Theory and Model of Democracy (Cambridge: Cambridge University Press, 2012).

[^32]: The language of “upstream” and “downstream” in relation to preference formation draws on, though is not identical to, Cass Sunstein’s discussion of adaptive preferences in Free Markets and Social Justice (Oxford: Oxford University Press, 1997), 13–31.

[^33]: Miranda Fricker, Epistemic Injustice: Power and the Ethics of Knowing (Oxford: Oxford University Press, 2007).

[^34]: Antonio Gramsci, Selections from the Prison Notebooks, ed. and trans. Quintin Hoare and Geoffrey Nowell Smith (New York: International Publishers, 1971), especially 12–13, 52–55, 195–96. For a useful overview of the development of the concept of hegemony, see Perry Anderson, “The Antinomies of Antonio Gramsci,” New Left Review 100 (1976): 5–78.

[^35]: See, e.g., Jürgen Habermas, Between Facts and Norms: Contributions to a Discourse Theory of Law and Democracy, trans. William Rehg (Cambridge, MA: MIT Press, 1996), 304–8.

[^36]: See, e.g., William H. Riker, Liberalism Against Populism: A Confrontation Between the Theory of Democracy and the Theory of Social Choice (San Francisco: W. H. Freeman, 1982).

[^37]: See, e.g., Hanna Pitkin, The Concept of Representation (Berkeley: University of California Press, 1967), especially chapters 7–8.

[^38]: On the effects of framing, sequence, and context on judgment, the foundational work remains Amos Tversky and Daniel Kahneman, “The Framing of Decisions and the Psychology of Choice,” Science 211, no. 4481 (1981): 453–58. For a recent treatment of algorithmic framing effects specifically, see Cass R. Sunstein, “Algorithms, Correcting Biases,” Social Research 86, no. 2 (2019): 499–511.

[^39]: Shoshana Zuboff, The Age of Surveillance Capitalism: The Fight for a Human Future at the New Frontier of Power (New York: PublicAffairs, 2019). Zuboff’s analysis is invaluable for understanding the economic logic of data extraction, but her central categories — “behavioral surplus,” “prediction products,” “instrumentarian power” — are oriented toward the commodification of experience rather than the political conditions of self-governance. The concept of epistemic domination differs in locating the threat not in what corporations extract from citizens but in what they impose upon the epistemic conditions within which citizens reason and judge.

[^40]: On the opacity of algorithmic systems as a distinctive political problem, see Frank Pasquale, The Black Box Society: The Secret Algorithms That Control Money and Information (Cambridge, MA: Harvard University Press, 2015); and Jenna Burrell, “How the Machine ‘Thinks’: Understanding Opacity in Machine Learning Algorithms,” Big Data & Society 3, no. 1 (2016): 1–12.

[^41]: The fragmentation of shared epistemic environments is discussed in Eli Pariser, The Filter Bubble: What the Internet Is Hiding from You (New York: Penguin, 2011); for a more rigorous empirical treatment, see Eytan Bakshy, Solomon Messing, and Lila A. Adamic, “Exposure to Ideologically Diverse News and Opinion on Facebook,” Science 348, no. 6239 (2015): 1130–32.

[^42]: On the epistemic implications of generative AI, see Regina Rini, “Deepfakes and the Epistemic Backstop,” Philosopher’s Imprint 20, no. 24 (2020): 1–16, on the erosion of testimonial norms by synthetic media.

[^43]: See Lina Khan, “Amazon’s Antitrust Paradox,” Yale Law Journal 126, no. 3 (2017): 710–805; and Tim Wu, The Curse of Bigness: Antitrust in the New Gilded Age (New York: Columbia Global Reports, 2018).

[^44]: For a discussion of the limits of rights-based frameworks in addressing structural epistemic conditions, see K. Sabeel Rahman, “The New Utilities: Private Power, Social Infrastructure, and the Revival of the Public Utility Concept,” Cardozo Law Review 39, no. 5 (2018): 1621–89.

[^45]: On platform regulation as media regulation, see Philip Napoli, “Social Media and the Public Interest: Governance of News Platforms in the Realm of Market Failures,” Telecommunications Policy 39, no. 9 (2015): 751–60. The European Union’s Digital Services Act (2022) represents the most ambitious effort in this direction; see Regulation (EU) 2022/2065.

[^46]: I develop the concept of epistemic non-domination and its institutional implications in a companion piece currently in preparation.

Last week, Die Zeit, the German magazine on whose board of publishers I serve, asked some of the world’s leading thinkers to answer a deceptively simple question: Should Europe break with the United States? Here is my answer.

A few weeks ago, Germany, France, the Netherlands, and a host of other European nations sent troops to Greenland to protect the Danish territory against… the United States. Even a year ago, as Donald Trump took office for the second time, it would have been hard to imagine such a turn of events. But the realization that an old political order is breaking apart, and that we are unlikely to return to the relative calm of the postwar years anytime soon, has slowly been dawning on political leaders desperate to keep living in the past.

That practically forces the question of whether Europe should break up with the United States. But natural though it may be to ask that question at this moment, it betrays naivety about the sorry state of the continent—and risks pushing it in the wrong direction.

It is clear that Germany, in particular, can no longer rely on the United States the way it once did. The extent to which European countries outsourced their military security to America in the postwar era relied on the knowledge that, despite all of their differences, both Democratic and Republican presidents would value NATO and tolerate the EU. Given the hostility that Trump—and, crucially, other parts of the rising right—harbor towards NATO and the EU that reliance has become a liability.

But by the same token it is clear that Europe can’t fully break up with the United States. For all of the understandable rage that Europeans have towards the Trump administration over his flirtations with the Kremlin, for example, it is still American arms and intelligence reports that are making it possible for Ukraine to keep defending itself against the Russian invasion. And which paragons of European values should substitute for the United States if Europe decided to make a clean break with Uncle Sam: Narendra Modi in Delhi? Xi Jinping in Beijing? Vladimir Putin in Russia? MBS in Saudi Arabia? The mullahs in Iran?

Subscribe now

The answer to Europe’s weakness is therefore twofold. First, the continent must work with the countries that actually exert power and influence in the world in a less sentimental way. This of course includes being willing to deal with uncomfortable partners even if they don’t fully share Europe’s values. But it also includes trying to sustain the increasingly rocky alliance with the United States, Europe’s most longstanding partner. NATO may well break apart over the next three years; but Europe should do what it can to forestall, not to provoke, that outcome.

Second, Europe must at the same time do everything it can to get back on its own two feet. The last months have made it painfully obvious that a strong yet declining economy combined with an extensive and ever-increasing bureaucracy are not enough to have a real voice in the world. If Europe wants more autonomy, the key is not breaking with Washington; it is being able to provide military security on its own continent, to generate genuine economic growth, and most of all to play a real role in the technologies of the future, from electric cars to artificial intelligence.

Subscribe now

The real obstacles to Europe’s ability to shape its own fate have nothing to do with the people in charge in some faraway capital. They are rooted in the lack of ambition and imagination that has slowly come to characterize contemporary Europe. After a disastrous first half of the 20th century, the model onto which the western part of the continent stumbled in the wake of the Second World War has worked incomparably better. This makes it tempting to stick with it even as it has come to be increasingly ill-adapted to the changing times. But if Europe wants to play a leading role in the world—or simply to stand up for its own values on its own continent—it must recognize that this model has now run out of road. For Europe to thrive in a new historical era, the continent must adopt a new vision for its own future.

Promises of breaking with the United States are as tempting as they are easy. But if Europe doesn’t get its act together first, reducing its reliance on the White House only means increasing its reliance on the Kremlin or the CCP. The only way for Europe to take its fate into its own hands is to awaken from its slumbers and resolve that it no longer wants to be a museal continent.

One of the fundamental problems with populist leaders is that they love to do so many outrageous things that it becomes incredibly hard to separate the grave from the trivial, the wheat from the chaff, the action that is worth pondering at length from the one that will inspire an endless litany of ephemeral takes. But over the course of the dozen or so years of my life which I have now spent thinking about figures like Viktor Orbán and Recep Erdoğan and Narendra Modi and Benjamin Netanyahu, I have developed strong views about what is a distraction and what is actually consequential.

What tends to be a distraction is individual breaches of run-of-the-mill political norms. I fully understand why people are dismayed when populists hurl insults at their enemies, insist on claims that are evidently untrue, or engage in shameless self-flattery. It is certainly important to stay attuned to the ways in which this poisons a political culture, laying the ground for a personality cult and making it easier to demonize the opposition. But when the media obsesses over every tasteless remark made by a political leader, it hands him total control over the political agenda—and many ordinary people wrongly get the impression that objections to him are rooted in the aesthetic sensibilities of the professional-managerial class rather than the actual damage he is doing to the country.

Subscribe now

Far more consequential are breaches of the fundamental political norms that make democracy possible. There are numerous such norms. They include such things as a willingness to respect the decisions of the courts, to appoint key officials on the basis of competence rather than blind loyalty, and to accept the outcome of free and fair elections. But when I look at the countries which have fared the worst under the rule of populists, from Turkey to Venezuela, there are two fundamental norms which stand out as especially important in terms of their impact on ordinary people.

The first of these fundamental norms is that the state should not be able to prosecute political opponents on spurious grounds. The ability of the state to imprison its citizens is one of the most fearsome powers it holds. When the machinery of justice is perverted to serve as a tool of revenge against anybody who stands up to the government, it creates an especially chilling effect on the opposition’s ability to restrain abuses of power. And while the first prosecutions are usually directed against political elites that have little in common with ordinary people, they often broaden to go after ordinary citizens. This is how authoritarian populists have, again and again, used supposedly legal means to transform formal democracies into de facto autocracies.

The second of these fundamental norms is that there must be some limit on the extent to which economic policy is subject to the will and the whim of the central government. For politicians who are subject to the electoral cycle, it is always tempting to juice the economy in such a way that their countries find themselves at the top of a boom in an election year. The easiest way to do that is to ease monetary policy to stimulate the economy. But this also leads to significant inflationary pressures. And when partisan apparatchiks rather than serious economists are setting interest rates, those inflationary pressures can easily turn into unstoppable spirals.

There are many missteps which explain how both Turkey and Venezuela went from flawed-but-real democracies with unequal-but-flourishing economic systems to repressive autocracies that are in the grip of inflationary spirals which are impoverishing much of their population. But the fact that both Hugo Chávez (as well as his successor, Nicolás Maduro) and Erdoğan (as well as his son-in-law, Turkey’s longtime finance minister) repeatedly broke these two fundamental norms is probably more responsible for the disastrous outcomes for ordinary Turks and Venezuelans than any other single step they took.

Subscribe now

That is what makes the news that the Department of Justice is prosecuting Jerome Powell, the Chair of the Federal Reserve, particularly striking. In a crowded news environment, it will be tempting to write this off as one more norm that the Trump White House has decided to break, one more extreme thing about which we should roll our eyes before moving on to discuss yet another unhinged post on Truth Social. But it is far more significant than that.

Powell is only the latest in a litany of political opponents, from James Comey to Letitia James, that Trump’s Department of Justice has prosecuted for evidently partisan reasons. In the case of Powell, the ostensible ground for his prosecution is that he supposedly perjured himself in his testimony regarding the costly renovation of the Fed’s headquarters. But the Trump administration is barely even trying to conceal its true motivation: a battle over the control of America’s monetary policy.

Trump has repeatedly voiced his displeasure with Powell’s reluctance to lower interest rates as far and as fast as he prefers, and has put enormous pressure on him to resign before his statutory term ends this year. In other words, Trump has, in a single political act, doubled down on his willingness to dispense with the two most important guardrails which stand between the freedom and prosperity of the United States and the fear and impoverishment experienced by countries like Turkey and Venezuela.

This is not to say that the same fate necessarily awaits the United States. For now, significant checks and balances remain. Getting grand juries to indict defendants is notoriously easy in America; as one prosecutor famously put it in the 1980s, he could get a grand jury to “indict a ham sandwich.” Securing convictions is thankfully much harder. Indeed, the Trump administration’s previous attempts to go after James Comey and Letitia James—on similarly spurious grounds in the case of the former, on marginally less spurious grounds in the case of the latter—both failed badly.

Thanks to the statutory independence of the Fed, it even seems likely that Powell will be able to serve the rest of his term. More likely than not, monetary policy in the United States will continue to be set by a competent economist until May.

Subscribe now

But none of this diminishes the significance of this step. The desire of the Trump administration to break with our system’s most important guardrails is more evident than ever. If they succeed, the victim will not just be a decent public servant unjustly prosecuted, but rather the livelihood of millions of Americans, including both those who hate and those who love Trump.

Just over a week ago, Trump captured Nicolás Maduro in a spectacular raid on Caracas. While there are good reasons to worry that things won’t actually improve for ordinary people in Venezuela, Maduro was a brutal dictator who undoubtedly deserves to be in chains. That makes the timing of Powell’s indictment bitterly ironic: the man who ordered Maduro’s capture is, in his own country, now emulating the worst sins of the regime that led Venezuela into such a terrible political and economic catastrophe.

There are many reasons to fear that this protest movement could end badly. The regime could once again decide to crack down on its own citizens, killing dozens or hundreds or perhaps thousands of them in the process. (Indeed, according to eyewitness reports, it has already started doing so.) Power might shift from the ailing Ayatollah Khamenei to the Revolutionary Guards, perhaps lifting some restrictions on the country’s women but frustrating the broader political and economic aspirations of the population. Even a transition to democracy need not bring lasting results, as the failed experiments with democratic rule from Egypt to Tunisia prove.

But the sympathies of every single person who believes in freedom and equality and the basic rights of women should be with those courageous millions in Iran. And yet, across the West, there has in the face of these historic protests been a deafening silence.

This silence has been evident in mainstream media outlets, from the British Broadcasting Corporation to National Public Radio, that have been oddly slow to grasp the importance of this moment. Worse, when those outlets did deign to cover the events, they often downplayed the significance of the protests; in a few especially egregious cases, reporters even seemed to harbor sympathies for the country’s brutal regime. (At the outset of the protests, The Guardian even published an op-ed by Abbas Aragchi, Iran’s foreign minister.)

The silence has been even more deafening in the left-wing newspapers and magazines of the anglophone world. On Saturday morning, I searched the principal publications of the American left for any mention of Iran. There was nothing on the websites of The Nation or The New Republic or Jacobin or Slate or even Dissent.

There are some straightforward explanations for why a lot of attention is currently elsewhere. There is good reason for American media outlets to focus on what is happening in Venezuela, and in Minnesota, and more broadly on the various outrages daily perpetrated by the White House. And it is genuinely hard to report on a country that tightly controls foreign journalists and currently has a nationwide internet blackout. At Persuasion, we have been lucky to publish a moving essay by an anonymous Iranian who has written for us before. On the podcast, I have been fortunate to have a deep conversation with Scott Anderson about the country’s revolutions, past and present. But is it really so difficult to have some staff writer type up a report about what is happening in the country, or to source an op-ed by some Iranian in exile about their hopes for their country?

Subscribe now

The silence is far from random; it is a choice. And while I suspect that this choice is not fully conscious, and that the people making that choice haven’t fully spelled out the logic which motivates it, even to themselves, it ultimately goes back to a very simple calculation that (as he pointed out more eloquently than anybody else) has plagued leftist intellectuals ever since the days of George Orwell.

For far too many progressives and leftists, their founding commitment is not to some principle or aspiration for the world. It is to believing that their own countries and societies are at the root of profound evil. This creates in their minds a simple demonology: Anybody who is on “our side” must be bad and anybody who is on the “other side” is presumptively good. As Orwell said about some of the intellectuals of his day, their “real though unacknowledged motive appears to be hatred of western democracy and admiration for totalitarianism.”

It has in the past week not been difficult to find especially harebrained leftists who follow this logic to its bitter end: ones who malign Iranian protesters as hapless agents of imperialism, or for that matter are unwilling to acknowledge that Nicolás Maduro was a terrible dictator. But most are a little more subtle than that. They don’t go all the way toward celebrating Khamenei or Maduro; but nor can they quite bring themselves to hope for the downfall of the regimes they built.

I have, since I started to be politically conscious, been a man of the left. I joined the German Social Democratic Party at the age of 13 and still believe in many of the same ideals as I did then: in international solidarity; in the need for a generous welfare state; in the supreme evil of racial hatred and ethnic cleansing and war. I would love once again to feel part of a mass movement that stands up for those values in a principled manner. But with a left that finds itself unable to cheer on the brave women and men now taking to the streets of Tehran and so many other Iranian cities, I have little in common.

Follow Persuasion on X, Instagram, LinkedIn, and YouTube to keep up with our latest articles, podcasts, and events, as well as updates from excellent writers across our network.

And, to receive pieces like this in your inbox and support our work, subscribe below:

Subscribe now

One of my minor gripes about the last decade is that far too many smart people have spent far too much of their lives trying to make sense of the strange psyche and selfish motivations of one single man. As you know, I try to avoid writing too much about the actions of Donald Trump in these pages, and the many of you who have kindly filled out my survey over the holidays seem to like this approach: the number of people who want me to write about big issues like philosophy, technology and culture is much greater than those who want me to focus on the Trump White House or, for that matter, the state of the Democratic Party. (If you haven’t yet had a chance to fill out the survey, you can do so here.)

So the bar for when I decide to write about Trump, and especially for when I try to offer an interpretation of what makes him tick or a guess as to what he might do next, is especially high. But as I have been reflecting on the daring capture of Nicolás Maduro, and the ignominious betrayal of Venezuela’s opposition movement, over the last days, a hunch I have long harbored about Trump’s foreign policy has slowly consolidated into a lightly-held theory.

We tend to analyze foreign policy in terms of doctrines or ideologies. But from The Art of the Deal to his first primary campaign, Trump has always been more defined by a way of doing things than by a firmly held set of commitments or objectives about what to achieve in the world (other than to look out for Number One). That same mindset can help us make sense of Trump’s actions in Venezuela, and perhaps even to get some kind of handle on what kinds of actions the White House might pursue next.

Subscribe now

From a traditional foreign policy perspective, it makes little sense that America would stage such a daring operation in Venezuela, only to hand the country over to a close ally of the dictator it just captured. But from the vantage point of Trump’s instincts and interests—from the view, that is, of the Trump Playbook rather than some imaginary Trump Doctrine—the events of the past week start to make a little bit of sense.

For anybody who cares about the fate of Venezuela, it is getting clearer by the day that the country’s future is looking about as bleak as it did before Maduro was forcibly relocated to Brooklyn. And while Trump’s evident disregard for the democratic aspirations of the Venezuelan people is a key reason for that, the more profound explanation stems from the fact that the United States now faces two horns of a gnarly dilemma.

One horn is for America to effect regime change by putting boots on the ground. This might actually help to topple a brutal regime that has arguably done more to worsen the prospects of a nation than any other ruling clique in any other country over the past two decades. But it would also involve enormous costs. Going roughly in order of most to least important consideration for the White House, it would be hugely unpopular, both among Trump’s political base and among the general public; potentially get the country stuck in a years-long quagmire, risking the lives of many American soldiers and costing enormous amounts of money; and kill a lot of Venezuelans.

Another option is for America to accept that the Venezuelan regime stays in place essentially unchanged. In this scenario, Trump would keep touting the capture of Nicolás Maduro as a great accomplishment; come to some kind of minimum understanding with the new president, Delcy Rodríguez, that allows both sides to save face; and then turn a blind eye as the country continues to get poorer, many dissidents continue to languish in jail, and new victims of political repression join their ranks. It would have the advantage of avoiding all of the pitfalls of real regime change operations—and the small little downside of doing virtually nothing to lastingly defang the malign influence of the Venezuelan regime, either at home or abroad.

For anybody who primarily cares about outcomes in foreign policy, this suggests that the operation is likely to turn into a terrible failure. And that likely failure makes the course of action chosen by the Trump administration puzzling. Are they so amateurish that they had no plan at all for what to do after Maduro’s capture? Did Trump feel he had to go after Maduro because the latter had taunted him by imitating his dancing? Was the real reason he betrayed María Corina Machado, the leader of the Venezuelan opposition, that she refused to hand him her Nobel Peace Prize?

This way of looking at the matter has the advantage, which a lot of people understandably find to be emotionally satisfying, of portraying the Trump administration in the most venal and incompetent manner imaginable. But it also has the disadvantage of failing to understand what makes the administration tick, and therefore being unable to guide our imagination as to what might come next.

There is, I suspect, a better analytical alternative. For while I don’t believe that Trump has a coherent foreign policy doctrine, it increasingly looks to me as though he has a somewhat predictable playbook. And the trick to understanding that playbook is to recognize the commonalities between the capture of Nicolás Maduro a few days ago and the bombing of Iran a few months ago.

The first element of the Trump Playbook is a set of views about where America should project its force. As I have argued in the past, Trump clearly views the world in terms of spheres of influence. Whereas his predecessors saw themselves as the leaders of the free world, and wanted to project American strength around the globe, Trump is perfectly happy to carve it up into different fiefdoms. That is why he does not mind that Russia feels entitled to impose its will on Eastern Europe, and China increasingly claims dominion over East Asia. No wonder that his administration is deeply enamored with its bizarro version of the Monroe Doctrine. Where President James Monroe once vowed that European powers should desist from colonizing countries within the Western Hemisphere, the newly christened “Donroe Doctrine” holds that America is, by the eternal law of the stronger, entitled to do whatever it wants within its own sphere of influence.

Subscribe now

The second, and more important, element of the Trump Playbook is a set of instincts and tactical rules of thumb about how America should project its force. These rules are relatively easy to summarize: Look for the element of surprise. Deploy America’s superior military strength to overpower the enemy. Design daring missions that risk the lives of few American soldiers and are effectively over by the time anybody learns about them. Make it spectacular, headline-grabbing, attention-commandeering. And don’t worry too much about what happens to the world in the weeks and months after the attack—for the general public will in any case have moved on to the next issue.

The capture of Maduro is hardly the only instance of the Trump Playbook in action. Take the attack on Iran’s nuclear facilities last June: It made clever use of America’s air superiority and its ability to deploy bunker-busting ammunition that weighs 13.5 tons. It probably put no more than a couple of hundred American servicemembers in harm’s way. It delivered beautiful images of explosions. By the time Americans were waking up on the morning of June 22, the mission was already over. Trump characterized it as a spectacular success—and while members of the security community soon suggested that the damage to Iran’s nuclear program had likely been rather limited, the American public had moved on to debating other things by then.

From this vantage point, the capture of Maduro, the purpose of which might otherwise elude a seasoned foreign policy analyst, has been just as big a success. This operation too made use of the enormous skill and might of the American armed forces, from the aircraft carrier parked in the Caribbean to the bravery of the elite special forces. It too took Americans by surprise, with the bulk of the action over by the time most of us woke up to the astonishing news that Maduro was in American hands. It too delivered incredible images that showcase the strength of the administration, such as the remarkable picture of Maduro aboard an American military vessel, sporting a Nike track suit, oversized protective headphones, and what looked like some kind of large sleep mask. And while this action is, sadly, unlikely to prove any more effective in fixing the underlying foreign policy challenges, Trump has probably once again been right to count on the American public to shift its attention to the next topic, from ICE killing an American citizen in Minneapolis to whatever horrors tomorrow’s news may have in store for us.

One question journalists keep asking me when I am giving interviews about Trump’s foreign policy is whether Trump’s base is going to turn on him because of his use of force abroad.

It is certainly possible that Trump will miscalculate and go on some ill-advised military adventure that grows to be deeply unpopular back home, even among his own supporters. As George W. Bush and Barack Obama—both of whom had ascended to the presidency in part on a promise to restrain the use of American power abroad—learned to their chagrin, any president who has access to so formidable a war machine will at times be seduced into using it in irrational ways.

But if the president is clever enough to stick to the Trump Playbook, it is far from clear to me that this is going to happen. The objections to the wars in Iraq and Afghanistan have always been born of self-interest more than of ideology. Members of the MAGA Movement don’t have some principled problem with America using its power abroad; they simply thought that the enormous costs, human and financial, that these wars imposed on America were far too high.

Some of these same voters may also dislike the idea of Trump bombing Iranian nuclear facilities or capturing Venezuelan dictators. But I suspect that most of them are cheering on his actions. He is, in their minds, living up to his promise of being strong and smart; in both cases, Trump showcased the country’s resolve to the world at little cost and with minimal risk to American lives.

Early polling supports this hunch. The Economist just reported that only about half of MAGA supporters supported removing Maduro from office just before the invasion, with most of the rest likely fearing a major operation resembling that in Iraq. But in the wake of the operation, the vast majority are cheering on the operation. Eighty percent expressed a favorable position, with only 9 percent opposing it.1

Recent events in Venezuela support this interpretation of the Trump administration.

Over the past week, Trump has kept claiming that the United States would run, or somehow is running, Venezuela. Even while I remained skeptical that Trump had any desire to put boots on the ground, this raised the specter of an imminent invasion—and made me wonder whether I had really chosen the right frame for understanding the administration’s actions.

But an invasion has become even less likely over the last 24 hours. Venezuela has started to liberate a significant number of political prisoners, one of the few good pieces of news in the country since Maduro’s capture. Trump used this as an occasion to claim that the Venezuelan government was fully cooperating, and to call off a second wave of attacks that had supposedly been planned. It looks increasingly as though he will let Rodríguez stay in power and rule much as before as long as she minimally pretends to play ball.

Even so, I’m well aware that much could change. Trump is impulsive and he is deeply status-conscious. I would never want to rule out the possibility of him getting dragged into a major confrontation somewhere in the world. The Trump Playbook is neither a doctrine nor a rigid ideology. But while it can always be put back on the shelf, it is Trump’s go-to way of operating in foreign policy—and, for now, I find it to be a more useful frame for understanding and predicting his actions than any of the available alternatives.

The question, then, becomes what target Trump is likely to pick for the next operation inspired by his playbook. Invading Canada is far too costly; Canada does have a real army, after all, and the resistance from the local population would likely be fierce and long-lasting.

Subscribe now

Annexing Greenland might be more tempting. Doing so would likely lead to a fundamental break with America’s European partners, and it is clear that Greenlanders themselves would be deeply opposed to such a move. But Greenland does not have a real army defending it; last I checked, a main component of the Danish military presence on the island consisted of a (no-doubt adorable) unit of elite sled dogs. And the Trump administration might wager on the idea that it is much easier to bring 56,000 Greenlanders dispersed across a landmass of 836,000 square miles under control than it was to bring 25 million Iraqis concentrated on 169,000 square miles under control.

Occupying the Panama Canal might be even more tempting. The United States controlled the Canal Zone for most of the twentieth century. Panama does not (at least officially) have an army at all. And the goal of the operation would be to seize an economically valuable asset rather than to rule a country.

Leaders of other countries would be foolish to rule out any such actions. Europeans, in particular, have talked a lot over the past year about how unpredictable the United States has become without truly internalizing the lesson. Do Friedrich Merz and Emmanuel Macron and Ursula von der Leyen and Mette Frederiksen know what they would do if American troops marched into Nuuk tomorrow? I suspect they don’t, and that is a big problem.

But the truth of it is that it’s likely impossible to predict the next move of the Trump administration. For the Trump Playbook thrives on the element of surprise. And the strategic purpose is often less important than the headlines it generates. In that sense, the next big American foreign policy adventure will probably share some of the characteristics often ascribed to the ending of a good story: it will be surprising but, at least in retrospect, feel inevitable.

On the day before it happens, none of us will have predicted it. But after we wake up to hear the news, many of us will say: but of course this is the kind of thing that the Trump administration would come up with!

Follow Persuasion on X, Instagram, LinkedIn, and YouTube to keep up with our latest articles, podcasts, and events, as well as updates from excellent writers across our network.

And, to receive pieces like this in your inbox and support our work, subscribe below:

Subscribe now

For most of American history, higher education was dominated by men. But over the course of the last four decades, male dominance on campus has not just attenuated; largely unnoticed in the broader culture, women have started to outcompete men by a long stretch.

Women began to graduate from high school and college in greater numbers than men in the 1980s, and to obtain a majority of doctoral degrees in the 2000s. Today, girls represent two-thirds of all students who graduate with a GPA in the top 10 percent of their high school class, while boys represent two-thirds of all students who graduate with a GPA in the bottom 10 percent of their class.

The knock-on effect for higher education has been enormous. Undergraduate institutions in the United States currently enroll 8.9 million women, compared to only 6.5 million men. In 2021, men received just 42 percent of all bachelor’s degrees in the United States. The last time the gender imbalance among American undergraduates was similarly stark was at the end of the 1960s, when about three in five college students were male.

These changes are extremely visible on all kinds of campuses. Community colleges, historically black institutions, and big public schools are now heavily female. So, increasingly, are the country’s most selective private universities. Women make up the majority of incoming students at every Ivy League school except Dartmouth.

If they were to admit applicants without considering their sex, the best schools in the country would end up with incoming classes that have an even greater predominance of women than they already do. So, largely unnoticed by the public, they have started to embrace a solution to this supposed problem that is simple, effective, and manifestly unjust: affirmative action for men.

It is impossible to be certain just how blatant current forms of discrimination against female applicants are.

Colleges have no interest in a broader public debate about such a sensitive subject. So they closely guard the kind of data, like the average SAT scores of male and female admits, that would allow the uninitiated to assess how large a bonus they give to male applicants. This lack of transparency should, in and of itself, qualify as a major scandal.

But despite the paucity of publicly accessible data, there is strong reason to believe that the practice is widespread. Admissions rates by gender, which some colleges do publish, for example, usually show higher rates for men than for women. In the 2024-25 cycle, 29,917 women applied to Brown, and 1,309 were offered a slot, for an admission rate of just 4.4 percent. The number of men who applied was far lower: 18,960. Even so, the number of men who were offered a slot was actually somewhat higher, at 1,326, giving men a much higher admission rate of 7 percent.

For another, senior campus bureaucrats have publicly acknowledged that the practice is routine. “Gender parity is something that’s an institutional priority for most private colleges and universities in the United States,” Sara Harberson, a former dean of admissions and financial aid at Franklin & Marshall, recently said. Shayna Medley, a former admissions officer at Brandeis, was even more blunt: “The standards were certainly lower for male students.”

It is, in other words, an open secret in admissions circles that many highly selective universities now put a big thumb on the scale to help their male applicants and artificially deflate how big a share of the undergraduate population is female. As Susan Dominus concludes in a long article about the subject in the New York Times Magazine, “The easiest way for many competitive schools to fix their gender ratios lies in the selection process, at which point admissions officers often informally privilege male applicants.”

Discrimination is often driven by animus or prejudice. But while it is of course impossible to rule out the possibility that some admissions dean somewhere in the country has a bias in favor of male applicants, that likely isn’t the reason for how widespread this practice has become. Rather, universities are motivated by cold calculations of self-interest—and operate in the knowledge that these practices, while morally dubious, are perfectly legal.

Universities have become accustomed to seeing their students as paying customers, whose preferences for everything from lavish meal plans to easy As must be indulged at any cost. And since many prospective students, both male and female, express a strong preference for being on a campus that has rough gender parity, they do their best to accommodate these wishes.

Subscribe now

The stakes for colleges are even higher because they have traditionally prided themselves on the share of accepted students who choose to enroll at their institution. If one school stopped discriminating against women while its peers continued to do so, the gender balance on that particular campus would quickly and significantly shift. If this should in turn prompt some accepted students to enroll elsewhere, it would affect the university’s prized yield rate.

Many readers likely suspect that it must be illegal for universities to discriminate against women in such a blatant fashion. After all, civil rights era legislation prohibits universities from discriminating against students on the basis of their sex in many other contexts. Colleges are, for example, barred from offering disproportionately generous athletic scholarships to male students. Surely, similar constraints must also apply to the admissions process?

Not so. When these civil rights laws were drafted, many of the country’s leading universities were still single-sex. Elite colleges fought tooth and nail to win carve-outs from pending civil rights laws, ensuring that private colleges could continue to admit far more men than women if they so chose. Those same carve-outs now make the new regime of affirmative action for men presumptively legal for private colleges.

The incentives shaping the behavior of universities are real, and the law doesn’t appear to prohibit such practices. But that doesn’t make it morally justifiable for colleges to pick a less qualified male applicant over a more qualified female applicant.

Part of the problem with the current practice is that it is both individually rational and collectively futile. There are simply not enough young men who are motivated and prepared to excel at college. By giving a big leg-up to male applicants, the best colleges in the country can artificially boost the share of male students on their own campuses. But this only means that slightly less exclusive colleges wind up with even more lopsided sex ratios. Rather than solving the growing gender imbalance in higher education as a whole, affirmative action for men merely attenuates the problem at the very best schools while deepening it everywhere else.

Subscribe now

An even bigger part of the problem with the current practice is that it is unethical. A key argument for meritocracy is that it provides an institution that needs to allocate a small number of coveted slots among a large number of applicants with an explanation that it can in good conscience proffer to those whom it must disappoint. Applicants who are turned down from their dream school are always going to be sad. But if the college can truthfully tell them that they were rejected because other applicants had higher GPAs or better SAT scores, they should be able to see that the decision was made on fair criteria. If, by contrast, the college was sufficiently forthright to tell them that they were turned down for the sole reason that they are female, they would, for good reason, feel that the decision was made according to deeply unjust criteria.

Indeed, there is, if you pause to think about it, something fundamentally unseemly about administrators caring so much about the gender balance on campus. It may well be true that many applicants prefer colleges with roughly equal numbers of men and women, in part because they worry about the dating scene on campus. But should it really be the job of admissions officers to make sure that students have a suitable number of potential romantic partners available to them? And might some of the broader problems of academia—such as the extent to which it has become the training ground for a professional-managerial class that is increasingly out of touch with the rest of the country—not even be alleviated if a few college students had reason to venture off campus in search of a potential date once in a while?

There is a positive reason for the feminization of campus: Women have more opportunities than they did in the past, and they are working hard to seize them. There is also a negative reason: A growing share of men is doing poorly, with a substantial minority lacking all purpose or ambition.

The struggles of boys are especially stark at the high school level. According to the American Institute for Boys and Men, they are three times more likely than girls to be expelled from school. The ranks of young men who are not pursuing a degree, not formally employed, and not part of a vocational training program have swelled ominously: The share of such men has grown by about a third since the beginning of the century.

As Richard Reeves has chronicled in recent years, it really is a serious societal problem that boys are falling behind. A growing number of men dropping out isn’t just bad for economic prosperity; it also presages a rise in disease and loneliness, in crime and even deaths of despair. A healthy society needs both boys and girls to thrive.

Subscribe now

Fixing this problem should therefore be a serious political priority. And as Reeves has argued, there are significant reforms that can help boys succeed at higher rates. To name but one example, K-12 schools should consider embracing more forms of active learning, which, according to some prominent researchers in the field, is more suitable for the learning styles of young boys.

But it would be naïve to think that universities can, or should, fix this pipeline problem. If elementary and secondary schools are failing boys to such an extent that some of the most talented men are dropping out, then they are in need of serious reform; but those lost boys aren’t in any way helped by giving a male applicant who is already on a path to a good life an unfair advantage over a better qualified female competitor when they both apply to Harvard.

It is remarkable how little attention has so far been paid to the quiet scandal that is daily taking place in admissions offices around the country.

Part of the explanation for that quiet acquiescence, I think, lies in the fact that the country has for so long been consumed by the fight over race-based affirmative action. Another part of the reason lies in the secrecy with which colleges have instituted these practices, which makes it hard for their victims to recognize the injustices they have suffered. But perhaps the biggest part of the reason lies in a background assumption which has become such a well-entrenched part of American life that we have grown blind to its fundamental strangeness.

Admissions officers at elite schools have long ago convinced themselves that it is their job to socially engineer the “perfect” incoming class. They think they must make sure that each group of freshmen has the “right” racial balance; has somebody who can play the second violin in the university orchestra; includes a good number of students who are likely to make (or, better still, inherit) money they can donate to the university; and, apparently, that it should have a roughly equal ratio of men to women.

This assumption would strike most citizens of other countries as thoroughly odd. In Cambridge and Oxford, professors personally interview applicants with a focus on whether prospective students are likely to excel academically. In China and South Korea, students qualify for places at top universities through national exams that assign them a numerical score. Though none of those universities have a dean of admissions who claims to know the secret formula for how to create the perfect entering class, all of their orchestras somehow seem to find a second violinist who is up to the task.

The search for a “balanced” class amounts to verbal dress-up for rank discrimination. It is wrong when it entails disproportionately rejecting Asian applicants, a practice that widely persists even though it has officially become illegal. And it is just as wrong when it entails disproportionately rejecting women.

Ideally, colleges would recognize how indefensible this practice is of their own accord. If they don’t, the federal government should step in. For while it might sometimes be driven by the best of intentions, the search for the perfectly balanced entering class simply isn’t a good enough reason to discriminate against college applicants on the basis of their sex.

This article was originally published by The Dispatch.

We are at that strange stage in the adoption curve of a revolutionary technology at which two seemingly contradictory things are true at the same time: It has become clear that artificial intelligence will transform the world. And the technology’s immediate impact is still sufficiently small that it just about remains possible to pretend that this won’t be the case.

Nowhere is that more clear than on college campuses.

The vast majority of assignments that were traditionally used to assess—and, more importantly, challenge—students can now easily be outsourced to ChatGPT. This is true for the essay, the most classic assignment students complete in humanities and social science courses. While the best students can still outperform AI models, a combination of technological progress and rampant grade inflation means that students who are content with an A- or perhaps a B+ can safely cheat their way to graduation, even at top universities.

Subscribe now

Something similar holds true for the dominant mode of assessment in many science courses. If anything, AI models that have won top marks in math and science olympiads may be even better at answering the questions contained in problem sets in biology, chemistry, physics or computer sciences classes.

For the most part, professors have responded to this problem by ignoring it.

Some are in outright denial: Many academics and writers have convinced themselves that the real flaws from which chatbots still suffer, such as their tendency to hallucinate, make them far less competent than they actually are at fulfilling a wide range of academic tasks. Even as a significant proportion of their students are submitting AI-generated work, they proudly reassure each other that their courses are too demanding or too humanistic for any machine to understand them.

Others are well-aware of the problem but don’t really know what to do about it. When you suspect that an assignment was completed by AI, it’s very hard to prove that without a confrontation with a student that is certain to be deeply awkward, and may even inspire a formal complaint. And if somehow you do manage to prove that a student has cheated, a long and frustrating bureaucratic process awaits—at the end of which, college administrators may impose an extremely lenient punishment or instruct professors to turn a blind eye.

Alternative forms of assessment may be a way out. But oral interrogations and in-person exams with pen-and-paper have gone out of fashion. They are likely to inspire the ire of students—and in any case require a lot more effort to administer. So even for those who are conscious of the problem, the path of least resistance remains pretending that it doesn’t exist.

An old Soviet joke held that “we pretend to work and they pretend to pay us.” At many colleges today, students merely pretend to do their academic work. For now, most professors still diligently read and comment upon the efforts of ChatGPT; but I suspect that some of them will increasingly decide to outsource their grading to artificial intelligence as well. Campuses will then have reached a new stage of AI decadence: the students pretend to do their assignments, and the professors pretend to grade them.

Denial won’t, however, be an option forever.

Over the next years, the technology will continue to advance. Students who have used AI tools throughout their high school careers will start to arrive on campus. They will be much more skilled at using those tools to complete traditional assignments. They may even become adept at accomplishing genuinely impressive things with the aid of these new tools. The pretense that current forms of assignment are meaningful, or that a college GPA gives employers a meaningful signal about candidate quality, will become untenable. At the same time, some of the basic skills students need to master to truly understand their chosen disciplines—or merely become fully-formed citizens capable of reasoning carefully about the world—will rapidly atrophy.

What should colleges do in response? Is the right path a full embrace of AI tools or a much more radical set of precautions against their widespread use?

The answer, I have increasingly come to think, is: Both.

Anybody who wants to make a genuine contribution in the future, whether in the workplace or even in academic research, will likely need to be fluent in exploiting AI tools. It is thus the task of universities to teach students how to make the most full and creative use of these tools, something many of them currently fail to do.

But even in a world in which AI tools become ever more powerful and widespread, basic skills like clear thinking and strong writing will remain extremely important. And this means that the ease with which AI tools can help students evade ever having to do the hard work that is required to pick up these skills is a genuine threat to their intellectual growth.

Subscribe now

Writing essays may feel like a deeply artificial exercise. And of course we are entering a world in which many of the writing tasks that were once involved in white-collar work, from email to business plans to PowerPoint presentations, can be outsourced to AI just as easily as college assignments. Some will be tempted to conclude that academic skills that were once very important, like the ability to write, have lost their significance.

But this ignores a point I have stressed to my students since long before the release of capable AI models: Writing is thinking. When we talk, it is easy to be vague about ideas we don’t fully comprehend, or to skip a few logical steps. The moment you try to commit an argument to paper, such weaknesses are mercilessly exposed. (Indeed, that is why I don’t really believe that people are being honest with themselves when they claim that they are merely bad writers: for the most part, people who are bad writers are bad at writing because they haven’t taken the effort to think through their own ideas.)

If you want to be a successful artist today, you will probably spend little of your time etching still lifes or producing work that involves challenging problems of perspective; but for the most part, art schools still recognize that mastering those skills is a necessary part of your education. Something similar holds for skills, like writing, that could in theory be outsourced to ChatGPT: While you may not need to call on them directly once you graduate, mastering them will give you the skills and habits that will make you much better able to understand the world and act in it.

This is why universities need to put more emphasis than we currently do on both basic skills and on the use of new technologies. The students best able to make a contribution in the future are those who have both been forced to write plenty of traditional essays without the use of digital tools and who are skilled in using AI to push the boundaries of human knowledge

At the moment, universities are choosing a dangerous middle path: they are persisting with old forms of assessment as though they remained meaningful, without leaning into the potential that comes from calling upon the prodigious powers of AI. Instead, they should bifurcate different forms of assessment: In some courses and contexts, students must be forced to prove their intellectual mettle without the use of digital tools. In other courses and contexts, they should be given the knowledge and the knowhow to use these tools to the best effect.

This is what I myself hope to experiment with when I teach two undergraduate seminars at my university, Johns Hopkins, next term. For the first time since I started teaching at the university, I will administer an in-person exam that students need to complete on pen-and-paper. They will have three hours to write three essays about the broad themes of the course, demonstrating their mastery of the material and their ability to make a compelling argument without any outside assistance. But for their final research paper that is the capstone of any demanding undergraduate seminar, I will encourage them to use AI liberally. While they will need to acknowledge and document the exact ways in which they use AI to assist them with that project, I will assess the final product exclusively on whether it makes a meaningful intellectual contribution.

Subscribe now

The most skilled pilots are both capable of flying a simple Cessna that contains little technology and of handling the myriad gadgets contained in a Boeing 787. Similarly, the best-prepared workers and scholars and citizens of the future will both be capable of thinking for themselves without the help of ChatGPT and of expertlyly calling upon the help of such magician’s apprentices when appropriate. Our task as their teachers is to help them accomplish both.

This essay grew out of a short contribution to a forum on AI and education in The Chronicle of Higher Education.

Writing about the coronation of Napoleon Bonaparte’s nephew, Louis, as the emperor of the French, Karl Marx coined one of his most famous phrases: “Hegel remarks somewhere that all great world-historic facts and personages appear, so to speak, twice. He forgot to add: the first time as tragedy, the second time as farce.”

I have been thinking about this phrase a lot in recent weeks, as it has become increasingly clear what shape the Democrats’ response to Trump 47 is going to take.

The first time Trump won office, the response to his presidency turned out to be a tragedy. There were mass marches. There was the repeated invocation not to “normalize” him. There was a general expectation that his administration would eventually collapse under the weight of its own contradictions. When all of that turned out to be false, many progressives responded by embracing a new and more radical political ideology.

With every passing year of the first Trump administration, the “resistance” to him grew more woke. To many on the left, his ability to win power seemed to vindicate the worst possible interpretation of their own country. Who could possibly argue with the idea that America is a deeply racist country, one whose nature is rotten to the core, when such a boorish demagogue resides in the White House?

Trump’s malign influence over the country also made it hard for moderates on the left to keep in check the extremists in their own ranks. There might, as many of them privately admitted, be much to criticize about the most radical theories and practices that were rapidly spreading in progressive circles, including a taste for cancellation that was ruining the lives of many innocent people and making key institutions deeply dysfunctional. But wasn’t it the duty of every right-thinking person to focus primarily on the threat posed by Trump—and wouldn’t they, if they disobeyed that apparent strategic command, be accused of doing his bidding?

A series of coincidences helped to ensure that the tragedy of the left’s response to Trump’s first presidency did not allow him to win a second consecutive term. Joe Biden, too old to understand where the mood of the party was supposedly going, and therefore less tarnished by the embrace of identitarian ideas than virtually all of his competitors, unexpectedly won the nomination. COVID led to widespread discontent with governments across the democratic world and showcased Trump’s managerial failings. More by luck than by strategic foresight, Democrats eked out a victory in the 2020 presidential elections.

But while the tragic consequences of the Democratic embrace of wokeness were put off, they were not averted. It is one of the reasons they proved incapable of building a sufficiently broad anti-Trump majority to force the Republican Party to moderate if it wanted to be competitive in future elections. It is a big reason for the Biden administration’s missteps on issues like the southern border, as well as for a broader loss of trust in key social institutions—such as universities and the mainstream press—with which the Democratic Party is now deeply associated in the minds of voters. And it helps to explain why so many working-class voters, especially from the minority groups that were supposedly in the bag for Democrats, fled the coalition, helping Trump to win a second presidential term in 2024.

When Trump won reelection, the obvious question was how Democrats would respond to his second administration. Would they learn from the mistakes they made the first time around or fall right back into the same trap?

Optimists argued that Democrats were sure to course-correct. There was a “vibe shift” underway, after all. Exit polls made it unmistakably clear how toxic the party’s stances on cultural issues had become. And some elected officials were even cautiously starting to break rank on a few divisive topics.

Subscribe now

Pessimists, including me, cautioned that the ideological obsession with a particular conception of identity had by now become so deeply entrenched in progressive circles that it would continue to shape the movement’s language and instincts. Even if a few elected officials might course-correct on a few salient issues, the party’s basic framework for how to talk and what to do was unlikely to change. And as Trump committed one outrage after another, any attempt at moderation would once again go out of the window: All of the dynamics that pushed the resistance toward wokeness the first time around would repeat the same feat a second time over.

It is still early days. We are, after all, a mere 10 months into a four-year term. With the Trump administration growing more radical by the day, both the government and the opposition are likely to be fundamentally transformed over the next three years. But so far, I would say that the pessimists have more or less been proven correct—albeit with an ironic twist.

The initial instinct to moderate on key cultural issues has mostly petered out. There is precious little indication of the party learning to speak a different language. Even though faith in the most extreme shibboleths of the woke movement, such as the idea that fusion cuisine is a harmful form of cultural appropriation, seems to have evaporated, Democrats keep semi-apologetically semi-embracing the same practices and talking points. (One of many examples: The Democratic National Committee still performs land acknowledgments at its meetings.)

What is left is a bizarro version of the initial tragedy: a tendency toward radicalization and an inability to keep bad actors in check, shorn of all conviction. In fact, the best description of the emerging Democratic strategy may simply be that the party has decided to emulate Trump, in style if not in substance.

Gavin Newsom, the governor of California who is currently favored by betting markets to become the Democratic Party’s 2028 nominee, is Exhibit A.

After last year’s election, Newsom’s first instinct seemed to consist of a ham-fisted attempt at “moderating” his political position, something he did by cozying up to key proponents and allies of the Trump movement. When he launched a new podcast, his first guests included the right-wing talk radio host Michael Savage, former Trump aide Steve Bannon, and a certain conservative very popular among young voters by the name of… Charlie Kirk.

But while this strategy succeeded in gaining public attention, it also led to massive blowback from the progressive base. Never slow to follow the shifting winds, Newsom quickly corrected course.

Instead of moderating his ideological position, Newsom decided to emulate Trump’s style. He started to echo the president’s unpresidential manner of tweeting, posting all-caps messages that imitated Trump’s distinctive diction. He started to dunk on opponents on social media in the no-holds-bar manner that fueled Trump’s rise. And despite having championed a California law that would impose prison sentences on anybody who spreads AI-created videos portraying real people just a year ago, he himself now posts deep fakes of J.D. Vance and other political opponents.

The recent selection of guests on Newsom’s podcast is a telling sign of his shift: They include resistance-y writers like the historian Heather Cox Richardson; liberal media figures like Jordan Klepper, the co-host of The Daily Show; Democratic Party stalwarts like Connecticut Sen. Chris Murphy; and foul-mouthed firebrands like Texas Rep. Jasmine Crockett. There’s no more trace of anyone who might upset the base.

Newsom is ideologically ambiguous: As a California Democrat, he has taken some very progressive positions. But he is also very much a member of the party’s establishment. Indeed, what’s striking about this moment is that the decision to imitate Trump’s style isn’t contained to one side of the ideological spectrum: Other elected officials who have done so include both avowed progressives like Crockett and relative moderates like J.B. Pritzker, the governor of Illinois.

Subscribe now

Take Abigail Spanberger, a former U.S. representative and the Democratic gubernatorial nominee in Virginia. A CIA veteran firmly rooted in the moderate wing of the Democratic Party, she has voted against strict COVID restrictions and loudly opposed defunding the police. She made headlines in the wake of the 2020 presidential election, which left Democrats with a diminished majority in the House of Representatives, when she let loose on the radicals who had tarnished the party’s brand in an internal caucus call: “We need to not ever use the word ‘socialist’ or ‘socialism’ ever again. … If we are classifying Tuesday as a success … we will get f—ing torn apart in 2022.” But Spanberger, often named as one of a handful of moderates who could one day run for national office, is no longer nearly as willing to distance herself from radicals in 2025.

In October, National Review published shocking text messages by Jay Jones, the Democratic nominee for attorney general of Virginia, in which he openly wished for a Republican colleague in the Virginia House of Representatives to be shot dead: “Three people, two bullets. Gilbert, hitler, and pol pot [sic]. Gilbert gets two bullets to the head,” he wrote. Jones even wished harm upon Gilbert’s children, texting that he is “breeding little fascists.”

Repeatedly pressed on whether Jones still enjoys her support at a Virginia governor’s debate last month, Spanberger proved incapable of either defending or ditching him, reduced to sputtering the same empty consultant-written phraseology over and over. Pressed on whether she still supported Jones, she kept inartfully side-stepping the question: “Importantly, at this point, as we move forward, the voters have this information … and it is up to voters to make an individual choice based on this information.”

Nor does Spanberger seem to have learned from the issue that swing voters found most off-putting in the 2024 presidential election. Asked her stance regarding the participation of biological men in women’s sport in the same debate, Spanberger kept resorting to the same tactic of evasion: “In cases across Virginia, I think it is incumbent upon parents and educators and communicators, in each local community, to make decisions locally … My priority would be to ensure that local communities, importantly parents, and teachers, and educators, are able to work together to meet the unique needs of each school and each community, and that is important, and I say that as the mother of three daughters in Virginia public schools.”

The most striking refusal to engage in basic political hygiene has come in the debate over Graham Platner. Platner is a bundle of contradictions. He is running to be the Democratic nominee for the Senate in Maine, one of the most competitive races expected in 2026, as an unabashed economic populist. Cultivating a compelling image as an everyman straight-talker on social media, he quickly drew endorsements from Sen. Bernie Sanders and other progressive stalwarts. And yet Platner was born to an affluent family, attended a $75,000-a-year boarding school, and did a tour of duty in Afghanistan as a security contractor with the private firm Constellis (better known by its previous name: Blackwater). And he has turned out to have a rather checkered political past, with new revelations about the racist and homophobic comments he has made on Reddit seemingly trickling out every day.

The climax of these revelations came late last month, when old photos emerged showing that he had a large tattoo of a skull-and-bones in the style widely used by the SS on his chest. Platner claims that he did not know what the tattoo symbolized when he got it on a drunken night out in Croatia two decades ago, but a former acquaintance of his reportedly told Jewish Insider that he jokingly referred to it as his “Totenkopf,” the symbol used by the SS units that ran the concentration camps. (Only after news of the tattoo broke did Platner have it covered up.)

Distancing yourself from a political candidate who had a literal Nazi symbol engraved on his body until news of it broke would seem like a pretty minimal test of political decency for Democrats. This is especially the case—these things shouldn’t matter, but of course they do—when he hasn’t even secured the party’s nomination yet, and would likely make it much harder for Democrats to flip a much-needed Senate seat in a winnable race. But motivated by the frustration that Republicans are failing to discipline extremists and cranks in their own ranks, a surprising number of power players in the Democratic Party are failing this test.

Platner’s ideological allies have been especially quick to make excuses for him: “He went through a dark period. He’s not the only one in America who has gone through a dark period,” Sanders said after news of the tattoo broke. But a surprising number of establishment figures have ridden to Platner’s rescue, too. Jon Lovett, a prominent speechwriter for Barack Obama who is now a co-host of Pod Save America, for example, tweeted in an apparent reference to the Platner scandal: “Only perfect candidates off the harvard law conveyor belt pls, highly disciplined, all boxes checked, well liked and humble, absolutely no spiritual connection to having a physical body except for severe IBS, volunteered at a soup kitchen in high school, signs email ‘cheers,’ etc.” (Apparently, there are only two types of Americans: those who have graduated from Harvard Law and those who have Nazi symbols tattooed on their chest.) Meanwhile, the party base seems to be rallying to Platner’s side: In a recent poll, he leads his principal rival for the nomination by 34 points.

Michelle Obama famously summarized the motto that (for the most part) defined the political style of her husband, the Democratic Party’s most successful politician of the 21^st century, by saying that: “When they go low, we go high.”

It is of course understandable that many Democrats are growing impatient with that principle at a time when Trump and his allies are breaking every basic rule of personal and political decency. I can even see the basic logic for why Barack Obama himself has recently recorded videos urging California voters to embrace a blatantly antidemocratic redistricting reform to counteract the effects of an equally antidemocratic effort at gerrymandering that has already taken place in Texas. When your political opponent is proudly embracing every dirty trick in the book—up to and including open calls to prosecute perceived enemies—staying true to your principles can feel like a sucker’s game.

But, in another ironic echo of the first failed wave of resistance to Trump, the problem with this strategy is not only that it is immoral; it is also that it is likely to backfire. Voters who want a shameless bully in the White House already have an impressive specimen available to them; in this respect, at least, it is hard to improve on the original. And as the leaders of Occupy Wall Street used to say in more idealistic times, successful revolutionaries tend to govern in the way they win power: If Democrats should, against the odds, succeed in replacing Trump by copying him, it is far from certain that they would prove any more loyal to the basic principles of the American Republic once they are back in the White House.

Subscribe now

Watching the rise of woke during the first Trump presidency, I felt powerless to stop what looked to me very much like a giant train crash in the making. Watching the rise of Newsom and Platner and Jones—and the excuses made for them by everyone from Sanders to Spanberger—I now feel a similar sense of dread and inevitability.

Once upon a time, the #resistance was woke. Over the next years, it looks set to become soft-woke in content and soft-Trumpy in style. I never thought that I would one day feel nostalgia for the tragic mistakes that helped to cement Trump’s central role in American politics, but this new round of farcical missteps is likely to prove equally self-destructive.

This article originally appeared in The Dispatch.

Over the past month, my mind has kept going back to one of the most trivial, and perhaps also one of the most profound, internet scandals of recent times.

You remember the scene: A camera at a Coldplay concert is showing audience members enjoying the show, with lead singer Chris Martin making a few friendly comments about each fan. The camera cuts to an attractive middle-aged couple in the midst of a cute embrace, with the man holding the woman from behind as they sway to the music. Then the couple spots the Jumbotron, and a perfectly choreographed series of panicked actions unfolds. The woman, shocked, covers her face, and turns away from the camera. The man dives to his left, out of the camera’s view. A younger woman, sitting behind them, and evidently in the know about what is happening, comes into view, the look on her face a poetic mix of horror and glee. “Oh, what?” Martin comments. “Either they’re having an affair or they’re just very shy.”

It didn’t take long for the internet to confirm Martin’s first hypothesis. The man was the CEO of a tech company, someone known in his milieu but far from famous. The woman was the company’s head of HR (or, to cite the correct corporate appellation, its Chief People Officer). Both were promptly tarred-and-feathered in the public sphere, and nearly as promptly resigned from their jobs. The clip of their embrace and its dissolution has been viewed by tens, perhaps by hundreds, of millions of people around the world.

A lot has been written about this incident. But the aspect of it which I found most striking has barely been mentioned: The culture of the second half of the twentieth century was in many ways defined by the worldwide growth of huge cities, and the relative anonymity they afforded—with all its opportunities to escape the constraining norms of smaller towns and villages, but also to engage in actions many would consider immoral. But this culture ended sometime in the first two decades of the twenty-first century. For even if you think that you are hiding in plain sight, with over 60,000 people surrounding you in a massive stadium, the power of social media can now expose you to a massive worldwide audience in a matter of minutes.

In a literal sense, cities are still growing and the world is still urbanizing. In a cultural—or, if you will, spiritual—sense, the urban interlude of human history has come to an end. We all live in a village again.

The Postwar Aberration

I’ve been thinking a lot of late about the ways in which the postwar world, which we took to be the baseline for what developed democracies would look like for the foreseeable future, has turned out to be a brief historic aberration.

Take the economy. North America and Western Europe experienced an extraordinary growth spurt in the decades after 1945. A huge portion of the population gained access to basic medical care like antibiotics, acquired household goods like fridges and washing machines, and got to own a car for the very first time. Even life expectancy rose markedly over the course of a few short decades. Despite the considerable political turbulence of the postwar era, which we have a tendency to underestimate with the benefit of hindsight, this gave the institutions of liberal democracy an extent of “output legitimacy“ that they are unlikely to enjoy again anytime soon.

Similar points could be made about the way in which other factors which helped to create a comparatively stable world in the postwar years have turned out to be artifacts of a very unusual era. The widespread commitment to the basic rules and norms of the democratic game, for example, was usually thought to be a hallmark of mature democracies, and widely expected to last indefinitely. But as the memory of the horrors of Nazism, and the contemporaneous evidence of the dysfunction of communism, faded from view, more and more citizens lost their attachment to liberal democracy; as I chronicled in some of my earliest academic work, a significant share of citizens now has deep skepticism about our political system.

Subscribe now

The postwar years also saw the rise of a relatively orderly public sphere, with people often agreeing about the facts even when they disagreed about their opinions, and gatekeepers working at mainstream media outlets able to define the realm of the reasonable. This too was thought to come downstream from big structural transformations, such as the rise of literacy, the near-universal attainment of a high school degree, and the increase in the college-educated population. And yet that dynamic has turned out to be an artifact of the unusual conditions of the postwar era, with media companies located in a geographic center able to broadcast out to the periphery, but with the technological preconditions for any one individual to share their opinion with millions of others over social media not yet in place.

For the last few days, I’ve been reflecting on yet another way in which a postwar development which we took to presage what the world would look like for the foreseeable future has turned out to be a short aberration: a certain culture of personal freedom facilitated by urban life. For it turns out that the life of the city, with its attendant freedoms from neighborly supervision and collective constraint, was really just a short interlude in the history of humanity. Facilitated by social media, the village has returned with a vengeance—stripped of its warmth, and supercharged by the cruelty of the crowd.

The Cage of Norms

For most of human history, most of the human race lived in roaming bands of hunter-gatherers, or in small sedentary settlements engaged in agriculture. These two forms of early human organization have important differences, which anthropologists have explored at length. But they also have one crucial commonality: Both create small communities of people in which most people know each other, and the actions of each individual are subject to constant social surveillance.

This social surveillance has historically served an important function. Thomas Hobbes, in Leviathan, famously argued that we need a coercive political order to keep the worst angels of human nature in check. When the state isn’t able to monopolize violence, simple conflicts between different individuals will quickly escalate, producing a “war of all against all” that renders life “nasty, brutish, and short.” But as Daron Acemoglu and James Robinson have pointed out in The Narrow Corridor, the best ethnographic evidence suggests that such mayhem is much rarer than Hobbes imagined; in truth, most rural societies in which state authority is absent or very limited are governed by a strict “cage of norms.”

Traditional societies tend to evolve elaborate, and often highly repressive, codes of conduct. Even in the absence of a formal police force or court system, they turn out to be extremely effective at enforcing these moral strictures. Since everybody knows each other, and village life makes it very difficult to conceal anything you do, violations of that moral code are easily discovered. And since people in rural areas traditionally rely on a significant amount of mutual aid, and social death is a fear that millennia of evolution have baked deeply into our DNA, the mechanisms of ostracism are nearly as effective a deterrent to deviance as a modern-day penal code.

Another way of saying this is that for most of human history, most of the human race has lived in fear of cancellation. Rural life had many advantages. At its best, it provided a genuine sense of community; a thick social network of deeply familiar people; and collective help in everything from child-rearing to building a new barn. But the cage of norms that facilitated that cooperation came at a steep price for personal liberty—a fact to which just about any member of an ethnic, religious, or sexual minority group, or indeed any individual with idiosyncratic tastes or opinions, could vividly attest.

The Urban Interlude

It wasn’t primarily a change in moral convictions or a decline in religiosity or even the resistance of those it oppressed which eventually set us free from the cage of norms; it was urbanization.

Urbanization roughly proceeded in four phases. The first and slowest of these phases involved the emergence of a small number of moderately sized towns, which housed a vanishingly small percentage of the overall human population, but played an outsized role in creating the modern world.1 The second phase, which roughly started with the Industrial Revolution, saw the rapid emergence of bigger urban conglomerations, which in virtually every country remained home to a minority of the overall population, but started to erode the hold that the cage of norms enjoyed over national life.2 The third phase, which shaped the first half of the 20th century, saw a rapid growth of cities, with countries like France, Germany and the United States all seeing a majority of their populations living in urban areas for the first time in history, raising the expectation that the relative anonymity of the city would remain the default mode for the indefinite future. The fourth phase, which started around 1950, saw this process of urbanization expand to much poorer parts of the world, with the United Nations estimating that a majority of the total human population has lived in urban centers since sometime in the first decade of the 21st century; the urban future had seemingly gone global.

Subscribe now

Many key elements of postwar culture are downstream from that structural transformation. The sexual liberation movement, for example, had nearly as much to do with the ability not to be branded with a Scarlet Letter as it did with the invention of the pill. (Tellingly, mid-17th century Boston, the setting for Nathaniel Hawthorne’s famous novel, had fewer than 2,500 inhabitants at the time.) Contraceptive methods, though far less reliable, were in widespread use even before the revolutionary invention of the pill; but the ability to engage in sex before marriage also required freedom from the reputational consequences for engaging in such “immoral” acts, which could previously include professional ruin for the man and an inability to find suitable marriage partners for the woman.

Other cultural transformations tell a similar story. Homosexuality, for example, has been prohibited and punished in the vast majority of rural settings. This is a reason why those gays and lesbians lucky enough to enjoy some agency over their lives have long been drawn to the relative anonymity of larger towns and cities. It is why gay life began to thrive over the course of the second half of the twentieth century in cities like San Francisco and London and Cologne and Chengdu. And it is why the gay rights movement developed at this particular juncture in history, with the attitudes of most citizens in developed democracies swinging from unabashed hostility towards homosexuality to widespread acceptance over the course of the late 20th century.

These changes long seemed unstoppable, even inevitable. In the year 2000, most social scientists would likely have argued that the decline of the extent to which communities policed the moral deviance of their members was rooted in attitudinal shifts produced by the process of modernization. According to the eminent sociologist Ronald Inglehart, for example, the second half of the twentieth century was characterized by the rise of “postmaterialist” values. As people became better able to procure the bases of a materially prosperous life, they set their sights on higher ambitions like self-actualization. This was reflected in a liberalization of their attitudes about the world, one that would slowly spread from the most affluent to the great majority.

If all of this was true, then it was also natural to assume that the relative freedom of city life in the second half of the twentieth century would prove resilient to technological change. Perhaps it was just about possible to imagine a regression to “materialist” values if the share of the urban population rapidly declined, if serious material hardship made a comeback, or if a major war focused minds on survival and tribal loyalty. But technological changes that give people a greater ability to express themselves, and to connect with each other, it was widely assumed, would only accelerate the spread of postmaterialist values. The future, Inglehart and most of his contemporaries believed, would be more and more tolerant.

As we now know, that assumption was hopelessly naive.

The Structural Transformation of the Social Media Sphere

The process of urbanization is continuing apace at the beginning of the 21st century. Every year, a greater share of the world’s population lives in cities. Countries like China, which were overwhelmingly rural in living memory, are now predominantly urban.

But there has also been another massive change, which has transformed the culture of our age even more profoundly. In a strange historical irony, the very decade which saw a majority of the world population living in urban areas for the first time in history also saw the invention of a technology which ensures that all of us have now effectively returned to the moral structure of village life: social media.

Subscribe now

Social media has a lot of benefits.3 It also has two major effects which undo the anonymity of city life, and thereby reintroduce the cage of norms under modern conditions. First, it creates the danger that anybody who violates a social norm may suffer social shame on a massive scale. (Interestingly, this is even true when the social norm in question is widely violated and comparatively minor.) And second, it transforms each community with thick social connections into a digital village, allowing for the supervision and enforcement of norms even in the absence of national publicity.

The “Coldplay Couple” is a perfect example of the first dynamic. Marital fidelity is of course an important virtue; but it is one that millions of people across the world breach every day. And at a concert with tens of thousands of attendees, a secret couple must of course expect that many people will “see” them; but, as per the realities of urban life, they may reasonably hope that none of the people who see them will know or care who they are. You can see why the Coldplay couple expected to remain anonymous during their outing, and thereby to avoid the adverse social consequences for their infidelity.

But social media has fundamentally changed the structure of the public sphere, making it dangerous to keep relying on the presumption of anonymity we have inherited from the urban interlude. If some video clip is sufficiently compelling, it can pull two concert attendees out of their relative obscurity, beaming their image across millions of smartphones in a matter of hours. And when their illicit behavior is thus presented to a vast global audience, the relatively common nature of their misdeed does not protect them from being fired, ridiculed, and socially ostracized. In this way, social media facilitates the stochastic enforcement of the cage of norms: While most people can get away with breaching social norms most of the time, everyone must live in fear that their particular transgression—whether serious or trivial—will randomly be brought to the world’s attention.

When we think of the ways in which social media robs us of the anonymity of big city life, our minds turn to famous incidents like the Coldplay couple. But important as those are, this is an optical illusion. Most social media drama plays out on a much more local scale. Every day, thousands of people around the world suffer severe social punishment in their high school, on their university campus, or in some local community, because of social media posts that are seen not by millions but by thousands or hundreds or dozens of people.

For the most part, discipline is now exacted and punishment imposed in the semi-obscurity of our highly diffuse social networks. Just as social media facilitates near-total communication, so too does it facilitate near-total surveillance, a panopticon much more omniscient than those dreamt up by Jeremy Bentham and dreaded by Michel Foucault.

One Cage, Many Rules

Villages have varied widely in the content of the norms that they have enforced on their inhabitants. Most villages are patriarchal, some matriarchal. Most villages strongly impose monogamy and punish premarital sex, some favor different sexual and marital arrangements. Most villages discourage homosexuality and persecute those who engage in it, a few are tolerant of certain forms of same-sex attraction.

When I say that the brief urban interlude is ending, and that we are returning to the moral constraints of village life, I am therefore not predicting that all of the cultural changes of the last two centuries will somehow vanish. The content of the cage of norms can vary widely even as its form stays constant. And while in many parts of the world, from rural India to urban China, social media is often being used to impose a conservative notion of sexual morality, I have always thought invocations of The Handmaid’s Tale to be a deeply misguided metaphor for the United States: the prospect of an America whose most dominant cultural figures are Donald Trump, Taylor Swift, Beyoncé, and LeBron James turning into a theocracy are slim indeed.

Subscribe now

Nor are all of us residents of the global village in which we now find ourselves likely to be subjected to the exact same norms. In the past, customs could vary significantly from one village to the next. Today, the norms whose breach may lead to social death can vary widely from one online community to another.

But what the online cage of norms shares with the one that is offline is the basic mechanism that is used to discipline and punish. The content of the norms to which you are subject are ultimately arbitrary; what remains unchanging is that these norms are deeply coercive, and that any breach of them, real or imagined, has such steep social costs that most people choose to stay in line.

A Bizzarro Global Village Without the Joys of Rural Life

Villages have benefits that can, to some extent, compensate for their vices.

I am writing these lines in the Italian village in which my family has owned a modest home for two decades. When there is a problem with the house in our absence, we have local friends who never hesitate to help. I do not worry about burglars because our neighbors are likely to spot and remember any stranger walking up or down the street. And when I try to buy coffee at the bar that is a hundred yards away, it sometimes takes me half an hour to get there, because I end up chatting with so many people along the way.

One year, a cat somehow snuck into our house as we were departing from the country, and got locked in while we were away. When a passerby heard her pitiful meowing a few days later, a complex rescue operation began. A neighbor had the key to an absent neighbor’s house who had the key to an absent neighbor’s house who had the key to our house. Within half an hour, the poor kitty was freed and fed.

Subscribe now

The revillageification of the world thus poses a double problem: it deprives us of the most important benefits of big city life without affording us the compensating benefits that have traditionally accompanied village life. If a pipe has burst in your home, the people surveilling your behavior online aren’t going to stop the flood. If someone is about to break into your house, the people calling for you to be canceled because you broke the unwritten norms of the chess world or the knitting community aren’t going to call the police. And when you are feeling down, your Facebook friends and TikTok followers sure aren’t going to bump into you on your way to the bar, holding you up with the kind of chitchat that makes it so hard to feel true loneliness in a bustling village.

As for so much of human history, we all live in a village now. But it is a digital village, a bizarro version of the original, hypercharged with the easy judgments and harsh punishments of rural life, and painfully devoid of its joys.

For the most part, I try to avoid writing pieces which respond to the latest big thing in the headlines about what Donald Trump’s second administration is up to.

This is in part out of a desire for some division of labor. There are lots of people who spend their days writing about Trump’s every move and utterance. They diligently chronicle all of the bad things his administration is up to. Often, I don’t feel like I can add something that isn’t widely known to anybody who has any desire to know.

It is also out of a belief that a constant stream of disdain isn’t what’s going to get the country out of the deep crisis in which it finds itself. The mainstream media has spent the past decade expressing its outrage about everything Trump has done wrong. For the most part, that ire was well-deserved. But all that sound and fury has added up to very little political change, with Trump more powerful today than he has ever been before.

Subscribe now

In the end, the only way to defeat demagogues like Trump is at the ballot box. And while politics involves battle, and part of that battle is to define your adversary, the thing that’s most striking about America today isn’t how popular Trump is; it’s how weak and tired and unpopular his opponents are. So on most days, I feel that I can better serve the goal of defeating Trump by being an in-group critic than by being an out-group detractor.

But I would like to think that my reluctance to cry wolf, or to beat up on Trump every single day of the week, buys me some credibility as an arbiter of when something he does is truly dangerous. Recent attempts to undermine the independence of the judicial system and go after his personal enemies unreservedly qualify. Unlike a lot of other stupid or unseemly things the administration has done, they are a five-alarm fire.

One of the most awesome powers of the modern state is its ability to imprison people who have violated the law. This is why the Founding Fathers were so obsessed with procedures and principles meant to protect citizens from arbitrary arrest. As they recognized, no liberty worth its name is possible when a head of government, even one elected by popular vote, can direct the machinery of the state to punish those who have displeased him. And yet, that is precisely what Donald Trump is attempting to do in the case of James Comey.

Comey is a complex figure.

He loves to present himself as a public servant of unimpeachable civic virtue, always faithful to his higher calling of serving the constitution. And yet, he has, over the last decade—in part by virtue of happenstance, and in part by virtue of his own decisions—found himself at the center of one political firestorm after another. In the process, Comey has earned himself the enmity of both the left (who blamed him for Hillary Clinton’s loss after he took the unusual step of writing to Congress about reopening an investigation into her emails days before the 2016 presidential election) and the right (who blamed him for instigating an investigation into spurious links between Trump and the Kremlin which significantly hamstrung his first presidency).

In a sense, this makes Comey a victim of the high moral standards to which he so ostentatiously holds himself. We live in a moment in which the public is much more willing to forgive depravity than hypocrisy. Politicians like Trump get away with tremendous corruption in part because they never claim to be better than you or me. Public servants like Comey, by contrast, inspire so much mistrust in part because they hold themselves out as paragons of virtue. In our cynical age, this raises the immediate suspicion that they can’t possibly be as perfect as they claim—which, the world being the world, and people being people, usually turns out to be at least somewhat true.

Personally, I feel that we should have greater admiration for somebody who holds himself to high moral standards and ultimately falls a little short than for somebody who proudly disdains the idea that there should be moral constraints on how to act at all. But at some gut level, I do understand why hypocrisy feels singularly galling, and even why this inspires in some people an instinctive dislike of Comey.

Here’s the thing though: Comey’s likability, even his moral status, is not what matters about the news that a grand jury in Virginia has just indicted him.

The published indictment of Comey is so brief and cryptic that it is hard to tell what exactly he stands accused of. According to initial news reports, the accusation may be that Comey perjured himself when telling Congress that he had never authorized his then-deputy, Andrew McCabe, to leak to the Wall Street Journal a confidential conversation about the investigation into Hillary Clinton’s emails. If this is true, the main evidence for this accusation seems to come from McCabe himself, and he is unlikely to be regarded as a credible witness by a jury; after all, an independent investigation about his conduct in this very matter concluded that he had “lacked candor, including under oath, on multiple occasions.”

But what makes this case truly concerning is not the substance of it, remarkably thin though it may turn out to be; it is the extraordinary manner in which the President of the United States openly demanded that the government should go after somebody he sees as an enemy, and used executive power to bring about that outcome.

A few days ago, Trump wrote a remarkable message, which explicitly mentioned Comey, to Pam Bondi, the attorney general, on TruthSocial: “Pam: I have reviewed over 30 statements and posts saying that, essentially, same old story as last time, all talk, no action. Nothing is being done. What about Comey, Adam “Shifty” Schiff, Leticia??? … We can’t delay any longer, it’s killing our reputation and credibility. They impeached me twice, and indicted me (5 times!), OVER NOTHING. JUSTICE MUST BE SERVED, NOW!!! President DJT.”

Subscribe now

These weren’t mere words. Over the last weeks and months, Trump has fired multiple prosecutors when they didn’t prove sufficiently willing to do his political bidding. In fact, the prosecutor who was handling the investigation into Comey was apparently fired after determining that it would be inappropriate to charge him in this matter; it is only after Trump appointed a new prosecutor, who had previously served on his own legal team and does not have any experience in federal law enforcement, that the Justice Department decided to indict.

All in all, the extreme degree to which this prosecution comes at the direct behest of Trump is well-nigh comical:

An inexperienced prosecutor loyal to President Trump, in the job for less than a week, filed criminal charges against one of her boss’s most-reviled opponents. She did so not only at Mr. Trump’s direct command, but also against the urging of both her own subordinates and her predecessor, who had just been fired for raising concerns that there was insufficient evidence to indict.

Trump is not the only political actor to abuse the judicial system to go after his opponents. Indeed, it is surely true that some of his anger is occasioned by the way in which he himself suffered a prosecution that was deeply political.

After Trump left office in 2020, there were a number of actions for which he could credibly have been prosecuted. Most obviously, his demand that Brad Raffensperger, the Secretary of State of Georgia, “find” the votes he needed to win the state was deeply immoral and likely illegal. But Fani Willis, the elected District Attorney in Fulton County, badly bungled the case. In the end, the only criminal prosecution that was allowed to proceed to trial concerned a matter that was far less morally weighty and far more legally dubious.

That case, which revolved around Trump paying hush money to Stormy Daniels, a famous porn star, substantially turned on the argument that Trump should have declared the payments as a campaign contribution. It was brought by Alvin Bragg, who had been elected to the position of Manhattan District Attorney by one of the most heavily Democratic-leaning electorates in the country after repeatedly promising during his campaign that he would hold Trump accountable. And it used a previously untested and highly unusual legal construct, according to which Trump’s alleged commission of a misdemeanor under New York law was elevated to a felony on the theory that he was doing so in furtherance of, or to conceal, another crime—apparently a federal election violation that the state never made an attempt to prove.

The degree to which all of these prosecutions have been bungled and mired in partisan interests demonstrates that there are deep structural problems with America’s judicial system. Most notably, the extent to which prosecutors and district attorneys and judges are elected, and therefore need to campaign for their positions, is highly unusual by international standards. Those structural flaws may have been sustainable during less polarized periods of American politics; now they make it hard for citizens to trust that justice is impartial when it comes to the most controversial—and therefore important—cases.

But the danger which now emanates from the White House goes much further than these longstanding structural flaws. The federal government has incomparably greater resources at its disposal than any single district attorney. The FBI can go after supposed suspects in every part of the country. The dangerous profusion of federal laws makes it easy to concoct some charge against virtually anybody, especially if they have served in public office. And prosecutors have historically found it so easy to procure indictments that New York Chief Judge Sol Wachtler famously said that he could, if he so chose, get a grand jury to “indict a ham sandwich.”

For now, the justice system still retains enough independence that Trump may not be able to put his enemies behind bars. Though Comey has now been indicted, scrupulous legal observers like Andrew C. McCarthy, of the National Review, expect that his case may be quickly dismissed, and that he would likely prevail even if the matter does come to a jury trial. But if Trump’s political opponents come to fear that anybody who sufficiently inspires his ire will need to go through the scary and costly process of defending their liberty in federal court, then even the prospect of their eventual acquittal won’t stop political speech in America from being chilled to an astonishing degree.

A key challenge for our political system is that its principles are as obscure, and seemingly even contradictory, as they are important.

We live in a political system which claims to let the people rule. And yet, a core component of it is to grant individuals very far-reaching rights designed to insulate them against the tyranny of the majority, like the freedom of speech and the freedom of worship.

We live in a political system which delegates vast powers to an elected president, allowing him to impose his agenda on the country, and especially the executive branch, for the length of his term in office. And yet, a key component of this system is to ensure that important state agencies, including key parts of the executive branch itself, should act in a manner that is independent of the president’s will and his whim.

Subscribe now

These seemingly contradictory principles are difficult to explain to ordinary citizens. When they are violated, neither the nature of the problem nor the magnitude of the consequences are intuitive. Millions of decent Americans probably greeted the news of Comey’s indictment with a shrug; powerful people, they may have thought to themselves, always play stupid games with each other; who wins or loses any one round doesn’t really affect the rest of the country.

But though the kind of lawlessness pursued by Trump’s second administration always starts by affecting political insiders like Comey, it has a way of spreading throughout the system. If a former Director of the FBI can be prosecuted for his political disloyalty, there’s a real danger that ordinary citizens won’t be far behind. And that’s why the opaque and seemingly convoluted saga of Comey’s indictment should matter to all Americans, left or right, liberal or conservative, who value their liberty.

After half a year out of the public eye, Kamala Harris reemerged… to promote a book. In an appearance this summer on the “Late Show With Stephen Colbert,” Harris announced that her book, 107 Days, would give readers a “personal and candid” tour of last year’s ill-fated presidential campaign. But it rapidly became clear that the book would hardly provide a hard-hitting look at the reasons Donald Trump won back the White House.

When Colbert asked what Harris would have done differently, she responded that “none of us achieves any success without having an incredible team.” Asked whether she could have done more to distance herself from Joe Biden, Harris assured the audience that “I have an incredible amount of respect for him.” By the end of the half-hour interview, even Colbert, about as sympathetic an interviewer as Harris could have hoped for, lost patience. When Harris evaded yet another question by saying that a full answer “requires a lot more time than we have right now,” Colbert turned to the audience and dead-panned: “Are we in a hurry, guys?”

Subscribe now

The book, published this week, confirms that Harris doesn’t have a serious theory as to why she lost. She has become a little more willing to criticize Biden; but rather than grappling with the real failings of the administration in which she served as vice president, she mostly focuses on his supposed lack of loyalty to her. (She was, she writes, “angry and disappointed” after Biden called her in the run-up to her debate with Donald Trump to warn her not to distance herself from him: “I just couldn’t understand why he would call me, right now, and make it all about himself.”) She suggests that she decided against choosing Pete Buttigieg as her running-mate in part because she thought Americans would struggle to accept a gay vice president, writing that he would have been a perfect running mate for her if she was a straight white guy. (“We were already asking a lot of America: to accept a woman, a Black woman, a Black woman married to a Jewish man … It was too big a risk.”)

Other than that, the entire book is custom-tailored to hone in on a single argument, which has the disadvantage of being boring and unconvincing, but the apparent advantage of preserving her ability to run again: Harris insists over and over that she simply did not have enough time to mount a compelling campaign.

Given how disastrous the consequences of Harris’s loss are likely to prove, her lack of introspection about the reasons for it are especially galling. And as it happens, her attempt to deflect any blame from herself is so ham-fisted that it is likely to backfire; the title, the thesis and the tenor of her book practically invite readers, whatever their political orientation, to retort with all of the ways in which she herself is at fault for her defeat.

But it would be unfair to single her out, for in truth she is closer to being the rule than the exception. Other parts of the Democratic Party don’t appear much more keen to discover the causes of their defeat. The party is, for example, about to publish an “autopsy report” on the 2024 election. According to media accounts, it will exclude any consideration of mistakes made by the Harris campaign or even the role played by Joe Biden’s initial insistence on staying in the race.

This has left the Democrats in a strange position. After eight tumultuous months in office, Donald Trump has grown unpopular with the American public. His approval ratings have steadily fallen. He is now about 10 points underwater. But despite this window of opportunity, Democrats are failing to capitalize on their opponent’s weakness.

According to a poll this summer in The Wall Street Journal, 33 percent of voters hold a favorable view of Democrats, compared with 63 percent who hold an unfavorable one—the party’s worst numbers in the history of the poll. The generic ballot, which has historically been a good predictor of results in elections like next year’s midterms, is a little less scary. House Democrats hold a 3-point advantage over House Republicans. But at the same point in the 2018 electoral cycle, when they beat Republicans in a landslide, they held a 7-point advantage.

So what would an honest autopsy reveal? Why are Democrats so unpopular with so many Americans? And how can the party accomplish the one thing that is indispensable if it wants to resist Trump’s escalating attacks on the basic rules and norms of the American Republic—win elections?

Insofar as Democrats have grappled with their defeat at all, they have blamed an unfavorable information landscape, sometimes even claiming that voters soured on Biden’s administration due to “misinformation.” On every metric that mattered, they claim, his term in office was a huge success; if ordinary voters do not recognize the merits of “Bidenomics” or the successes of his foreign policy, it is because of the omnipresent propaganda on X, Fox News, and the Joe Rogan show.

The truth is less flattering. The inflation-adjusted income of average Americans fell over the course of Biden’s term in office, as Jason Furman, a Harvard professor who served as Barack Obama’s chairman of the Council of Economic Advisers, has pointed out. The poverty rate rose. Nor was the crisis at the southern border imaginary. In part because Biden’s White House issued a series of executive orders that reduced enforcement, the number of illegal crossings surged in an unprecedented manner between 2020 and 2023.

Democrats were also harmed by quashing debate about Biden’s evident cognitive decline. His incapacity left the administration without an effective spokesman. It also provoked a crisis of trust in its principal protagonists. That will likely cast a shadow over the party’s future until a new generation of leaders is willing to level with the American public about this collective failing in a—truly—“personal and candid” fashion.

Nor, as her ill-fated interview with Colbert once again demonstrated, was Harris a strong candidate. Back in 2016, Hillary Clinton’s campaign suffered from talking too much about policy detail and too little about a broader vision for America—but at least voters understood the kinds of things that Clinton would seek to do on her first day in office. Harris’s campaign, by contrast, was an exercise in vibes. Harris would, she promised, spread joy; but many voters struggled to understand what she actually wanted to do with the power to which she aspired.

The most important reason for the difficulties Democrats are facing is even more profound: They are out of step with the views and the values of most Americans.

It is at times tempting to think that American voters don’t know what they want. They were angry at Biden’s lax handling of the southern border but quickly turned on Trump’s heavy-handed immigration policies. They mistrust Democrats on economic policy, fearing that they will raise taxes without courting economic growth, and yet they dislike Trump’s “big and beautiful” budget bill.

But there is a coherence beneath the apparent confusion. On both economic and cultural issues, most Americans have views that are both moderate and reasonable. Those views don’t merely amount to splitting the difference between the current positions of Democrats and Republicans; they are a principled expression of moderation.

Economically, most Americans are deeply aspirational. They want their leaders to focus on economic growth and believe in the promise of the market economy. This makes them skeptical of Democrats’ tendency to favor high taxes and introduce onerous regulations. At the same time, most Americans are angry at the ease with which billionaire hedge fund managers and large corporations can evade paying their fair share of tax. They both believe in capitalism and are angry at the privileges enjoyed by self-serving insiders.

Culturally, most Americans despise any form of bigotry, discrimination, or exclusion. They are outraged by racism, appreciate the contributions that immigrations have made to the country, and believe that sexual minorities should be able to live their lives as they choose. This makes them deeply concerned when Trump deports Hispanics to foreign jails without a semblance of due process and throws patriotic service members out of the military because they happen to be trans. But most Americans also suspect that universities, and other important institutions, routinely discriminate against white and Asian American applicants in the name of diversity; that it is important for a nation to control its own borders; and that athletes who have experienced male puberty enjoy an unfair advantage in female sporting competitions.

All of this suggests a path forward for Democrats that is both principled and pragmatic.

Take the economy. When Democrats attack capitalism, they make themselves electorally irrelevant in large swaths of the country they desperately need to vanquish Trumpism. But Democrats can absolutely expand their coalition by combining an appreciation of the free market with a sharp condemnation of the ways in which the current practice of capitalism is rigged. They should fully embrace an aspirational vision centered on economic growth—while full-throatedly condemning corrupt forms of crony capitalism.

Something similar holds true for culture. During the time of Richard Nixon, the “silent majority” of Americans may have been sexist, racist, and homophobic. Today it is not. It is absolutely possible to win electoral majorities if you fight for a tolerant America that opposes racism without degenerating into a zero-sum brand of identity politics; if you celebrate the contributions of immigrants without giving up on enforcing the southern border; and if you stand up for the rights of sexual minorities, such as the trans service members who are being pushed out of the military, without decrying as a bigot anybody who has concerns about the fairness of trans athletes competing in female sporting competitions.

So why didn’t Harris say any of these things in her interview with Colbert? Why, in fact, are so few Democrats anywhere in the country willing to level with the American public?

Political scientists have long constructed models of electoral politics in which parties swiftly and efficiently move toward the positions that are most likely to let them win national elections. But in practice, there are many obstacles that stop parties from responding to the preferences of voters.

Legislators in safe seats may care more about winning primaries than about building nationwide majorities. Activist groups, young staffers, and big donors may be more interested in their own political purity than in winning elections. Elected officials, increasingly stuck in a narrow partisan echo chamber, may fail to understand the preferences of the voters for whose support they are supposed to vie. All of these factors help to explain why Democrats haven’t been able to seize the vacant center of American politics.

Subscribe now

Since the election, there has been some debate about the outsized influence of “The Groups,” the sprawling network of nonprofit organizations, from Indivisible to Poder Latinx, funded by billionaires and progressive foundations that have an outsized influence on the Democratic Party. As critics have pointed out, many elected leaders are hamstrung by a perceived need to fill out an endless stream of questionnaires from such organizations, thereby committing them to honoring the orthodoxies that alienate most other voters. But the more fundamental problem is that the party’s personnel is increasingly drawn from an elite milieu that is likely to agree with those orthodoxies in the first place.

The Democratic Party sees itself as the advocate of the little man. But according to one telling chart, Harris’s electoral coalition was so affluent that it most closely resembled that which voted for Bob Dole, the Republican candidate, in 1996. For all of its lip service to diversity, the personnel that staffs the Democratic Party and its affiliated organizations is even more homogeneous. These staffers are highly likely to have attended a prestigious college, to live on the coasts, and to have spent the bulk of their lives working in politics.

For all these reasons, the energy in the party has for the past decade been with a toxically unpopular form of identity politics. Some senior figures within the party continue to defend these ideas—and the more radical the actions of the Trump administration become, the more loudly they will claim that any course correction amounts to capitulating to the White House. If Democrats decide to dig in their heels, they will likely continue to lose favor with the American public.

Even quietly walking back some of the most extreme ideological excesses of the past decade, as the Harris campaign arguably did in 2024, is unlikely to suffice. To fix the party’s brand, Democrats need to distance themselves from their most unpopular positions—and then formulate a new worldview with enough clarity that voters actually understand what they now stand for. Some leaders have had the courage to criticize the party’s positions on a few hot button issues, like Representative Seth Moulton of Massachusetts and Senator Ruben Gallego of Arizona. But so far they too have failed to give voice to such a broader vision in a principled and steadfast manner.

The irony of the present political moment is that Republicans are also failing to speak for the great majority of Americans.

Trump has pulled off a remarkable electoral feat. Back in 2016, he was seen as helming a coalition of the past. Against the odds, he had somehow managed to mobilize enough old, rural white voters to defeat the Democrats’ supposedly ascendant coalition. But this feat was sure to prove temporary, as indicated by Trump’s inability to win the popular vote. As the American electorate continued to diversify—with demographic groups that have traditionally voted for Democrats growing and those that traditionally voted for Republicans shrinking—the specter of Trumpism was widely expected to be banished from American politics.

Instead, Trump gradually diversified his electoral coalition. Between 2016 and 2024, he significantly lost in vote share among white voters. He compensated by increasing his share of among black, Asian American, and especially Hispanic voters. As many of the Republican Party’s younger leaders have explicitly stated, its future likely lies in turning into a movement of the multiracial working class.

But that is not how Trump has governed so far. His budget may have included a few shrewd concessions to aspirational voters, such as exempting tips from income tax; on the whole, it was an exercise in redistribution from the bottom to the top. So far, the pull of special interest groups and the ideological predilections of big donors count for more than electoral self-interest.

Nor does this administration speak for most voters on cultural issues. A clear majority of Americans—incidentally including most Hispanics—were unhappy with Biden’s permissive handling of the southern border. But only a minority of Americans favor the cruel chase for illegal immigrants on which top administration officials have publicly prided themselves.

Over the last few electoral cycles, America has seemed split into two rigid ideological blocs: Blue America and Red America. But the reality is rather more subtle. On major policy questions, most Americans have reasonable views that aren’t well represented by either party. Far from polarizing into two implacable blocs, Americans are increasingly refusing to identify with either Democrats or Republicans; indeed, the number of independents has steadily risen.

Subscribe now

As Yuval Levin and Ruy Teixeira have argued, this leaves a giant political opening that could allow either party to construct a much broader electoral coalition, one that would likely dominate the next quarter-century of American politics. Both parties have a clear path toward building such an electoral juggernaut by overcoming the special interest groups and ideological constraints that have made them so inflexible. If Democrats want to win elections and put an end to the MAGA movement, they need to be the first to get there.

That means they need a leader who shares the worldview of the majority of Americans, someone who can fight for an inclusive America without sounding woke and take on special interests without talking like a socialist. That candidate will need the courage to confront the constituencies, from activist groups to progressive billionaires, that currently hold outsized sway in the party. A candidate sufficiently inured to the wrath of the ideological enforcers within the party will talk like a normal person—and actually say something worth listening to when they are given an opportunity to speak to millions of people on TV.

Trump is doing what he can to squander the huge opportunity for a political realignment that last year’s victory handed him and his party. It is perfectly possible for Democrats to step into the breach, and set themselves up to win a lasting majority for a more inclusive vision of America. If they fail, they may have only themselves to blame.

A version of this essay was originally published by the Boston Globe.

This month marks the 10th anniversary of the death of somebody whom I only had the privilege of knowing towards the very end of his life, but who nevertheless greatly shaped me: Stanley Hoffmann.

Stanley was a larger-than-life figure on Harvard’s campus, where he taught for over half a century. But he was also something much more profound: the representative of a humanist left deeply steeped in an appreciation for the complexities of the world and the need to reject wanton violence as a means of politics. I have been thinking of him, and missing the clarity of his moral convictions, particularly acutely over the past two weeks.

For this reason, I decided to share an appreciation of Stanley’s work and his character, first published a few days after his death, with you today.

I met Stanley Hoffmann at Harvard when I had only been in graduate school two weeks, and was just about ready to despair of the whole enterprise.

Those first weeks had been spent in something that Harvard’s government department referred to as “math camp.” With the social sciences taking a quantitative turn, the main purpose of the first years of graduate school had become to ensure that students “tool up.” A true political scientist, I learned, pursues general laws, not particular truths. He hopes to derive these laws from columns of numbers, not stumble upon them through a deep immersion in a particular place. Asked by a student how much time he should spend on learning the history and culture of the area in which he hoped to specialize, a senior professor in the department answered without hesitation, “Oh, you can always learn about that kind of stuff later on. I strongly suggest you prioritize the stats sequence.”

Subscribe now

I was happy to brush up on math, keen to learn statistics, and impressed with some of the insights these new methods afforded. But the department’s pre-professional atmosphere depressed me. Before arriving in Cambridge, I had been giddy at the prospect of trying to understand some of the world’s most pressing problems at the world’s finest university. Instead, I was spending my days talking about the importance of advanced statistical skills on the “academic job market.” Within a few days, I was starting to wonder whether I had come to the right place.

Then I got to know Stanley.

If math camp is an image for what much of the academic world has become, Stanley was the embodiment of what it had once been. Nowadays, there is an assumption that one can be an influential intellectual or a serious academic, but not both. Stanley was living proof of this statement’s falsity—and he has been an inimitable role model to me, as he had been to countless others, ever since.

Born to a Jewish mother in Vienna in the fall of 1928, Stanley moved to Paris in the early 1930s, surviving the war in hiding in southern France. “It wasn’t I who chose to study world politics,” he wrote in a memoir about his childhood. “World politics forced themselves on me at a very early age.”

His contributions to our understanding of the world of politics, and of much beyond that, were prodigious. He wrote about international relations with the same fluency as he wrote about French politics and culture, making equally accomplished contributions to our understanding of cross-border duties and the shortcomings of the European Union. He shared his knowledge generously, both with his readers at the New York Review of Books and with the legions of students to which he remained devoted until his last days.

In contrast to the current self-understanding of mainstream political science, Stanley knew many of these truths to be specific rather than universal. Politics, he believed, could not be reduced to eternal laws because it was shaped by the ideas of great thinkers as well as the personalities of great statesmen. Structural factors were, of course, at work in human history, and some of them might surely be captured by numbers—but much of what mattered most was irreducibly cultural, and stubbornly contingent.

Though Stanley could feel like a peripheral figure at Harvard in his later years, his work largely ignored by the department in which he had taught since 1955, the university as a whole will long continue to benefit from his institutional legacy: He founded the Center for European Studies, and was among a small group of professors who created the popular Social Studies concentration.

To anybody who knew him, however, his personal gifts outshone all of these professional accomplishments. His demeanor was calm but passionate, his smile winning yet sly. In a milieu that claims to be egalitarian, but in which status differentials are often palpable in every greeting and gesture, Stanley treated each person he met with the same respect and consideration, from the most famous scholar to the greenest undergrad.

At times, being around Stanley could feel like being around a grandparent. His goodwill was boundless. When he would reach for something in the pockets of his corduroy pants, I half expected him to offer me a Werther’s Original. But this warmth could be deceptive, for it never softened the acuity of his intellectual judgments, nor the breadth of his knowledge. Arthur Goldhammer once recalled how graciously Stanley pointed out a mistake in one of his papers: “You’re probably right that it was published in 1955, but that would make it difficult to explain how I read it at Sciences Po in 1949.”

Subscribe now

But perhaps the most enthralling thing about Stanley’s company was that, as his former colleague Pratap Bhanu Mehta put it, “he had that rare gift of deploying humor and irony for a serious purpose.” Never was this more evident than when Stanley was telling a good story—which was all the time.

The story I remember best was about Charles de Gaulle. After riot police had violently quashed the student occupation of the Sorbonne in May 1968, de Gaulle toured the old university buildings, TV cameras in tow. Suddenly, he stopped to inspect a piece of graffiti that had been scrawled on the wall: “Kill all the assholes!” it demanded. De Gaulle turned to the assembled journalists, who expected an angry outburst, or perhaps a thunderous denunciation. But de Gaulle cracked a bemused smile. “Vaste projet,” a huge undertaking, he remarked, and walked on.

Stanley, it was evident, admired de Gaulle’s joke, even though he had disapproved of many of his other decisions in that fateful spring. A convinced liberal in outlook and temperament, Stanley believed in the possibility of remaining civil even amidst deep disagreement—and knew the art of embracing imperfect political compromises without ever compromising his own moral compass.

In the last years of his life, Stanley began to suffer from dementia. His mind was going, and even for somebody who knew him as peripherally as I did, the slow deterioration of his mental capacities was painful to watch. He began to forget names, to confuse facts, to repeat his favorite quips twice in a row.

But though many dementia patients experience a change in personality as well as a loss in cognitive ability, the remarkable thing about Stanley was that, in illness, he seemed to become ever more himself. His kindness, his curiosity, and his courage shone through even in his increasingly frequent moments of confusion.

One of the last times I saw Stanley was at dinner in a vast new building at Harvard Law School, which he disliked with characteristic good humor. “The dean,” he said with a bemused sneer, which dispensed with any need for further elaboration, “keeps boasting that it contains more office space than the whole of Yale Law School.”

About a hundred people had been invited to discuss a lecture Michael Sandel had given earlier in the day. Asked about same-sex marriage, Sandel said that it is facile to claim, as some of its advocates do, that it doesn’t affect straight people. “Marriage is a social institution. Of course it affects the nature of marriage whether or not some people are excluded from it.”

Everyone in the audience understood that Sandel was no opponent of same-sex marriage. Allowing gays and lesbians to marry did change the nature of marriage, he thought—for the better. Only Stanley, who had never hesitated to call out injustice, whether it was the infatuation of many French intellectuals with the Soviet Union or the connivance of some of his erstwhile colleagues with the Vietnam War, didn’t catch Sandel’s drift. Visibly shaken, he interrupted his friend mid-sentence.

“How can you say such a thing?”

“Say what, Stanley?”

“You are such a decent person, Michael. How can you say that they shouldn’t be allowed to get married if you and I can?” Stanley shook his head in sadness. “I just don’t understand.”

Subscribe now

The moment was bitter, but also sweet. Back when he had his full mental capacities at his disposal, Stanley would never have made such a mistake. But just as his illness was on painful display before many of his friends and colleagues, so was his unwavering decency. In error and old age, he was as principled and courageous a man as any of us can hope to be.

Stanley was the last of a certain breed of intellectual academics, and he knew it all too well. The only times I saw him bitter, or despairing, was when he complained about the direction in which the university to whom he had devoted the bulk of his life was going. He was disappointed that many of his colleagues did not seem to him to be interested in gaining deep knowledge about politics and culture, and lamented their lack of moral purpose. To him, the study of politics had been a vocation, forced upon him by the great disasters of the 20th century. To them, it seemed to be a good career.

Stanley Hoffmann had a full life. Even in his twilight years, he remained surrounded by the boundless affection and gratitude he himself had sowed for decades. And yet, I find myself more distraught by his passing than I had anticipated. Perhaps this is because he taught so much to so many, and yet he lacks for true successors. With Stanley’s passing, the world has lost not only his charm, his kindness, and his knowledge. It has lost a model for what it means to be a scholar, an intellectual, and a mensch.

It has been a long time since I have felt so pessimistic about America.

In the immediate hours after the assassination of Charlie Kirk, a small number of sociopaths celebrated his murder. From numerous posters on Bluesky to the incoming president of the Oxford Union, some people explicitly took joy in seeing someone whom they considered a political enemy killed.

Even so, the response to the assassination of Charlie Kirk was, at first, dominated by widespread revulsion. For a few hours it felt as though much of the country could still agree on such basic values as condemning wanton murder. And some political leaders really did rise to the moment, calling on their followers to lower the temperature, and to see the humanity in those with whom they disagree.

Subscribe now

In a compelling video, Bernie Sanders acknowledged that he “strongly disagreed [with Kirk] on almost every issue.” But he also paid homage to Kirk’s willingness to engage the American public in debate and expressed his heartfelt condolences to his widow. “Political violence,” Sanders insisted, “is political cowardice. It means that you cannot convince people of the correctness of your ideas, and you have to impose them through force.”

Speaking at a press conference with the FBI and local law enforcement, Spencer Cox, the Republican governor of Utah, was just as compelling. He told young Americans that they are “inheriting a country where politics feels like rage.” He then encouraged them to recognize that they now have “an opportunity to build a culture that is very different than what we are suffering through right now—not by pretending differences don’t matter, but by embracing our differences.”

Even as Sanders and Cox called upon the best angels of our nature, the hell machine of social media called upon the worst, feeding and fueling our collective need for rage. Within a span of 48 hours, the loudest voices found excuses for going back to the place in which they are most comfortable: hating anybody who disagrees with them.

Over the past years, horrible acts of political violence have targeted prominent Americans of every political hue. Even so, much of the right has seized upon this moment to insist on a Manichean worldview. Senior figures made clear that they would use Kirk’s killing as a justification for unprecedented forms of repression; likening universities to madrassas, White House Deputy Chief of Staff Stephen Miller said that, “I don’t care how—it could be a RICO charge, a conspiracy charge, conspiracy against the United States, insurrection—but we are going to do what it takes to dismantle the organizations and the entities that are fomenting riots, that are doxing, that are trying to inspire terrorism, and that are committing acts of wanton violence.” Elon Musk was even more explicit in rejecting any semblance of “unity” for the prospect of “victory,” tweeting: “Either we fight back or they will kill us.”

Meanwhile, much of the left has been searching for reasons why they should not need to have sympathy for an outspoken political adversary like Kirk. Viral social media posts blatantly misrepresented Kirk’s words. In one instance, famous writers and other celebrities claimed that Kirk had called for gay people to be stoned; the actual clip shows that Kirk was invoking that infamous verse from Leviticus to explain why politics should not be based on stray lines drawn from the Bible.

In fact, the one thing that nobody seems able to tolerate at this moment is any indication whatsoever that anyone on the other side of the political spectrum may be a somewhat decent person. During his remarkable speech, Cox made a perfectly humane point about our need to grapple with the evil among us. As governor of Utah, he had hoped “if this had to happen here, that it wouldn’t be one of us, that somebody drove from another state, somebody came from another country. Sadly, that prayer was not answered the way I hoped for, just because I thought it would make it easier on us if we could just say, ‘Hey, we don’t do that here.’” On social media, and even in supposedly serious magazines, the rage machine quickly misrepresented these heartfelt words as an expression of hate. A tweet omitting Cox’s mention of “another state,” thereby implying that he had been inciting hatred against immigrants, has to date garnered over 19 million views.

This week is the stuff with which the road to hell is paved.

As scholars of civic conflict have long argued, political violence is always in search of excuses. It is hard to dehumanize others to such an extent that it seems justified to kill them. That’s why the descent into large-scale political violence nearly always starts with a more subtle proposition: conflict entrepreneurs paint their political adversaries as so intent on causing harm that violence is the only realistic means of self-defense.

Subscribe now

We now live in a country in which millions of people on, yes, both sides of our partisan divide have convinced themselves of that dangerous article of faith. And that, more than anything else, makes me fear for our country right now.

Amidst these dark times, it is important to remember that most Americans aren’t sociopaths who hate anyone who disagrees with them. Most Americans do not celebrate political violence even if it hits what they consider the “right” target. But the minority of Americans who are consumed by their longing for chaos and violence are doing what they can to draw the rest of us into their warped logic.

Over the past days, these merchants of rage have been frighteningly successful. If there is any political duty which this darkest of timelines calls forth, it is to resist these bad actors irrespective of what ideological garb they happen to wear.

Political violence descends over the land like a heavy curtain falling at the end of a play.

A shooter wounded Donald Trump, and killed an attendee of his rally, in Butler, Pennsylvania, on July 13, 2024.

A shooter killed Brian Thompson, the CEO of UnitedHealthcare, in midtown Manhattan on December 4, 2024 (and was widely celebrated for this cowardly act).

A shooter killed two attendees of a gala at the Capital Jewish Museum in Washington, DC, on May 21, 2025.

A shooter killed Melissa Hortman, a Minnesota state representative, and her husband, and wounded John Hoffman, a state senator, and his wife, in the suburbs of Champlin, on June 14, 2025.

A shooter killed two children, and injured about twenty others, in an attack on a Catholic Church in Minneapolis on August 27, 2025.

Today, on September 10, 2025, a shooter killed the political commentator Charlie Kirk in an attack at Utah Valley University.

David Foster Wallace was fond of telling a joke about fish and water.

Two young fish encounter an old fish.

“How’s the water?” the old fish asks.

“What the hell is water?” one young fish asks the other, once the old fish is out of hearing.

Our most important freedoms are like water.

Most people in the United States, for example, do not fully understand how remarkable it is that they can freely go about their lives, eating in ordinary restaurants and popping into a local coffee shop for their morning granola, without fear of being kidnapped and ransomed and possibly murdered. But as any moderately rich person in Latin America can attest, that is a remarkable civilizational achievement, one that many countries sorely lack.

The same goes for our ability to engage in political debate, and stand up for our views, without fear for life and limb. In many places, and in many periods of America’s own history, it was physically dangerous to say things that might be deeply unpopular among some of your fellow citizens. If you displeased the wrong person, you might have been arrested by the state or beaten up by a mob or assassinated by your political enemies.

It has over the past fifty years been one of the remarkable achievements of liberal democracies to render that fear relatively remote. Though presidents have always had to be closely protected, and the risk that some individual madman might get it into their head to kill some famous public figure for some idiosyncratic reason could never fully be ruled out, most could speak their minds without any rational fear that they may be courting death.

That is now changing.

It is trite in these moments to call for political unity. But sometimes, in response to a sufficiently horrible event, trite is right.

Charlie Kirk had great gifts as a communicator. His political activism also earned him a lot of enemies. Those enemies will now be tempted to affix “buts” and “howevers” and “at the same times” to the wave of shock elicited by his assassination. Indeed, some Democrats already seem to have fallen into that trap, objecting to a Republican motion for the House of Representatives to observe a moment of silence in Kirk’s honor. But this is a time to “but me no buts”: to close ranks, across the ideological spectrum, without any hint of hemming or hawing.

Defenders of free speech often worry about the heckler’s veto. Some protestors believe that the First Amendment gives them the right to disrupt the speech of those they do not like. But this is a misunderstanding of the logic of free expression. For if hecklers had the right to disrupt any speech, they would quickly come to be in control of what can and cannot be said. While everyone must be free to peacefully protest forms of expression they do not like, they do not have the right to stop such speech from taking place.

I share those concerns over the heckler’s veto. But the danger which now faces the American Republic is deeper still. As violence descends on the land, and the price of engaging in political speech grows and grows, we are increasingly faced with something even scarier, both for the individual and for our political culture: the assassin’s veto.

Violence as a means of politics must always remain unacceptable in a democracy, whether it targets outspoken conservative podcasters or progressive politicians or senior judges or corporate executives. For we all stand to lose when the price of sharing one’s ideas, right or wrong, left or right, radical or milquetoast, becomes incalculable.

Subscribe now

Something has gone badly wrong with the American university.

As recently as a decade ago, a big bipartisan majority of Americans said that they have a lot of trust in higher education. Now, the number is down to about one in three.

The decline in public support for universities has many causes. It is rooted in the widespread perception that they have become ideological monoliths, barely tolerating the expression of any conservative opinions on campus. It has to do with the rapidly growing endowments of the largest universities, which now command a degree of tax-exempt wealth that seems to many people out of all proportion to their pedagogical mission. It has to do with their admissions policies, which judge prospective students on the color of their skin and the degree of their disadvantage, seemingly in defiance of a recent Supreme Court order. And it has to do with the rapidly rising costs of university, with the annual price of attendance now approaching six figures at many selective schools.

The decline in public support for higher education has also had severe consequences. Donald Trump and his allies have clearly identified universities as a significant bastion of left-wing political power, and seem determined to weaken them by any means possible. The resulting assault on top institutions from Columbia to Harvard is deeply illiberal. Whatever the faults of the universities, it obviously chills speech and undermines academic freedom when the federal government tries to exact revenge by doing what it can to weaken the sector. But what’s striking about the Trump administration’s attack on American higher education is not just how brutal and illiberal it is; it’s also how little most Americans seem to care.

Anybody who wants American universities to thrive—as I do—therefore needs to walk and chew gum at the same time. Institutions like Harvard are right to resist attempts to erode their academic freedom by imposing the substantive views of the Trump administration on them. It is therefore good news that a district court judge ruled yesterday that the manner in which the administration canceled federal funding for Harvard violated the university’s First Amendment rights. But rightful resistance to an illiberal president must not serve as an excuse to keep ignoring the genuine problems which have led to such deep popular revulsion for the entire sector.

Subscribe now

A few voices within academia are starting to recognize that. It is, for example, smart that Yale University has instituted a new committee that is tasked with investigating the roots of the university’s fall from public grace, and to investigate possible remedies. But given that such committees usually struggle to go beyond the smallest common denominator, and that this particular committee is exclusively composed of faculty members at the university who by definition have a large stake in preserving the status quo, I am not holding my breath for its findings.

To change the massive shift in public perception of academia, it would, it seems to me, be necessary to take radical steps to change its current nature. And so I want to make a modest proposal for how universities can refocus on their core mission of teaching and research—and become both much more affordable, and much more deeply embedded in the fabric of American society, in the process.

One of the strangest things about an American university education is that it bundles a whole lot of different things together. If you want to take a course in high-level mathematics or listen to the lectures of an accomplished historian of Ming China, you must also buy membership in one of the country’s most lavish gyms; purchase all-you-can-eat meals at breakfast, lunch, and dinner; rent a room in a student dorm even if your parents happen to live a few miles down the road; pay an army of administrators whose jobs range from organizing parties to hiring puppies for you to pet during finals; subsidize student clubs that are devoted to such varied activities as playing Dungeons & Dragons or blind-tasting exclusive wines; and help to pay the lavish salaries of football and waterpolo coaches.

This is a financial problem. Attracting top-flight professors and investing in cutting-edge research would be expensive even in the absence of all of these frills. But one reason why tuition has skyrocketed at leading institutions is that they have turned themselves into four-year luxury vacations that offer a breadth of services with which not even the lavish resorts featured in the White Lotus could compete. If students could attend Harvard or Rice without having to purchase the world’s most exclusive and extended all-in-vacation package, it would be much more affordable to attend these institutions.

Subscribe now

Bundling also helps to turn universities into tightly sealed bubbles at odds with the communities in which they are located. The vast majority of students at top institutions barely interact with the community around them. They don’t have local landlords or neighbors, don’t have locals for roommates, don’t run into locals at the gym, and barely patronize local establishments. The fact that they barely leave campus or interact with somebody outside the university community is a major reason why many campuses have turned into such monochrome hot-house environments.

Bundling is also at the core of the crisis of ideological conformity on campus. Many conservative critics suspect professors of using the classroom to propagandize their views; while that is certainly true for some faculty members, it simply does not describe the behavior of most professors. Faculty members, in turn, like to complain that the true culprits are administrators, who are indeed more likely to be evaluated for the degree of their ideological conformity with the basic tenets of DEI and CRT; but even an army of administrators would struggle to impose ideological conformity on students who were embedded in ordinary communities. Indeed, a lot of the ideological conformity at American universities is simply grounded in the all-encompassing nature of the campus experience: It is vastly harder to disagree with other people in your discussion section if your classmates are also your roommates and your gym buddies and your teammates and your fellow worshippers and your only friends in a hundred mile radius.

Many American readers will probably assume that it is natural for all of these things to go together. But America is in fact highly anomalous in this regard. In most countries in Europe, Asia, and South America, universities are much more closely associated with their core academic functions. When students play sports, they usually do so as a part of private clubs. When they need a place to stay, they rent normal apartments in normal neighborhoods. And when they go to pray, they do so in a local house of worship.

The immersive campus experience characteristic of elite American institutions admittedly has real advantages. As I know from my own undergraduate experience at a campus university in the UK, there is something special about spending one’s formative years surrounded by smart and ambitious young people. If they are given the choice, many college students will, despite its steep cost, still choose to opt into that experience.

But societies in which the undergraduate experience looks very different also turn out to have big advantages. In these countries, a much greater share of students goes to university close to home, making it much easier for them to stay friends with high school buddies or to form new friendships with members of the local community who are not on a similar trajectory towards wealth and power. As a result, the governing elites of these countries tend to be much more rooted in ordinary communities and much more knowledgeable about the lives of people outside the small elite bubble that has come to dominate American life.

Subscribe now

And of course, the material savings also matter greatly. Young people in these societies can access an excellent education without going into huge debt. Graduates from top universities abroad are much less constrained in their career choices, making it possible for them to go into public service or to take entrepreneurial risks like founding a start-up; in the United States, by contrast, a disproportionate share of the brightest minds educated at great cost in the Ivy League goes straight off to Goldman or McKinsey.

Here is how unbundling the American university would work.

When students are accepted to any university, they would henceforth have a choice between (at least) two prices. The first price—let’s call it the White Lotus option—would offer the bundled service which they currently need to purchase in order to enroll. On top of access to their academic coursework, it would provide them with a room in a dorm, with a meal plan, with access to the university gym, and with all of the other amenities to which college students have become accustomed.

The second price—let’s call it the I’m Here to Learn option—would be based solely on the cost of providing a stellar education. It would allow students to complete their undergraduate education, including access to lectures and seminars and laboratories, but exclude the other amenities which have come to be such a big part of the university experience. Students would themselves be responsible for securing housing, for feeding themselves, and for figuring out their leisure activities.1

Are colleges, as nearly all of them claim, actually serious about making their institutions “financially accessible,” about catering to a “diverse set of needs,” and about creating greater “ideological diversity”? Well, here’s the logical first step towards realizing all of these goals.

To be sure, most colleges are very unlikely to heed my advice. Allowing people to opt out of the White Lotus option would likely lead to a reduction in income for universities. It might force them to abandon ongoing plans for ever-more lavish campus buildings. And it may even negatively affect their standing in the influential rankings compiled by U.S. World and News Report.

But if universities refuse to unbundle themselves, the government could easily step in. If the federal government makes funding for neuroscience or cancer research depend on ensuring that faculty members don’t say (supposedly) offensive things, it is violating the First Amendment, and its implicit prohibition on viewpoint discrimination. But courts have long recognized the government’s ability to make federal funding conditional on a broad set of conditions as long as these don’t discriminate against particular viewpoints, and past administrations have already used that power to shape how universities behave in highly intrusive ways. So, unlike the current attacks from the Trump administration, which violate longstanding principles of free speech, such a rule would be perfectly compatible with the First Amendment. To tell a university like Columbia that it needs to put a particular department into academic receivership or to command a university like Harvard to survey the ideological leanings of key staff members violates viewpoint neutrality; to tell both that the federal government will stop subsidizing institutions that compel a student who simply wants to learn to cross-subsidize the school’s water polo team or its puppy social hour does not.

As I have feared since (before) the day Trump got reelected, many of those who are deeply worried about his administration are responding by digging in their heels. Instead of recognizing that mainstream institutions, from media outlets to public health authorities, have made genuine mistakes that made them lose the trust of many ordinary Americans, they are insisting that they have all along been right about everything. This kind of denialism simply isn’t going to work. If they want to regain public support, America’s leading institutions must persuade the public that they are capable of learning from their mistakes—and take action to fix them.

This is especially true for academia. Over the last decades, universities have increasingly strayed from their mission of teaching students and advancing research. If they are to regain the public’s trust, they must find bold and innovative ways to refocus on their core societal purpose. Allowing students to access a world-class education without having to book a four-year holiday in a world-class luxury resort is the right first step on that long journey.

For the last few years, experts have been fighting a battle over the impact of social media on young Americans.

On one side of this battle, there were psychologists like Jonathan Haidt, who has forcefully argued that social media has terrible impacts on young people. As Haidt writes in The Anxious Generation, which has continuously been on the New York Times bestseller list since its release more than a year ago, adolescents have experienced rising rates of anxiety, depression, and self-harm over the past decade. The reason, according to Haidt, lies in a “great rewiring” of childhood, rooted in the rise of social media and the decline of in-person play.

On the other side of this battle are the skeptics who point to our collective tendency to exaggerate the impact of new technologies, and catastrophize their effects. If you go back through history, skeptics like Tyler Cowen have pointed out, you can find people complaining that there is “something wrong with young people these days” at every historical juncture. And even if they were well aware of that tendency, each generation has historically been tempted to insist that there was something about its particular time and place which made that complaint uniquely justified.

In this battle, I have until now chosen to be a non-combatant. While I always found Haidt’s worries to be plausible, I also felt that we didn’t yet have enough evidence to be confident that things were really as bad as he feared.

And then I came across a truly jaw-dropping chart.

That chart, published by Financial Times journalist John Burn-Murdoch and based on his analysis of data from the extensive Understanding America Study, shows how the traits measured by the personality test most widely used in academic psychology have changed over the past decade. The OCEAN test measures five things: openness to experience, conscientiousness, extroversion, agreeableness, and neuroticism. Decades of research have demonstrated that some of these traits are highly predictive of life outcomes; in particular, conscientiousness (“the tendency to be organized, responsible, and hardworking”) predicts everything from greater professional success to a lower likelihood of getting divorced. Extroversion (a tendency to be “outgoing, gregarious, sociable, and openly expressive”), is associated with better mental health, broader social networks, and greater life satisfaction. Meanwhile, neuroticism (understood as a propensity toward anxiety, emotional instability, and negative emotion) is strongly correlated with negative outcomes, such as higher rates of depression, lower life satisfaction, and poorer overall mental health.

With these facts in mind, you will quickly realize why Burn-Murdoch’s chart demonstrates that something very, very concerning has been happening to young people:

What Burn-Murdoch shows is that the traits most strongly predictive of positive outcomes are in sharp decline. Young people, in particular, have become far less conscientious and extroverted over the course of the past decade. Conversely, the trait most strongly associated with negative life outcomes, neuroticism, has sharply increased. To put it bluntly, the average 20-year-old today is less conscientious and more neurotic than 70 percent of all people were just a decade ago.

Personality tests writ large have gotten a bad rap, sometimes for good reason. But there is a huge body of evidence that these metrics, when measured in accordance with decades of scientific studies, really are meaningful. And if you break somewhat nebulous-sounding categories like “conscientiousness” down into their constituent parts—which Burn-Murdoch did in subsequent charts following the one above—it is easy to see why. It is hardly a stretch to imagine that young people who, by their own admission, find it much harder than their elders did at a similar age to “make plans and follow through on them,” or to “persevere with a task until it is finished,” may struggle at many core tasks that life throws at them:

This data doesn’t prove that these shifts in personality are driven by social media. But two details do point in that direction. First, some of the most obvious alternative explanations don’t seem to hold water. Some experts, for example, have argued that the COVID pandemic is to blame for some of the alarming changes in young people. But while this is plausible, most of the worrying changes noted by Burn-Murdoch set in well before 2020. Second, young people spend much more time on social media; and while many of these changes in personality are evident across generations, they turn out to be concentrated precisely among that age group that spends the most time online. All in all, it is hard to imagine what social transformation other than the rise of social media could have caused these changes.

What this data shows is not just that we should be very worried about the future of young people in America; it is that we have fundamentally misunderstood the impact that the internet would have on our lives. By all appearances, the very tools we built to connect us are, in practice, turning us into the worst versions of ourselves.

It is now hard to remember the optimism with which many people greeted the arrival of the digital world. But back in the 1990s and early 2000s, the evangelists of the internet confidently predicted that the internet would, as Thomas Friedman wrote in The Lexus and the Olive Tree, published at the cusp of the new millennium, “weave the world together.”

With the benefit of hindsight, it is easy to make fun of such predictions. But their logic was seemingly compelling. For all of human history until recently, it had been extremely costly and cumbersome for people in different parts of the world to communicate. As late as 1930, Friedman pointed out, a three-minute phone call between London and New York cost about $300. That made it hard for people to develop a greater understanding of each other, or to recognize that they might share all kinds of interests.

By the time Friedman was writing, such a phone call was basically free. It was easy to imagine that, in a world of costless communication, most people would choose to connect with people in faraway locations who are very different from them. Society would, the hope went, grow to be far more cosmopolitan: far more interested in the well-being of people unlike ourselves, and far less likely to prioritize those who share our group identities.

The truth, as we now know, turned out to be very different. Given the opportunity to communicate with anybody they wish, most people are spending their time on social media connecting with people they already know, with those who share their identities, or with those who share the exact same political views. The greater ease of communication was supposed to help the human species transcend its traditional boundaries and expand our collective horizons; instead, it has amplified our tribal instincts and turned every aspect of our politics and culture into a fevered battle between the in-group and the out-group. Early evangelists of the internet conjured up a touching vision of universal human connection. Instead, the technology they rhapsodized has turned us into tribalist creatures giving ever greater importance to our race, our gender, our sexual orientation, and our political convictions.

Even as the first big predictions about the internet were starting to prove wrong, commentators persisted in assuming that they could foresee the effects of new developments in the digital realm. Take the case of online dating.

The first online dating services, like Match.com, started to appear in the 1990s, and they began to lose their social stigma over the course of the 2000s. Even then, it took a while for them to become dominant. It wasn’t until the early 2010s that meeting online became the most common way in which couples formed—but the share of couples who meet online has continued its exponential ascent ever since:

When online dating went mainstream, many commentators assumed that it would lead to a lot more relationships, or at least to a greater number of hookups. One group of American psychologists argued in a 2012 assessment that online dating “offers unprecedented (and remarkably convenient) levels of access to potential partners.” Their main worry was that online dating might make people more likely to play the field indefinitely: “The ready access to a large pool of potential partners can elicit an evaluative, assessment-oriented mindset that leads online daters to objectify potential partners and might even undermine their willingness to commit to one of them.”

The logic that fueled this early assessment is obvious enough. In the real world, a person’s dating pool is restricted to people they physically encounter, and it can take considerable courage to ask somebody out. In theory, online dating services should greatly expand the dating pool, and reduce the fear of rejection. It stands to reason that this should lead to more couples forming, or at least to people having more sexual encounters.

But the impact of online dating has turned out very differently. Young people today are less likely to be in a stable relationship than they were a few decades ago. While nearly 4 in 5 Boomers had a romantic partner for some or all of their teenage years, for example, only about half of Gen Zers had a boyfriend or girlfriend in high school—and there are strong indications that this decline in couple formation persists as young people become adults. According to a 2023 Pew survey, for example, the share of 40-year-olds who have never been married has significantly increased over the course of the past decade.

As those psychologists pointed out during the advent of online dating, one reason why there are so few couples forming today may be that, with endless options, people might find it much harder to commit to one partner. Perhaps people aren’t forming stable bonds because they are hooking up with an endless stream of strangers?

Oddly, that doesn’t seem to be happening either. In fact, it seems today’s young people are much less likely to be sexually active than they were in the past. According to one study, from 2013 to 2015, 9 percent of men aged 23 to 32 hadn’t had sex for the past 12 months; in the latest data, from 2022 to 2023, the share of similarly aged men who had not had a sexual partner for the past 12 months had jumped to 24 percent.

America isn’t just going through a romantic drought; it’s also experiencing a social one. As Derek Thompson has recently shown, Americans have become much less likely to spend time socializing with friends or neighbors over the course of the last two decades. And while this trend holds for Americans of all ages, it is once again especially pronounced among the young: Those aged 15 to 24, for example, now spend a staggering 69 percent less time attending or hosting a social event than similarly aged Americans did two decades ago:

The internet was supposed to make us realize how much we have in common with those who are very different from us. It was supposed to make it easier to find romantic partners and friends. And all of that was supposed to turn us into better versions of ourselves.

The truth has turned out to be radically, and depressingly, different.

Despite making communication virtually costless to the average consumer, the internet has inspired a worldwide return to identity and tribalism. Though it presents us with an endless stream of potential romantic partners, it has left more people single and celibate. While it makes it easy to find people who share the same interests, it has made people far less likely than in the past to socialize “in the real world.” And all of that has somehow led young people to cultivate personality traits, like neuroticism, that make them increasingly ill-equipped to face the world.

That is an astonishingly negative balance sheet. But there is one small ray of hope. Perhaps two decades of data give us enough information to make more accurate predictions about the long-term impact of the internet than we could have done at the dawn of the digital age. But we would do well to remember that we have, so far, gotten the impact of the internet badly wrong at every stage. And we still stand at the cusp of the digital age, with the rise of artificial intelligence likely to transform our world as fundamentally as did the invention of social media. Might we eventually figure out the habits, norms, and regulations needed to soften the remarkably destructive impact that the internet has so far had on society?

Given how badly things are going, that seems unlikely. But I don’t want to rule out that some form of deliverance may be hiding behind the next historical corner. For if there’s one thing that the brief history of the internet has taught us, it’s that we find it nearly impossible to predict the social impact of such revolutionary changes in technology.

A version of this essay originally appeared in The Dispatch.