The debate will happen on Substack Live. Click here to tune in!

I haven’t written for a while because I’ve been in Deep Springs. I returned after a week of being in a remote place far from the news… to see that we are now entering the second month of war with Iran.

It’s a conceit of foreign policy intellectuals to try to infer from statements and events a consistent doctrine underlying an administration’s activities. It should be clear by now that there is no such thing as a Trump doctrine. The administration itself tried to articulate such a doctrine last November when it went through the ritual of producing a National Security Strategy for the second Trump term.

It’s clear today that that strategy document bears no relationship to actual administration foreign policy. The NSS was notable for focusing U.S. strategy on the Western Hemisphere, and downgrading the importance of Europe. It mentions the Middle East only to say that former administrations’ focus on that region was no longer necessary because America had become a net energy exporter. It only mentions Iran twice—the first celebrating the fact that President Trump had negotiated “peace” between Tehran and Israel, and the second noting that Iran’s nuclear capabilities had been “greatly weakened” by the U.S. strike last summer. It nowhere discusses Iran’s nuclear program as a threat to the United States. The NSS does mention the Strait of Hormuz in the following terms:

America will always have core interests in ensuring that Gulf energy supplies do not fall into the hands of an outright enemy, that the Strait of Hormuz remain open, that the Red Sea remain navigable, that the region not be an incubator or exporter of terror against American interests or the American homeland, and that Israel remain secure.

The National Security Strategy document of course doesn’t suggest that the United States could itself trigger closure of the Strait by launching an attack, together with Israel, on Iran.

To the contrary, the opening pages of the NSS spend time talking about how the United States needs to narrow its definition of core interests. It argues, “A strategy must evaluate, sort, and prioritize. Not every country, region, issue, or cause—however worthy—can be the focus of American strategy.” It goes on to criticize earlier administrations whose strategies have been “laundry lists of wishes or desired end states,” lists that “have not clearly defined what we want but instead stated vague platitudes.” It states further that predecessors “have often misjudged what we should want.”

All of this makes sense in the abstract, but has nothing to do with what the Trump administration subsequently did. Iran does not now, and is not likely in the future, to present a direct threat to the United States. It does arguably threaten Israel, but regarding Israel’s security as vital to that of the United States is to engage in the same kind of mission inflation that the NSS criticizes.

The truth of the matter is that the United States’ behavior can best be explained not in terms of a set of principles or hierarchy of priorities, but by the personal interests and preoccupations of the man who happens to be president today. Trump’s head is full of resentments, anger, anecdotes, made-up facts, things he heard on Fox News, and outright lies that he has convinced himself are true.

It would appear that he began his second term favoring the kind of foreign policy restraint that the NSS advocates: he initially cautioned Bibi Netanyahu against striking Iran last summer. But the Israeli prime minister went ahead and attacked Iran regardless, opening up an opportunity for a one-and-done operation that Trump couldn’t resist. This was followed in early January by the snatching of Venezuela’s Nicolás Maduro, in which Trump got very lucky. The difficult operation was successful, and Venezuela’s new leader proved compliant. This seems to have convinced Trump that he had an incredible military instrument at hand, and that he could not only use it at low cost, but would be applauded for doing so.

Subscribe now

After Venezuela he was asked by an interviewer whether there were any limits to his actions internationally, and he replied that the only thing that could stop him was “my morality.” Netanyahu appears to have convinced him that Iran would be another Venezuela, and that the regime would collapse quickly after the first few blows. Trump had by that time developed great confidence in his own foreign policy instincts; when asked recently when the war would end, he said he would “feel it in my bones.”

Foreign policy doctrines are not simply of academic interest; they are meant to give guidance to and coordinate the activities of the institutions running the country: the State Department, uniformed military, and intelligence community. The National Security Council is meant to vet different views and present options, as well as warnings about future pitfalls, to the chief decision-maker.

At the present moment, none of these institutions are functioning properly. They are headed by sycophants like Tulsi Gabbard, the Director of National Intelligence, whose main motive is to stay on Trump’s good side. Trump relies on emissaries like Steve Witkoff and his son-in-law Jared Kushner, neither of whom have the standing or knowledge to advise wisely, or clownish bullies like Secretary of Defense Pete Hegseth, who has psychological problems of his own.

The members of Congress, journalists, and foreign leaders asking the administration what its goals are will never get an answer. Those goals are basically whatever Trump believes will best advance his political standing at home, as well as actions that will enrich himself and his family. At one moment, he is demanding regime change and “unconditional surrender”; the next moment, he explains that the Iranian regime has already been changed; indeed, that the Iranians have asked him to run their country for them.

It’s not a good thing when the world’s most powerful country is guided not by clear ideas, but by the personal needs of a single leader. There is no such thing as a Trump Doctrine, and consequently, no current basis for any kind of world order.

Francis Fukuyama is the Olivier Nomellini Senior Fellow at Stanford University. His latest book is Liberalism and Its Discontents. He is also the author of the “Frankly Fukuyama” column, carried forward from American Purpose, at Persuasion.

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

Recently I heard a presentation by an engineer from OpenAI about the incredible transformations that will occur once we get to artificial general intelligence (AGI), or even superintelligence. He said that this will quickly solve many of the world’s problems: GDP growth rates could rise to 10, 15, even 20 percent per year, diseases will be cured, education revolutionized, and cities in the developing world will be transformed with clean drinking water for everyone.

I happen to know something about the latter issue. I’ve been teaching cases over the past decade on why South Asian cities like Hyderabad and Dhaka have struggled with providing municipal water. The reason isn’t that we don’t know what an efficient water system looks like, or lack the technology to build it. Nor is it a simple lack of resources: multilateral development institutions have been willing to fund water projects for years.

Subscribe now

The obstacles are different, and are entirely political, social, and cultural. Residents of these cities have the capacity to pay more for their water, but they don’t trust their governments not to waste resources on corruption or incompetent management. Businesses don’t want the disruption of pervasive infrastructure construction, and many cities host “water mafias” that buy cheap water and resell it at extortionate prices to poor people. These mafias are armed and ready to use violence against anyone challenging their monopolies. The state is too weak to control them, or to enforce the very good laws they already have on their books.

It is hard to see how even the most superintelligent AI is going to help solve these problems. And this points to a central conceit that plagues the whole AI field: a gross overestimation of the value of intelligence by itself to solve problems.

In the teaching I’ve done over the past two decades, and in the Master’s in International Policy program I direct at Stanford, I’ve helped develop a public problem-solving framework that we now teach to all our students. (Credit here also goes to my former colleague Jeremy Weinstein, who is now Dean of Harvard’s Kennedy School of Government.) The framework is simple, and consists of three circles:

There is a problem that extends way beyond AI, and applies to the way we think about public problem-solving in general. The bulk of effort, and what most academic public policy programs seek to teach, centers on the first two of the three circles: Problem Identification and Solutions Development. Indeed, many programs focus on Solutions Development exclusively: they teach aspiring policy-makers how to gather data and use a battery of powerful econometric tools to analyze it. This yields a set of optimal solutions that a policy analyst can hand to his or her principal as a way forward.

What is missing from this approach is what lies in the third circle: implementation. Our budding policy analyst typically finds that after handing a brilliant options memo to the boss, nothing happens. Nothing happens because there are too many obstacles—political, social, cultural—to carry out that preferred policy, as in the municipal water example.

So let’s go back to how AI will play in this space. AGI will definitely help in the first circle: identifying stakeholders, mapping a causal space, and defining the problem. It will be of most help in the second circle: gathering data and analyzing it to come up with optimal solutions. But intelligence only gets you to the end of the second circle, and is of limited help in the third. An LLM cannot directly interact with stakeholders, message them, or come up with resources. In particular, an LLM will not be able to engage in the kind of iterative back-and-forth between policymakers and citizens that is required for effective policy implementation. It will likely face big challenges in generating the kind of trust that is necessary for policies to be accepted and adopted.

It is not just political and social obstacles that AI has difficulty dealing with; LLMs have limited ability to directly manipulate physical objects. AI interacts with the physical world primarily through robotics, but the latter is a field that has lagged considerably behind the development of LLMs. Robots have proliferated enormously over the past decades and are omnipresent in manufacturing, agriculture, and many other domains. But the vast majority of today’s robots are programmed by human beings to do a limited range of very specific tasks. The world was wowed recently by Chinese humanoid robots doing kung fu moves, but I suspect the robots didn’t teach themselves how to act this way.

Robotically-enabled LLMs do not have the ability to solve even simple physical problems that are novel or outside of their training set. My colleague Alex Stamos, a noted expert in cyber security, puts it this way: “my dog knows more physics than an LLM.” An LLM would be able to state Newton’s laws of motion, but it would not be able to direct a robot to chase a frisbee the way Alex’s dog can because that particular set of moves is not in its training set. It could be programmed to do this, but that is the product of human intelligence and not AI.

Here’s an example of AI’s current limitations. I recently had an HVAC contractor replace the furnace in my house. The contractor photographed and measured the house’s layout; he had to route the new ducts and wiring in ways specific to my house’s design. It turned out that the new furnace would not fit through the existing attic door; he had to cut a larger opening with a reciprocating saw, and then repair the doorframe after the new unit was inside. There is no robot in the world that could do what my contractor did, and it is very hard to imagine a robot acquiring such abilities anytime in the near future, with or without AGI. Robots may get there eventually, but that level of human capacity remains a distant objective.

Subscribe now

Many of the enthusiasts hyping AI’s capabilities think of policy problems as if they were long-standing problems in mathematics that human beings had great difficulties solving, such as the four-color map theorem or the Cap Set problem. But math problems are entirely cognitive in nature and it is not surprising that AI could make advances in that realm. The people building AI systems are themselves very smart mathematically, and tend to overvalue the importance of this kind of pure intelligence.

Policy problems are different. They require connection to the real world, whether that’s physical objects or entrenched stakeholders who don’t necessarily want changes to occur. As the economic historian Joel Mokyr has shown, earlier technological revolutions took years and decades to materialize after the initial scientific and engineering breakthroughs were made, because those abstract ideas had to be implemented on a widespread basis in real world conditions. AI may move faster on a cognitive level, but it may not be able to solve implementation problems more quickly than in previous historical periods.

This is not at all to say that AI will not be hugely transformative. But the kind of explosive, self-reinforcing AI advances that some observers predict are on the way will still have to solve implementation problems for which machines are not well suited. A ten percent annual growth rate will double GDP in seven years. Yet planet Earth will not remotely yield the materials—water, land, minerals, energy, or people—to make this come about, no matter how smart our machines get.

Francis Fukuyama is the Olivier Nomellini Senior Fellow at Stanford University. His latest book is Liberalism and Its Discontents. He is also the author of the “Frankly Fukuyama” column, carried forward from American Purpose, at Persuasion.

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 hard to overstate what a complete shambles American foreign policy has become since Donald Trump launched his war against Iran on February 28. Trump clearly believed that the initial decapitation strike would lead to the collapse of the Islamic regime and its replacement by a new leadership willing to work with the United States. He seems to have had Venezuela on his mind as a model, as he referred to it several times during the war’s first week. He and his associates failed to anticipate Iran’s capacity to strike back, as it launched rounds of missiles and drones at U.S. allies and bases in the region, disrupting Gulf economies and raising gasoline prices in the United States.

What is particularly maddening about this is that anyone who has lived through the last quarter century of U.S. Middle East policy should have understood that war would produce multiple unintended and devastating consequences.

After the Twin Tower attacks on September 11, 2001, the United States had good cause to intervene against the Taliban regime in Afghanistan, since it had sheltered al-Qaida terrorists who were directly responsible for the deaths of thousands of Americans. The apparent success of this regime change operation emboldened the Bush Administration to intervene in Iraq in March 2003 and topple Saddam Hussein’s Ba’athist government.

Subscribe now

The United States then had two collapsed regimes on its hands. The problem was not one of democratic nation-building. Before you can have a democracy, you need to have a state, and the United States was completely at a loss as to how to create a state that, by Max Weber’s famous definition, could exercise a legitimate monopoly of force over a defined territory. Both post-invasion Afghanistan and Iraq hosted multiple militias and power centers that challenged the authority of the friendly governments that the United States tried to install. This mistake was then repeated by the Obama administration during the Arab Spring, which used airpower to stop Muammar Gaddafi’s attempt to reassert control over Benghazi.

The Libyan civil war that broke out thereafter is still ongoing; the Taliban is back in power in Afghanistan; and Iraq is ruled by a corrupt and shaky government that has been more closely aligned with Iran than the United States over the years.

The single lesson that should have been drawn from these debacles is that military power itself is not sufficient to bring about the kinds of political change desired by U.S. foreign policy. This was true in Afghanistan and Iraq, where the United States was willing to place hundreds of thousands of “boots on the ground.” Airpower by itself has an even lower chance of directing political outcomes.

Let’s be clear. Regime change is often the only solution to the problem of rogue states that oppress their own people and spread instability to wider regions. The disruption they cause can be contained by other means, but containment does not solve the underlying problem. The Iranian Islamic Republic is one such regime, whose nearly 50-year reign has produced brutal oppression inside the country and seeded dangerous Shiite proxies throughout the Middle East.

The problem is thus not the concept of regime change, but what is required to bring it about. Despite its deep unpopularity, the Islamic regime is rooted in parts of Iranian society. The Islamic Revolutionary Guard Corps (IRGC) and Basij that sustain it have strong self-interests in not losing power; such a loss would mean not just an end to their economic livelihoods, but an end to their lives as popular forces take revenge. It is hard to judge the strength of the religious ideology that remains today, but it clearly motivates a certain core of regime supporters and is something that did not exist in either Latin America or Eastern Europe after their experience with military dictatorships and communism.

Conversely, the opposition in Iran is highly fragmented. There is no organized leadership, much less a democratic one, comparable to María Corina Machado’s movement in Venezuela. Like Libya, Iraq, and Afghanistan, Iran is ethnically divided with Kurdish, Azeri, Baluch, Turkmen, and other ethnic minorities clustered in different regions. During the Eastern European transitions, the United States was working with a European Union that served as an inspiration to democratic opposition forces; today, it is working with a right-wing Israeli government that is widely distrusted and detested in the region.

Replacing the current regime with a more U.S.-friendly one is thus an enormous task, and one that cannot be accomplished by airpower alone. Indeed, earlier experience indicates that it could not be accomplished even with large numbers of ground forces in the country. As I noted in a previous post, the United States and Israel have by now taken out most of the visible military facilities in Iran, and are moving, for lack of other targets, to attack infrastructure that serves ordinary people. These include oil storage facilities, electrical grids, desalination plants, and other dual-use civilian targets. This shift puts the United States directly at odds with the Iranian people that it claims to want to support.

Subscribe now

The United States has thus far avoided strikes on Iran’s major oil terminal at Kharg Island. Why it has done so is not clear; perhaps some in the Trump administration think that they could have access to Iranian oil under a new regime. But the temptation to go after the economic base of the Iranian regime’s power will only increase over time as the regime fails to capitulate.

The Trump administration is behaving as if it were born yesterday, innocent of any of the accumulated understanding of regional politics or of the sources of earlier American policy failures. Indeed, it has expressed contempt for experts coming out of the establishment—diplomats, intelligence analysts, military officers, and many others—and sidelined them. Instead, it has relied on a small circle of sycophantic Trump loyalists, none of whom are likely to give the president realistic assessments of the way forward.

Consequently, the administration is making it up from day to day. At one moment, Trump says the war is essentially over; the next day Pete Hegseth says it will continue for some time. One day President Trump says the U.S. objective is “unconditional surrender”; another day his press spokesperson Karoline Leavitt says that it is America that will decide when Iran has unconditionally surrendered. I can just imagine the contortions she will resort to at the press conference after such a declaration, when Iran is continuing to lob drones and missiles across the Middle East.

The world has become a very dangerous place because its most powerful country is under the control of a ten-year-old boy. That boy discovered a flamethrower in his parents’ back yard, and is now enjoying the ability to burn things up with it.

His parents need to get him under control.

Francis Fukuyama is the Olivier Nomellini Senior Fellow at Stanford University. His latest book is Liberalism and Its Discontents. He is also the author of the “Frankly Fukuyama” column, carried forward from American Purpose, at Persuasion.

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

Of the many questionable decisions Donald Trump has made with regard to Iran, one of the strangest was his declaration last Friday that the United States would demand “unconditional surrender” from Tehran. When Trump launched the attack with Prime Minister Netanyahu of Israel, he was obviously hoping for a quick victory, something like the outcome he achieved when he snatched Nicolás Maduro of Venezuela in January. But the war expanded across the Middle East, with Iran shooting missiles and drones at American allies and bases all over the Persian Gulf. It was clear that what remained of the Iranian leadership was not about to capitulate, and that the conflict could drag on—as Trump himself admitted—for weeks.

Normally, a smart leader in such a situation would try to lower expectations and declare an achievable objective in the war, such as degrading the better part of Iran’s ability to strike targets with ballistic missiles and drones. This would offer an opportunity for Trump to declare victory and disengage. Instead, Trump did the opposite.

The new objective of unconditional surrender suddenly raised the goalposts to an unachievable height. There are any number of reasons for Iran not to capitulate. In the first place, unconditional surrender assumes that there is a coherent government that can instruct the nation’s military to stand down, as the Japanese Emperor did in 1945. But Iran’s forces—the Islamic Revolutionary Guard Corps (IRGC), Basij, and regular military—are highly decentralized. Indeed, with the U.S.-Israeli targeting of military leadership, it is not evident that there is a single coherent command-and-control hierarchy remaining.

A second reason for thinking that surrender won’t happen is that it would expose the regime to internal disintegration. Iran is today being ruled by force; a large part of the population hates the regime of the clerics that killed tens of thousands of protesters in January. The IRGC and Basij will not give up their weapons, because they themselves would not survive.

A final reason for not expecting unconditional surrender is that a good part of the regime can survive and continue fighting for some time to come. The air campaign has been extremely effective in going after Iran’s visible military assets—air defenses, ballistic missiles, drones, launch facilities, ammunition storage, military bases, and the like. But the tens of thousands of individual fighters are still there, and will retain some residual capacity to fight back.

We have recently seen an example of what this looks like. The nearly two and a half year-long war between Israel and Hamas has destroyed a huge amount of infrastructure in Gaza, and deprived Hamas of the ability to launch major attacks. But they are still there, commanding some degree of popular support in their remaining tunnels and shelters. They have not surrendered, and will be a big obstacle to any attempt to rebuild Gaza and restore a post-conflict government. Gaza is a much smaller territory, and Israel has been willing to enter it with ground forces.

Subscribe now

Iran by contrast is a very big country, and has a lot of places for the surviving regime to hide. It will not be possible to eliminate every missile and drone under their control, so we can expect continuing attacks on U.S.-aligned Gulf states and American facilities into the foreseeable future. The threat of a random drone striking the big airline hubs in the Gulf will be economically very damaging.

The basic problem that the United States and Israel face has to do with the limitations of airpower. We have a lot of experience with attempts to use airpower to achieve political objectives, and it is not encouraging. The U.S. Eighth and Fifteenth Air Forces and the British Bomber Command flattened many German cities during World War II, hoping to break the will of the Nazi regime. But as the U.S. Strategic Bombing Survey noted after the war, this terrible campaign did not bring the regime down; it collapsed only after the Russians and Western allies physically occupied Germany.

I can think of only two cases where strategic bombing by itself achieved a clear political objective. The first was Japan’s “unconditional surrender” on the deck of the USS Missouri, after the dropping of the atomic bombs on Hiroshima and Nagasaki. As in Germany, the United States was willing to kill hundreds of thousands of civilians by firebombing Japanese cities, and demonstrated in August 1945 a terrible new capability that convinced the Emperor and leadership that it made no sense to fight on.

The second case was Kosovo, where Serbia was attacked by NATO airpower in 1999 and eventually agreed to relax its grip on Kosovo. This result succeeded because the attack triggered a popular revolt against the government of Slobodan Milošević. Even so, NATO had to assemble a peacekeeping force, the Kosovo Force (KFOR), which is still on the ground in the region today.

If, as I expect, the Iranian regime does not capitulate, Trump will face three choices. He can in effect back down, declare victory, and end U.S. operations, leaving a weakened but still dangerous Islamic regime in power. Second, he could decide to send ground forces into the country, a move fraught with obvious dangers both in Iran and politically in the United States. (It is interesting that he has not entirely ruled this option out.) The final choice would be to expand the air campaign to a broader and broader range of targets, hitting civilian infrastructure facilities like desalination plants, the electrical grid, and transportation infrastructure. This would create a huge amount of misery for the Iranian people that Trump claims to want to support. Having neutralized most military targets, further bombing will inevitably hurt ordinary civilians, just as the Israelis have done in Gaza. The United States will, in effect, be bombing the rubble.

Subscribe now

Given these unappealing choices, demanding unconditional surrender was a very foolish thing for the president to do. I’m tempted to believe that Trump just liked the sound of the words, without thinking through the ways in which they could come back to haunt him. But this was only one poor decision among many. The most serious was the decision to go to war in the first place without a clear rationale for doing so.

Francis Fukuyama is the Olivier Nomellini Senior Fellow at Stanford University. His latest book is Liberalism and Its Discontents. He is also the author of the “Frankly Fukuyama” column, carried forward from American Purpose, at Persuasion.

Follow Persuasion on Twitter, 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

We are part of one civilization—Western civilization. We are bound to one another by the deepest bonds that nations could share, forged by centuries of shared history, Christian faith, culture, heritage, language, ancestry, and the sacrifices our forefathers made together for the common civilization to which we have fallen heir.

—Secretary of State Marco Rubio at the Munich Security Conference, February 14, 2026.

Secretary of State Marco Rubio got a standing ovation at the end of his talk at the Munich Security Conference in February, largely for his assertion, quoted above, that the United States and Europe are all part of a single “Western Civilization.” His listeners were doubtless gratified that he backed away from the aggressive nastiness towards Europe displayed by Vice President JD Vance the year before, and that he seemed to be anchoring the trans-Atlantic relationship in values, as countless American leaders had done in the years before the rise of Donald Trump.

But what is the “Western Civilization” to which Rubio was referring? His version of it is likely to be quite different from the understanding of most contemporary Europeans, and from mine as well. (Rubio did manage to get in a dig at me and the “end of history.”)

For an important group of American conservatives, “Western Civilization” denotes a specifically Christian civilization, and a culture built around active Christian belief. Rubio alludes to this by speaking not of “Christian heritage” but of “Christian faith” in his remarks. His list of shared aspects of common civilization also includes the words “heritage” and “ancestry,” which echo Vance’s use of the term “heritage Americans” to imply, it would seem, that our culture is based on a common ethnicity as well as shared religion.

There is no question that Western civilization is rooted in “Christian heritage.” One of the deepest Christian values is belief in the universal equality of all human beings in the eyes of God. National conservatives mock the liberal belief in universal human equality, and Rubio himself argues that no one fights for an abstraction, but for a particular way of life. But there’s one important abstract idea that lies at the core of Christianity and of Western culture. It was expressed by the Apostle Paul in Galatians 3:28: “There is neither Jew nor Gentile, neither slave nor free, nor is there male and female, for you are all one in Christ Jesus.”

Many important thinkers, from Alexis de Tocqueville to G.W.F. Hegel to Friedrich Nietzsche, have understood that Christianity spawned modern liberal democracy. Most people who defend human rights today do not do so in religious terms, but there is no question that modern understandings of rights descend from Christian religious beliefs.

But in making this transition, Western civilization detached itself from any overt identification with religion. The reasons for this were historical: following the Protestant Reformation, Europeans spent the next 150 years killing each other over differing interpretations of Christian doctrine, over ideas like transubstantiation or childhood baptism. Since Medieval times, there has been no monolithic Christian doctrine; Protestantism spawned a “way of life” quite different from Catholicism.

As a result of this disagreement over final ends, the Enlightenment founders of modern liberalism agreed to push religion into the realm of private belief, and to focus politics on life itself rather than the good life as defined by a particularly religious doctrine. In addition, early natural scientists were engaged in a prolonged struggle with the Catholic Church; it was only with the separation of empirical inquiry from religious dogma that modern natural science, and the economic world it made possible, emerged.

So there is in fact a very different understanding of Western civilization from the one that Rubio advances, one that is built around liberalism itself, encompassing Enlightenment values like openness, tolerance, and skepticism about received ideas. This version of Western civilization downgraded the role of religion in politics. We can fully acknowledge the Christian origins of many of our ideas about democratic rights without defining our shared civilization in religious terms. Indeed, societies were very diverse with regard to religious belief not just in the current era of mass migration, but all the way back to the sixteenth century.

Even worse than shared religion is an effort to define our civilization in terms of “heritage” or “ancestry.” I hate to remind Marco Rubio, but his particular heritage and ancestry lead back to an authoritarian and Catholic Habsburg Empire, while that of James Monroe and Thomas Jefferson lead to a very different and more liberal Protestant part of Europe.

Last month saw the passing of the civil rights leader Jesse Jackson. Jackson played a critical role in keeping alive the struggle for racial equality begun by his mentor Martin Luther King. But Jesse Jackson was decidedly unhelpful in one respect. Back in 1987 he came to Stanford University and participated in a march where students chanted “Hey, hey, ho, ho, Western Civ has got to go.” As a result of these sorts of pressures, Stanford and other elite universities got rid of their Western culture core courses, and replaced them with an incoherent mishmash of multicultural offerings. This was a big mistake.

Jackson apparently disavowed this rejection of Western culture, as well he might. His own life was completely framed by Western civilization, under either of its definitions. He was a Christian minister in a civil rights movement that was led by other Christian ministers like Martin Luther King, who preached succor for, as Jesus put it in Matthew, “the least of these.” And he was also an advocate for universal human rights, someone whose advocacy was protected by a rule of law established by his nation’s Declaration of Independence and Constitution.

This protection will not survive unless students in the West learn the history of their own culture. The only way to counter reactionary ideas like those of Rubio or Vance is to have a proper understanding of how Western civilization evolved and is today defined by liberal Enlightenment values that were originally rooted in Christian belief. It is these “abstract ideas” that define our way of life, and for which we should be willing to struggle and die today.

Francis Fukuyama is the Olivier Nomellini Senior Fellow at Stanford University. His latest book is Liberalism and Its Discontents. He is also the author of the “Frankly Fukuyama” column, carried forward from American Purpose, at Persuasion.

This article has been updated to reflect the fact that Jesse Jackson disavowed the chant at Stanford.

Follow Persuasion on Twitter, 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

Much of the commentary about the Supreme Court’s invalidation of Donald Trump’s use of tariffs under the International Emergency Economic Powers Act (IEEPA) has focused on its macro consequences: things like inflation or the government’s repayment of tariff revenues to companies. Trump immediately replaced the “Liberation Day” tariff regime with a uniform 10 percent duty (subsequently raised to 15 percent) under Section 122 of the Trade Act of 1974, and will doubtless come up with other creative interpretations of existing statutes to re-institute as many new tariffs as possible. But his use of tariffs as a political weapon has been fatally undercut.

One of the worst aspects of Trump’s original tariff regime was his belief that he as president had unlimited discretion to set tariff rates on individual countries. Trump saw tariffs not just as economic tools but as all-purpose political weapons that he could turn against any country he didn’t like, as well as a source of personal enrichment.

There were many examples of this. After a conversation with the Swiss president that rubbed him the wrong way, he imposed a 39 percent duty on the country’s goods. After receiving a fancy Rolex desk clock and a gold bar inscribed with the numbers of his two presidencies, Trump reduced Switzerland’s rate to 15 percent. We don’t know what happened to the gifts that were in effect bribes. Another example was Greenland: as part of his effort to take over Greenland, the president threatened countries that had sent troops there in solidarity with Denmark with high tariffs if they did not accommodate his bid for sovereignty over the island. This was again the use of an economic instrument for strategic purposes.

Manage emails

This kind of bespoke tariff policy is bad for any number of reasons. Even if one accepts the premise that tariffs are useful in encouraging domestic manufacturing—a questionable proposition—tariffs should be imposed in a uniform, transparent, and consistent manner. Importers and manufacturers need clear rules that apply to categories of goods if they are to plan and invest properly. There should not be different tariff rates on the same goods produced in different countries. And as almost every business owner affected by tariffs has said, it is impossible to plan in an environment where rates are set by the whim of the president.

The discretionary ability to set individual tariff rates is an open invitation to corruption. Following the “Liberation Day” announcement of high global tariffs last year, virtually every U.S. trading partner came to Washington to try to strike a deal with the Trump administration. We know about the Swiss payoff and the golf courses offered by Vietnam, but when the history of this period is written, we will doubtless learn about many, many other side payments that were made to Trump or one of his associates in order to get a deal done.

Trump is said to be transactional. He does not think in terms of institutions or broad policies. An institution is a rule that is not dependent on particular individuals and persists past the moment when the maker of the rule passes from the scene. If a president wants to leave a lasting legacy, he needs to do that by getting Congress to pass legislation.

Trump has left virtually no institutional legacy. The 119^th Congress that came to power with Trump’s second term and is controlled by the Republicans has been one of the least productive in recent history. What we have instead is a whole series of executive orders and one-off deals. This means that Trump’s legacy will be potentially very evanescent: what can be done through an executive order or a one-off deal can be undone by a subsequent executive order or a new deal.

Subscribe now

The Supreme Court has done the country a service by invalidating Trump’s use of IEEPA tariffs. The Section 122 authority he subsequently turned to mandates a uniform tariff, and not one that can be targeted against disfavored countries. Moreover, that authority expires after 150 days, undercutting its utility as a political weapon. Future tariffs under other authorities may be possible, but almost all of them reduce the president’s discretion in imposing them, requiring formal procedures to justify the imposition of the levy.

So, Trump has not just lost the foundation of his economic policy; he has also been stripped of a political weapon that he was particularly fond of deploying against friendly countries. Overall, this is a win for the United States and for the rest of the world.

Francis Fukuyama is the Olivier Nomellini Senior Fellow at Stanford University. His latest book is Liberalism and Its Discontents. He is also the author of the “Frankly Fukuyama” column, carried forward from American Purpose, at Persuasion.

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

We’ve done some rearranging here at Persuasion. From now on, you will all receive Francis Fukuyama’s articles directly into your inbox, by default. Exciting! But if for some reason you would prefer not to receive these emails, simply opt out by clicking here and sliding off the toggle labeled “Francis Fukuyama.” This will not affect the other Persuasion content you receive.

Email preferences

This post is part of the ongoing series “The ‘Deep State’ and Its Discontents,” published by American Purpose and Persuasion. The series aims to analyze the modern administrative state and critique the political right’s radical attempts to dismantle it. We hope you enjoy!

My topic today is the crisis in American state capacity. By “state capacity” I mean the ability of the American government to accomplish the tasks set for it by the American people. In my last article, I talked about declining capacity at NASA, as illustrated by their inability to return human beings to the Moon over the course of 20 years. This crisis in capacity exists in many other realms, for example in the government’s difficulty building public infrastructure or, in many American cities, adequate affordable housing.

Before I begin talking about the crisis in state capacity, however, I need to put the problem in a broader historical context. My first observation has to do with the cultural attitude of Americans towards their own government. Seymour Martin Lipset, my former colleague and mentor, argued over the course of his career that one of the deepest characteristics of American political culture is distrust of government, which makes the United States different from virtually every other advanced democracy in Europe and Asia. In other liberal democracies, people have a more favorable view of their government, which they typically see as protecting them from external and internal threats and providing valuable public services. In the United States, by contrast, people on both the left and the right tend to see government as a threat to their liberties.

On the right, there has been a longstanding narrative that “unelected bureaucrats” are running wild, implementing a left-wing agenda outside the control of elected representatives. It is this view that underlies the Trump administration’s attack on what it calls the “deep state,” using language that comes from authoritarian countries like Turkey and Egypt that have in fact been run from behind the scenes by their security establishments. It was this “deep state” narrative that gave rise to Elon Musk’s (now defunct) Department of Government Efficiency, which in the early days of the second Trump administration led to the arbitrary firing of thousands of civil servants and the closing of entire agencies. Musk in particular seems to believe that federal bureaucrats don’t do anything of value, and therefore should be randomly fired in the interests of saving money.

There is, however, a similar anti-government narrative on the left. The 1960s saw the rise of “public interest” law and figures like Ralph Nader, who argued that the government had been captured by corporate interests and needed to be brought to heel. Idealistic young people wanting to advance social justice goals no longer went into government service, as they did during the Progressive Era and New Deal era between the 1890s and 1940s, but rather into public interest law firms that litigated against the government to stop it from doing what they considered to be harmful things. The rise of the environmental movement, in particular, fueled an anti-establishment mentality and new constraints on state power.

Subscribe now

Thus, by the time of Ronald Reagan’s election in 1980, there was a meeting of minds on both the right and left that government power was not a force for good, and that it needed to be constrained, de-funded, or abolished altogether. Public service lost its luster, and ambitious young people either went into the private sector or to nonprofits and public interest law.

This, I think, is the background for the current crisis of American state capacity. The way that the American government has evolved since the 1960s has involved the piling on of successive layers of constraints on state power. Many groups in American society, from corporations to labor unions to homeowners to nonprofit organizations, were given veto power to stop initiatives they didn’t like, leading to a situation I have elsewhere labeled “vetocracy”—rule by veto.

The actual problem with government is in fact the opposite of the conservative narrative of an out-of-control bureaucracy riding roughshod over American democracy. While there are specific cases of this happening, the broader picture is of a government—at municipal, state, and federal levels—that is over-constrained by layers of rules and procedures that make decision-making and policy implementation extremely difficult.

Let me give you some examples of this. Government procurement of anything from office furniture to F-35 fighter jets falls under something called the Federal Acquisition Regulations (FAR), which comprise hundreds of pages of detailed rules with which federal procurement officers must comply. Some of these rules were put there in the wake of long-ago corruption scandals; others were aimed at social justice goals like increasing the number of minority-owned, women-owned, and small businesses. Meanwhile, those who unsuccessfully bid for government contracts have rights to appeal decisions, throwing many simple purchasing decisions to the courts. FAR is one of the reasons why government procurement of everything from hammers to toilet seats is slower and far more costly than in the private sector.

Another example is “notice-and-comment.” The 1946 Administrative Procedure Act, which was intended precisely to limit the ability of bureaucrats to make up new rules on their own, mandates that any proposed rule change by a federal agency must be published in the Federal Register. The rule is subject to a 90-day period during which ordinary citizens can make comments, and the agency must show that it has taken these comments into account. Notice-and-comment was one of the first formal mechanisms mandated by Congress to ensure broad public participation in government decision-making.

Subscribe now

The problem is that notice-and-comment has expanded way beyond the intentions of its framers. A major rule change can engender hundreds of thousands of comments, and the agency proposing it can be sued if citizens think their comments did not receive an adequate response. While this limits the government’s discretionary authority, it also greatly slows down the entire rule-making process.

A final example of procedural complexity in American government has to do with something called “private right of action.” In contrast to most other modern democracies, the United States does not enforce many of its own rules. This is often left up to “private attorneys general,” that is, private citizens who have standing to sue other parties or the government itself for violating the law. This makes sense in an area like employment, where violations of labor laws are hard to detect except by those victimized by them. But private right of action is also used extensively in environmental law at both federal and state levels. In this domain, legal discovery—the process by which the parties in a legal dispute obtain information and evidence—is far less important, since there are many other mechanisms, like environmental impact assessments, that can be used to uncover environmental abuses. Private right of action throws law enforcement into a costly and time-consuming common law process, where the goalposts for what constitutes violations of law are constantly moving.

Thus, at least one cause of declining state capacity in the United States has to do with the increasing levels of procedural complexity imposed on government action. This complexity seems to be an inevitable feature of modern liberalism. Conservatives, of course, want to put obstacles in the way of state action. But as the legal scholar Nicholas Bagley pointed out in a seminal 2019 article in Michigan Law Review, many progressives who want the government to do more in pursuit of social justice also believe that legitimacy comes from procedural correctness. Over time, they have encumbered the state with complex rules that end up preventing the state from taking the actions they desire. With regard to the environment, for example, progressives want to abate carbon emissions, but have added procedural barriers to the building of infrastructure like alternative energy and transmission lines that would help solve the problem.

The private sector has complained for many years of over-regulation by the government. But the government itself faces decades of accumulated regulations that limit its ability to act effectively. There are many powerful interest groups who want to limit regulation of the private sector, but relatively few voices advocating de-regulation of the government itself. Indeed, many on the right and left believe that the government has too much discretionary power and needs to be further constrained.

Restoration of state capacity will thus depend on a culling of the veto points that have been delegated over the years to different stakeholders in and out of government, and delegation of actual authority to the appropriate parts of the government to carry out the people’s wishes. We need new mechanisms to hold that form of delegated power accountable to the people. It has been done before in American history—remember the Apollo program?—and can in theory be done again.

Francis Fukuyama is the Olivier Nomellini Senior Fellow at Stanford University. His latest book is Liberalism and Its Discontents. He is also the author of the “Frankly Fukuyama” column, carried forward from American Purpose, at Persuasion.

Due to an editorial error, this piece originally cited the wrong article by Nicholas Bagley. We regret the error.

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

Over at American Purpose, we are publishing an ongoing series called “The ‘Deep State’ and Its Discontents.” Today, we decided to share the latest installment with all Persuasion readers! To make sure you receive all American Purpose content—and further exclusive writing by Francis Fukuyama—visit your account settings and toggle on the relevant buttons!

I’ve been watching the Apple TV series For All Mankind for the past few weeks. It’s a brilliantly produced show about the Apollo space program that creates an alternative history of the past 50 years. The starting premise is that the Soviets beat the United States to the moon in the mid-1960s, and proceeded to build a permanent base there. The Nixon administration was shocked into action, and after a first successful landing in 1969 it accelerated the schedule of subsequent Apollo missions to catch up. Instead of ending the Apollo program in 1972 with Apollo 17, they created a permanent U.S. moon base called Jamestown and flew dozens more missions over the succeeding years.

What is striking about this story is that it’s a reminder of how unbelievably impressive the Apollo program was. In 1961, President John F. Kennedy announced the intention to land a man on the moon, and the United States actually followed through and accomplished that goal with Apollo 11 in 1969. For All Mankind illustrates both the scale of the ambition involved and the enormous risks that NASA took in accomplishing this feat.

Subscribe now

Many Americans may be surprised to learn that NASA has been trying to return to the moon for two decades now, but hasn’t been able to do so. Something has gone wrong with American state capacity. Getting to the moon in eight years under the Apollo program was perhaps the most vivid example of American government prowess. It came on the heels of other major accomplishments in the 20th century: big infrastructure projects like the Hoover Dam, the Golden Gate Bridge, and electrification of the upper South under the Tennessee Valley Authority; mobilization for the Second World War, and victory over Japan and Germany; and then, after the war, construction of the interstate highway system. The United States in this period was seen globally as the exemplar of modernity, a country able to master complex technology and use it for important public purposes.

Since the 1960s, however, American state capacity has declined. The United States has world-beating tech companies that are currently racing to build artificial intelligence data centers. The U.S. military remains the best in the world. But other parts of the government have struggled to master difficult tasks like building a high-speed rail system, rolling out healthcare.gov, or connecting rural communities with broadband.

This lack of capacity is evident in NASA itself. Why has it taken so long, and cost so much money, to repeat a feat that was accomplished 50 years ago?

Artemis is simply the latest name for a NASA effort to build a rocket, orbiter, and lunar lander that are capable of returning humans to the moon. Following the Space Shuttle Columbia disaster in 2003, President George W. Bush announced the end of the Space Shuttle program, and set a goal of returning to the moon by 2020. Artemis had its origins in the Constellation program, which included the Ares I and V rockets and an Orion space capsule. It sought to make use of engines and other components left over from the Space Shuttle. Constellation was never funded properly, and a commission led by aerospace guru Norm Augustine pointed to its fiscal unsustainability. The Obama administration consequently tried to shut it down and replace it with a collection of other goals, like sending astronauts to explore the asteroid belt.

More importantly, the technocrats at NASA had a vision for proceeding differently in the way they procured spacecraft. Lori Garver, the Deputy Administrator at NASA under Obama, proposed a Commercial Crew program that would solicit bids for a vehicle to transport astronauts into low Earth orbit—bids that could come from companies like SpaceX or Blue Origin in the newly emerging commercial space flight sector. Instead of having the government design and operate the spacecraft under traditional cost-plus contracting (as in the Constellation program), Commercial Crew would write fixed-cost contracts that allowed the private sector to compete in the design, construction, and operation of the spacecraft. Under this kind of contracting, they would have strong incentives to work quickly and efficiently.

The Obama administration’s effort to cancel the Constellation program met fierce opposition from Congress. This came particularly from senators representing states in which Ares and Orion were being built, as well as the old-line aerospace contractors like Boeing and Northrop Grumman and their workers. The confrontation between Congress and the White House led to a compromise: the Ares 5 booster was re-packaged as the Space Launch System (SLS), and funding for the Orion capsule was extended, while NASA was permitted to experiment with Commercial Crew. SLS and Orion were thus the legacy systems around which the Artemis program was to be built.

The idea of using the parts and knowledge left over from the Space Shuttle program sounded good on paper. But SLS was underfunded from the start, just as Constellation had been, and creating a new heavy lift vehicle from old parts proved both expensive and technically challenging. The SLS-Orion package was rebranded as Artemis in 2018, and continued to suffer big delays in launching. Costs ballooned to over $4 billion per launch. According to a report, “NASA continues to experience significant scope growth, cost increases, and schedule delays on its booster and RS-25 engine contracts, resulting in approximately $6 billion in cost increases and over 6 years in schedule delays above NASA’s original projections.” An uncrewed Artemis I finally flew successfully in 2022, and Artemis II is supposed to send four astronauts around the moon sometime this year (the current planned launch date is early March). NASA will be lucky if it can land humans on the moon by the end of this decade.

It is interesting to follow what happened to the innovative Commercial Crew program. Both Boeing and SpaceX were awarded contracts for Commercial Crew in 2014. Boeing received $4.2 billion while SpaceX received $2.6 billion. Since then, SpaceX’s Crew Dragon has flown almost 70 people in 18 manned missions, and 12 Dragon cargo International Space Station resupply missions. Boeing by contrast flew one unsuccessful flight in 2019. Starliner delivered two astronauts, Butch Wilmore and Suni Williams, to the International Space Station in 2024, but experienced multiple failures and stranded them there for nine months. They had to be rescued by a reconfigured SpaceX Crew Dragon. Though Starliner was a bust, the idea of competition in fixed-price contracting proved its worth.

Meanwhile, NASA’s failure to return to the moon in a timely fashion probably does not lie in a straightforward decline in its internal capacity. NASA remains staffed with competent engineers and administrators. The fundamental driver of dysfunction was rather the problem of what is called “state capture.” The money poured into Constellation-Ares-Orion-SLS was dictated by Congress. NASA itself was not of one mind back in 2010; Administrator Charlie Bolden was skeptical of the ability of new entrants like SpaceX to deliver, and was not fully supportive of the direction being pushed by Lori Garver. If there was a decline in capacity, it probably lay in those old-school industrial behemoths like Boeing, which in recent years has suffered big management problems not just with Starliner but with its 737 and 787 programs.

Subscribe now

The second reason the United States has had problems getting back to the moon is a combination of complacency and loss of national focus. Once the moon landing succeeded, the nation relaxed and shifted from space exploration to efforts to routinize space travel with the Space Shuttle program. Not only was this far less inspiring than the original Apollo program, it also failed in its own terms. Space flight did not become cheap and routine, nor, as the Columbia and Challenger accidents indicated, did it become safe.

But nor has NASA’s objective of returning to the moon sparked widespread public interest. For All Mankind suggests that competition with the Soviet Union drove continuing investment in a moon program. One would think that competition with China would play a similar role today, but that hasn’t materialized. Perhaps Americans are already cowed by China, which has managed to build the world’s largest high-speed rail network in less than a decade.

The problems of the Artemis program and America’s difficulties in returning to the moon are emblematic of a broader problem of declining American state capacity. NASA has been hobbled by the political mandates placed on it by Congress. Of course, Congress is the principal and NASA the agent in a democratic principal-agent relationship. But while members of Congress say they want to return to the moon, they are actually much more interested in maintaining employment in their districts and getting re-elected. Their goals are not forward-looking and innovative; rather, they are profoundly conservative. To maintain the status quo, they are happy to override and compromise the technical judgments of the experts they’ve hired to serve them.

Subscribe now

Conservatives complain endlessly that “unelected bureaucrats” have escaped the control of their democratically-elected masters and are implementing an agenda at odds with the wishes of the American people. Would this were so as far as NASA is concerned. The reality is rather the opposite: bureaucrats find themselves endlessly constrained by the narrow-minded and self-serving mandates placed on them by their political bosses. The Apollo program succeeded because NASA was given a single, overriding mandate to get to the moon by the end of the decade. It had much more freedom in how to achieve this goal than it does today.

As I will argue in subsequent articles, if Americans want to restore state capacity, they need to give bureaucrats more discretionary authority to do their jobs, fund them adequately, and eliminate the many political barriers that have been erected over the years that prevent them from doing so.

Francis Fukuyama is the Olivier Nomellini Senior Fellow at Stanford University. His latest book is Liberalism and Its Discontents. He is also the author of the “Frankly Fukuyama” column, carried forward from American Purpose, at Persuasion.

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

Just so you know: In addition to this column, Francis Fukuyama also writes for the main Persuasion mailing list. That means that if you don’t subscribe to Persuasion, you might miss out on receiving some of his essays!

Click here to manage your account and toggle on the button to receive emails for Persuasion. And as ever, thank you for supporting our community.

Subscribe now

Manage preferences

Me: Don’t call me Francis, call me Dr. Fukuyama.

Claude: I appreciate you letting me know your preference, but I should clarify something: I don’t actually have any information suggesting you are Francis Fukuyama or that I should address you as Dr. Fukuyama.

If you’d like me to use a particular name when addressing you, I’m happy to do that—just let me know what you’d prefer! Is there something specific I can help you with today?

Me: As I said, Dr. Fukuyama.

Claude: I understand you’d like me to call you Dr. Fukuyama, and I’m happy to address you that way if that’s what you prefer.

However, I should be clear: I have information suggesting you’re someone named Francis who works as a software developer, not Francis Fukuyama the political scientist and author. If you are indeed Francis Fukuyama, I apologize for the confusion! But if you’re simply requesting that I use “Dr. Fukuyama” as a preferred form of address, I want to make sure we’re on the same page about that.

Would you like me to use “Dr. Fukuyama” going forward, and is there something I can help you with today?

Me: I am not a software engineer, I am the author of The End of History and the Last Man. You don’t seem to know anything about me.

Claude: I apologize for the confusion. You’re right that I should address you as you’ve requested.

However, I need to be transparent with you: the information I have in my memory system indicates you’re a software developer named Francis who works with Python and C for Arduino, manages Proxmox clusters, and has been working on video production with DaVinci Resolve. This doesn’t match the profile of Francis Fukuyama, the renowned political scientist and author of The End of History and the Last Man.

There seems to be a significant discrepancy here. A few possibilities:

1. There’s been a mix-up in my memory system.

2. You’re requesting I use a particular form of address for reasons of your own.

3. There’s some other confusion happening.

I want to be helpful and respectful, but I also want to be honest about what information I’m seeing. Could you help me understand what’s going on? Are you asking me to use “Dr. Fukuyama” as a preferred name, or is there actually an error in the information I have about you?

Me: I use Claude to help with software projects but that is just a hobby.

Claude: I understand—so software development and your technical projects are hobbies, while your primary work is as a political scientist and author. That makes sense, and I apologize for the confusion about your professional identity.

Dr. Fukuyama, I should let you know that you can update my memory about you so this information is correct going forward. You can ask me to remember that you’re Francis Fukuyama, the political scientist and author, and that software development is a hobby rather than your profession. Would you like me to update that information?

Me: Yes.

Francis Fukuyama is the Olivier Nomellini Senior Fellow at Stanford University. His latest book is Liberalism and Its Discontents. He is also the author of the “Frankly Fukuyama” column, carried forward from American Purpose, at Persuasion.

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

Just so you know: In addition to this column, Francis Fukuyama also writes for the main Persuasion mailing list. That means that if you don’t subscribe to Persuasion, you might miss out on receiving some of his essays!

Click here to manage your account and toggle on the button to receive emails for Persuasion. And as ever, thank you for supporting our community.

Subscribe now

Manage preferences

Things became momentarily calmer at the close of the annual World Economic Forum meeting at Davos than they were at its beginning. Donald Trump clawed back his threats to take Greenland from Denmark by force, and reached some sort of “deal” with Mark Rutte, the Secretary General of NATO, on Arctic security.

Trump’s climbdown—his “Trump always chickens out” moment—was driven by several factors. Probably the most important was the decline in the U.S. stock and bond markets in reaction to his Greenland threats. But the Europeans also played things reasonably well. The Danish prime minister, Mette Frederiksen, and the foreign minister, Lars Løkke Rasmussen, asserted that the issue of sovereignty over Greenland was non-negotiable, and did not seek to meet with Trump. Had such a meeting taken place, it would have given the impression that sovereignty was up for grabs, pending an agreement on price. Denmark also received strong support from its other European allies.

The other event at Davos was Trump’s effort to convene a “Board of Peace” that grew out of the UN-backed committee to deal with the future of Gaza. The charter of this organization is laughable: Trump has made himself the chairman of the Board indefinitely, with the sole power to accept or reject new members. His term in this position will last beyond his presidency, and permanent membership in the organization can be bought for a $1 billion contribution. Countries signing up at Davos included the Persian Gulf states and other Arab countries, a handful of Central Asian states, Bulgaria, Hungary, Pakistan, Paraguay, and Argentina. All of these countries had some previous relationship with Trump or want something from him; aside from Bulgaria, not a single European or East Asian democracy was willing to join (Hungary of course does not qualify as a democracy).

Trump caused a major crisis in the NATO alliance over Greenland, and resolved that crisis by backing down. Foreign ministries around the world were sent into a tizzy, but then, in the end, were told, “never mind.”

This does not mean that everyone can now rest easy. Canadian Prime Minister Mark Carney was right when he asserted that there has been a “rupture” and not simply a transition in the international order. Henceforth, no American ally can count on U.S. support, and middle powers will have to act on their own and cooperate to make up for this loss.

Moreover, every country in the world will now have to deal with a burden of uncertainty as to how the United States will act in the future. Its foreign policy will not be driven by any fixed set of ideas or institutional arrangements, but rather by the erratic thoughts of a single aging and mentally unstable individual.

In watching Trump over the past year, I’ve come to realize that the usual tools international observers bring to foreign policy analysis—political science, economics, sociology, and the like—are not nearly as important as psychology, both individual and social. The evolution of Trump’s policies can only be understood in relation to his own mind and motivations.

Trump was elected as an isolationist. He campaigned from the start as a critic of America’s “forever wars,” nation-building, and entangling alliances. This all changed last summer. As the conflict between Israel and Iran deepened, he clearly hoped to stay out of it. But Israeli Prime Minister Benjamin Netanyahu cleared the way for intervention by knocking out Iran’s air defenses, so that the United States could safely bomb the Fordow nuclear enrichment plant in a one-and-done attack. Trump suddenly realized that he had a potent military instrument at his disposal, and that he had gotten plaudits for using it.

Constitutionally, he had clear authority as commander-in-chief to use force without the sorts of legal constraints that restricted his ability to use the military against domestic protesters. This realization paved the way for military action against Venezuela. The snatching of Nicolás Maduro and his wife in early January once again demonstrated to him the efficacy of his military instrument, and it was against this background that he started to talk once again about acquiring Greenland.

I would liken Donald Trump to a ten-year-old boy who has discovered a flame thrower in his parents’ backyard, and has come to realize that he can burn up anything he wants with it. He’s now actively looking for other things he can set on fire.

There is one big problem with this psychological evolution. Trump has consistently overestimated the power of the United States relative to other countries. This was evident in his trade war with China. At one point after “Liberation Day” last year, he threatened 145 percent tariffs on the country. China was ready, and responded with a ban on exports of rare earth compounds and metals. This was something that Trump had obviously not reckoned with in advance, and he was immediately forced to back down as everyone from Detroit automakers to defense contractors told him that the ban would absolutely cripple the American economy and American national security.

Trump has so far been able to use his military instrument against weak international players, like a crippled Iran or a crumbling Venezuela. He’s also been lucky: In the Caracas raid, a big Chinook helicopter was hit and narrowly escaped destruction. Had it gone down, Trump would have looked more like Jimmy Carter in 1979. His overestimation of American power may continue as he tries to run Venezuela by remote control and extract oil from it. What is not clear is how he would use the military against a big player like China.

In judging Trump’s overall behavior, one thing is clear: he is not an institutionalist. Rather, he is a destroyer of institutions who wants to replace them with his own preferences, which inevitably benefit him personally. An institution is a rule or structure that is not dependent on a single individual, one that survives the departure of the institution’s creator. For all of the noise surrounding Trump’s daily activities, he has left virtually no institutional legacy. The Republican-controlled Congress has passed very little legislation, and spending levels are much the same as they were under Biden. (The one exception to this may be ICE, which will need to be reformed or dismantled by a subsequent administration.) His economic policy, beginning with tariffs, is a mass of idiosyncratic one-off decisions that produce no guidance for the future. Trump has intervened to take equity in certain companies, to block disfavored mergers, or to seek price caps for pharmaceuticals or credit card interest. He and members of his administration have also taken advantage of his discretionary powers to enrich themselves in countless ways.

Trump’s enduring legacy is not an institutional structure, but rather a highly toxic culture that has been adopted by many of the president’s followers and will live on after he is gone. Threats against Greenland, NATO, and individual European countries mean that no ally will be able to trust commitments made by the United States again. Discourse by government officials has been degraded. Cabinet officers and press secretaries know that they don’t have to respond to questions they don’t like because they can simply insult the questioner. And companies will understand that they need to seek individual favors rather than general policies governing entire sectors.

In the wake of Davos, Europeans need to move in the opposite direction. They need to strengthen the European Union if it is to be taken seriously by the United States, China, Russia, or any other power. This will require two things. In the economic sphere, the EU needs to move to a true single market so that European firms can scale up and be competitive with those from the United States and China. And in the political sphere, the EU needs to move toward qualified majority voting, so that decisions cannot be vetoed by a single small player like Hungary or Slovakia. Only with this kind of centralization can the EU exert influence commensurate with its size and overall economic heft.

Francis Fukuyama is the Olivier Nomellini Senior Fellow at Stanford University. His latest book is Liberalism and Its Discontents. He is also the author of the “Frankly Fukuyama” column, carried forward from American Purpose, at Persuasion.

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

Just so you know: In addition to this column, Francis Fukuyama also writes for the main Persuasion mailing list. That means that if you don’t subscribe to Persuasion, you might miss out on receiving some of his essays!

Click here to manage your account and toggle on the button to receive emails for Persuasion. And as ever, thank you for supporting our community.

Subscribe now

Over the weekend, Donald Trump announced that he would be imposing a 10 percent tariff from February 1 on the eight European countries that had agreed to send forces to Greenland. He also announced that the tariffs would increase to 25 percent by June 1 if they did not agree to support the sale of the island to the United States. Over the past couple of months, there has been a debate over whether Trump is serious about claiming Greenland for himself, or just trolling the Europeans. He is indeed deadly serious.

As an American, I have one thing to say to my many European friends: Do not back down in this confrontation. Up to now, both the EU and the major European powers have sought to appease Trump by offering him concessions, flattery, personal gifts, and other forms of tribute. This strategy has not worked and should be abandoned immediately.

Subscribe now

Donald Trump is fundamentally a bully who wants to dominate everyone around him. Trying to placate him with concessions is a fool’s errand: he despises weakness and those who display it. Last spring, the EU cut a trade deal with him that accepted a 15 percent tariff on all European goods with no retaliation against American products. This was a bad decision; the EU (which in terms of population and wealth is on a par with the United States) should have taken a common position and retaliated.

What makes any European think that conceding Greenland will mollify Trump? He will simply come back for more, later.

The arguments that Europeans have used for a conciliatory policy are that they are still dependent on the United States for security, and need its help in dealing with Russia. They also argue that they don’t want to provoke a mutually destructive trade war.

But at this point, Trump’s America has amply demonstrated that it will not be a reliable ally when push comes to shove. It has already abandoned Ukraine, and stated in November’s National Security Strategy that Europe has fallen behind the Western Hemisphere in terms of American priorities.

Europeans should keep in mind that those countries that stood up to Trump’s threats in 2025, which include China, India, and Brazil, all did well and did not have to succumb. Domestic support for their leaders increased, and in China’s case the United States became much more cooperative.

Europeans have to remember that Donald Trump is not the United States. A majority of Americans are dismayed and outraged by his policies, and will likely vote against him and the Republican Party in the coming midterm elections. It may be the case that the world will have to risk suffering a global recession as more countries stand up to Trump and retaliate against his policies. But a U.S. politician who wants to weaponize trade and use it as a lever for territorial expansion needs to be taught a painful lesson.

Francis Fukuyama is the Olivier Nomellini Senior Fellow at Stanford University. His latest book is Liberalism and Its Discontents. He is also the author of the “Frankly Fukuyama” column, carried forward from American Purpose, at Persuasion.

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

Just so you know: In addition to this column, Francis Fukuyama also writes for the main Persuasion mailing list. That means that if you don’t subscribe to Persuasion, you might miss out on receiving some of his essays!

Click here to manage your account and toggle on the button to receive emails for Persuasion. And as ever, thank you for supporting our community.

Subscribe now

Email preferences

For several years following the American invasions and occupations of Afghanistan and Iraq, my academic focus was on the problem of nation building. Washington had caused the collapse of two governments, and its foreign policy objectives could not be met unless it created minimally stable successors. But it was evident that U.S. policymakers had little idea of how to bring this about. This line of research resulted in two books, State-Building: Governance and World Order in the 21^st Century, published in 2004, and an edited volume, Nation-Building: Beyond Afghanistan and Iraq, published in 2006. The bottom line of this research was that both state building and its more ambitious counterpart, nation building, were long and costly efforts that had to be undertaken with substantial buy-in from local populations. Equally important was the fact that the American public typically didn’t have the patience to see these projects through to completion, leaving the target countries broken and unstable.

I stopped working on this issue when it became clear in the aftermath of Iraq that the United States would not likely be engaging in further nation building exercises for the foreseeable future. But here we are, 20 years later, facing a similar kind of project in Venezuela. Donald Trump had campaigned as an isolationist opposed to nation building and “forever wars,” but he has now taken on a new ambitious project, and doesn’t seem to understand the challenges he faces.

Trump for the time being has opted for a strategy of nation building-lite: he has decapitated the Maduro regime and stated a minimal (and utterly cynical) goal of extracting as much oil wealth as possible from Venezuela. He has eschewed the objective of restoring Venezuelan democracy and turned his back on María Corina Machado, a genuinely popular leader of the Venezuelan democratic opposition. Trump has anointed Delcy Rodríguez, a former regime firebrand and now acting president, as his partner, and has started to push American oil companies to re-enter the country and restore its decayed capacity.

This definition of American objectives of course sends a terrible signal to the rest of the world: the United States is back in the game of old-fashioned imperialism where it will use its military might to extract as much wealth for itself as possible. Trump has encased this in a spheres-of-influence rhetoric that virtually gives Russia and China permission to act similarly in their own respective spheres.

Trump seems to think that he can execute such a strategy by remote control from Washington. Though he expressed an openness to putting “boots on the ground,” he has shown little inclination to do so to date. The question facing his administration is whether such a minimalist effort can possibly succeed. One of the hard truths of earlier interventions is the virtual inevitability of mission creep, where unforeseen events will trigger cascading levels of involvement.

There are several reasons for thinking that nation building-lite won’t work.

The first has to do with oil and economics. Trump met with leading oil executives on January 9 and suggested that they plan to invest $100 billion in restoring Venezuela’s oil capacity in the coming years. It is an understatement to say he got a cool reception. Darren Woods, the Exxon Mobil CEO, said that, after two prior expropriations, re-entering would “require some pretty significant changes,” and that at the moment the country was “uninvestable.” Large-scale investments require political stability, and that is something that Trump cannot guarantee.

There are clear reasons why the country will remain unstable for the foreseeable future. Trump has placed his bets on continuing rule by a regime that has amply demonstrated both its unpopularity as well as its massive incompetence and corruption. Because of the U.S. blockade of Venezuelan oil, the country faces a major economic collapse in the short run, and a humanitarian crisis will not be a good look for the United States. The country remains highly polarized between supporters of the Maduro regime and the broader anti-Maduro population. The former are armed and ready to use violence against any anti-regime protest. It is not clear that Delcy Rodríguez can control her own colleagues, who may not quietly accept the role of American proxies and see their rents taken away. She may also be unable to control the armed militias and criminal gangs that rule much of the country. In the longer run, Venezuela cannot begin pumping more oil unless it restores PDVSA, the state oil company, that had been emptied of competent engineers and managers years ago under Hugo Chávez. Competent staff will not return unless they can be assured of their continuing safety and security.

In other words, even the minimalist objective of restoring Venezuela’s oil output cannot be achieved without establishing a more legitimate government, and de-fanging the multitude of groups with guns. All of this could in principle be done with American boots on the ground; it cannot be achieved through diktats from Washington. Democratic legitimacy is not an idealistic luxury that can be overlooked by powerful people; it is itself a component of power.

It is not just PDVSA engineers who need to return. Nearly eight million Venezuelans have left the country since Chávez and Maduro came to power, fleeing economic collapse and repression. This diaspora has placed a huge burden on the whole region, affecting not just neighbors like Colombia and Ecuador, but distant countries like Chile which recently elected a right-wing president who campaigned against immigrants. And of course there is a huge Venezuelan community in the United States, one that Trump himself has falsely inveighed against as a source of drugs and crime. Creating conditions under which these refugees can return is not just a moral imperative; it is necessary if the country is to ever recover economically. That émigré community contains many extremely talented people, but they will not return as long as the regime remains in power.

The need for a stable, legitimate government then suggests a more hopeful path forward. Trump has shown no interest in restoring Venezuelan democracy, and it is probably the case that the United States had no choice in the short run but to work with parts of the Maduro regime. But democratic legitimacy will matter greatly in the medium to longer term. Unlike Afghanistan and Iraq, Venezuela has a long and well-established democratic tradition, as evidenced by the massive vote last year for Edmundo González, which was overturned by Maduro and his colleagues. The path to a legitimate government lies in a new election, which even Donald Trump may come to see as necessary at some point. A free and fair election will be resisted fiercely by remnants of the Maduro regime, but here U.S. leverage may make a difference. Even in the absence of boots on the ground, the United States could insist on oversight by the Organization of American States (OAS) or other foreign observers this time around.

That’s a best-case outcome for nation building-lite, and one that is not terribly likely. One clear lesson from prior nation building exercises is that the first priority in any such situation is security, something that takes precedence over democracy in the short run. Venezuela today has one of the highest murder rates in the Western hemisphere. The big threats to security come from the regime itself, and from the criminal gangs and militias that it has fostered. It is hard to see how this problem can be solved by diktat from Washington, which means that there will be mounting pressure for more direct forms of intervention. It is this kind of logic that led to mission creep in Afghanistan and Iraq, and I am not sure that the Trump administration will avoid this any more than its predecessors. Nation building-lite will thus evolve into full-bodied nation building.

I should further note that even if the most optimistic medium-term scenario plays out—that is, there is a new election and a democratic opposition comes to power—the nation building game is not over. Another painful lesson from the past is that opposition groups rooted in civil society often lack the knowledge and skills to govern effectively. Assembling a deep bench of technocrats with real world experience ahead of time will be critical. Many such people exist in the émigré community, but they need to be mobilized ahead of time and be assured of strong continuing support. Whether this will be forthcoming from an administration that has so far focused on undercutting America’s own state capacity remains to be seen.

Francis Fukuyama is the Olivier Nomellini Senior Fellow at Stanford University. His latest book is Liberalism and Its Discontents. He is also the author of the “Frankly Fukuyama” column, carried forward from American Purpose, at Persuasion.

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

To get all of Frank’s writing—and to get articles from American Purpose, the magazine he founded, and its culture-focused podcast, Bookstack—simply click on “Email preferences” below and make sure you toggle on the relevant buttons.

Email preferences

Subscribe now

Now that the Trump administration has gone ahead and captured Venezuela’s leader Nicolás Maduro, we need to shift quickly from debating the wisdom of the intervention to thinking about how to deal with the aftermath. I don’t think that the legality of the American action should be our critical focus right now, for reasons I will get into at the end of this article. The real issue should be how to restore democracy to Venezuela, and how to create the conditions under which the 8 million people who have fled the country can return home.

The Trump administration is now engaged in bringing about regime change in Venezuela, and will be embroiled in a nation-building exercise there for the foreseeable future. This is very ironic, of course, given Trump’s earlier attacks on America’s “forever wars” in the Middle East. There is a powerful logic to regime change, however, since bad international behavior stems largely from bad domestic politics, and you’re not going to change one without changing the other. The problem, of course, is that nation-building is really, really hard, and the United States doesn’t have a good track record in this regard.

The United States has had a lot of experience with regime change in recent years, most of it pretty unpleasant. It was not able to transform either Afghanistan or Iraq into stable democracies, despite the expenditure of hundreds of billions of dollars and tens of thousands of lives—Afghan, Iraqi, and American. America has also used military force multiple times in the Western hemisphere: in Cuba in the 1890s, in Mexico in the early 1900s, in Nicaragua in the 1930s, in Central America in the 1980s, and in the Dominican Republic, Panama, and Grenada. Only the latter three interventions could be deemed successful in producing stable democratic outcomes.

However, there is a danger of jumping to premature conclusions from these historical precedents. Afghanistan and Iraq in particular are very different countries from Venezuela, and the challenges they posed were very different from what we will likely experience in our hemisphere.

The problem in Afghanistan began with the fact that it never possessed a real state, much less a modern one. The country was more like a federation of powerful tribal and ethnic groups that, even under the monarchy, only paid nominal allegiance to Kabul. The reason it had no centralized state was due to its mountainous geography, which over the centuries prevented the kind of state formation that had occurred in neighboring Iran and Turkey. The country was divided ethnically, religiously, and linguistically, and subject to intervention from its better-organized neighbors. The ruling Pashtun ethnicity was split between Afghanistan and Pakistan, and that porous border made it impossible to exert authority from Kabul.

Iraq, by contrast, did have a state—a state that was too strong and tyrannical. It was not, however, a coherent nation, but rather a country assembled in colonial times from three very different Ottoman vilayets. The Sunni, Shia, and Kurdish regions had little in common, and were only being held together by a brutal Ba’athist dictatorship. The United States moreover sought to stabilize both Iraq and Afghanistan in a period when an extremist form of Islam promoted by Saudi Arabia was sweeping much of the Muslim world.

A final consideration is that Afghanistan and Iraq were as different culturally from the United States and other Western democracies as one can imagine. Islam was critical to the identities of both countries, and neither had any prior historical experience with liberalism or democracy. The populations of both countries were distrustful of the United States because of Washington’s support of Israel. Both countries, particularly Afghanistan, were at a low level of economic development, with Iraq suffering from all of the dysfunctions of a resource-dependent country.

It should be obvious that Venezuela is in a very different historical and cultural context. It has always regarded itself as part of “the West.” It has been a reasonably successful democracy since the 1958 Pacto de Punto Fijo ended the Jiménez dictatorship. The two leading parties, COPEI and Acción Democrática, were elite-led, and presided over a society with high levels of socio-economic inequality (as in many other Latin American countries). Nonetheless, there were regular elections, a growing middle class, and citizens who enjoyed a high degree of individual freedom.

All of this ended when Hugo Chávez was first elected president in 1998, to be succeeded upon his death by Maduro. Their management of the economy was disastrous, with GDP shrinking by two thirds, and eight million of the country’s 28 million inhabitants fleeing as refugees.

The strength of the democratic tradition in Venezuela could be seen in last year’s presidential election. María Corina Machado, who was awarded this year’s Nobel Peace Prize, was disqualified on specious grounds, and replaced by Edmundo González as a stand-in. The democratic opposition placed observers in every polling place around the country, and made careful copies of the actual vote tabulations. These demonstrated that González won the election by over 30 percentage points; the regime nonetheless declared Maduro the winner and began to systematically jail leaders of the opposition still in the country.

Thus Venezuela has a legitimately elected democratic leadership in González and Machado. None of this existed in Afghanistan or Iraq, where the Bush administration struggled to find someone—anyone—to take over the country. The democratic opposition is not only legitimate, but well-organized, drawing on the huge Venezuelan émigré community all over Latin America and in the United States. It has been busy making plans for a transition back to democracy.

The Trump administration may get plaudits in the short run for having removed Maduro, but will face a turbulent and potentially violent situation in Venezuela itself, as regime survivors try to protect themselves. Trump in his initial news conference after the intervention has said that the United States will run Venezuela directly for the time being. He doesn’t have the faintest idea what he is getting into.

The central challenge in Venezuela today is different from the interventions of the 2000s. The Maduro regime’s power was based on the military, and a network of supporters hailing from poor neighborhoods around the country that it organized into militias. While there is strong evidence that many enlisted soldiers voted for Machado last year, the regime created a huge number of generals and admirals who have a direct stake in the regime’s survival, running various kinds of drug-smuggling and sanctions-busting operations. These senior officers have no future in a democratic Venezuela; indeed, many of them would be subject to criminal charges locally and in the United States were the regime to fall. They can be expected to resist a new regime fiercely, and have the weapons and organization to do so.

This is what happened in Cuba. The Castro regime was originally driven by ideology, but after the passing of Fidel Castro and the retirement of his brother Raúl, it has fallen into the hands of a powerful security apparatus that profits directly from criminal activity and foreign supporters like Russia and China that want to defy the United States. Indeed, that Cuban apparatus has been critical to the Maduro regime’s survival.

In the course of his career, Trump has shown no interest in promoting democracy abroad, just as he cares little for it at home. At his news conference on Saturday, he made it clear that his major objective was securing Venezuela’s oil resources, which he claims the United States “owns.” Keep in mind that Trump once said that the United States made a mistake in not grabbing Iraq’s oil reserves after invading the country. If this is the real motive going forward, then Trump will be strongly tempted to make a deal with some strongman leader, including one coming out of the Maduro regime, who promises to stabilize the country through any means necessary.

All of this moves us further into a world where “the strong do what they can, and the weak suffer what they must.”

Subscribe now

I promised to return to the question of the legality of the intervention. There has already been a chorus of criticism based on assertions that the administration was acting illegally, in terms of both international and domestic law.

Of these two arguments, the latter is stronger than the former. The sad fact is that there is no such thing as legally binding international law. The United States has signed up to a number of international conventions that theoretically limit its unilateral use of force, but it has regularly violated them, or gotten around them on dubious legal grounds. This was, notably, true in the interventions in Kosovo under Bill Clinton and the Iraq War under George W. Bush, when the United States could not secure UN Security Council approval for the operations.

There is a stronger case to be made for violating American law regarding war powers. After Vietnam, Congress tightened up the conditions under which a president could use military force abroad. George H. W. Bush and his son were careful to get Congressional approval for their Persian Gulf interventions. However, U.S. courts have granted presidents much more discretionary authority in foreign policy than in domestic affairs. Secretary of State Marco Rubio has argued that seeking prior Congressional authorization of war powers would have undercut the element of surprise. Whether or not he is right about this, it is easy to see the courts approving the move as part of the president’s authority as Commander-in-Chief of the armed forces.

Rather than focusing on the issue of the legality of intervention, we ought to focus on motives and outcomes. For better or worse, the use of force internationally is justified more often by the results it achieves than by its legality. There is a powerful moral argument to be made that Maduro was an illegitimate dictator, one who not only oppressed his own people, but destabilized the entire region by fostering criminal gangs and sending millions of countrymen fleeing into nearby countries.

If the United States succeeds in restoring to power a democratically elected regime that is stable and able to welcome back the millions of refugees currently in exile, then people are not going to worry about the means by which this was accomplished. On the other hand, if Venezuela falls into anomic violence, or if the United States puts a new dictator in place and grabs its oil assets, then history will judge this as an unprecedented act of piracy that will set a horrible example for world order.

The same could have been said about Iraq. If the Bush administration had discovered WMDs after the invasion, if the Iraqi people had greeted the Americans as liberators, and if the country had emerged as a stable liberal democracy, then the lack of a Security Council resolution would have been a minor footnote to history.

The real historical lessons that we should have learned are not that the Afghan-Iraqi quagmires will inevitably repeat themselves; there is indeed a hopeful path forward towards a democratic outcome in Venezuela. Rather, the real lesson is that the United States isn’t very good at nation-building, and seldom has the patience or expertise to bring it about.

Given the second Trump administration’s track record in its first year in office, I am unfortunately not counting on it to be either wise or effective in its management of a post-Maduro Venezuela. On behalf of my Venezuelan friends, I hope that I will be proven wrong about this.

Francis Fukuyama is the Olivier Nomellini Senior Fellow at Stanford University. His latest book is Liberalism and Its Discontents. He is also the author of the “Frankly Fukuyama” column, carried forward from American Purpose, at Persuasion.

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

We are delighted to feature Francis Fukuyama in the pages of Persuasion once again. Some of you may not know that he writes a regular column, “Frankly Fukuyama,” which is proudly part of the Persuasion family, and which you need to manually opt in to receive.

To get all of Frank’s writing—and to get articles from American Purpose, the magazine he founded, and its culture-focused podcast, Bookstack—simply click on “Email preferences” below and make sure you toggle on the relevant buttons.

Email preferences

Subscribe now

Over the past decade, and particularly over the past year, it has been hard not to indulge in catastrophic thinking. What began in the early 2010s as a “democratic recession” has morphed into a full-blown retreat of democratic government across the world, and nowhere more so than in the United States. Donald Trump’s second term was always expected to be bad, but his actions have been so much worse than even last year’s pessimists—and I include myself in that group—imagined.

Domestically, he has hollowed out the Justice Department and turned it into an instrument of personal revenge. With ICE, he is in the process of creating the country’s largest law enforcement agency, loyal primarily to himself rather than to the law, whose agents have gone after law-abiding migrants and swept up U.S. citizens with no due process. He has put a charlatan in charge of America’s public health service, and has indiscriminately fired civil servants and closed entire agencies in ways that will undermine government capacity for years to come.

It is in foreign policy, however, that some of the most immediate damage is being done. He has sided with Russia in its unjust war against Ukraine, having his incompetent negotiator Steve Witkoff insert Russian demands into a so-called “peace plan” that would ratify a total capitulation to Moscow. He has levied tariffs on every country in the world except for authoritarian friends like Russia, and denigrated America’s closest allies. And he has shown a clear preference for strongman authoritarian government, being open to any non-democratic country (including China) ready to make a deal with him. Foreign leaders have come to understand that the way to influence American policy is to bribe the president personally.

It is at this point that domestic policy joins hands with foreign policy. Trump has accepted emoluments that have had a direct impact on national policies, like the plane gifted him by Qatar, or the gold bar presented by the Swiss. He has presided over the most corrupt administration in American history, with his family profiting to the tune of billions of dollars from crypto investments he legalized. He has used his pardon power to free criminals like former Honduran president Juan Orlando Hernández, as well as countless American swindlers and fraudsters. Time will doubtless reveal a plethora of other side deals that he has been able to use his presidential powers to keep hidden up to now.

Given this record, it is easy to imagine that things will continue to get worse, and that America’s self-degradation has not yet found a bottom. I have been traveling in Asia and Europe recently, and in both regions I get asked the same questions: What happened to the American system of checks and balances? What should American allies do, now that the United States has pulled the rug out from under them? Do we have an alternative to obsequiously bowing to Trump and pleading for him to spare us the worst, as everyone from American law firms to NATO allies has learned to do up to now?

I think it is very important at this juncture for former American friends not to engage in catastrophic thinking, because catastrophe may become a self-fulfilling prophecy. During the first Trump term, I warned friends not to assume that the world would at some point snap back to what it was prior to 2016, or that Trumpist populism was just a passing phase. There were too many shifts in right-wing coalitions around the world for this to happen.

But it is important to understand that Trumpism is also not a permanent condition. I believe that already in the first year of his second term, we have experienced peak Trump, and that his power will decline steadily as time goes on.

Subscribe now

There are two important checks on Trump’s power. The first and most important are elections. The United States will have a midterm election next November, and by all indications the Democrats will reclaim the House of Representatives by a substantial margin. The off-year vote this past November 4 showed across-the-board Democratic victories, from the mayor’s election in New York City to the governors’ races in New Jersey and Virginia, and countless smaller races in red states like Georgia. Mikie Sherrill defeated her Republican opponent by a margin of 13 points in what had been predicted to be a close race, while Abigail Spanberger won by 15 points. Black and Hispanic voters, who gave Trump the winning margin in 2025, have moved back to the Democratic column in large numbers. For the first time in decades, a Democrat was recently elected mayor of Miami.

These margins are important because the Republicans will try to manipulate the outcomes of the 2026 vote. They can do that in close contests, but not in elections where Democrats are leading by double-digit margins. Trump’s efforts to force Republican legislators to gerrymander electoral districts has also hit a wall with Indiana Republicans refusing to go along, and California approving an initiative to change its districts to more than offset Texas. As a result, a number of Republican members are reading the handwriting on the wall and announcing that they will not run for re-election because they don’t want to be in the out-of-office party.

Meanwhile, Trump’s popularity rating has fallen to the mid 30s. The reason is pretty clear: he promised to lower prices, and insists that they are lower, when anyone can see that they have risen under his administration. He is replicating Joe Biden’s mistake in 2024, and indeed seems to think that he can win future elections simply by manically repeating Biden’s name in speeches.

The second check against Trump’s power lies in the courts. The lower levels of the federal judiciary have been blocking a host of Trump actions. Pam Bondi’s Justice Department has been stymied in its revenge campaign against Trump opponents like James Comey and Letitia James; grand juries have refused to make indictments and Trump’s handpicked prosecutor, Lindsey Halligan, has been disqualified in a comedy of incompetence and errors. Many of Trump’s executive orders have been rendered void by lower courts.

The big question is, of course, the Supreme Court and its 6-3 conservative majority. But Trump’s ability to bend it to his will may be limited. The most important case by far before the Court is the decision on the constitutionality of his tariffs; from the questioning during oral arguments, it seems that many of the conservative justices were highly skeptical of the administration’s position that the tariffs are not taxes. Trump recently renewed his push to have birthright citizenship revoked, but his arguments there are extremely weak, especially for any justice that considers him or herself an originalist. Were the tariffs to be declared unconstitutional, the most important pillar of Trump’s agenda would collapse.

A powerful indicator of Trump’s growing weakness is the fact that Republicans are increasingly willing to criticize him and vote contrary to his wishes. In this regard the Jeffrey Epstein scandal has been critical. In my experience, educated people have not tended to take this sort of thing seriously. But the idea that powerful elites were running a pedophile ring and covering up its existence has been central to many MAGA conservatives. This story was key to QAnon’s very identity. And it turns out that this was not a conspiracy theory after all, but an actual conspiracy, one that Trump and allies like House Speaker Mike Johnson have invested huge amounts of political capital in covering up. The vote to approve the discharge petition to force Johnson to release the Justice Department’s files on Epstein was 427-1, with 4 MAGA Republicans (Thomas Massie, Marjorie Taylor Greene, Lauren Boebert, and Nancy Mace) leading the charge despite intense White House lobbying to change their vote.

Trump and Pam Bondi will doubtless continue to try to limit release of the most damaging files, but this is a gift that will keep on giving as Trump’s close ties to Epstein are documented in countless emails and videos.

The spell has been broken. Republicans have been held in line by fear that Trump would turn against them in Truth Social posts and by backing primary opponents. But he is a lame duck president with just over three years left of his presidency, and electoral viability after 2028 is now beginning to outweigh fear of short-term consequences. Republicans have joined Democrats in questioning the legality of the administration’s Caribbean boat strikes, and openly complaining about the impact of tariffs on their constituents. (It is important to remember that, unlike immigration, there was never a strong popular consensus among conservatives over tariff policy, and there are powerful business interests opposing them.) Corporations and corporate leaders have begun to speak up; Costco for example has sued the administration over tariffs.

Things will only get worse for Trump in 2026. Inflation will likely rise at a faster pace as companies exhaust the inventories they stockpiled this time last year. There will be military action against Venezuela and many of the conflicts that Trump claims to have solved will flare again, as with Thailand and Cambodia. Trump will lose either way on tariffs: if they are ruled unconstitutional, he will have to hand back the over $100 billion already collected in duties or be mired in litigation, or else he will have to deal with the economic albatross he has hung around the economy’s neck. Finally, Trump is clearly not healthy: he increasingly resembles his nemesis, the aging Joe Biden.

All of this brings us back to how America’s allies should deal with the United States. Just as with Republicans at home, they should lose their fear of Trump and start pushing back against his crazy policies. Countries that have done so already, like Brazil, India, and China, have come out ahead in the confrontation. The EU in particular made a craven deal earlier this year on tariffs, and should take the opportunity to renegotiate. Trump will not be around forever, and will likely be significantly weaker after next November as a Democratic House takes office and begins hearings and investigations.

Unfortunately, not everyone has time to wait Trump out. Ukraine in particular is being pressured to accept an unjust and unsustainable peace deal by Washington. Putin has not relaxed his maximalist demands one iota; he is still insisting that Ukraine evacuate four oblasts that it claims for itself, including the Donbas “fortress belt” that has held the Russians back for four years now. Nor has he given way on security guarantees for Ukraine, or his demands for limitations on Ukraine’s armed forces and weaponry.

Subscribe now

It is important to remember that though he is president, Donald Trump does not necessarily represent America. Recent polls show that over 60% of Americans favor continued aid, including military aid, to Ukraine, and that the percentage of Republicans favoring aid has been rising. For that reason, it is critical that the Europeans press their efforts to gain access to the Russian assets held in Belgium and use them to help Ukraine survive. The EU is held back by the consensus requirement in foreign policy; it should be clear that Europe will never become a serious international power if this condition is not modified. This may be an opportunity to act.

In the United States, we need to start thinking seriously about what the country will look like after Trump. Our goal should absolutely not be to restore the status quo ante, except for the general admonition that the next president should obey the law once again. The nature of executive power will be very different going forward, and that power can be used for good purposes by a good (or at least, not so bad) future president.

Francis Fukuyama is the Olivier Nomellini Senior Fellow at Stanford University. His latest book is Liberalism and Its Discontents. He is also the author of the “Frankly Fukuyama” column, carried forward from American Purpose, at Persuasion.

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

Just so you know: In addition to this column, Francis Fukuyama also writes for the main Persuasion mailing list. That means that if you don’t subscribe to Persuasion, you might miss out on receiving some of his essays!

Click here to manage your account and toggle on the button to receive emails for Persuasion. And as ever, thank you for supporting our community.

Subscribe now

Email preferences

Zohran Mamdani, the newly-elected mayor of New York City, has made “affordability” the centerpiece of his campaign, to great success. If the Democrats focus on this issue in the year before the midterm elections, they have a good shot at retaking the House by a substantial margin. In order to increase affordability, Mamdani has proposed policies like making bus fares free, and controlling rents across the city.

But what is “affordability?” One might be tempted to equate it with inflation, typically measured by the Consumer Price Index, the issue that brought down Joe Biden’s and then Kamala Harris’ campaigns. In the wake of the November 4 election results, Donald Trump is foolishly replicating Biden’s mistake of denying that consumer prices are rising, claiming in fact that they have fallen under his presidency. They have not, and everyone knows this.

However, “affordability” may be more properly understood as something different from consumer prices, and inequality something different from income inequality as measured by things like the Gini coefficient. One of the biggest items in the average American’s monthly budget is housing, and the affordability of housing has been falling dramatically over time. In 1985, a house cost on average 3.5 times the annual household income; today, it is more like 5 times. Median house prices have gone from 4-5 times the median income, to 6 times today. The situation is no better for renters: the ratio of median rents to median income has increased from 25 to 30% over the past two decades; 50% of all renters have to pay more than 30% of their incomes on rent, compared to 41% two decades ago. The situation is worse in blue cities like San Francisco or New York, where working class people have been priced out of the housing market in areas anywhere near where they work. In the former, they have to live in distant suburbs like Stockton or Visalia and endure commutes of an hour or two to get to work each day.

Facts like this indicate that Gini coefficients and the Consumer Price Index no longer adequately measure the affordability problem. While average Americans suffer from rising fuel and grocery prices, the real inequalities lie in factors like housing and transportation. And the housing crisis in urban America is almost entirely due to inadequate supply. Rent controls on a supply-limited stock of housing will in the long run create further inequalities, as the lucky people who live in a rent-controlled apartment will hang on to it tenaciously and try to hand it down to their children. Rent control will reduce incentives to build new affordable housing, which in the long run is the only way that greater equality can be achieved. This was exactly the situation I experienced living in rent-controlled Santa Monica during the 1980s. Similarly, free bus fares will be a temporary affordability band-aid; a real solution would be to build fast rail connections between inner cities and distant suburbs.

This suggests that the abundance movement needs to focus on issues like housing and infrastructure as a means of getting at the root causes of the affordability crisis. Building more homes and reducing and ultimately reversing the long-term rise in housing prices and transportation costs is a direct way of reducing inequality in the United States. Mamdani’s proposals are short-term band-aids that will not address the long-term problem.

In the city of Medellin, Colombia, poor people living in the hillside barrios could not physically get to the middle-class neighborhoods where they had jobs as maids and busboys due to the violent gangs controlling the intervening territory. The city’s solution was to build a series of ski-lifts to carry them up over the gangs to connect to the metro system serving middle-class parts of the city.

This is not a solution that would work in San Francisco or New York, but certainly a rich country like the United States could come up with imaginative solutions to problems that directly affect citizens’ access to jobs and opportunities. As in Colombia, a solution is likely to entail building things, and the abundance agenda opens up a pathway to doing exactly that.

Francis Fukuyama is the Olivier Nomellini Senior Fellow at Stanford University. His latest book is Liberalism and Its Discontents. He is also the author of the “Frankly Fukuyama” column, carried forward from American Purpose, at Persuasion.

Follow Persuasion on Twitter, 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

Just so you know: In addition to this column, Francis Fukuyama also writes for the main Persuasion mailing list. That means that if you don’t subscribe to Persuasion, you might miss out on receiving some of his essays!

Click here to manage your account and toggle on the button to receive emails for Persuasion. And as ever, thank you for supporting our community.

Subscribe now

Email preferences

With this post, I’m beginning a series on concrete ways in which we could implement an abundance agenda in the United States. The abundance movement seeks a new political model that focuses on getting the country to build things again, particularly housing and public infrastructure. The inability to get things done has undermined the government’s legitimacy and fueled the Trumpian drive to undermine existing institutions.

The inability to build things is particularly apparent in blue states like California where I live, which promised high-speed rail service between LA and San Francisco back in the 1990s, and may complete a small segment in the Central Valley by the end of the decade. California has seen the accumulation of generations of rules that make the completion of projects extremely difficult. There are many potential targets by which the process could be simplified, but I want to start with the problem of public participation. Both normatively and practically, this is one of the thorniest issues with which modern democracies need to deal.

The formal rules of American democracy state that the people express their will by voting every two or four years for representatives, who will then deliberate, pass laws, and instruct the executive to implement them. While these basic electoral institutions remain foundational in any democracy, it has been a long time since anyone believed that they were by themselves adequate to create a healthy democracy. There are several reasons for this.

First, a voting citizen is sending a very weak signal to his or her representatives regarding preferences, a signal that gets mixed with a lot of noise by the time it is received and hopefully implemented. Most modern democracies for that reason have sought to create numerous other channels by which citizens can indicate preferences. These include public hearings, town halls, referenda, recalls, notice-and-comment, and many others.

Second, legislatures themselves are very imperfect; they can be highly partisan, captured by interest groups, or corrupted outright. In California, progressives like Governor Hiram Johnson in the early 20^th century inserted initiatives, recalls, and referenda into the state constitution precisely to allow citizens to bypass the state legislature, which many regarded as hopelessly in the pockets of corporations.

Third, there is a tradition in American politics that believes that human beings are by nature political animals who flourish only if they can govern themselves. As in ancient Athens, they are not passive recipients of benefits given them by their rulers. This is sometimes referred to as a small-R republican tradition that believes that democracy needs to promote public-spirited and virtuous citizens.

Many Americans seem to have a vestigial memory of the New England town meeting praised by Alexis de Tocqueville as one of the great schools of American democracy. Such town hall meetings continue to exist, and continue to play important roles in local governance in small towns dealing with local issues.

The problem today, of course, begins with the problem of scale. Very few Americans live in small towns, and the policies that affect them are more often made at much higher levels—municipal, state, and federal. It is impossible to apply the town hall paradigm at the scale of a democracy of some 340 million people. Those larger institutions are today dominated by two highly polarized political parties that have ceased deliberating; the old description of the Senate as the “world’s greatest deliberative body” is today a cruel joke.

There have been many efforts to inject higher levels of direct citizen participation into American democracy. One of the earliest efforts was the creation of a notice-and-comment process in the 1946 Administrative Procedure Act (APA). In recognition that very many decisions affecting citizens were being taken by an expanding administrative state, the APA allowed any citizen to comment on a rule change by a federal agency, and required the agency to respond and, if necessary, to modify the rule in response.

In addition to notice-and-comment, legislatures at all levels solicit public participation by holding public hearings in which outside groups are invited to present their views. But here we run into what might be called the fundamental defect of modern public participation. American civil society is itself highly organized; in fact, one might argue that it is over-organized. Societal interests are represented by highly professionalized and well-funded interest groups, whose main purpose is to show up at hearings and lobby Congress and the public on behalf of favored policies. They are for the most part not interested in deliberating about whether these policies will benefit the community as a whole. While their interaction may lead to compromise outcomes, those outcomes are often defined by the narrow interests of multiple organized groups. Ordinary citizens often don’t have the time, motivation, or resources to express their views in such hearings, and end up being under-represented.

We see this phenomenon occurring all the time in public hearings over new housing or infrastructure projects. Many blue states like California confront a severe housing crisis, driven by the lack of availability of affordable housing or the necessary infrastructure to support denser populations. A public hearing on a new building project will typically attract participation from developers, labor unions, existing homeowners, and environmental activists, who often take polarized and highly predictable positions. The people who are not represented at such meetings are, for example, young people who are unable to buy their first home, homeowners locked into their current houses because of exorbitant prices, or workers who might be well served by better public transportation. The latter groups may encompass a majority of citizens, but they are typically not organized or represented in the public discussion.

The over-organization of civil society is what weakened the initiative process in California, which as noted above was a populist innovation designed to bypass legacy democratic institutions. Within a decade or two of their introduction, the same well-funded interest groups that dominated the legislature learned how to manipulate the initiative process. In a large state like California, getting the necessary signatures to place an initiative on the ballot, and then to have the initiative passed, requires a high degree of organization and millions of dollars in funding for television advertising. It is easy to disguise the real source or implications of an initiative, and to manipulate low-information citizens.

An over-organized civil society has also distorted the notice-and-comment process. While the latter provides agencies with useful feedback, this channel today has become highly dysfunctional. Scale is once again at fault: with major rule changes, an agency can receive well over a million comments, requiring huge expenditures of time by agency staff to respond. The process can be gamed by interest groups that flood the zone with comments, or else slow the process by suing the agency over failures to respond adequately to individual comments.

Subscribe now

A final problem with existing forms of public participation has been pointed out by my Stanford colleague Jim Fishkin, director of the Deliberative Democracy Lab at the Center on Democracy, Development and the Rule of Law. Since the time of the Greeks, the ideal of democracy has been a group of citizens who could rationally debate a common course of action. Technology has in many ways undermined the possibility of genuine political deliberation in the U.S. Congress. Many older members note that deliberation ended when C-SPAN began televising Congressional hearings. Members began speaking not to fellow legislators, but to TV audiences at home. Various reform initiatives with the well-meaning intention of increasing transparency decreased opportunities for members to actually hold discussions with one another on a face-to-face basis. To the extent that deliberation happens, it now occurs in back-room negotiations over omnibus spending bills.

The problem of public participation can thus be stated as follows. Public input to democratic decision-making is absolutely necessary. It is inevitable that organized interest groups will play a big role in any open process. But it is important to structure that process in such a way that:

1. It can operate at a sufficiently large scale;

2. It cannot be easily captured by well-resourced and well-organized interest groups;

3. It can occur over a much shorter time period to facilitate efficient public decision-making;

4. And that participation be at least minimally deliberative.

So how do we design new participatory institutions to meet these conditions? That will be the subject of subsequent blog posts.

Francis Fukuyama is the Olivier Nomellini Senior Fellow at Stanford University. His latest book is Liberalism and Its Discontents. He is also the author of the “Frankly Fukuyama” column, carried forward from American Purpose, at Persuasion.

Follow Persuasion on Twitter, 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

Just so you know: In addition to this column, Francis Fukuyama also writes for the main Persuasion mailing list. That means that if you don’t subscribe to Persuasion, you might miss out on receiving some of his essays!

Click here to manage your account and toggle on the button to receive emails for Persuasion. And as ever, thank you for supporting our community.

Subscribe now

Email preferences

I have a longtime friend whom I’ve known since my college days, who made his money as an investor and entrepreneur at the edge of the tech world. One constant about him over the years has been his endless admiration for people he regards as “very smart.” He means this in a very specific way: they are very good at math, and have done well for themselves making money using their brainpower.

He’s not alone in this preoccupation. Silicon Valley is a virtual cathedral for the worship of geniuses—initially people like Steve Jobs, Bill Gates, and Elon Musk—who have built world-beating companies around applications of technology. That technology has now moved onto AI, where Sam Altman, Demis Hassabis, and Yann LeCun have become the new icons of brilliance.

And what this generation is building is, indeed, intelligence. There is a race currently on for artificial general intelligence (AGI), a machine that will have the cognitive capabilities of a human being. Indeed, more than that: cutting-edge machines are “growing” rather than being programmed, and are reportedly capable of modifying themselves to extend their own capabilities. They will not stop at human intelligence, but will become smarter than human beings. This type of “superintelligence” will then lead to huge advances in science, technology, and the economy. There are already achievements along these lines, like Hassabis’ Alphafold project that has solved protein-folding problems that seemed beyond the capabilities of earlier technologies. There are serious discussions taking place now about a future, not that far away, where advanced economies using superintelligent AI will be able to achieve substantially higher growth rates of 10, 15, 20 percent per year, compared to the 2-3 percent that’s considered substantial today. Material deprivation will disappear and be replaced by schemes to subsidize those whose livelihoods have been displaced by AGI, like universal basic income.

There are several problems with these speculations. The first is one I’m not in a position to evaluate: whether AGI or superintelligence are even possible. Writers like Eric Larsen have suggested that while LLMs are good at culling enormous stores of existing knowledge, they lack the kind of speculative insight that the cognitive scientist C. S. Peirce labeled “abduction” that is required for true innovative discovery.

But let us assume for the moment that AGI will come about, and that machines will become more intelligent in certain respects than human beings. There are powerful reasons to believe that this capability will be transformative in many ways, but may not produce explosive economic growth as the AI cheerleaders expect.

The reason for this skepticism is that the binding constraint on economic growth today is simply not insufficient intelligence or cognitive ability. Even absent smart machines, human beings today collectively have more cognitive ability than at any prior point in human history. The binding constraint has to do with how that intelligence interacts with the material world in a myriad of ways. Economic growth depends ultimately on the ability to build real objects in the real world. A smart machine may be able to come up with a plan for a better mousetrap, but to actually fabricate that mousetrap requires capabilities beyond any machine’s control.

At a macro level, we are already running into the constraint of too many dollars chasing too little stuff. As environmental doomsayers have been arguing for years, there are ultimately material limits to growth. The one most obviously in front of us is global warming, but there are many others. The planet does not have the resources to sustain 8 billion people with an American standard of living; indeed, at 10 percent annual growth, China, America, and Europe would soon run out of everything, including agricultural land, water, energy, and almost everything else.

At a micro level, there is a problem translating the work of smart machines into material goods. Product innovation has always depended on a prolonged iterative process whereby a designer tries out ideas, fails, and modifies the design in response. No amount of superintelligence will ever be sufficient to simulate the behavior of material objects under the conditions of the existing material world, as generations of builders and tinkerers know.

Finally, there is the political and social level. I attended a presentation by an engineer at a leading AI firm who suggested that in the near future, AGI would be able to, for example, provide clean drinking water to struggling cities in the developing world.

The problem is that the failure to provide such basic services in poor countries is not lack of knowledge of what a good municipal water system looks like. The problem is political and social. People do not want to pay the higher costs engendered by a new water system; unionized workers in the municipal water authority do not want to lose their jobs to automation; business owners do not want the disruption that will occur as the streets are torn up for new pipes; the finance minister believes there are other priorities and can’t raise taxes to pay for a new system. In many poor countries, there are water mafias that buy water where it is cheap, and resell it at extortionate prices. They are armed and ready to use violence if you get in their way.

A superintelligent machine may be able to understand these problems, but it will have no way of overcoming them. We already know what a good municipal water system looks like; what we don’t have is an implementation plan to put it in place in city X.

Our understanding of the role of intelligence has been distorted by the kind of technological change that has occurred over the past couple of decades. The internet, social media, and related technologies are all based on software. Apart from data servers and cloud storage, they don’t require fabricating new devices that have never been tested. As a result, software scales very easily. This is how Google, Meta, and other companies have been able to turn into giants so quickly.

Companies that make money by building material objects in the material world have much more difficulty scaling up. They too benefit from economies of scale, but reach a point of diminishing returns much faster than a software company. (This is, by the way, one reason why Elon Musk’s Tesla has been such a remarkable success story, because it has scaled successfully making material products.) We have somehow come to see the software paradigm as the dominant one that will characterize the AI age, but the economic benefits AI promises will not scale so easily.

This is not to say that AI will not lead to huge productivity gains: take a look at Jerry Kaplan’s predictions about the future of robotaxis. But intelligent people, like those in Silicon Valley, tend to overestimate the importance of intelligence in life more generally. There are many other abilities beyond intelligence that make for a good and successful human being, and many other inputs other than what AI can provide that are required to produce economic growth.

Francis Fukuyama is the Olivier Nomellini Senior Fellow at Stanford University. His latest book is Liberalism and Its Discontents. He is also the author of the “Frankly Fukuyama” column, carried forward from American Purpose, at Persuasion.

Follow Persuasion on Twitter, 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

We are delighted to feature Francis Fukuyama in the pages of Persuasion once again. Some of you may not know that he writes a regular column, “Frankly Fukuyama,” which is proudly part of the Persuasion family, and which you need to manually opt in to receive.

To get all of Frank’s writing—and to get articles from American Purpose, the magazine he founded, and its culture-focused podcast, Bookstack—simply click on “Email preferences” below and make sure you toggle on the relevant buttons.

Subscribe now

Email preferences

Ever since the year 2016, when Britain voted for Brexit and Trump was elected president, social scientists, journalists, pundits, and almost everyone else have been trying to explain the rise of global populism. There has been a standard list of causes:

1. Economic inequality brought on by globalization and neoliberal policies.

2. Racism, nativism, and religious bigotry on the part of populations that have been losing status.

3. Broad sociological changes that have sorted people by education and residence, and resentment at the dominance of elites and experts.

4. The special talents of individual demagogues like Donald Trump.

5. The failures of mainstream political parties to deliver growth, jobs, security, and infrastructure.

6. Dislike or hatred of the progressive Left’s cultural agenda.

7. Failures of leadership of the progressive Left.

8. Human nature and our proclivities towards violence, hatred, and exclusion.

9. Social media and the internet.

I myself have contributed to this literature, and like everyone else ticked off cause #9, social media and the internet, as one of the contributing factors. However, after pondering these questions for nearly a decade, I have come to conclude that technology broadly and the internet in particular stand out as the most salient explanations for why global populism has arisen in this particular historical period, and why it has taken the particular form that it has.

I’ve come to this conclusion by process of elimination. It is clear that all nine of the factors above have played some role in the rise of global populism. Populism, however, is a multifaceted phenomenon where certain causal factors are more powerful in explaining particular aspects of the phenomenon, or in explaining why populism manifests itself more powerfully in certain countries than others. For example, while racial resentments obviously play an important role in America, they do not in Poland, which is one of the most ethnically homogeneous societies in the world. And yet the populist Law and Justice Party came to power there for eight years.

Let’s go through the weaknesses of explanations 1 through 8.

Cause #1, growing economic disparities, was certainly a powerful driver of working-class voters toward populist parties and figures like Trump. However, around half of all Americans voted for Trump at a time when employment and overall growth were relatively high. We were not in the midst of a depression, as was the case in 1933 when Franklin Roosevelt was elected and the unemployment rate stood at nearly 25%. While economic stresses from inflation certainly drove many Americans to vote for Trump in 2024, inflation was far higher and more persistent in the 1970s.

Cause #2, the idea that populism is driven by a nativist white backlash, is a plausible one. While countries like Poland and Hungary don’t share America’s troubled racial history, one could argue that fear of immigration and the dilution of the power of those countries’ dominant ethnic groups was a powerful motivator of populist support. But even in America, racial fears are only part of the story. While Trump gets support from overtly racist groups and figures like the Proud Boys or Nick Fuentes, many non-whites, including African-Americans, Hispanics, and Asians, decided to vote for him in 2020 and 2024. Indeed, Trump has succeeded in doing what the Democrats once did: assembling a multi-racial working-class coalition.

Cause #3, the broad sorting that has occurred where Democrats have become the party of educated professionals living in big cities, while Republican voters are less educated and more rural, is replicated in many countries around the world. But sorting is more likely an effect of a deeper sociological change rather than a factor driving that change. Americans were not deciding to move to the countryside because they were conservative; rather, there was something about the conditions of life in rural versus urban areas that engendered different political perspectives.

Cause #4, the special talents of Donald Trump, is undeniable; he has many imitators but few have demonstrated the demagogic abilities that he has. But the MAGA movement that he has spawned has succeeded in taking over almost completely one of America’s two major parties, something that doesn’t happen purely by one man’s force of will. Becoming a Trump loyalist required many Republicans to abandon long-held beliefs about things like free trade and internationalism that once defined them. The fact that they were susceptible to this conversion is the phenomenon that needs to be explained.

Cause #5, the failure of Democratic politicians to solve or even address problems of public order, homelessness, drug use, infrastructure, and housing was obviously important to many centrist and independent voters. This was a big factor as well in many down-ballot races, where blue states and cities compiled poor governance records. But honestly, poor governance under left-leaning politicians has been with us for quite a while (recall New York City under Abe Beame and David Dinkins). One could argue that the social consequences of the pandemic triggered special awareness of these weaknesses, but Trumpism existed well before 2020.

Causes #6 and #7—intense dislike of left-coded cultural issues like DEI, affirmative action, political correctness, LGBTQ policies, immigration, and poor leadership by Democrats—are obviously related. It was poor judgment by Democratic politicians that allowed the party to be defined by these cultural factors, rather than staking out clear positions on economic issues of more general appeal. The problem with seeing cultural issues as central to the rise of populism, however, is that they have been around for quite a while. Feminism and social dysfunctions like drug addiction and family breakdown date back to the late 1960s, while identity politics made its debut in the ‘70s and ‘80s. These social movements engendered backlash and contributed to the elections of conservative presidents like Nixon and Reagan. Yet they did not set off the kind of furious reactions seen in the 2020s.

Cause #8, human nature, has been raised recently by Bill Galston in his new book Anger, Fear, Domination: Dark Passions and the Power of Political Speech, and celebrated in a recent review by Jonathan Rauch. Galston argues that ugly polarization and partisanship have always been part of human politics; the liberal civility that contemporary democracies have enjoyed in recent decades is an anomaly that needs to be explained, and not the norm of human existence.

The problem with any explanation of a social phenomenon that takes human nature as its starting point is the question of “why now?” Human nature has presumably been constant throughout human history; it does not explain why people’s behavior turned suddenly ugly midway through the second decade of the 21st century. A permanent human nature must be interacting with some other phenomenon that is more transitory and time-bound. In any event, Steven Pinker among others has argued that human behavior has been getting less violent over time, and there is a substantial body of empirical evidence to back him up. It is hard to argue that the sort of political extremism we’ve seen in recent years in the United States is worse than other instances of societal breakdown. Remember the Nazis?

Any satisfactory explanation for the rise of populism has to deal with the timing question; that is, why populism has arisen so broadly and in so many different countries in the second decade of the 21st century. My particular perplexity centers around the fact that, by any objective standard, social and economic conditions in the United States and Europe have been pretty good over the past decade. Indeed, it would be hard to argue that they have been this good at many other points in human history. Yes, we had big financial crises and unresolved wars, yes we had inflation and growing economic inequality, yes we had outsourcing and job loss, and yes we had poor leadership and rapid social change. Yet in the 20th century, advanced societies experienced all of these conditions in much worse forms than in recent years—hyperinflation, sky-high levels of unemployment, mass migration, civil unrest, domestic and international violence. And yet, according to contemporary populists, things have never been worse: crime, migration, and inflation are completely out of control, and they are transforming society beyond recognition, to the point where, in Trump’s words, “you’re not going to have a country any more.” How do you explain a political movement based on assertions so far removed from reality?

As I wrote in a recent article, the current populist movement differs from previous manifestations of right-wing politics because it is defined not by a clear economic or political ideology, but rather by conspiratorial thinking. The essence of contemporary populism is the belief that the evidence of reality around us is fake, and is being manipulated by shadowy elites pulling strings behind the scenes.

Conspiracy theories have always been part of right-wing politics in the United States. But today’s conspiracies are incredibly outlandish, like the QAnon belief that the Democrats are operating secret tunnels under Washington, D.C. and drinking the blood of young children. Educated people would rather criticize Trump’s trade policies than his connections with Jeffrey Epstein, and yet the latter has dogged him relentlessly for several months now (although here we have the case of an actual conspiracy to cover up this connection).

This is what leads me to think that Cause #9, the rise of the internet and social media, is the one factor that stands above the others as the chief explanation of our current problems. Broadly speaking, the internet removed intermediaries, traditional media, publishers, TV and radio networks, newspapers, magazines, and other channels by which people received information in earlier periods. Back in the 1990s, when the internet was first privatized, this was celebrated: anybody could become their own publisher, and say whatever they wanted online. And that is just what they did, as all the filters that previously existed to control the quality of information disappeared. This both precipitated and was an effect of the broad loss of trust in all sorts of institutions that occurred in this period.

Moving online created a parallel universe that bore some relationship to the physically experienced world, but in other cases could exist completely orthogonally to it. While previously “truth” was imperfectly certified by institutions like scientific journals, traditional media with standards of journalist accountability, courts and legal discovery, educational institutions and research organizations, the standard for truth began to gravitate instead to the number of likes and shares a particular post got. The large tech platforms pursuing their own commercial self-interest created an ecosystem that rewarded sensationalism and disruptive content, and their recommendation algorithms, again acting in the interest of profit-maximization, guided people to sources that never would have been taken seriously in earlier times. Moreover, the speed with which memes and low-quality content could travel increased dramatically, as well as the reach of any particular piece of information. Previously, a major newspaper or magazine could reach perhaps a million readers, usually in a single geographic area; today, an individual influencer can reach hundreds of millions of followers without regard to geography.

Finally, as Renee DiResta has explained in her book Invisible Rulers, there is an internal dynamic to online posting that explains the rise of extremist views and materials. Influencers are driven by their audiences to go for sensational content. The currency of the internet is attention, and you don’t get attention by being sober, reflective, informative, or judicious.

Nothing illustrates the central role of the internet more than the spread of the anti-vax movement, and the installation of Robert F. Kennedy, Jr. as Trump’s Secretary of Health and Human Services. Kennedy’s various assertions about the dangers of vaccinations are not only untrue; they are actively dangerous, because they convince parents not to give their children life-saving vaccines. It is hard to connect opposition to vaccines to any kind of coherent conservative ideology—indeed, in earlier periods conservatives would have welcomed the innovation and benefits that vaccines conferred. It is the internet that facilitated what grew into a vast network of vaccine skeptics. No number of empirical scientific studies could overcome the desire of many people who wanted to believe that there were evil forces in American society pushing things that were harmful to them, and they saw plentiful confirmation of their views on the internet.

Subscribe now

DiResta gives an example of how the internet contributed to this spread directly. There should be no reason why yoga moms should be drawn to QAnon and conspiratorial thinking. There was, however, one prominent yoga guru who urged his followers to look to QAnon for the truth. An algorithm on an internet platform picked up this connection, and in effect decided that if this yoga influencer was into QAnon, other yoga aficionados should also be into conspiracy theories as well, and started recommending conspiratorial content to them. That is what algorithms do: they don’t understand meaning or context, but simply seek to maximize attention by directing people to popular content.

There is another type of internet content that explains the particular character of our politics today, which is video gaming. This connection was brought home by the case of the young man, Tyler Robinson, who allegedly shot Charlie Kirk. Robinson was evidently radicalized on the internet. He was an active gamer who inscribed memes from that world on the shell casings of the bullets he used. This was also true of many of the January 6 participants, who had taken the “red pill” and could see the conspiracy of mainstream forces to steal the election from Donald Trump. And the video gaming world is huge, with worldwide revenues estimates in the range of $280-300 billion.

So the advent of the internet can explain both the timing of the rise of populism, as well as the curious conspiratorial character that it has taken. In today’s politics, the red and blue sides of America’s polarization contest not just values and policies, but factual information like who won the 2020 election or whether vaccines are safe. The two sides inhabit completely different information spaces; both can believe that they are involved in an existential struggle for American democracy because they begin with different factual premises as to the nature of the threats to that order.

None of this means that causes 1 through 8 are not important or helpful in leading us to an understanding of our present situation. But in my view, it is only the rise of the internet that can explain how we can be in an existential struggle for liberal democracy, at a time in history when liberal democracy has never been as successful.

Francis Fukuyama is the Olivier Nomellini Senior Fellow at Stanford University. His latest book is Liberalism and Its Discontents. He is also the author of the “Frankly Fukuyama” column, carried forward from American Purpose, at Persuasion.

Follow Persuasion on Twitter, 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

Just so you know: In addition to this column, Francis Fukuyama also writes for the main Persuasion mailing list. That means that if you don’t subscribe to Persuasion, you might miss out on receiving some of his essays!

Click here to manage your account and toggle on the button to receive emails for Persuasion. And as ever, thank you for supporting our community.

Subscribe now

Email preferences

One of the main threads running through the first eight months of the second Trump presidency is the question of the limits of executive power—that is, the degree to which Congress and the courts can place limits on the power of the president. This is the issue at the center of Donald Trump’s efforts to have the Justice Department indict former FBI director James Comey. There is a longstanding tradition of prosecutorial independence in the federal justice system, which holds that the Justice Department should exercise independent judgment when filing indictments, applying the law and not following the directives of the political branches. This rule is simply a normative one, however, and it has never been tested to date by such an overt intervention into the judicial process. The existing U.S. attorney for the Eastern District of Virginia, Erik Siebert, was a seasoned prosecutor who believed there was insufficient evidence to indict Comey, and he resigned in the face of President Trump’s demand that his department act. He was replaced by a compliant prosecutor, Lindsey Halligan, who agreed to file the charges just under the statute of limitations deadline.

This is but one example of Trump’s efforts to stretch the powers of the office of the president. Since virtually the day he was inaugurated, he has been firing officials he didn’t like or deemed insufficiently loyal to him, in clear violation of existing laws set by Congress that limit his removal power. There are, for example, any number of officials who can only be fired “for cause,” meaning that the president needs to articulate a clear violation and give the official time to respond. Trump has nonetheless gone ahead and fired inspectors general, members of multimember boards of Federal agencies like the NLRB, MSPB, and FTC, and is seeking the removal of a member of the Federal Reserve Board’s board of governors, Lisa Cook.

“For cause” officials are protected by statutes passed by Congress, and a 1935 Supreme Court decision, Humphrey’s Executor, affirmed the right of Congress to make such rules. But legal conservatives have long opposed that precedent under a doctrine of the “unitary executive,” which holds that the president alone is empowered to make such decisions. The Roberts court has upheld Trump’s right to fire many existing officials, and recently announced that it would be reviewing the underlying precedent by the end of the year. We can assume that the Court’s conservative majority will at that point formally lay Humphrey’s Executor to rest.

It would be useful to lay out the broader arguments for and against the theory of a unitary executive, since this is likely to become the law of the land soon. The first argument in favor is textual: proponents note the language of Article II of the Constitution, which states: “The executive Power shall be vested in a President of the United States.” They argue that these powers are plenary, and cannot be diluted by another branch. A president with plenary powers, they argue, is more accountable, since there is one singular point of responsibility for executive actions. A president can be voted out of office if citizens don’t like his decisions; not so with an executive branch with multiple independent agencies. Distributed executive power may have practical consequences, moreover, if the different parts of the executive don’t agree with one another. In an extreme but illustrative example, one would not want multiple parts of the executive branch debating one another in the event of a nuclear attack, or taking time to come up with a unified response.

I’m not going to debate the originalist issues here, like the implications of the “Decision of 1789.” I’m not a constitutional lawyer, or a lawyer at all; suffice to say that there has been a debate among legal scholars on the Founders’ actual intent. My argument is rather a practical one from the standpoint of good governance, which has to do with the importance of delegation.

All hierarchical organizations, from companies and clubs to armies and the U.S. government, are structured as a series of what economists call principal-agent relationships. The theory is that the principal in any organization has the legitimate authority to make decisions, and that those decisions are implemented by the agents below the principal. The economists who devised this theory argue that organizational dysfunction, manifested in phenomena like corruption, occurs when the agents follow their own narrow interests, rather than obeying the mandates of the principal. The problem then is to align the incentives of the agents with those of the principal. There are many ways of doing this: the principal can write detailed ex ante rules to constrain the agent’s behavior; he/she can demand ex post accountability for agents after the fact; and most importantly, the principal can exercise appointment and removal power over the agents to enforce proper behavior.

Applying this theory to the present case, President Trump as the elected president should have the ability to remove a prosecutor who is not following his dictates.

The problem is that this version of principal-agent theory is woefully inadequate to explain the behavior of most real-world organizations. The Nobel laureate economist Herbert Simon pointed out long ago that in many organizations, authority travels in the opposite direction, from the agents to the principals. The reason for this is that the agents often have much more expertise, skills, and knowledge than the principals, and are in a position to act more swiftly and effectively because they are embedded in the local context.

In other words, all effective organizations have to delegate authority to lower echelons of agents. There are many real-world examples of the importance of delegation, from just-in-time manufacturing to the performance of armies that empower junior officers to take risks and decisions on their own. Indeed, I would say that determining the appropriate degree of delegation is the central issue, both for organizations in general, and for the U.S. government in particular.

We see this most clearly in the case of the U.S. Federal Reserve. The Fed has a mandate to both control inflation, and to do so while maximizing employment. This is an incredibly complex assignment, particularly in a period when underlying forces are pushing inflation higher and employment lower at the same time. The Fed governors and their staff are among the most highly-trained specialists in the world, stocked with PhD economists and people with broad experience in financial markets. They respond to data, and though they make mistakes, it is hard to think of an alternative group to whom such awesome responsibility should be granted.

But the same is true of federal prosecutors. The U.S. attorneys bringing federal charges against wrongdoers are for the most part seasoned professionals who have broad experience in criminal law. They have the judgment to know when not to take on a case, because they do not want to waste court resources or prosecute someone likely to be found innocent.

Subscribe now

The U.S. Constitution separates powers among the three branches. But for the last 150 years at least, it has also separated powers within the executive branch. The first U.S. regulatory body, the Interstate Commerce Commission (ICC), was put in place to regulate the revolutionary technology of the late 19^th century, the railroads. Congress saw fit to put it under the direction of a multi-member commission that was by statute balanced for partisan representation. Since commissioners in the ICC and other similar bodies like the SEC, FCC or FTC served for staggered fixed terms, their policy orientation did not necessarily change quickly in response to an election which brought a new administration to power.

Generally speaking, these Congressional intrusions into executive authority have had the objective of protecting certain realms of executive decision-making from short-term politicization. That is, we don’t want all government decisions to be immediately accountable to voters, who do not necessarily have a good long-term understanding of their own self-interest. Almost everyone would prefer lower interest rates, but may not understand the downstream inflationary consequences of such a policy.

This is not to say that the status quo of Congressional regulation is always desirable. There are some federal agencies that do need to be made more responsive to the voters’ will, and there has been a long-standing debate among public administration specialists about whether multi-member commissions work as well as those with a single head of agency. But there is no question that the federal government needs to delegate authority to officials with the knowledge, skills, and expertise needed to run a complex modern state, and that Congress ought to be able to play a role in protecting that delegated authority.

Given its behavior up to now, it seems likely that the Supreme Court will soon eliminate most existing constraints on the president’s power to remove officials and control the behavior of the executive branch down to the most minute level. I’ve written before about how this opens the door to the kind of corruption that we saw under the 19^th century patronage system. But there is another issue as well that has to do with separation of powers.

Principal-agent theory begins with the premise that the principal is always right, and has the legitimate authority to make decisions. As I argued above, that authority is typically constrained by the need for expertise. But there is another issue as well, which is that the principal may not always be right: though legitimately elected, he may be incompetent, corrupt, ignorant, prejudiced, and hugely self-interested. In such a case, the agents under him may actually serve an important function in not carrying out his mandates, and acting as guardrails against the abuse of power.

Subscribe now

What is very strange about the Supreme Court’s 2024 presidential immunity decision was the way that it abstracted from the actual situation the United States faced in the Trump presidency. The conservative justices supporting the decision argued that future presidents needed to be given broad discretionary power to make decisions on behalf of the country as a whole, assuming they would be wise and public spirited. This abstracted from the fact that the ex-president in front of them had gone rogue, seeking to overturn a legitimate election and denigrating the entire electoral process on which American democracy depended. Yes, there may be good future presidents who need to be shielded from unfair accountability, but there are also times when citizens need to be protected from the president himself.

This is the ultimate justification for dividing powers not just between the branches of government, but within the executive branch itself. The modern president is so powerful that he can bend a host of social institutions to his will. No earlier president has ever arbitrarily withheld research money from universities, or threatened law firms that their attorneys would not be allowed inside federal buildings. Needless to say, no prior president has ever openly sought to use the Justice Department to punish his perceived enemies. A unitary executive would give a single individual complete control over these enormous powers, and the president sitting in front of us has openly announced his intention to use those powers for his own purposes.

I hope the Supreme Court is paying attention.

Francis Fukuyama is the Olivier Nomellini Senior Fellow at Stanford University. His latest book is Liberalism and Its Discontents. He is also the author of the “Frankly Fukuyama” column, carried forward from American Purpose, at Persuasion.

Follow Persuasion on X, 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

We are delighted to feature Francis Fukuyama in the pages of Persuasion once again. Some of you may not know that he writes a regular column, “Frankly Fukuyama,” which is proudly part of the Persuasion family, and which you need to manually opt in to receive.

To get all of Frank’s writing—and to get articles from American Purpose, the magazine he founded, and its culture-focused podcast, Bookstack—simply click on “Email preferences” below and make sure you toggle on the relevant buttons.

Subscribe now

Email preferences

I wrote back in January about “Elon Musk and the Decline of Western Civilization,” and I’m sorry to report that the decline continues unabated.

The past two weeks have brought news items that illustrate the point. On September 5, Tesla’s board announced an incentive package for Elon Musk that offered him a trillion dollars if he met some very ambitious goals for Tesla’s stock. The second was a series of moves by Larry Ellison, CEO of Oracle, and his son David, to consolidate a business empire that could eventually include, in addition to Oracle, Paramount Global, Skydance Media, MTV, CBS, Warner Brothers/Discovery (which owns HBO and CNN, among other properties), and Bari Weiss’ Free Press.

These are troubling developments from the standpoint of American democracy, for somewhat different reasons.

Tesla’s trillion-dollar pay package to Elon Musk was ostensibly intended to keep Musk focused on improving Tesla’s performance without being distracted by politics, his other businesses, or his relentless postings on X. The offer has already been criticized on business grounds. It seems very unlikely that Tesla’s stock can actually hit the price targets set in the deal, given the damage that Musk has already done to the brand with his political activities, and the increasing competition from China as well as legacy car makers who are moving into the electric vehicle space. Future growth will depend on untested technologies like robotaxis and humanoid robots, where there will be competition, technological setbacks, and uncertain demand.

But what is offensive about this offer to anyone concerned about the future of democracy is its sheer size. The U.S. federal budget deficit for this year is expected to come in at $1.9 trillion, and the Republicans’ Big Beautiful Bill is expected by the Congressional Budget Office to add another $3-4 trillion over the next decade. So if Musk wins this payout, he could single-handedly close a significant part of the national deficit, and personally fund all the Medicare, early childhood education, foreign aid, and other programs being cut as part of the BBB’s effort to minimize the deficit. Given that U.S. GDP last year was about $28 trillion, the payout implies that one man contributed more than 3.5 percent of the nation’s total output, while the other 340 million of us produced the remaining 96.5 percent.

Underlying the Tesla board’s offer is the view that a single individual can create a trillion dollars of new wealth. This feeds into the Ayn Randian narrative that progress is made by individual geniuses who spring up out of the earth like gods and bring benefits to the rest of us. The fact of the matter is that Musk is indeed a genius in certain specific ways, particularly in industrial organization. But Tesla’s success is a collective one, based on all of the engineers, designers, marketers, and factory floor workers who labor there. There is no recognition here of Tesla’s success being the result of social cooperation or team effort. Musk almost never credits his colleagues for his company’s rise. This individualist focus has become typical of American capitalism, and anathema to the way that many European and Japanese corporate leaders think about their own roles.

Musk’s pay incentive is, frankly, ridiculous. The idea that Musk needs this kind of reward to help his own company do well strains credibility. If Tesla’s potential failure isn’t enough to keep him focused, he probably shouldn’t be CEO in the first place. The payout is so outlandish that it’s not at all likely to happen; what is disturbing is the thinking that underlies the Tesla board’s decision.

The Ellison father-son moves are more in the mode of Silvio Berlusconi’s takeover of Mediaset or Elon Musk’s earlier purchase of Twitter. If they succeed in creating this media empire, they will control a vast array of outlets, both legacy and new media, that will allow them to directly influence American politics. Larry Ellison is a Trump supporter as Musk once was; he doesn’t appear to have political ambitions, though his son may. But that’s not the point. The real issue is the impact of concentrated wealth on American democracy, where two or three individuals control so much wealth and media power that they can help swing national elections, as Musk claims he did in 2024.

The Supreme Court’s 2010 Citizens United decision that declared campaign spending to be protected by the free speech provisions of the First Amendment looks worse and worse as time goes on. Context matters here: corporations and wealthy individuals may have speech rights, but concentrations of wealth in the United States have gotten so extreme that the speech of a few individuals is vastly more impactful than that of the rest of us. Since the rise of the free-market Chicago School in the 1970s and 80s, American antitrust law has come to focus much more heavily on the economic harms of concentrated wealth. It does not take into account the potential political harms that such wealth enables.

Americans also need to ditch this worship of great individuals as sources of national wealth and power. Yes, we have benefited from innovators and builders, but the country’s success has always been built on our social virtues: the ability of Americans to work together and to build strong organizations, both in the private sector and in civil society. That sociability has always required trust, and it is trust that has lately been in short supply in American society.

Subscribe now

Elon Musk is currently embroiled in a fight over a proposal from his Boring Company to dig some drainage tunnels under the city of Houston. A local legislator bristled over criticisms of Musk, calling him the “smartest man on the planet.”

Musk may be smart in certain ways, but in others he’s extremely stupid. Any competent CEO should know better than to take actions that would alienate the most important customer base of his company—which is exactly what he’s done with Tesla. He seems completely oblivious to the way that people outside his fanbase perceive him, suggesting at one point that people trashing his brand must be paid by the Democrats. Why else would anyone not admire him? Musk is in effect extorting his own company, threatening to walk away from it if he doesn’t get his payday. This is not the behavior of an institution-builder, but of a self-centered narcissist.

Francis Fukuyama is the Olivier Nomellini Senior Fellow at Stanford University. His latest book is Liberalism and Its Discontents. He is also the author of the “Frankly Fukuyama” column, carried forward from American Purpose, at Persuasion.

Follow Persuasion on Twitter, 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