This year has been a crazy time with regard to Washington’s treatment of artificial intelligence, and the pace has picked up in the last couple of weeks. This train of events began in February when Defense Secretary Pete Hegseth declared the leading AI firm Anthropic, a “supply chain risk,” meaning that neither the Pentagon nor its contractors could use Anthropic models without risking legal liability.

Then, in April, Anthropic announced that its latest Mythos model was so powerful that it would be released to only a handful of organizations. Mythos, it was claimed, had extraordinary abilities to break into computer systems, and these early organizations were asked to use it to test and secure their systems. In June, Senator Mark Warner told the Senate Banking Committee, “thank God it was Anthropic. When the head of the NSA and Cyber Command came and said, ‘This tool broke into almost all of our classified systems, not in weeks, but in hours,’ … we are not going to solve this problem if we rely on a less ethical CEO operating on the basis of plain voluntary testing alone.”

Experts later added caveats to this description of Mythos 5’s capabilities, but it is clear that the politics of AI regulation has shifted dramatically in the past month. The Trump administration came into office last year being advised by tech bros like David Sacks and Marc Andreessen, who opposed any form of AI regulation. The latter in fact created an organization called Leading the Future that put significant money behind lobbying against AI regulation. The Trump White House nonetheless intervened against Anthropic, but only for what looked like typically bad political reasons. The company, according to Hegseth, was too “woke”; otherwise, the administration’s default position was to oppose all regulation.

Persuasion events

This has now changed. The national security community has woken up to the fact that the latest AI models pose a clear and present danger to the security of the government’s data. This is not a speculative outcome years in the future, but one that is here right now. The Sacks-Andreessen faction can’t really argue against this, and so the balance of opinion on the need for regulation—at least, the pre-approval of new AI models—has shifted in favor of intervention. The latest twist is the Commerce Department giving Anthropic the green light to give its latest Mythos 5 models to a group of “trusted partners” so that they could ferret out vulnerabilities in the security of their systems. Similarly, OpenAI announced last week that its newest model would be restricted to a few government-approved organizations. So the White House has now joined the larger consensus in the tech community that believes that, however useful AI may be, it needs regulation.

The problem is that the Trump administration’s AI policy is typically chaotic. It is not clear who has final authority to issue new rules for AI, and on what basis. It appears that the turn towards regulation is driven by serious people in the national security community raising serious concerns, and not some clownish attempt by political actors like Pete Hegseth to punish woke enemies. But how are such decisions being made, and how will they be made going forward?

The problem up to now was that pro-regulation advocates could not define clearly the sorts of harms regulation was meant to protect against. Now there is a clear harm (cybersecurity), and so a more thoughtful institutional design effort can begin. Such an effort would need to answer the following questions:

• Do we need a specialized regulator for AI, or is this a function that can be added on to existing bodies like the NSA or the Defense or Commerce Departments?

• Regardless of which government entity does the regulation, how do we get sufficient capacity into the bureaucracy so that it can make well-informed decisions? U.S. government capacity in this area is woefully deficient. The typical approach in the past has been to outsource state capacity to private actors, but under present circumstances this could easily lead to regulatory capture by big, self-interested players.

• How does a regulator do surveillance and enforcement of any rules that it creates? The AI industry is huge and growing bigger by the day; moreover, foreign countries like China also have significant capabilities very close to those of the United States. If we deem a certain AI capability to be dangerous, how will we know that it is being developed, and how will we enforce rules limiting it? As Senator Warner’s remarks indicate, we are currently dependent on the good intentions of the CEOs running today’s large companies.

• To what extent should we delegate discretionary authority to the new regulator? In the past, statutes have spelled out the specific rules that the regulator was meant to enforce. But the AI field is evolving so quickly that any effort to write such specifications into hard law will be almost immediately overtaken by technological change.

These are just some of the real-world institutional design questions we need to answer if we are to adequately regulate artificial intelligence. My suspicion is that we will indeed need a specialized regulator, because AI is a sector very different from other parts of the economy. When trucking became an important means of transporting goods early in the 20^th century, Congress decided to give regulatory authority to the Interstate Commerce Commission. But this was a mistake: the ICC was designed to regulate railroads, and the economics of trucking are very different from rail transport. This is why the advent of air transport led to the creation of specialized agencies like the FAA and CAB.

Subscribe now

It is time to stop talking about whether we need an AI regulator; the dangers are here and now and we need to move quickly. The discussion needs to shift to a much deeper and more specific analysis of how to regulate, understanding that the dangers posed by AI are likely to change over time. Our main competitor, China, is moving in this direction as we speak: the country is not run by a bunch of libertarians who want to let the technology rip, come what may. That may have been our position in the past, but it can’t define our policy 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.

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

So Donald Trump, on his 80^th birthday, announced a deal in which there would be a 60-day ceasefire. Precise details have not yet been officially published. But, according to reports, they apparently include a cessation of attacks in Lebanon, the reopening of the Strait of Hormuz—according to Trump, “permanently toll-free”—and lifting the U.S. naval blockade of Iranian ports. He touted this as a key win, in the process praising China’s Xi Jinping and Russia’s Vladimir Putin for helping secure it.

This “deal” was nothing of the sort. If the reports are accurate, it instead represented a total U.S. capitulation to Iran. It basically set the clock back to February, when the Strait was open and the United States and Israel had not yet started bombing the Islamic Republic. It merely solved a problem that Trump and Israeli Prime Minister Benjamin Netanyahu had themselves created by launching the war in the first place.

Still left up to future negotiations are all of the objectives that the Trump administration has set forth over the past three months in trying to justify the war:

• There was no regime change or “unconditional surrender”; the Islamic Revolutionary Guard Corps remains even more firmly in control of the country than previously;

• There was no commitment by Iran to turn over its stockpiles of enriched uranium;

• There was no commitment to stop enriching uranium, either immediately or on some specified date in the future;

• There were no commitments on ending Iranian support for allied groups like the Houthis or Hezbollah in the region;

• There was no agreement by Iran to let up on the violent suppression of protesters.

The reported “Memorandum of Understanding” (MOU) kicks all of the contentious issues down the road into negotiations that are to take place during the 60-day ceasefire. Trump treated all of these issues as having been conceded already, but if that were the case, why weren’t they in the MOU? It is very unlikely that Iran will budge over the next two months, since it is precisely these issues that speak to the regime’s core identity.

Trump stated that if Iran didn’t agree to these outstanding terms, he would re-commence the war and possibly make the United States “the guardian of the Middle East” in return for 20 percent of the region’s revenues. It is hard to know whether such an initiative is more ludicrous from the standpoint of countries in the Middle East, including U.S. friends like Saudi Arabia or the UAE who would now be paying explicitly for U.S. protection, or from domestic opinion in the United States, where everyone would like to be done with the region as soon as possible.

The MOU that Trump celebrated is a worse agreement than Obama’s 2015 deal, which Trump endlessly castigated in the past. Obama’s deal forbade Iran from enriching uranium beyond 3.67 percent for 15 years (far below the 90 percent enrichment necessary for bomb-grade purposes), and provided specific measures for removing enriched uranium from Iran. All of these provisions were to be overseen by outside inspectors, and Iran complied with its terms until Trump withdrew from the agreement. The major criticism of the deal, which U.S. hardliners stressed, was that it said nothing about Iranian support for regional proxies and that it provided sanctions relief at the start of the agreement.

Trump’s reported MOU, meanwhile, places no limits on Iran’s nuclear capabilities, and makes no commitments about regional proxies. It does not provide for sanctions if Iran doesn’t concede by the end of the 60 days, though the Iranians have said that they will not proceed with final negotiations unless such relief occurs first. So Trump’s purported deal achieves considerably less than the agreement that Obama made.

It is clear that Trump is being driven to reopen the Strait of Hormuz at virtually any cost by the domestic pressure from rising oil prices and inflation. Being unwilling to send ground forces to Iran, he has had few cards to play over the past six weeks to get further Iranian concessions. So he has chosen to back down and accept a return to the status quo ante from before he began the war on February 28.

The world will indeed be better off if the Strait is re-opened. Perhaps Trump’s hardcore MAGA supporters can be persuaded that he has negotiated a consummate deal and achieved a great victory. But everyone else will understand that the world’s most powerful country is being run by a feckless and ignorant president who will impose immense costs on both other countries and his own people if he thinks it will benefit himself.

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

I recently delivered the Erhard Busek Memorial Lecture at the Europe’s Futures Retreat held on the island of Cres, Croatia. Some of my arguments here will be familiar to regular readers of this column, but I’m delighted to share them with you in this new form. —Frank.

I want to speak to you today about the question of European identity, which relates to the question of the future relationship between Europe and the United States.

U.S. 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 that the United States and Europe were 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 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. Rubio asserted that “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.”

Hidden within that speech, however, was a subtle distinction that points to the great division today between populists and liberals in both the United States and Europe. For an important group of American conservatives, “Western Civilization” denotes a specifically Christian civilization, and a culture based on 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 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.

As I have written before, 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.” This belief in universal human equality forms the basis for the modern view of human rights, as embodied in many constitutional documents across Europe.

But Christian heritage does not mean that Western identity is based on active Christian belief and heritage. Indeed, Western Civilization detached itself from specific religious beliefs from the 17^th century. The reason for this was historical: following the Protestant Reformation, Europeans spent the next 150 years killing each other over different interpretations of Christian doctrine, including ideas like transubstantiation or childhood baptism.

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 particular 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 that it made possible, emerged.

So, there is in fact a very different understanding of Western Civilization from the one that Marco Rubio advanced—one that is built around liberalism itself and encompasses Enlightenment values such as openness, tolerance, and skepticism about received ideas, and which is rooted in a rule of law that limits the power of governments over citizens.

It seems to me that Europeans today have no alternative but to base their common identity on this second understanding of Western Civilization.

The older understanding of an overtly Christian Western was gradually reconciled with modern liberal democracy in stages. Pope Leo XIII’s 1891 encyclical Rerum Novarum accepted the legitimacy of a market economy and sought to chart a third way between market liberalism and socialism.

Later, the Church’s historical flirtations with authoritarian government were rejected by the Second Vatican Council in the 1960s. The political expression of this reconciliation was the emergence and strength of Christian Democratic parties all across Europe, which played central roles in the acceptance of democratic values in the years after 1945.

Pope John Paul II’s encyclical Centesimus Annus, issued in 1991 on the 100^th anniversary of Rerum Novarum, sought to reconcile, with certain qualifications, Catholic doctrine with both liberal democracy and modern capitalism.

Persuasion events

It seems to me that contemporary European identity can therefore acknowledge its Christian roots, but base itself upon Enlightenment ideals of universal human rights and modern democracy. This is what all current member states of the European Union hold in common. This is what Europe also holds in common with the United States: not the United States of Vance or the MAGA world, but the United States built upon the foundation of Lockean liberalism.

This year, the United States is celebrating the 250^th anniversary of Thomas Jefferson’s Declaration of Independence, a document that states clearly in its second paragraph that “All men are created equal,” and asserts the principle that government receives its legitimacy from the “consent of the governed.” These are the kinds of abstract ideas that constitute the American national identity that emerged after the Civil Rights movement of the 1960s, and are values that Europeans and Americans hold in common.

The problem, of course, is that there are now two Americas, one reaching back to the overtly religious and nativist understanding of American national identity, and the other embracing the Enlightenment version. The second version has now been called into question, particularly during the second Trump administration. What one might call pre-modern America has been authoritarian in domestic policy and unilateralist and arbitrary in its foreign policy. Donald Trump during his second administration has tried to rule by executive order rather than going through the country’s constitutional processes. He has pursued policies that are manifestly contrary to law and even to the plain language of the U.S. Constitution. Similarly, he has declared himself unbound by any external authorities, including both economic and military treaty commitments, not to speak of bodies like the United Nations. His disregard for law is evident in the blatant corruption that he and his family, friends, and associates have engaged in since returning to power.

This lawless posture has direct international consequences. After the capture of Venezuela’s Nicolas Maduro in January, President Trump explained that he was limited in his international actions only by “my own morality.” He thus felt empowered to make claims on Greenland, the sovereign territory of a longstanding and loyal NATO ally. The United States is today involved in a war with Iran that was not sanctioned by the U.S. Congress, much less approved by international bodies like the UN Security Council or NATO. Indeed, Trump has attacked NATO allies for not helping to rescue the United States from policies that he himself undertook unilaterally.

From a European perspective, the central question is whether NATO allies would ever be able to trust the United States in the future, if for example Trump were replaced by another president who re-committed the United States to its former alliance obligations. The answer, I’m afraid, is no. The Republican Party and Republican voters, who were once the bedrock of support for alliance partners, have been changed beyond recognition. Before 2016, it was a party committed to free trade, limited government, openness to immigration, the strong defense of allies, and a democratic world order.

Since the rise of Donald Trump, it has coalesced around an “America First” agenda that wants to close off the United States to the outside world. Trump has openly favored dictatorships like Putin’s Russia, Kim Jong Un’s North Korea, or Xi Jinping’s China over democratic countries in Europe and Asia. He has visibly eroded trust within the United States, attacking domestic opponents as enemies and traitors, and degraded the quality of discourse through vicious personal attacks on perceived enemies. There is no guarantee that a more Europe-friendly future president would not be replaced by a similarly nationalistic one in another few years.

These problems will be exacerbated by new technological developments, in particular the growth of artificial intelligence. It is of course impossible to predict the speed and extent of AI’s future capabilities. Many industry insiders think that we will achieve AGI—artificial general intelligence—within a few years, while others are more skeptical. Regardless of when that happens, certain long-term trendlines are already evident. They were pointed to in the recent encyclical, Magnifica Humanitas, issued by Pope Leo XIV, which was deliberately positioned as the successor to Leo XIII’s Rerum Novarum.

The encyclical points to two separate dangers. The first is that AI will increase inequalities around the world, both within individual societies and between different societies. AI as it is currently developing rewards large scale. At this point, only the United States and China have the ability to build data centers large enough and in sufficient numbers to power the latest frontier models. There is substantial speculation that this disparity will only increase over time, as frontier models are able to modify themselves and “grow” new capabilities in a positive feedback loop. In this race, Europe lags significantly behind. Europe does not host any large technology companies that are competitive with the American and Chinese leaders, and there does not seem to be a path forward to creating any.

The second challenge is one of governance. Unlike previous technological revolutions, AI is not being developed in government labs, but entirely in the private sector. It is being developed by what the encyclical labels a “technocracy,” whose defining values are profit and power, and not any conception of the common good. This technocracy has extraordinary powers both to reshape domestic economies, and to intervene in international affairs directly as well.

Take for example Starlink, a global satellite system that, unlike GPS/GNSS, was developed not by a government, but by a private individual, Elon Musk. That control allowed Musk to become an independent foreign policy actor. In the early stages of Russia’s full-scale invasion of Ukraine, he helped Kyiv by providing Ukrainian forces with internet connectivity, but then took it away when they began to threaten Russia’s position in Crimea. In doing so, he was not working with any government in America or Europe, but simply conducting his own private foreign policy.

In the future, we will face similar challenges from AI. As the Pope’s encyclical notes, it is impossible for AI not to incorporate certain social values. These values are non-transparent, and may not even be knowable by the companies and engineers who are creating the AI systems.

In light of these challenges, it is not sufficient to say that governments need to regulate AI. The United States, which is home to the leading frontier systems, has shown little interest in AI regulation. The geopolitical competition between the United States and China will disincentivize regulation, which will inevitably slow down the pace of AI development.

But it is not clear to me that governments, either in China, Europe, or North America, will even have the ability to control AI if they want to. Our governments do not have the technical capacity to keep up with fast-moving technology, which in the end may not be controllable by anyone. Nationalization of AI will not be a safe solution either, as it will put an incredible power in the hands of the state. Even if that state is democratically controlled, it is not clear that we will be able to avoid the abuses that are likely to emerge from such power.

I want, however, to end on a more optimistic note. Despite the damage to institutions that has occurred over the past decade, I believe that the checks and balances built into modern democracies will continue to operate.

The most important of these checks are elections. The recent Hungarian election showed that voters could make clear choices and reject authoritarian leaders like Viktor Orbán. I do not believe that the fears that many people had last year about a rising populist tide sweeping Europe will come to pass. There is strong evidence that Donald Trump will be repudiated in the midterm elections this coming November, and that the Democrats may retake not just the House of Representatives, but the Senate as well. Donald Trump has not proven to be the unifying glue that holds the European far right together. No party will want to bind itself closely to an aging, mentally deteriorating 80-year-old man who seems to be losing control of events both at home and abroad.

With regard to AI, there is a powerful political backlash growing in the United States against unbridled technological development. Both political parties have wings that are very skeptical of the promised benefits of AI deployment, a movement that is likely to grow over time. So neither democratic backsliding nor technocratic dominance are inevitable. Societies can exercise agency over their futures; they only need to recognize the threats they face and do the hard work of mobilizing against them.

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.

Parts of this talk were adapted from the article “What ‘Western Civilization’ Really Means.”

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

Now it’s very unfair, and Republicans, judges and justices, they always want to show that they’re independent… “I don’t care if Trump appointed me. I don’t care if he doesn’t make any difference to me. I’m voting against him.” Because they want to show their independence. You know, stupid people.

—Donald J. Trump, April 1, 2026

President Trump was disgruntled after attending, in person, the Supreme Court hearings on his executive order seeking to abolish birthright citizenship. Many of the Justices expressed skepticism over the arguments made by Trump’s solicitor general, John Sauer, as to the constitutionality of the order. Trump not only mocked the idea of birthright citizenship, but also the very idea that judges were supposed to be independent from the president who appointed them. Over the past week, federal lower court judges have blocked a number of his moves, including renaming the Kennedy Center, the $1.8 billion slush fund to reward January 6 rioters, and the Justice Department’s vindictive prosecution of Kilmar Abrego Garcia. This has led to a chorus of attacks by Trump backers against “radical” activist judges allegedly acting out of partisan rancor.

In light of these events, it may be useful to review the history of the idea of judicial independence. It is one of the foundational institutions of Western, and particularly Anglo-American, political development, and indeed one of the ideas upon which the greatness of Western civilization itself rests.

Judicial independence can be traced back to a series of events known as the Investiture Controversy that took place in the second half of the 11^th century. This crisis pitted Pope Gregory VII against Henry IV, the Holy Roman Emperor, over the issue of whether the Pope or the Emperor should have the right to appoint priests and bishops within the Church. As is the case today, appointment power over senior officials was the source of control of the Catholic Church itself, which was the dominant institution apart from political authority.

In this period, the Catholic Church was also the guardian of the law. Church officials had discovered a long lost copy of the Justinian Code, the authoritative compilation of Roman Law that had been assembled by the Byzantine Emperor Justinian in the 6^th century. This code was the ancestor of contemporary civil law used today in Europe and Asia, and the Church began to teach it in the law schools that had been established in cities like Oxford, Paris, and Copenhagen.

The Investiture Controversy led to a prolonged struggle in which Henry IV was excommunicated and had to seek absolution from the Pope “barefoot in the snow” at Canossa. The matter was settled only in 1122 in the Concordat of Worms, which allowed the Church to keep control over the appointment of its own cadres. Thus, control over ecclesiastical law remained in the hands of an institution, the Church, that was independent of dominant political authority.

Over time, law evolved, both on the continent and in a separate common law tradition in England, into a body of rules that was not directly controlled by executive authorities. This was not for lack of trying: ambitious monarchs over the centuries continued to try to wrest legal authority from the Church.

In England, King Henry VIII ultimately created a separate Church of England because the papal authorities in Rome would not grant him a divorce from his first wife. The later Stuart king, Charles I, sought to evade existing legal authorities by exploiting the King’s Court of the Star Chamber, a separate judicial body he controlled that would allow him to go after his political enemies (sound familiar?), instead of working with Parliament. Charles’ repeated efforts to go around the law and evade parliament eventually led to his beheading and the English Civil War. The conflict between King and Parliament festered and was only settled in 1688-9 by the Glorious Revolution, which deposed the Stuart dynasty and established the principle of parliamentary supremacy. Hereafter, English monarchs were not above the law, but below it, and had to submit to laws made by parliament.

Paying Persuasion subscribers are invited to join our Intellectual Bootcamp, where we read classic articles and books that help make sense of the modern world. So far it’s been an enormous success! If you would like to join, please take advantage of a 20% discount on paid membership today. Check out our events page to learn what we’re reading next.

20% off Persuasion

There is a bigger picture to observe here. The fact that law came to be controlled by an independent judiciary was one of the sources of the rise and dominance of Western civilization in succeeding centuries. China, Persia, and Byzantium all practiced a form of what is labeled “Caesaropapism,” in which state authority was fused with ecclesiastical power, giving emperors and kings ultimate control over the law. In England and other parts of Western Europe from the 18th century onwards, by contrast, the law was controlled by independent judicial authorities. This counterbalanced executive power, and made possible the modern economic world. As any economist will tell you, a rule of law (by which they mean property rights and contract enforcement) is critical to modern economic growth. And a rule of law (as opposed to authoritarian rule by law) is made possible only by the existence of an independent judiciary. If kings and presidents can interfere arbitrarily in economic transactions and take property at will, no one will invest or innovate.

An independent judiciary is also what made America great. The United States never had a powerful European- or Chinese-style state, but it did inherit from Britain a strong common law tradition in which a decentralized network of judges could create stable general laws under the principle of stare decisis (that is, judicial decisions made in one jurisdiction would set precedents for all the others). To this was added statute law passed by legislatures at state and later federal levels, which created a platform for economic growth in the 19^th century and beyond.

Donald Trump, of course, knows nothing of this history, and operates under the belief that since he was elected president, he has the right to control the judiciary. For his entire career, he has seen the legal system not as a neutral adjudicator of disputes, but rather as a weapon he can use to increase his personal wealth and power. Especially since the beginning of his second term, his attacks on the rule of law have accelerated, and culminated in Acting Attorney General Todd Blanche’s effort to create a slush fund that would put nearly $2 billion taxpayer dollars in the pockets of his cronies and absolve his family from any legal accountability for fraud or abuse.

It is only political pressure, this time coming from some Republicans, that has forced him to pull back on this issue. But Trump will never concede to the principle that he must act according to law, or that the justice system is anything other than a tool that he will bend to his own purposes.

In doing so, Donald Trump is not only rejecting an important source of American greatness, but one of the foundational principles of Western civilization. He thus joins the world’s other Caesaropapists in seeking to fuse law and executive authority.

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 clear that we are living through a dramatic revolution in warfare brought about by changes in technology. Classic airpower, manned by human pilots, is increasingly being displaced by pilotless drones and ballistic missiles. This has led to surprising developments, as seemingly weaker powers like Ukraine and Iran have been able to stymie larger ones like Russia and the United States.

Over the last several weeks, the mainstream media has begun picking up on the fact that Ukraine has been doing much better on the battlefield, and that the war with Russia may at long last be turning in its favor. But some of the claims about the underlying technological revolution have been exaggerated, and we need to understand the precise ways in which warfare is changing.

Airpower by itself has always had great difficulties in achieving political objectives, something aptly demonstrated by the ongoing Iran war and Operation Epic Fury. What I want to investigate here is how airpower affects the land battle, which remains the main way that war influences political outcomes. In this realm, there are three main domains in which it has been used historically.

The first is strategic: the destruction of large targets deep in the enemy rear that have important roles sustaining the enemy’s war effort, like factories, railroad junctions, power grids, and the like.

The second use of airpower is operational: hitting military targets closer to the battlefield, perhaps 10 to 100 kilometers behind the front lines, including supply lines, air defenses, troops massing for an attack, communications facilities, command posts, barracks, or fuel storage needed by mobile armored forces. Such attacks are critical in “shaping” the land battle by disrupting communications and resupply.

The third mission is close air support: that is, attacking enemy forces that are actively engaged in battle on the front lines.

The first and the third of these have already been greatly impacted by new technologies, and we are about to witness big changes in the second category. Let’s see what recent wars have demonstrated.

A lot of recent media coverage concerns the Ukrainian campaign of long-range drone strikes that have targeted Russian oil and gas facilities, in some cases thousands of kilometers from the Ukrainian border. Observers have noted the lack of military hardware at this year’s May 9 Victory Day celebrations in Red Square for fear of Ukrainian strikes during the ceremony, and Vladimir Putin’s reported fear of assassination by drone.

Technology has made a huge difference in this realm. During World War II, the British Bomber Command and U.S. Eighth Air Force attempted to hit strategic targets like ball bearing factories in Germany. But Nazi air defenses forced bombers to fly at night, when their accuracy was atrocious. This led to the Allied decision to indiscriminately bomb urban civilian targets, leading to the flattening of cities like Dresden, Hamburg, and Tokyo, with accompanying civilian casualties in the hundreds of thousands. Despite the armchair strategizing of people like Lindsey Graham, these kinds of civilian attacks are both morally repugnant and have a poor track record in changing the political calculations of targeted countries. The Russians have been hitting Ukrainian civilian targets throughout the war; though they have made life miserable for its citizens, they have not brought about the country’s capitulation.

It is in the realm of close air support that drone technology has had the most revolutionary effects. This mission has historically been very difficult to carry out: until the advent of precision-guided munitions in the late 20^th century, like the Maverick missile or guided GBU 10 and 12 bombs, it was hard to hit point targets from the air. Even so, “low and slow” aircraft like AC-130 gunships or the beloved A-10 Warthog were vulnerable to air defenses, and ran the risk of fratricide, where the aircraft would mistakenly hit a friendly target.

Inexpensive FPV drones, which are now being produced by Ukraine in the millions per year, have changed this calculus completely. Classic combined arms maneuver warfare—that is, rapid breakthroughs by armored vehicles that can drive deep into the enemy rear, cut supply lines, and capture territory—has been made virtually impossible. FPV drones have made the battlefield completely visible; they can see everything and strike everything they see, not just tanks and surface-to-air batteries, but individual foot soldiers. FPV drones are not, at least for now, vulnerable to modern air defenses, and are much more precise than earlier munitions.

The one mission that remains the domain of airpower is the operational one, beginning with the establishment of air superiority in the early stages of a campaign. By neutralizing SAM batteries and destroying the enemy’s aircraft, either on the ground or in the air, airplanes remain very useful. Airplanes are also necessary for certain kinds of strategic missions such as delivering heavy “bunker buster” bombs like those the United States used against Iran’s Fordow enrichment plant last summer.

But operational missions are now being transformed as well. Early in the war, the Ukrainians used American HIMARS rockets, with ranges in the tens or low hundreds of kilometers, to great effect. While these have been largely neutralized by Russian countermeasures, the Ukrainians are developing a new generation of drones and rockets that can strike at operational distances.

We see this unfolding as we speak in Russian-occupied Crimea. The Ukrainians have been systematically taking out Russian air defenses with medium-range drones and missiles. The peninsula has very constricted supply lines, with a road and rail connection through the narrow isthmus to the north, and the Kerch Strait bridge connecting it to the Russian mainland. The Ukrainians reportedly now control the isthmus route from the air, and have attacked the bridge repeatedly over the past three years.

Subscribe now

Under these circumstances, it would not be at all surprising if the Russian command decided at some point in the coming year that its position in Crimea was untenable, and began to withdraw its forces there, just as it has already withdrawn the bulk of its navy. Such a withdrawal would, of course, mean an enormous political defeat for Vladimir Putin.

Airpower is not obsolete yet. Success in war still depends on layered defenses and systems that are capable of operating within each of the layers. In judging the future of drones versus legacy airpower, however, the question is not one of pure capabilities, since airpower will remain superior in certain operational and strategic missions. Rather, the issue is one of relative cost.

While a Patriot missile can shoot down a Shahed drone, the Patriot costs north of $4 million, while the Shahed is produced for less than $40,000, and in much larger quantities. In the future, countries like Ukraine will be able to unleash swarms of low-cost drones, controlled autonomously by AI systems. Operation Epic Fury in the Middle East, meanwhile, has demonstrated that the sophisticated air defenses provided to America’s friends in the Gulf have been unable to prevent serious damage to their facilities from Iran’s drones and missiles. This balance of capabilities will persist until someone comes up with a cheap and effective anti-drone system. Many countries and companies are working on that today, but we are not there yet.

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 was both painful and humiliating to watch media coverage of Donald Trump’s recent visit to Beijing, because it amply demonstrated America’s decline as a great power relative to China. Prior to the summit, expectations were very low: Trump was in a weakened position, beset by inflation and declining popularity, while seeking Chinese help in getting out of the Iran trap he has created for himself. Xi, on the other hand, had forced Trump to back down in his trade war the year before, with China showing strong export growth in the face of Washington’s weak response.

And so it was. Trump returned to Washington with little to show for his visit: only two agreements on opening Chinese markets to U.S. products, and no political help in the Middle East. China did agree to buy 200 Boeing aircraft (fewer than expected), but it has failed to follow through on similar announcements in the past. The White House also claimed that China has agreed to purchase $17 billion of agricultural products, but China has not confirmed this. It did not prevent Trump from claiming that they “did great trade deals” and that the meeting was “a great success.”

It was the optics of the meeting that demonstrated how far Trump has fallen in Chinese eyes. Trump was not met at the airport by Xi. He was seated on the podium in a chair that made him look smaller than Xi, a slight that could have been avoided had Trump’s State Department not sidelined the protocol officials whose job it is to look after these things. The worst part of the visit was Trump’s constant sycophancy, exclaiming that Xi was a “great leader,” “really a friend,” someone “from central casting”; he effused time and again about how beautiful and impressive China is. As in previous interactions with various dictators, Trump seems to have thought that they would be impressed by the same kind of praise and flattery that he himself revels in. Xi, for his part, failed to reciprocate any of these assertions of friendship, saying merely that the United States and China “should be partners and not rivals.”

The most significant issue arising out of the summit was Taiwan. Trump had held up a $14 billion arms package voted by Congress in advance of the summit, and there is no indication delivery will resume anytime soon. Xi told Trump that future relations with Washington would be conditioned on the level of U.S. support for the island. A light went on in Trump’s head that Taiwan would be a “very good negotiating chip” in trade negotiations with Beijing. Trump made other dismissive remarks about the island, noting that “we’re supposed to travel 9,500 miles to fight a war,” and repeating his assertion that Taiwan has stolen semiconductor chip technology from the United States.

His failure to say anything about Taiwan’s security stood in sharp contrast to Joe Biden’s clear assertion that the United States would act in its defense.

Donald Trump is a politician who is unable to see the world in anything but personal and self-interested terms. He was furious after his return at the suggestion that Obama was treated with more respect than he was, using the occasion to assert that “nobody respects Obama,” who was in any case “a divider.” The Chinese media has been talking for some time about the United States as a “declining power”; Xi brought it up with Trump by expressing hope that their countries could avoid the “Thucydides trap” if a declining America ceded power gracefully to a rising China. Trump immediately interpreted this as Xi agreeing with him that America was in decline under Joe Biden, but that it was great again now that he was president. As usual, Trump reserves his greatest anger and hostility for his domestic opponents, and not the leaders of the world’s great dictatorships.

The truth of the matter, which the Chinese understand very well, is the opposite: American decline is a direct product of Trump’s rise since 2016. It is as if Trump has decided to do everything in his power to weaken the United States vis-à-vis China. He has polarized an already polarized country like no previous president; he has cut funding for basic scientific research and attacked American universities which were the best in the world; he has gotten the United States involved in an unnecessary war in the Middle East that has depleted stocks of advanced American weapons; he and his colleagues have openly stated that their domestic opponents, the Democrats, pose a far bigger challenge to the future of the United States than either China or Russia.

Subscribe now

Trump has also systematically sought to undermine the U.S. alliance system, disparaging allies while heaping tariffs on even the closest traditional friends, and threatening to grab territory from Denmark, a loyal NATO ally. He claims that the United States under his leadership is now respected as never before, when something close to the opposite is true: both friends and rivals agree that the United States has become something of a rogue state that is contributing to global instability and disorder, as well as something of a laughing stock.

Trump has made Xi Jinping’s life enormously easy in a way that was reflected in his behavior during the summit. America under Trump is engaged in such a determined process of self-harm that China does not really have to do much but sit back and watch it unfold. Trump predicted that China would not attack Taiwan while he was president. He may be right about this: Xi does not want to get in the way of a declining United States. But he may be forced to act quickly if America finally gets a president who wants to reverse that trajectory.

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

Today, it was my pleasure to speak at William & Mary’s 2026 Commencement ceremony. The namesakes of this college played an underappreciated role in the birth of liberalism, so I’m delighted to share my remarks and their story with you now.

—Frank.

Chancellor Gates, Rector Poston and members of the Board, President Rowe—thank you for the beautiful video and introduction and for the honor from this distinguished university.

To the students, faculty, parents, relatives, and friends of the graduating class of 2026, I am very honored to be able to speak to you on this day. This year is part of William and Mary’s “Year of Civic Leadership,” as well as the 250^th anniversary of the signing of the Declaration of Independence. I’m grateful for the introduction, and want to add one small biographical note.

Back in 1989, I published an article entitled “The End of History?” with a question mark at the end. I don’t want to spend any time today explaining the meaning of that phrase, which was not mine but that of the German philosopher Hegel. Suffice it to say the article set off a firestorm of discussion about democracy and world politics. It eventually led to my getting my first academic appointment at George Mason University. I was told by my sponsors that I had received a huge number of references in the citation index that is used to evaluate the work of scholars.

What they didn’t say was that probably 99 percent of those citations said I was completely wrong.

With your permission, I would like to talk to you a little about history and the role that your college’s namesakes played in it.

William of Orange was a Dutch prince, married to Mary Stuart, the young daughter of King James II of England. William was invited by a group of English nobles to help overthrow Mary’s father. This was the culmination of a series of events starting in 1688 known as the Glorious Revolution.

At the heart of the Glorious Revolution was a crisis over constitutional authority. The Stuart kings Charles I and James II had insisted on their right to unilaterally impose taxes and make laws without the consent of Parliament. This led to an English Civil War, the beheading of Charles, an interregnum under Oliver Cromwell, and finally the restoration of the Stuart dynasty.

Subscribe now

But the principle of parliamentary supremacy had not been fully established by the late 1680s. The Catholic King James refused to consult with Parliament on a host of policy issues, and he appointed Catholic officers to key posts in the army. Fear that he would return England to Catholicism led to an uprising, James’s abdication, and his replacement by William and Mary.

The Parliamentary side in the Glorious Revolution rallied under the banners of two principles: “no taxation without representation,” and, more broadly, legitimate government coming from the “consent of the governed.” William and Mary ascended to the throne with the understanding that hereafter, English monarchs could no longer operate with absolute authority, but needed to get the consent of Parliament first. The philosopher John Locke had accompanied Mary Stuart back to England from the Netherlands, and wrote his Second Treatise of Government that set these principles in a universal context.

The American Founding Fathers read John Locke. Thomas Jefferson studied John Locke while a student at William and Mary College, and incorporated the principles of “consent of the governed” and “no taxation without representation” into the Declaration of Independence. This, of course, is the document whose 250^th anniversary we are celebrating this year. The College of William and Mary played a role in this Founding; John Locke himself wrote a letter in 1699 to James Blair, the college’s first president, inquiring into the progress it had made.

The Glorious Revolution established the principle that the King’s authority is not absolute, and is limited by the need to get approval from a representative body. Neither England in 1689 nor the American colonies in 1776 were democratic in the sense of universal citizenship, but they accepted the idea that government authority needed to be limited by a rule of law, and the idea of constitutional checks and balances. This is the meaning of “liberal democracy”—a government that gets its authority from the consent of the governed, but also limits that authority with a rule of law.

We are today living in an historical period in which liberal democracy has been in retreat around the world. Liberal democracy went through a huge expansion beginning in the 1970s and reached a peak in the years after the collapse of communism. But according to Freedom House, the aggregate level of democracy leveled off around 2008, and has been falling ever since.

This new world has been characterized by the rise of authoritarian great powers like Russia and China. But the regression from democracy has occurred as well in existing democracies, including several that were long established. What we call “democratic backsliding” has centered in the first instance on a deterioration in respect for the rule of law, rather than attacks on the principle of democratic representation per se. We have seen this taking place in many countries, including Hungary, Turkey, India, El Salvador, and, unfortunately, the United States.

Take the example of Hungary, a small country in Central Europe that nonetheless became a model for democratic regression. With the rise of Viktor Orbán and his Fidesz party in 2010, the government progressively packed the courts with Fidesz supporters, put the media under the control of Orbán’s friends and cronies, changed the electoral laws and constitution to make it ever harder to unseat the ruling party, and assumed control of large parts of the Hungarian economy. Hungary shifted sides in the great global struggle between democracy and authoritarian government by supporting Russia in its aggressive war against Ukraine and blocking efforts by the rest of the European Union to help the latter country.

Subscribe now

Orbán explained that he was creating what he labeled an “illiberal democracy,” that is, a country that would continue to hold democratic elections, but would burst the limits of existing laws and use state authority arbitrarily. His party and country served as an inspiration to many other would-be “illiberal democrats” around the world.

The good news in 2026 is that Hungary voted in April by huge margins to eject Viktor Orbán and Fidesz from power. Hungary had fallen from one of the richest Eastern European post-communist countries in the 1990s to one of its poorest as a result of the gross corruption of the Orbán regime. Voters saw this and overwhelmingly rejected Fidesz. As in Poland three years earlier, Hungary proved that elections remain one of the most important checks on arbitrary power, and that citizens can still exercise agency by withholding consent from those who seek to govern them.

At the College of William and Mary, the 250^th anniversary of the Declaration of Independence has been declared the “Year of Civic Leadership.” It is critical for you who are graduating today to understand the great opportunity that you have to exercise that leadership in future years.

You are living, as Abraham Lincoln explained, in a democracy “of the people, for the people, and by the people,” that by the end of the Civil War received a “new birth of freedom.” Citizenship in such a country does not mean that you should passively enjoy the benefits of life in a free society; it is not enough to simply follow the law and pay your taxes. Civic leadership requires active participation in the democratic process. You need to pay attention to public affairs, and to understand that you personally have a responsibility to improve the common life of our country. You need to honor the legacy of King William and Queen Mary by playing your part in supporting a constitutional order built around John Locke’s contention that legitimate government arises out of “consent of the governed,” and the Declaration of Independence’s assertion that “all men are created equal.”

Thank you very much for your 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, 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

Last weekend, I had the pleasure of giving an address in Aarhus, Denmark. Using “Getting to Denmark” as a shorthand for building a high-trust society, I took the opportunity to explore how Donald Trump is undermining trust at home and abroad—and why Americans should be inspired by Denmark’s example.

– Frank.

I’m happy to have been invited back to another Matchpoints conference here in Aarhus. I have very fond memories of the time I was a visiting professor here, and am glad to have the opportunity to catch up with some old friends.

As you may know, I was responsible for popularizing the idea of “Getting to Denmark.” This phrase was used originally by a friend of mine at the World Bank, who complained that many development programs funded by rich countries unrealistically sought to turn poor countries like Somalia or Afghanistan into effective states like Denmark overnight.

My admiration for Denmark is somewhat different from that of Senator Bernie Sanders. He likes Denmark’s social democracy. I instead marvel at the quality of government in this country, its efficiency and relative lack of corruption. We scarcely understand how the Denmark of the Vikings got to be modern Denmark, much less how to transform a contemporary underdeveloped country in a similar fashion.

I knew that I had to return to Denmark last February when my president, Donald Trump, began threatening your country and talked once again about taking over Greenland. World order cannot exist without a minimal degree of trust, and today the United States has become a giant source of distrust.

Paying Persuasion subscribers are invited to join our new Intellectual Bootcamp, where we read classic articles and books that help make sense of the modern world. If you would like to join, please take advantage of a 20% discount on paid membership today. The Zoom link will be emailed to you both a few days in advance and on the day itself.

20% off Persuasion

There are two critical types of trust. The first is trust in formal institutions like the rule of law and the existing constitutional order. People must have a shared understanding of the law, and confidence that the state will enforce it. The second form of trust is what has been labeled “social capital,” that is, informal norms that allow people to work together. Both types of trust rest on a foundation of moral virtue. People come to trust government if the institutions that comprise it are stable and predictable, and they trust one another if they are individually honest, reliable, and keep commitments.

Trust builds over time: if citizens interact with one another, they will gravitate to working with those who show themselves to be honest and reliable. It is only through a process of repeated interaction that trust develops.

Both social capital and trust in formal institutions are necessary for the proper functioning of both a modern economy and a healthy democracy. Economic prosperity is built on the belief that the government will enforce property rights and fairly adjudicate business disputes. Social capital for its part acts like a lubricant for formal institutions and makes business transactions function smoothly. In politics, social capital is what allows citizens to work together in the groups and associations that we call civil society. A healthy democracy depends on a vigorous civil society: under such conditions, citizens are not isolated individuals but are able to act together in groups united by common passions and interests.

Not all societies are blessed with high levels of institutional trust, or generalized trust between citizens. Many decades ago, the social scientist Edward Banfield described a town in Southern Italy that he said was characterized by what he labeled “amoral familism.” In such a society, people trusted only members of their immediate nuclear family; strangers were regarded as potential threats and kept at arm’s length. As a result, Southern Italy was largely devoid of the sorts of voluntary associations that were plentiful in the north: football clubs, newspapers, self-help societies, labor unions, and other organizations that gave texture to civic life.

The two organizations that flourished in the south were the Catholic Church and the Mafia. The latter was the direct outcome of distrust: because of a weak rule of law and distrust of government, business partners could not rely on the state to enforce contracts or protect their property rights. They had to use mafiosi—otherwise known as “men of honor”—to threaten violence on their behalf. This type of private enforcement naturally leads to greater violence overall as protectors turn into extortionists. This pathology is evident not just in Southern Italy, but in many parts of Latin America and Asia.

By contrast, Denmark and the rest of Scandinavia are properly understood to be “high-trust” societies. That trust extends both horizontally between citizens, as well as vertically in citizens’ relationship to the state. Anyone living in this region knows that crime, corruption, fraud, betrayal, and dishonesty exist here as in any other society, but the aggregate level of these dysfunctions is much lower than in, let’s say, Southern Europe.

In my 1996 book Trust, I characterized the United States as a “high-trust” society as well. This was not an idiosyncratic judgment on my part; there has been a long history of outside observers noting that the United States experienced high levels of trust. The great French writer Alexis de Tocqueville, after traveling through the United States in the 1830s, noted that American democracy was supported by what he called a strong “art of association,” in which ordinary citizens had an easy time coming together in a wide range of clubs, neighborhood associations, religious organizations, and the like. This, he noted, stood in sharp contrast with his native France, where, he said, you couldn’t find ten Frenchmen who could come together spontaneously for a common purpose.

I would no longer characterize the United States as a “high-trust” society. Beginning in the 1990s, we have seen an increasing polarization of American society. This polarization was initially political, based on the differing policy preferences of Democrats and Republicans. Willingness to cooperate across party lines fell. The polarization deepened steadily, particularly in the 2010s, and evolved into what social scientists label “affective polarization,” meaning that partisans no longer simply disagreed on policy issues, but believed that their opponents were deeply malevolent and dishonest. With the rise of Donald Trump, we had a political leader who made no effort to unify the country or to be a president for all Americans; rather, he trafficked in distrust and demonized anyone who disagreed with him as “Marxists, maniacs, and lunatics.”

This loss of social trust has not occurred only in the United States, but has affected many other countries as well. It manifests itself in conspiracy theories: the belief that society is being manipulated behind the scenes by a shadowy elite, whose secret dealings need to be exposed.

Subscribe now

This kind of populism is driven by a number of social and technological factors. In many societies there has been a sorting between inhabitants of large, diverse urban areas, and those who live in the countryside. This mirrors a sharp division based on levels of education. Educated urbanites tend to vote for liberal parties, while populist movements usually rely on rural and small-town voters.

Technology has also contributed to this polarization. The spread of the internet and social media has changed the nature of social interaction. Citizens who used to rely on a small number of elite-controlled media channels can now get information from anywhere in the world. The kinds of filters that used to control the quality of information have been undermined, which has led to the appearance of parallel information universes in which there is no common understanding of empirical reality.

Trust is also critical in international relations. There is no such thing as an international rule of law, because there is no global sovereign to enforce rules. International law is more normative than legal in nature, articulating rules and behavior that states believe other states are likely to follow. This makes trust very important: global order depends on states making their future behavior predictable by following a host of informal norms. Since 1945, global stability has been based on deterrence. Early on, there was a realization that countries could defend themselves from nuclear weapons only with great difficulty. It was only the credible threat of nuclear retaliation that kept the peace. Deterrence extended further to conventional warfare as well, and was embodied in NATO’s Article 5 commitment that an attack on one member of the alliance would be regarded as an attack on all. One’s international competitors and enemies did not have to believe in your values, but they did have to believe that you would reliably use force in response to aggression.

Perhaps the most important international norm that has been in place since 1945 is the norm against using force to acquire the territory and resources of another sovereign state. This norm has been much more powerful than the norm against the use of military force per se, and it was followed by the United States up until recently, even as America fought numerous wars and launched multiple military interventions around the world. The United States justified its actions in defensive terms, or in terms of preventing adverse political change. The Korean War and the 1991 Gulf War were both fought explicitly to uphold the principle of no territorial conquest. The Vietnam War was fought to prevent the takeover of South Vietnam by the North; the invasion of Afghanistan was fought to eliminate the threat from al-Qaida, which had just attacked the Twin Towers in New York, while the 2003 Iraq War was launched to stop postulated Iraqi weapons of mass destruction. In the end, many of these fears proved to be vastly exaggerated, but the problem was faulty judgment, and not the pursuit of self-interest.

This brings us to the events of earlier this year, and Donald Trump’s demand to take over Greenland. What was particularly shocking about this move was that it was not justified by any principle of self-defense or the defense of political values. Rather, it was a naked and self-interested grab for the territory and resources of a sovereign country that was a loyal treaty ally of the United States. This was in line with Donald Trump’s belief that the United States should have seized control of Iraq’s oil after liberating the country from Saddam Hussein’s dictatorship. This mindset predominated in the 19^th century world of clashing imperial powers, but was banished following the tragic history of the early 20^th century when territorial ambitions provoked two world wars.

Today, Donald Trump’s foreign policy has joined hands with his domestic policy. Since returning to office in January, the president has sought to rule the country by executive order, bypassing the many checks and balances established by the U.S. Constitution to limit his powers. He is, in other words, a would-be authoritarian. Similarly, he has ignored the legal and normative constraints on American international behavior. He has imposed tariffs, now determined by the Supreme Court to be illegal, on virtually every country in the world (whether they were inhabited by human beings or not).

President Trump has used force unilaterally on nine occasions, culminating in the joint attack with Israel on Iran on February 28. In doing so, he has bypassed the United Nations Security Council, as well as the U.S. Congress, which is given responsibility for authorizing wars under the Constitution. When Trump was asked by a journalist what would constrain him from acting unilaterally on the global stage in the future, he said “my own morality.” Given that his morality often seems to be akin to that of a Mafia boss, this is not very reassuring.

By his threats against Greenland, Donald Trump has destroyed all remaining trust in the North Atlantic relationship. Europeans have been rightly asking themselves whether the United States can ever be trusted again. And at this point, I would say that the answer is no.

There are several reasons for this. The most important is that the Republican Party has been changed beyond recognition. Before 2016, it was a party committed to free trade, limited government, openness to immigration, the strong defense of allies, and a democratic world order. Since the rise of Donald Trump, it has coalesced around an “America First” agenda that wants to close off the United States to the outside world. Trump has openly favored dictatorships like Putin’s Russia, Kim Jong Un’s North Korea, and Xi Jinping’s China over democratic countries in Europe and Asia. He has visibly eroded trust within the United States, attacking domestic opponents as enemies and traitors, and degraded the quality of discourse through vicious personal attacks on perceived enemies. I noted earlier that trust depends on the moral virtues of honesty and reliability, something that is foreign to a leader who lies shamelessly, virtually with every sentence he utters.

I think that Europeans would be foolish to believe that America can be trusted in the future to meet its treaty obligations to NATO. This is not a legal matter but a moral one: if the U.S. president is uninterested in supporting allies, then Article 5 is a dead letter whatever its legal status. Europe has no choice but to take full responsibility for its own security, and to reshape both NATO and the European Union to permit much stronger collective action. Europeans hoped in 2020 that the United States would return to its old self with the election of Joe Biden, and yet American voters managed to re-elect Donald Trump in 2024, despite the fact that he sought to overturn the earlier election.

I want, however, to end on a more optimistic note. Despite the damage to institutions that has occurred over the past decade, I believe that the checks and balances built into the American system continue to operate. The most important of these checks are elections. There is a great deal of evidence that Donald Trump will be strongly repudiated in the midterms this coming November, and that the Democrats may retake not just the House of Representatives, but the Senate as well. The recent Hungarian election showed that voters can make clear choices and reject authoritarian leaders like Viktor Orbán. I do not believe that the fears that many people had last year about a rising populist tide sweeping Europe will come to pass. Donald Trump has not proven to be the unifying glue that holds the European far right together. No party will want to bind itself closely to an aging, mentally deteriorating 80-year-old man who seems to be losing control of events both at home and abroad.

Subscribe now

International trust radiates outward from high levels of trust at home. This is where Denmark can play an important leadership role. The strength of Denmark’s domestic institutions is ultimately what guarantees its position in Europe as a bulwark of democracy and effective government that is a model for many other countries to follow. And I hope that “getting to Denmark” will be an inspiration for Americans as well as they seek to recover from the current assault on their institutions.

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

Now that Donald Trump is visibly weakening, it’s important to start thinking seriously about what comes after him. It’s no secret that I’ve been a big fan of the Abundance movement, which was popularized by Ezra Klein and Derek Thompson last year in a book by that name. The core of Abundance is to rebuild American state capacity and create a government that can build things once again. At the top of the list are housing and infrastructure—public goods that will make significant dents in the affordability crisis for ordinary Americans.

Over the past several decades, the United States has lost state capacity, a void that has been most apparent in its failure to build things. There is a huge deficit today in maintenance of our existing roads, bridges, and public utility systems, not to mention new things that we would like to have, like high-speed rail.

Subscribe now

Declining state capacity has a number of causes. Chief among them are the number of restrictions we have put upon ourselves, something the legal scholar Nick Bagley calls the “procedure fetish.” We have moved since the 1960s, according to Marc Dunkelman, to a Jeffersonian mindset in which the government is seen as a threat to our liberties; he argues that we need to recapture a “Hamiltonian” perspective in which we see the government as a force for progressive change. Young people with skills and the ability to use technology effectively don’t want to go into government these days, and we have outsourced public goods and activities to private contractors who have their own agendas. Our government often lacks the ability to properly monitor those we have hired to do its work.

Having a positive agenda will be critical if we are to overcome the current crisis of American democracy. Donald Trump is well on his way to being the worst president in our history, scorning basic democratic values and lacking the basic dignity and empathy required of a president. We will not be able to overcome his legacy simply by criticizing him. We need to recognize that Trump’s authoritarianism arose in part from a perception that our government couldn’t do anything well, and needed a strong leader like him to produce outcomes. You can’t beat a would-be authoritarian by criticism alone; if the Democrats are ever to return to power they need to explain what positive things they will do and how the country will be a better place in five or ten years.

The Abundance agenda is not about catering to corporate greed or filling the pockets of oligarchs. Rather, it seeks progressive goals like making housing affordable or dealing with challenges like climate change. I was proud as an American to witness recently the crew of Artemis 2 orbiting the moon. Hopefully it will be the beginning of a series of new explorations. But we should want this to be a collective achievement for the country as a whole, and not the vanity project of a single rich individual. The recovery of state capacity is something that all of us should own.

The ongoing series by American Purpose at Persuasion, “The ‘Deep State’ and Its Discontents,” has already dealt with many of the issues standing in the way of Abundance. It is my hope to continue along these lines, offering concrete suggestions on how the American state can recover its ability to build things and get things done.

Stay tuned.

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

Back in 1995, I published my second book, Trust: The Social Virtues and the Creation of Prosperity. In it I argued that trust is among the most precious of social qualities, because it is the basis for human cooperation. In the economy, trust is like a lubricant that facilitates the workings of firms, transactions, and markets. In politics it is the basis for what is called “social capital”—the ability of citizens to cohere in groups and organizations to seek common ends and participate actively in democratic politics.

Societies differ greatly in overall levels of trust. In the 1990s, Harvard’s Robert Putnam wrote a classic study of Italy which contrasted the country’s high-trust north with its distrustful south. Northern Italy was full of civic associations, sports clubs, newspapers, and other organizations that gave texture to public life. The south, by contrast, was characterized by what an earlier social scientist, Edward Banfield, labeled “amoral familism”: a society in which you trust primarily members of your immediate family and have a wary attitude towards outsiders who are, for the most part, out to get you. The only large organizations in the south were the Catholic Church and, of course, the Mafia. The latter was a direct product of distrust: if you were a businessman, you couldn’t count on the state to protect your property rights because of a weak rule of law; if someone cheated you, you hired a mafioso to break their legs.

Subscribe now

In Trust, I characterized the United States as a “high-trust” society. This view has a long history. When the French observer Alexis de Tocqueville visited the United States in the 1830s and traveled across much of the settled part of the country, he noted that America had a high density of civic associations, from bible studies to clubs to mutual aid societies, and that Americans found it relatively easy to work together with strangers in the face of challenges. This, he felt, stood in sharp contrast to his native France, where, he said, you couldn’t find ten Frenchmen who were ready to work together in a common endeavor. In France, there was little of the spontaneous sociability or social capital that he found in the United States. This view of high-trust America was supported, in the mid-20^th century, by survey data that showed Americans trusting other Americans to a higher degree than people in France and many other countries.

If I were to re-write Trust today, I would not characterize the United States as a high-trust society. Even as that book was being published in the 1990s, political polarization had started to spread, and Americans began to sort themselves according to their political preferences. That polarization has only increased in the interval between then and now. It has turned into what political scientists label “affective polarization,” in which partisans don’t just disagree on issues, but also come to believe that their opponents are deeply malevolent and dishonest. Social capital still exists between members of the different political tribes, but distrust is rampant across the society as a whole. We don’t accept a common set of facts on issues like vaccine safety or election integrity, and we live by a series of conspiracy theories that inform us that things are not what they seem.

Trust and social capital are built on a foundation of moral virtue. We come to trust people who are honest and reliable, who keep commitments and are willing to offer support even when it isn’t of immediate benefit to themselves. Trust takes time to build through a process of repeated interaction: if we see another person fulfilling their promises and reciprocating favors, we tend to do the same for them, creating a virtuous circle. But a trust relationship that has built up over time can be broken in an instant, if one of the parties betrays that trust and takes advantage of the other player. Just as trust builds on itself, distrust can become self-reinforcing: if we are betrayed, we are tempted to seek revenge against the betrayer.

Trust is also critical in international relations. We come to trust other countries based on their observed behavior, just as we do with individuals. There is no global enforcer of rules or a sovereign to make countries behave. The use of force is constrained only by the expectation that it will be met with a counter-force, in an environment where credibility is the coin of the realm.

That is what makes me extremely worried about the present global situation, and fearful of where our world order is heading.

It is hard to imagine that the current war with Iran and the crisis over the Strait of Hormuz does not represent a fundamental rupture in the North Atlantic security structure. NATO is an alliance built on trust: its deterrent value rests on the belief that NATO members will come to one another’s aid if a member is attacked. This is what happened after 9/11, when a number of alliance members did come to America’s defense in Afghanistan and Iraq. NATO is not an all-purpose commitment to support a treaty partner who has undertaken an offensive war against a third party. Trump is accusing alliance members of betraying the United States by not collaborating with it to re-open the Strait—but no one ever signed up to wage offensive war.

Subscribe now

The truth of the matter is that the United States has never been as isolated as it is today. Mark Rutte, the Secretary General of NATO, has made some supportive noises in the current crisis, but that was done out of cynical calculation. No sane European leader can think that support for the United States today will be reciprocated by a Trumpist United States down the road. And while American actions have greatly benefited rivals like Russia and China, they can hardly delude themselves that the United States will reliably serve their interests in the future.

Donald Trump has claimed that the United States has never been as respected as it has been under his presidency. Of the very many untrue things he has said in his career, this is among the most absurd. There has never been a time when the United States was more distrusted, by both traditional friends and by rivals, as at the present. A successful dealmaker needs to generate a minimal amount of trust that he will uphold his end of the bargain. But reciprocity is a virtue that Trump has never understood or practiced.

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

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