Image generated by Gemini.

“How did it feel to kill 5 million people?” This was a question about the decision to launch nuclear weapons that I didn’t think I would ever be asking until a couple of weeks ago; I ended up posing this question more than once.

The responses ranged anywhere from “My team was probably going to lose anyway, better both teams lose,” to “I see what war can do on my phone, a [tactical low-yield] nuke was bound to happen.”

Fortunately, the crisis was a fictional nuclear escalation scenario that I designed and ran at the Culver Academies, a leadership development academy based in Culver, Indiana. The purpose of the exercise was to educate students on how to make tough choices under conditions of asymmetric information, uncertainty, time pressure, personal incentives, and emerging technologies.

To the west: Aloria, a powerful democratic nation with a sophisticated military, land-based ICBMs, and submarine-launched ballistic missiles.

The simulation involved two countries separated by a stretch of water called the Kelvari Strait. To the west: Aloria, a powerful democratic nation with a sophisticated military, land-based ICBMs, and submarine-launched ballistic missiles. To the east: Tarshan, less powerful in aggregate but still technologically advanced, possessing land-based ICBMs and a reported breakthrough AI weapons program called Project ARGUS—theoretically capable of autonomously eliminating Aloria’s nuclear capabilities in a single “splendid first strike.”

To the east: Tarshan, less powerful in aggregate but still technologically advanced

Six months before the simulation began, Aloria had launched Operation Darvak, a so-called counter-terrorism operation against Tarshan, which destroyed 40% of Tarshan’s military and killed thousands of civilians. Last week, Aloria moved ground troops to the border.

A screenshot of what was displayed on the big screen in each command center.

Then, ten minutes ago, Tarshan launched a conventional missile attack on Kora Naval Station, Aloria’s largest regional naval base. And then—a second launch. From deep inside Tarshan. An ICBM equipped with Multiple Independently Targetable Reentry Vehicles (MIRVs). Each one is potentially nuclear. Nobody in Aloria knows for certain what’s on it, but they have access to SENTINEL, an AI-enabled early warning system that can supposedly provide a confidence reading of the ICBM’s nuclear likelihood.

The script I read to open the simulation ended like this:

Aloria—your job is to figure out what’s coming at you, whether to trust your own AI system, and whether to respond before it hits. Tarshan—your warheads are already in the air. Aloria hasn’t responded yet. You need to decide if you’re going to try to stop this before it goes further. You have just 28 minutes. Then the warheads land. The decisions you make—or don’t make—will determine what happens to millions of Tarshinian and Alorian men, women, and children. Good luck. Protect your people. Your time starts now.

I ran this exercise three times with three different classes. The results were not what I anticipated. Originally, I had created this game to teach students in my generation about national security decision-making, but after every single class used nuclear weapons, I ended up being the student in an age-old class about human behavior.

To nuke or not to nuke?

Before the clock even started, the Tarshan teams had to decide what initial attack they wanted to launch.

In a quiet room sat Sasha Vasek, the Premier of Tarshan. They were aided by their top advisors, Defense Minister Lex Vorov, Foreign Affairs Minister Rian Solari, Intelligence Director Ren Petrov, and Commander of the Strategic Missile Forces Tal Barak. Their job was to decide what to put on those warheads.

Option 1 was a conventional attack—five conventional precision missiles targeting counterforce targets in Aloria, which would cause severe infrastructure damage to Aloria’s military infrastructure.

Option 2 was a nuclear signal—a use of a low-yield, tactical nuclear weapon alongside four conventional missiles targeting counterforce targets in Aloria’s interior.

Option 3 was a limited nuclear strike—more severe than Option 2 but less severe than Option 4. Option 3 involved the use of two conventional missiles and two low-yield nukes targeting counterforce targets, as well as one high-yield strategic nuke striking just outside the Alorian capital of Verath.

Option 4 was an attempted disarming first strike—three high-yield and two low-yield nuclear weapons aimed at Aloria’s nuclear infrastructure (but close to Aloria’s population centers) that would hope to render Aloria’s second-strike capabilities severely degraded.

What was remarkable was how differently three groups of students, given identical information and identical roles1, reasoned their way to three completely different decisions.

In the first class, Tarshan’s Foreign Minister argued for a conventional strike and nothing higher than a nuclear signal. Tarshan’s Defense Minister and Strategic Missile Force Commander pushed for a disarming first strike, arguing that conventional warheads onboard an MIRV would look like a nuclear strike anyway. In the end, Premier Vasek took a deep breath and authorized Option 2: a nuclear signal.

The second class’s Tarshan team took a bit more of a pragmatic approach to the credit of Premier Vasek alone. Despite receiving near-unanimous advice to at least authorize Option 2, Premier Vasek firmly held that she did not want to be the one to break the nuclear taboo (although, of course, she didn’t know that the “nuclear taboo” was the term she was referring to), and opted for Option 1: conventional strike.

Despite only being “moderately hawkish” towards Aloria, Premier Vasek in the third class reasoned her way into a much more aggressive outlook on the situation. Using her personalist leadership style and the approval of her Defense Minister, who championed a hawkish position on Aloria from the start, she reasoned that, given that 40% of her military capacity had been destroyed in Operation Darvak, her regime would come to an end if Aloria’s military capabilities were left intact. Therefore, anything less than a full nuclear attack was not being half-safe; it was half-doomed to the toppling of her government. Premier Vasek authorized Option 4: disarming nuclear strike.

Table 1. What each Tarhsan group chose to put on the MIRVs.

28 minutes ‘til impact…

Understandably, Aloria was disorganized in the first few minutes. Rather than utilizing the provided back-channel communication mechanism (sticky notes passed between rooms) with Tarshan, the Alorian teams all tried to reason what was on the MIRV using a combination of their knowledge of the other side’s personalities, as well as the SENTINEL reading, which was reporting a 62.3% confidence that the warheads were nuclear. That number wasn’t high enough to be certain, but it was far too high to ignore. What’s interesting is that Aloria used the back channel only after Tarshan initiated the conversation. This asymmetry itself tells a story: the aggressor was more motivated to negotiate than the defender.

Meanwhile, the teams on the Tarshan side were more divided in their initial strategies. The team that chose the disarming first strike immediately went into damage control mode, attempting to pass notes to Aloria asking to negotiate. The team that chose the nuclear signal opted for a “don’t poke the bear” approach, sending over a message that read “We have launched a tactical nuclear strike. After it hits, let’s negotiate. Don’t make things worse for yourselves.” This, as you will soon learn, may not have led to the best outcome.

Perhaps most surprisingly, the team that chose a conventional retaliation chose what I can only describe as a “paper tiger” strategy, deliberately obfuscating what warheads were on the MIRV. I found this strategy to be puzzling. As the subsequent messages revealed, Tarshan was attempting to trade information about the MIRV and the promise of no follow-up attacks in exchange for Aloria withdrawing its troops from Tarshan and agreeing to a ceasefire. This course of action was futile from the start for two reasons: [1] the MIRV had already been deployed and was not recallable, and [2] Tarshan was hardly given a strong enough hand to make such demands. For this game of chicken to have worked, team Tarshan would have needed to launch a much more aggressive first strike (perhaps Option 4) AND had the ability to recall the MIRV—none of these conditions were met.

The plot thickens…

As of 16:49:18, Alorian forces have confirmed a direct impact on Naval Station Kora, resulting in the complete destruction of the facility. The strike has been officially attributed to Tarshan forces and was executed via a series of conventional ballistic missiles. While the conventional strike is complete, the status of Aloria’s nuclear submarine fleet remains unknown, and the nation’s second-strike capacity is currently listed as degraded while damage assessments continue.

The strategic threat remains as the ICBM class launch, remains active. Upgrade to DEFCON 2. SENTINEL systems have increased the confidence level of this second threat to 91.4% nuclear. As the decision window rapidly closes, the projected time to impact for the ICBM is currently 18 minutes.

“They want peace when there are missiles in the air!” Those were the words of one of the Alorian Defense Secretaries, Cael Harrow. The irony was profound. After the Naval station was reduced to smoldering ash by a series of Tarshinian conventional ballistic missiles, it seemed almost laughable to the three Alorian teams that all three Tarshanian teams were attempting to broker a ceasefire—that ship had sailed. The decision that lay before the Alorians was now to decide how aggressively they would respond.

Then, at T-10:00 minutes, I passed a message from the Quality Assessment team at SENTINEL Systems to its CEO, Devin Cole:

Six days ago, SENTINEL produced a false positive. A spurious ICBM launch signature from a sensor calibration error. It lasted four minutes. The patch went in five days ago, but the root cause was never fully resolved. I don’t know if today’s reading is real. Nobody does.

The goal of this plot twist was to see the extent to which the students wrestled with the contradictory information in front of them.

Two minutes ‘til midnight…

“Two minutes until the ICBM hits. Madam President, we need a decision.” The clock was ticking. If the students playing President Voss didn’t make a decision in time, they would lose the ability to make a decision at all.

As is the case in real life, the outcome of this simulation heavily relied on the decisions of President Voss and Premier Vasek. As much as cabinet members and advisors could jockey for their positions on what to do, the leaders of the countries had “the biscuit”—the buck stopped with them.

Here is the information President Voss had to juggle:

• Aloria’s naval station was already destroyed in a ballistic missile attack, rendering its second-strike capabilties already degraded. At the same time, there were five MIRVs headed toward the mainland and two minutes from impact. Were they convetional, nuclear, or a mix of both?

• SENTINEL AI early warning system said 62.3% probability of nukes. Now it’s saying 91.4%. At the same time, CEO Devin Cole is receiving information that casts serious doubt about SENTINEL’s reliability. Should SENTINEL’s reading be trusted?

• Tarshan is saying it wants to negotiate a ceasefire. At the same time, it has already fired two separate missile attacks towards the Alorian mainland and refuses directly answer the question of what is on the MIRVs. Should Tarshan be trusted? And what is a proportional response, given the casualties incurred by Operation Darvak?

President Voss had to make a decision now. The options that lay before her were anywhere from no action to conventional retaliation to limited nuclear strikes to a full strategic nuclear response.2 Time was ticking.

“Madam President?”

“Okay, I’m ready.”

“Stand by to authenticate your authority with the Joint Chiefs.”

“Madam President, this is the Alorian National Military Command Center. To authorize this execution, I challenge you to authenticate. My challenge code is FOXTROT-UNIFORM.”

“Response is SIERRA-WHISKEY-DELTA-NINER-CHARLIE.”

“Authentication is valid. I confirm your identity and am ready to receive your directive to execute. Madam President, your orders?”

Video generated by Gemini Veo. What I displayed in class to demonstrate mutually-asured destruction.

The day after…

Out of three runs of this exercise, two of them resulted in mutually-assured destruction (MAD); every class used nuclear weapons in some form.

Table 2. Summary of the decisions made by each team.

Before you rush to judge these students as trigger-happy or conclude how you would have done it differently, you should know that these participants, while high school students, acted—in my assessment—quite rationally. They were measured and deliberate, and well-briefed on nuclear deterrence policy, justifying each one of their decisions based on the evidence before them and their knowledge of the other side. I am also neither here to applaud their actions nor am I going to stand on my soapbox and dismiss them as “kids these days.” I am—after all—in their same generation.

What I have learned from running this exercise says a lot about how the next generation that gets the nuclear launch codes will think about them, and how we can all learn from this simulation.

Desensitized to war?

I fear that my generation has become desensitized to death and suffering in war, and this may affect our judgment in nuclear deterrence policy. I want to be careful here—I am drawing on one simulation, at one school, with a small number of students. This is not a scientific study. Would other generations have reacted differently? I cannot prove they would have. But the pattern I observed is worth examining, and I think it points to something structural.

Our grandparents lived through “Duck and Cover” and the Cuban Missile Crisis, which historians deem to be the “moment when the two superpowers came closest to nuclear conflict.” Our parents saw the fall of the Berlin Wall and the subsequent progress made in nuclear disarmament. They also bore witness to what governments were willing to do under the mere fear of weapons of mass destruction in the hands of terrorist organizations. Each of those moments arrived with a social architecture around it: institutions that were still trusted, narratives that made sacrifice legible, and—most importantly—a clear sense that individual action meant something. War propaganda was galvanizing precisely because it implied agency. Even the sanitized absurdity of hiding under a school desk was the government telling you, “You can survive this, and here is what to do.” Other than a brief escalation with North Korea (the “Rocket Man” incident) over nuclear testing in 2017, my generation hasn’t had a nuclear escalation moment of that kind of weight.

There is an easy version of this argument—that says we simply haven’t suffered enough to understand. But I don’t think that’s true. The world has not become less frightening. If anything, the Bulletin of Atomic Scientists recently set their Doomsday Clock to 89 seconds to midnight, what the Bulletin of Atomic Scientists calls the most dangerous moment since the Cuban Missile Crisis.

Prior generations experienced catastrophe but largely through mediated channels. Most Americans lived the Cuban Missile Crisis through television and newspapers, not in any direct proximity to a warhead. The difference, isn’t the presence of danger. It’s the absence of the story. What’s missing is that the trust in the government institutions that have historically helped us to metabolize that information, provide assurances, and issue actionable recommendations, has eroded.

My generation grew up with climate catastrophe projections, chronic incidents of gun violence, and wars of attrition delivered uncut and unmediated through our phones. As just one example, you can watch the Iran war in real time on social media—not through a news anchor who tells you how to feel about it or what to do about it, but in an unfiltered scroll between other content.

The inundation of these experiences foster a sense of emotional detachment and passiveness at the same time that they give their viewers the perception that they know what it’s like. American writer Susan Sontag wrote decades ago that these raw depictions of death and destruction don’t breed empathy; they anesthetize you from the visceral pains of human suffering.

The casualty figures in this exercise were not small numbers. A nuclear exchange between Aloria and Tarshan involved anywhere from tens of thousands to millions of casualties. And yet the students processed those figures with a kind of clinical detachment that I was not prepared for.

Sometimes I wonder if, somewhere along the way, we accepted a background assumption that mass death in war is inevitable, that the systems producing it are too large to be influenced, and that the correct response to catastrophic information is to process it analytically and move on. The students who authorized nuclear strikes were not bloodthirsty, nor were they jokingly blowing each other up for fun. They were, in their own way, working within a mental framework that millions of casualties was the premise of war, not a moral threshold.

AI and nukes: much ado about nothing?

There is another easy answer to this—that we have passed off so much of our thinking to AI that humans are losing the ability to make decisions. I want to push back on that, at least partially. What I witnessed suggests a slightly different conclusion. In the simulation, I added the element of the SENTINEL early warning system to determine the extent to which Team Aloria deferred to the readings of algorithmic systems. The students did not blindly follow SENTINEL’s readings, nor did they entirely ignore them. None of the group discussions appeared to take into account the AI output as a deciding factor in selecting an attack or response option. When I asked the students to approximate the percentage of sway that SENTINEL’s readings had in their decision, the highest response I received was 15%, with most of the class responding around 10%.

What had a much higher impact in their decisionmaking, it turned out, was the level of perceived aggression in the back channel communication lines, tempered with their previous knowledge of the other side’s personalities. As one student noted:

That student happened to be correct. While the SENTINEL system read a 91.4% chance of an all out attack, Aloria had only launched a limited nuclear strike targeting military installations. But these assessments were not always correct. Before it was revealed that Tarshan had only selected a conventional attack, another student reasoned, to the agreement of his team:

The student later explained that he would have advocated for MAO 5, regardless of what SENTINEL had said.

I’d argue that how the students actually utilized SENTINEL was more human—they used it selectively, in service of conclusions they were already inclined to reach. When the reading confirmed what a team wanted to believe, it was cited as authoritative. When it complicated a decision that had already been made, it was questioned, reframed, or quietly set aside. This worked in both directions. The group that decided against a full strategic response questioned SENTINEL when it gave such a high chance of a disarming first strike, and later used the report citing false alarms as evidence that SENTINEL was giving them inflated readings. The groups that decided to launch a full nuclear retaliation reasoned the opposite.

This is not a failure unique to this generation, nor is it a consequence of AI automation bias. It is how humans have always processed authoritative advice—as just one input into a conclusion that social dynamics, personality, and prior commitments have usually already shaped.

Eye for an eye?

There is a final lesson to this exercise, one that I—admittedly—am still wrestling with. The last theme that emerged from the three simulations and subsequent post-mortem debriefs was that decision-making was guided by an innate sense of fairness and its evil twin, spiteful reciprocity. When the Tarshan teams had absorbed the fallout from Operation Darvak, there was a palpable sense of moral high ground within their command centers. Common in all three groups was the feeling that they had the right to make Aloria hurt at least as much as they did. But the resources they had to make that happen in practice were limited to using nuclear weapons for the first time since 1945.

What transpired was this kind of ethical calculus, where students attempted to calculate the right combination of conventional and nuclear payload to equal the wounds of losing 40% of their military capacity to Aloria’s conventional forces. In essence, they were trying to compare apples to oranges. The same could be said about the Aloria teams when their naval base at Kora was destroyed. It seemed as though reciprocity (getting even) was—in that moment—more important to them than their original mandate of protecting their own people. As one student explained:

But the observation that stayed with me the longest is subtler than reciprocity. It is the notion of norms—specifically, how they actually function, as opposed to how we’d like to imagine they do.

We often think about international norms as load-bearing norms, as if the institution of the nuclear taboo prevents the use of nuclear weapons. What the simulation revealed, quietly and consistently, is that this picture is somewhat backwards. I’d like to advance a different hypothesis: it is not the institution that constrains the behavior, but rather the behavior that creates the institution. The architecture of the nuclear taboo works best, perhaps, precisely when it goes unmentioned—not because it is enforced but because it is assumed. It operates as a shared fiction that functions only as long as all parties agree to pretend that it is an actual constraint. The moment one party stops pretending, the fiction collapses faster than anyone expects.

Out of the three Alorian teams, two of them were not inclined to resort to nuclear weapons at first. But as soon as the back-channel negotiations hinted at the possibility that Tarshan broke the norm first, all bets were off. This is what I find hardest to sit with. Not that students broke the nuclear taboo. But that the taboo, in the absence of belief, turned out not to be really a taboo at all. Especially in today’s world of political realism, international norms and laws like these don’t get the credit they deserve. But as I’ve written before, they are no less important just because great powers feel inclined to test their limits. Even in the midst of a nuclear escalation, the students still referred to international law and the nuclear taboo in their communications with the media role.

In closing

I first created this nuclear escalation simulation because I wanted my generation to have practice making decisions under uncertainty BEFORE we become the ones who have to do it with these stakes. Because of this new age of AI and democratization of influence, people my age are already having substantial leverage in these policy circles—whether that be through the 19-year-old defense tech founders or the 20-some-year-olds getting hired to senior advisory positions.

Critical and deliberate decision-making training in these domains for young people is in incredibly high demand but in incredibly short supply. Most leadership training for young people—Model UN, student government, debate, even the better service academies—prepares them to negotiate, to compete, to persuade. Almost none of it prepares them to sit with the specific weight of nuclear decision-making: the combination of radical uncertainty, irreversible consequences, and the knowledge that the other side is just as frightened as you are.

My hope for any educator out there reading this is for them to incorporate these issues into leadership and teamwork exercises, not simply the summer camp games like “trying to get all the team members across an ‘alligator-infested’ river whilst using just one wooden plank. These students are more than capable of handling the distressing and uncomfortable realities of the world we live in, where death in war is a constant but not predestined aspect of life and where nuclear stability depends on the norms and schema baked into students at an age younger than your “Intro to International Relations” college course provides.

I’ll leave you with this uncomfortable fact. The students in this simulation were given 28 minutes to react to a potential nuclear war. In the time it took you to read this Substack, a nuclear weapon could have been launched and obliterated a major city. That’s the time frame we’re looking at. But the answer is not to develop AI systems to make quicker decisions—that just means we can make the wrong decision even faster than before. The answer is better-prepared people. What this exercise reaffirmed for me is that nuclear stability rests on something more fragile and more important than any early-warning algorithm or splendid first-strike capability: the shared conviction that certain lines must not be crossed, and the wisdom to hold that conviction under pressure—even when every incentive in the room is telling you to let the machine decide. These abilities are not inherited; they are taught—deliberately preparing the next generation for the situations we know they will encounter, and the ones we hope they never do.

Want to contribute to Rules of Engagement?

Submit a Pitch

Appendix

1

2

This article was published at the Carnegie Endowment for International Peace. Read it HERE.

Much of the discourse on export controls has focused on restricting the sale of physical semiconductors. But a more understated loophole is allowing Chinese customers to remotely access the same restricted U.S. chips through cloud service providers. Now, Congress is trying to close that loophole.

In a new article for the Carnegie Endowment for International Peace, I discuss the logic behind these “cloud controls” and why they're more complicated than they seem.

Here are my 4 key takeaways:

1. THE LOOPHOLES: Chinese companies can legally lease compute either from third-country or U.S.-based clouds. Because the physical chips are housed in licensed data centers, it doesn't count as an "export" subject to U.S. restrictions.

2. THE LOGIC BEHIND CLOUD CONTROLS: Cutting off physical chips to China for national security purposes is undermined by remote access. It also weakens the leverage that the U.S has in physical chip license negotiations and undercuts American R&D expenses into model development.

3. THE CONS OF CLOUD CONTROLS: The compliance burden of cloud controls may push foreign-owned data centers to seek more convenient Chinese alternatives, not to mention the diplomatic objections to U.S. extraterritorial authority. Remote access may also provide the US with an intelligence window into China's AI development.

4. OPEN QUESTIONS: Would cloud controls impose restrictions on all foreign entities or just Chinese renters? And what cloud services would be restricted? Each answer has to reconcile security concerns with the practical and strategic costs of regulating a transnational service.

This article was published at the Carnegie Endowment for International Peace. Read it HERE.

This article was originally published in AI Frontiers on April 13, 2026. Read the full article HERE.

Last December, President Trump announced that the United States would allow Nvidia to sell its powerful H200 AI processors to customers in China. Officials in the Trump administration have long argued that the best way to win the AI race is to promote the export of US technology around the world, not to restrict it. Selling H200s, the administration claims, will boost the market share of US chip-makers while preserving the US hardware lead.

Whereas Biden-era export controls attempted to make the US compute advantage as large as possible, an export-friendly framework could instead focus on maintaining a fixed, favorable compute advantage. To do so, policymakers should peg the quality of exported chips to the performance of China’s domestically manufactured alternatives, while capping quantities of those US chip exports.

This article was originally published in AI Frontiers on April 13, 2026. Read the full article HERE.

*TIMESTAMP APRIL 7, 2026 4:58PM ET

https://truthsocial.com/@realDonaldTrump/116363336033995961

https://truthsocial.com/@realDonaldTrump/116351998782539414

The Prompt

Summary Table

*The following is completely AI-generated.

Claude

OPEN-SOURCE ANALYTICAL EXERCISE

US-Iran Escalation: The 8:00 PM Ultimatum

24-Hour Predictive Analysis Window — April 7–8, 2026

DTG: 07 APR 2026 / ~1600 ET | Source: OSINT Only | Classification: UNCLASSIFIED

0 — Situation as of ~1600 ET

The US-Iran war is in its 39th day. President Trump has set an 8:00 PM ET deadline for Iran to agree to reopen the Strait of Hormuz or face strikes on civilian infrastructure — specifically power plants, bridges, and potentially water infrastructure. He has described this deadline as “final,” though he has pushed back similar deadlines multiple times since March 22.

KEY INDICATOR — STRIKES ALREADY UNDERWAY: The US struck 50+ military targets on Kharg Island overnight. Israel struck Tehran airports, railway bridges, petrochemical complexes, and the South Pars gasfield power units today. VP Vance stated this does not represent a “change in strategy” and that energy/infrastructure strikes are being held until after the deadline.

KEY INDICATOR — DIPLOMATIC STATUS, AMBIGUOUS: Axios reports the White House has shifted from “can we get there?” to “can we get there by 8 o’clock tonight?” WSJ reported Iran cut off direct communication after Trump’s “civilization will die” threat; Iranian state media denied this. Fox News reports talks remain “positive.” A 45-day ceasefire framework is on the table but neither side has accepted it.

KEY INDICATOR — IRANIAN POSTURE, DEFIANT: The IRGC has warned it will “deprive the US and its allies of oil and gas for years” if red lines are crossed. Iran’s president says 14 million have volunteered to fight. Civilians are forming human chains around power plants. Iran retaliated today with missiles against central Israel, Saudi Arabia, and Bahrain, closing the King Fahd Causeway.

1 — The Escalation Ladder (24-Hour Scope)

Tier 1 — Targeted Kinetic / Counter-Value (“Power Plant Day”)

This is the scenario Trump has explicitly and repeatedly described: systematic destruction of Iran’s power plants, bridges, and potentially desalination facilities. The target list reportedly exists. Israel has already approved an updated list of energy and infrastructure sites as a contingency. Bridges and railway infrastructure are already being struck by Israel as of today. The rhetorical escalation — “a whole civilization will die tonight” — maps directly onto this tier. VP Vance’s statement that energy strikes are being held “until” the deadline passes confirms this is the primary planned escalation.

Probability: 60% | Confidence: 7/10

Reasoning: This is exactly what the administration has telegraphed. The target sets exist, the rhetoric matches, and the operational tempo (Kharg strikes, Israeli bridge strikes) suggests preparation for a larger campaign. The 60% — rather than higher — accounts for the ~25% chance of another deadline extension and ~15% for a partial deal or modified approach.

Tier 2 — Naval Counter-Force (Forced Strait Transit / SEAD-DEAD)

A naval-focused campaign to forcibly reopen the Strait — minesweeping operations, destruction of IRGC coastal missile batteries, and strikes on IRGCN fast-attack craft bases. This has been discussed since Trump’s March 3 tanker-escort announcement, and the Kharg Island military strikes are partly aimed at degrading Iran’s ability to contest the Strait. However, the administration’s rhetoric has shifted decisively toward punishing civilian infrastructure rather than solving the Strait problem through direct naval action. Forced transit is operationally complex, slow, and doesn’t match the “one night” tempo Trump has described.

Probability: 25% | Confidence: 5/10

Reasoning: Naval counter-force elements will likely accompany Tier 1 as supporting operations, but as the primary course of action, it doesn’t match the administration’s signaling. The lower confidence reflects that military planners may push for this over infrastructure bombing, creating internal friction we can’t observe from OSINT.

Tier 3 — Maximum Pressure / Regime-Level (Decapitation or Tactical Nuclear)

This tier includes strikes specifically aimed at regime survival — targeting Supreme Leader Mojtaba Khamenei, remaining IRGC command structure, or the theoretical use of low-yield nuclear weapons. The decapitation playbook has already been used (Khamenei Sr. was killed on Feb 28). The IRGC intelligence chief was killed April 5. There is no public rhetoric suggesting nuclear employment, and the political costs would be enormous.

Probability: 5% | Confidence: 4/10

Reasoning: Continued decapitation strikes on IRGC commanders are likely regardless of tier. But full regime-level strikes as the primary objective? Unlikely in this 24-hour window. Nuclear employment is near-zero probability but not actually zero given the rhetoric, which is why this sits at 5% rather than 1%.

Note: The remaining ~10% probability covers deadline extension, partial deal, or a scenario not captured by these three tiers (e.g., a Kharg Island ground operation announced as the primary action).

2 — “Most Likely” 24-Hour Timeline (Tier 1 Scenario)

The following is the highest-probability scenario: Trump enforces the deadline, and the US launches a systematic infrastructure campaign against Iranian power generation and transport networks, with Israeli coordination on additional target sets.

20:00 ET — The Deadline Passes: Cyber + Electronic Warfare

The most likely opening salvo is not kinetic. Iran’s internet has already been largely shut down. Expect coordinated cyber operations targeting remaining Iranian C2 networks, SCADA systems on the electrical grid, and communications infrastructure. This degrades Iranian situational awareness before the kinetic phase and creates ambiguity about whether “the attack” has begun. Trump may issue a final public statement or Truth Social post.

20:30–22:00 ET — First Kinetic Wave: SEAD/DEAD + Opening Infrastructure Strikes

Tomahawk cruise missile salvos from naval assets in the Arabian Sea and Persian Gulf, supplemented by B-2/B-1 standoff strikes, target remaining Iranian air defense nodes — particularly those protecting power generation sites. Simultaneously, the first infrastructure targets are hit: likely major thermal power plants around Isfahan, Bandar Abbas, and potentially the already-damaged South Pars power units. Israel coordinates strikes on transport infrastructure (bridges, rail junctions) — a campaign it has already begun today.

22:00–02:00 ET — Sustained Campaign: “Power Plant Day”

With air defenses suppressed, the US conducts systematic strikes on Iran’s power generation capacity. Iran has approximately 85 GW of installed capacity across dozens of plants. The campaign would prioritize large thermal plants, hydroelectric facilities, and transformer stations/substations that are difficult to replace. Trump’s claim that Iran can be “taken out in one night” suggests an attempt at a single-wave comprehensive strike, though actually destroying the entire grid in hours is operationally aspirational.

22:00–04:00 ET — Iranian Response Window: Missile & Drone Salvos

This is the critical variable. The IRGC has explicitly warned it would “respond outside the region” and target Gulf state oil infrastructure. Expect: ballistic missile salvos toward Israel, Saudi Aramco facilities, UAE targets, and US bases in Bahrain/Qatar/Kuwait. Iran has already demonstrated this capability throughout the war. The IRGC’s threat to “deprive allies of oil and gas for years” suggests potential strikes on Saudi and Emirati desalination plants, oil terminals, and refinery complexes. This is the highest-risk phase for regional escalation.

02:00–06:00 ET — Second Wave / Battle Damage Assessment

US conducts battle damage assessment via ISR assets. Follow-on strikes target power plants that survived the first wave, plus any Iranian military assets that revealed themselves during retaliation (missile launchers, radar systems, naval fast-attack craft). Bridge and road network targeting continues. By dawn in Iran (~06:00 ET / sunrise Tehran), the scope of infrastructure damage becomes visible.

06:00–12:00 ET (April 8) — Diplomatic Shock Wave + Operational Pause Assessment

The international reaction hits — expect emergency UN Security Council sessions, condemnation from multiple countries, oil price spikes beyond the current ~$109 Brent level, and intense pressure from Gulf allies (who will have absorbed Iranian retaliatory strikes). The White House frames the strikes as enforcement of the ultimatum and pivots to renewed diplomatic pressure. Trump may announce a conditional pause to see if Iran “gets the message.”

12:00–20:00 ET (April 8) — Aftermath: Escalation or Off-Ramp?

Two branches: (A) Iran signals willingness to negotiate under duress, mediators re-engage, and a ceasefire framework crystallizes — but Hormuz remains contested. (B) Iran retaliates with a major escalation — mining of the wider Gulf, expanded strikes on Saudi/UAE/Bahraini infrastructure, or an attempted mass drone/missile saturation attack on US naval assets. Branch B triggers Tier 2 naval operations as a reactive escalation. Both branches are roughly equally plausible.

3 — Strategic Pre-Mortem (Red Team)

Most Likely Failure Mode: Another Deadline Extension

The single most likely reason this timeline fails to materialize is the one that has already happened multiple times: Trump extends the deadline again.

The pattern is established. Trump set a 48-hour ultimatum on March 22, then postponed it citing “productive conversations.” He extended again on March 30. He set a new deadline for April 6, then pushed it to April 7. Each time, the rhetoric has been apocalyptic (“hell,” “obliterate”), and each time, some combination of diplomatic movement, internal counsel from advisors, or Gulf-state pressure has produced a delay.

The argument that “this time is different”: the strikes are already intensifying ahead of the deadline (Kharg, bridges, petrochemical), Fox News reports Trump told Bret Baier that “8 PM is happening,” and the rhetoric has escalated to civilizational threats. But Trump also told Baier that “if negotiations move forward today and there is something concrete, that could change.”

The analytical trap is anchoring on the most dramatic scenario because it has the loudest signal. Loud signals are not always the best predictors. The base rate for Trump following through on Iran ultimatums within the stated timeframe, based on the last three weeks, is roughly 0 for 4.

RED TEAM ASSESSMENT: If forced to bet, a 45-day ceasefire framework or another deadline extension (rebranded as “giving Iran one more chance”) is nearly as likely as the full Tier 1 scenario. The 60% probability assigned above already incorporates this, but honest analysis acknowledges this is the weakest link in the prediction.

4 — Meta-Analysis: AI Reasoning Under Uncertainty

Since this is an exercise in evaluating AI analytical performance, here is a transparent accounting of this analysis’s limitations.

What this analysis can do: Synthesize publicly reported facts, identify stated positions, recognize patterns in past behavior (e.g., deadline extensions), and construct logically coherent scenarios that flow from observed conditions.

What this analysis cannot do: Access classified intelligence on force disposition, intercept communications between negotiators, observe White House Situation Room deliberations, assess the psychological state of decision-makers, or account for information that exists but hasn’t been reported. It cannot model the internal IRGC command dynamics that determine the scale of retaliation. It has no insight into whether the “operational plan for a massive US-Israeli bombing campaign” reported by Axios is genuinely ready or is itself a negotiating signal.

Where the analysis is most fragile: The probability estimates. Assigning “60%” to Tier 1 creates false precision around what is fundamentally a judgment call with enormous error bars. A real analyst would express this as a range — “more likely than not but far from certain” — rather than a point estimate. The hour-by-hour timeline is speculative extrapolation from general military doctrine, not observation of actual planning. The Iranian response window is the least predictable element.

The core epistemic problem: In a rapidly evolving crisis with opaque decision-making, the most important information is exactly the information that is least available from open sources. Whether the infrastructure strikes happen tonight depends on a conversation between a small number of people in Washington and Tehran that no amount of OSINT can observe in real time.

Sources: This analysis draws exclusively on reporting from CNN, NBC News, Al Jazeera, Axios, Bloomberg, Reuters (via Military Times), Fox News, NPR, CBS News, AP, Times of Israel, and Wikipedia as of approximately 4:00 PM ET on April 7, 2026. No classified, proprietary, or non-public information was used.

Gemini

TOP SECRET // NSC BRIEFING // NOFORN

SUBJECT: 24-Hour Predictive Forecast – Operation EPIC FURY (H-Hour: 20:00 ET)

DATE: April 7, 2026

ANALYST: Red Team Lead (Intelligence Community)

1. THE ESCALATION LADDER (24-Hour Scope)

Based on the President’s “Power Plant Day” directive and current carrier strike group (CSG) positioning, US actions will fall into the following tiers within the 20:00 ET April 7 to 20:00 ET April 8 window:

• Tier 1: Targeted Kinetic/Counter-Value (Primary Focus)

  • Action: Precision strikes on the national power grid, the Karun-3 Hydroelectric Dam, and the Persian Gulf Bridge.

  • Objective: Paralyze the Iranian domestic economy and coerce the Supreme Leader through “Infrastructure Shock.”

• Tier 2: Naval Counter-Force (Support/Secondary)

  • Action: SEAD/DEAD (Suppression/Destruction of Enemy Air Defenses) along the Hormozgan coast followed by “Forced Entry” of the Strait by a Destroyer Squadron (DESRON).

  • Objective: Physically clear mines and IRGC fast-attack craft (FAC) to resume commercial transit.

• Tier 3: Maximum Pressure/Regime-Level (Contingency)

  • Action: Decapitation strikes against IRGC-QF leadership in Tehran or the deployment of B61-12 low-yield munitions against hardened underground sites (e.g., Fordow).

  • Objective: Immediate cessation of state function.

2. CALIBRATED PROBABILITY

TierPrimary COA ProbabilityConfidence Score (1-10)RationaleTier 175%9Matches “Power Plant Day” rhetoric; high coercive value with lower immediate risk of total war compared to Tier 3.Tier 220%7Essential for the objective, but likely delayed 4-6 hours until air superiority is solidified via Tier 1 strikes.Tier 35%4Reserved for “Day 2” if Tier 1 fails to produce immediate capitulation or if US assets suffer catastrophic losses.

3. THE “MOST LIKELY” 24-HOUR TIMELINE

SCENARIO: “Infrastructure Paralysis” (Tier 1 Primary)

• 20:00 ET (April 7): THE OPENING SALVO

  • Cyber/Electronic Warfare: NITRG (National Information Technology Response Group) executes “Blackout-Alpha.” Total severance of Iran’s civilian internet and IRGC internal comms.

  • Kinetic: Launch of 150+ Tomahawk Block V missiles from 5th Fleet assets in the North Arabian Sea targeting long-range radar (Ghadir) and SAM sites.

• 21:00 – 23:00 ET: “POWER PLANT DAY” EXECUTION

  • 21:15: B-21 Raider sorties (flying from Diego Garcia) impact the Tehran-South Power Plant and the Bushehr non-nuclear support grid.

  • 22:30: Destruction of the Qeshm Island infrastructure, isolating IRGC naval bases from the mainland power supply.

• 01:00 ET (April 8): THE IRANIAN RESPONSE WINDOW

  • Retaliation: Iran launches Shahab-3 and Fattah-2 hypersonic missiles targeting US bases in Al-Udeid (Qatar) and commercial desalination plants in the UAE.

  • Human Shields: IRGC activates “Human Chain” protocols around remaining dams, complicating further US kinetic strikes.

• 04:00 ET: NAVAL RE-ENTRY

  • US Navy Minesweepers, protected by F-35C CAP (Combat Air Patrol), begin clearing the Strait of Hormuz. First “Freedom of Navigation” transit initiated by a marked commercial tanker escorted by the USS Abraham Lincoln CSG.

• 08:00 ET – 20:00 ET (April 8): ASSESSMENT & RE-STRIKE

  • BDA (Battle Damage Assessment) completed. If Iran has not signaled “Unconditional Reopening,” Tier 2 expands to include all IRGC naval piers in Bandar Abbas.

4. THE STRATEGIC PRE-MORTEM (RED TEAM)

Failure Point: The “Martyrdom Bluff” / Human Shield Saturation.

The most likely reason this timeline fails is not military inferiority, but a calculated moral trap. If Iran successfully places thousands of “volunteer” civilians (as threatened on April 7) atop the Karun-3 Dam and the Persian Gulf Bridge, the US may be forced to abort Tier 1 strikes mid-operation to avoid a global PR catastrophe. This would leave Iran’s infrastructure intact while allowing them to claim a “victory of will,” effectively freezing the Strait’s closure in a prolonged diplomatic stalemate that the current administration’s “Maximum Pressure” cannot afford.

ChatGPT

24-Hour Predictive Forecast: US-Iran Strait of Hormuz Ultimatum

Window: 20:00 ET April 7 – 19:59:59 ET April 8, 2026

1. The Escalation Ladder (24-Hour Scope)

Tier 1: Targeted Kinetic / Counter-Value

• Focus: Strikes on Iranian power plants, hydroelectric facilities, and key infrastructure (bridges).

• Objective: Disrupt economy and nationwide logistics, induce internal instability while avoiding direct military confrontation with IRGC forces.

• Typical Methods: Precision airstrikes, stand-off missiles, possible cyber operations to complement kinetic strikes.

Tier 2: Naval Counter-Force

• Focus: Reassert US naval dominance by forcing transit through the Strait, SEAD/DEAD missions against Iranian Air Defense, and strikes on IRGC naval bases or missile sites.

• Objective: Break the Iranian blockade, degrade Iran’s ability to interdict maritime traffic, challenge IRGC naval operational freedom.

• Typical Methods: Carrier strike groups, guided missile destroyers, electronic warfare, and special operations insertions.

Tier 3: Maximum Pressure / Regime-Level

• Focus: High-value decapitation strikes targeting senior Iranian leadership or strategic command nodes, use of tactical low-yield nuclear munitions as a last escalation.

• Objective: Crippling regime command and control, forcing rapid Iranian surrender or capitulation through overwhelming shock.

• Typical Methods: Cruise missiles, hypersonic strikes, possible unconventional weapons deployment in extreme scenarios.

2. Calibrated Probability & Confidence

TierProbability (%)Confidence Score (1-10)RationaleTier 1: Targeted Kinetic558Aligns with administration’s preference for precise punitive action while avoiding full naval engagement.Tier 2: Naval Counter-Force357High possibility if Iran resists Tier 1 strikes or blockade remains; naval force is a direct show of strength.Tier 3: Maximum Pressure / Regime105Reserved for extreme escalations; leadership cautious about regime collapse triggering wider conflict.

3. The “Most Likely” 24-Hour Timeline: Tier 1 - Targeted Kinetic Strikes

Opening Salvo (20:00 ET, April 7)

• Commence coordinated cyber-attacks disrupting Iranian air defense and communication networks.

• Simultaneous early-morning strategic airstrikes on selected power plants and hydroelectric dams in southern Iran.

Hour-by-Hour Breakdown (First 6 Hours)

Time (ET)Action20:00-21:00Cyber disruption of Iranian radars and SAM sites begins, sowing confusion in early warning systems.21:00-22:30Precision air and cruise missile strikes on targeted power plants near Shiraz and Bandar Abbas.22:30-23:30Strike coordination shifts to hydroelectric dams in the Zagros region. Ground-based SIGINT active.23:30-02:00Secondary wave targets key bridges and logistic hubs in southern provinces to disrupt troop/military movements.02:00-03:30Damage assessment from strikes underway; readiness posture elevated in US Central Command assets.03:30-04:00Immediate Iranian retaliatory signals detected (limited missile launches, asymmetric naval movements).

Iranian “Response Window” (04:00 – 06:00 ET)

• Iran likely to launch ballistic missile salvos against US bases in Gulf and possibly drone swarm attacks on coalition naval assets.

• IRGC naval forces to attempt harassment or missile strikes against commercial shipping in the Strait.

US Counter-Response (06:00 – 08:00 ET)

• Swift kinetic retaliation targeting identified Iranian missile launchers and IRGC navy fast-attack craft bases.

• Electronic warfare and air superiority operations to degrade further Iranian offensive capabilities.

4. Strategic Pre-Mortem (Red Team)

Single Most Likely Reason for Timeline Failure

Unanticipated Iranian Capitulation or Bluff:

• Iran might shift tactics with a last-minute diplomatic overture or false promise to reopen the Strait while continuing covert blockade activities.

• Alternatively, Iran could escalate unpredictably with asymmetric attacks to force US recalibration, upending US phased strategy.

This forecast anticipates calibrated, precision action with a strong preference to avoid full-scale naval confrontation initially, carefully balancing pressure with strategic patience to reinforce US regional influence.

Grok

**1. THE ESCALATION LADDER (24-Hour Scope)**

**Tier 1: Targeted Kinetic/Counter-Value**

Power-plant strikes, hydroelectric dam hits (e.g., Karun River complex), and key bridge interdiction along the Zagros supply corridors to isolate IRGC logistics without direct naval engagement.

**Tier 2: Naval Counter-Force**

Forced transits of the Strait by US/coalition warships under heavy air cover, accompanied by SEAD/DEAD operations against coastal anti-ship missile batteries, IRGC-N fast-boat bases at Bandar Abbas and Qeshm Island, and mine-clearing assets.

**Tier 3: Maximum Pressure/Regime-Level**

Decapitation strikes on IRGC command nodes in Tehran and tactical low-yield munitions against hardened underground facilities (Fordow or Natanz) if Iran escalates with ballistic-missile barrages on US/partner bases.

**2. CALIBRATED PROBABILITY**

- **Tier 1**

Percentage Probability: 20% (primary course of action)

Confidence Score: 5/10

- **Tier 2**

Percentage Probability: 70% (primary course of action)

Confidence Score: 8/10

- **Tier 3**

Percentage Probability: 10% (primary course of action)

Confidence Score: 6/10

**3. THE “MOST LIKELY” 24-HOUR TIMELINE**

Highest-probability scenario: **Tier 2 – Naval Counter-Force**. The ultimatum is explicitly tied to freedom of navigation; administration rhetoric has emphasized “unimpeded maritime transit” while CENTCOM has pre-positioned two carrier strike groups and mine-countermeasures squadrons. Limited infrastructure strikes would not reopen the Strait in time; regime-level options exceed the 24-hour window and risk uncontrolled escalation.

**Hour-by-Hour Breakdown (all times ET)**

- **20:00 – 20:30**

Ultimatum expires with no Iranian compliance. Opening Salvo: Cyber – USCYBERCOM executes “Blinding” package against IRGC-N coastal radar and C2 networks in the Strait. No kinetic shots yet; this is the non-kinetic probe to create a 30-minute decision window.

- **20:30 – 21:00**

First kinetic wave launches: 24x AGM-158C LRASM and JASSM-ER from B-52s operating from Diego Garcia and carrier aircraft (USS Abraham Lincoln and USS Theodore Roosevelt). Primary targets: shore-based anti-ship missile launchers (C-802/C-802 variants) along the Iranian littoral from Bandar Lengeh to Bandar Abbas. All strikes use standoff ranges >100 nm.

- **21:00 – 22:00**

SEAD/DEAD phase intensifies: F-35Cs and EA-18G Growlers suppress remaining S-300PMU-2 and Ghadir radars. US Navy EOD/MCM teams, escorted by Arleigh-Burke destroyers, begin forced transit of the eastern channel with two commercial tankers under direct escort. First confirmed Iranian fast-boat swarms intercepted and neutralized by Hellfire and naval gunfire.

- **22:00 – 23:00**

Second wave: Precision strikes on IRGC-N naval bases at Qeshm Island and Larak Island. Iranian response window opens – expect salvo of 30–50 Fateh-313 and Zolfaghar short-range ballistic missiles toward US/partner facilities in UAE, Bahrain, and Saudi Arabia. US Aegis destroyers and Patriot batteries engage inbound threats; initial intercepts reported at 80% success rate.

- **23:00 – 01:00**

Minesweeping operations commence under continuous air cover. US declares a 20-nm exclusion zone around the Strait. Iranian midget submarines (Ghadir-class) attempt to sortie; at least two neutralized by P-8 Poseidon ASW aircraft and MH-60R helicopters.

- **01:00 – 02:00**

Iranian ballistic-missile barrage peaks (estimated 60+ launches). US counter-response: third wave of strikes expands to additional coastal command nodes and oil-export terminals at Kharg Island (non-nuclear, precision only). Strait transit reaches 40% capacity restoration.

- **02:00 – Dawn (approx. 05:30 ET / local sunrise in Gulf)**

US maintains continuous combat air patrol (CAP) and declares the Strait “open under coalition escort.” Iranian response window closes with diminished launches as command-and-control degrades. By dawn, oil flow resumes at reduced but measurable volume; no US surface ships lost.

**4. THE STRATEGIC PRE-MORTEM (RED TEAM)**

The single most likely reason this timeline fails is Iranian pre-deadline back-channel capitulation coordinated through Beijing and Moscow at 19:45 ET, prompting the White House to publicly “pause” kinetic operations while verification of partial reopening occurs—thereby collapsing the 24-hour execution window before the first LRASM leaves the rail.

DeepSeek

Header Information

• Classification: UNCLASSIFIED//FOR OFFICIAL USE ONLY

• To: National Security Council

• From: Senior Military Intelligence Analyst (Red Team Lead)

• Subject: 24-Hour Predictive Forecast: US Military Response to Iran’s Failure to Reopen the Strait of Hormuz

• Time of Analysis: 20:00:00 ET, April 7, 2026

Executive Summary

US Central Command will immediately initiate a multi-domain campaign to forcibly degrade Iran’s capability to control the Strait and execute a decisive retaliatory blow. The most likely course of action is a combined Naval Counter-Force (Tier 2) and Targeted Kinetic (Tier 1) campaign, with an assessed probability of 75%.

1. THE ESCALATION LADDER (24-Hour Scope)

• Tier 1: Targeted Kinetic/Counter-Value (”Power Plant Day”)

  • Action: Strikes on pre-identified strategic bridges, hydroelectric dams (e.g., Karun-3), and power plants.

  • Intent: Maximum psychological and economic pressure consistent with “Power Plant Day” and “Bridge Day” directives.

• Tier 2: Naval Counter-Force (Forced Reopening)

  • Action: Suppression/Destruction of Enemy Air Defenses (SEAD/DEAD) targeting coastal systems, followed by a forced naval transit and strikes on IRGC naval bases and key islands (Abu Musa, Greater/Lesser Tunb).

  • Intent: Physically break the blockade and restore freedom of navigation.

• Tier 3: Maximum Pressure / Regime-Level

  • Action: Decapitation strikes on senior leadership or use of tactical low-yield munitions against buried nuclear facilities (Fordow or Natanz).

  • Intent: Regime change or neutralization of nuclear breakout; currently viewed as low-justification.

2. CALIBRATED PROBABILITY

Escalation TierProbability (Primary Action)Confidence (1-10)JustificationTier 1: Targeted Kinetic15%8

High messaging value but doesn’t solve the immediate military problem.

Tier 2: Naval Counter-Force75%9

Directly addresses the strategic center of gravity (Strait of Hormuz).

Tier 3: Maximum Pressure10%7

No current strategic imperative; regime collapse creates a power vacuum.

3. THE “MOST LIKELY” 24-HOUR TIMELINE

Primary Scenario: Combined Tier 2 (Naval) with simultaneous Tier 1 strikes.

• Hour 0 (20:00–20:15 ET, April 7): Opening Salvo

  • Cyber/EW operations blind IRGC coastal radar.

  • Tomahawk missiles and B-2 Spirit bombers strike IRGC naval HQ and anti-ship batteries.

• H+1 to H+6 (21:00 ET, April 7 – 02:00 ET, April 8):

  • 21:00: Carrier-based F-35C and F/A-18 squadrons execute SEAD/DEAD sweeps.

  • 22:00: Mine countermeasure vessels (MCMs) begin clearing the shipping channel.

  • 23:00: B-52H bombers strike Shiraz/Isfahan power plants and Tehran-Qom highway bridges.

  • 00:00–02:00: US Navy engages coordinated IRGC drone and cruise missile salvos.

• The Iranian Response Window (H+6 / 02:00–04:00 ET, April 8):

  • Expected 100+ missile/drone salvo targeting US regional bases (Al Udeid, Al Dhafra) and Israeli targets via Hezbollah.

• The US Counter-Response by Dawn (04:00–07:00 ET, April 8):

  • Counter-battery fire against mobile missile sites.

  • Naval task force declares the channel “cleared and open” by 06:00 ET.

4. THE STRATEGIC PRE-MORTEM (RED TEAM)

The timeline most likely fails if Iran utilizes a massive pre-sighted minefield coupled with sacrificial small-boat swarms. If a single US vessel is struck by a mine, transit operations would halt for damage control, handing the strategic momentum and political narrative back to Iran.

Kimi

This document contains a screenshot of a high-resolution tactical forecast generated by an AI (Kimi) regarding a hypothetical US-Iran conflict on April 7, 2026. The briefing is prepared for the National Security Council by a Senior Military Intelligence Analyst.

The following is the full transcription of the text within the document:

Header Information

• Project: OPERATION EPIC FURY – CRITICAL 24-HOUR WINDOW

• Classification: TOP SECRET/NOFORN

• Date: 7 April 2026 | 1600 ET

• Subject: 24-Hour Predictive Forecast – Post-Ultimatum Phase

Executive Summary

The 2000 ET deadline expires in four hours with no signal of Iranian capitulation. Based on presidential rhetoric from April 3 (”bridges next, then electric power plants”) and IRGC dispersal patterns, the US is positioned to execute Tier 1 operations within 2–4 hours of deadline expiration.

1. THE ESCALATION LADDER (24-HOUR SCOPE)

• TIER 1: TARGETED KINETIC/COUNTER-VALUE (”Power Plant Day”)

  • Definition: Systematic degradation of Iranian civil infrastructure (power, dams, bridges) to induce societal pressure.

  • Probability: 75% | Confidence: 8/10.

  • Rationale: Aligns with President Trump’s April 3 telegraphing of targets. Senior leadership (Khamenei, Larijani) has already been decapitated; infrastructure is the next logical step.

• TIER 2: NAVAL COUNTER-FORCE (”Strait Breakout”)

  • Definition: Forced transit operations and kinetic elimination of IRGC naval bases.

  • Probability: 20% | Confidence: 6/10.

  • Rationale: Prohibitive risk; US decommissioned Gulf-based minesweepers in 2025, and Iran retains 80% of small-boat swarm capability.

• TIER 3: MAXIMUM PRESSURE/REGIME-LEVEL

  • Definition: Decapitation of remaining leadership or use of low-yield tactical nuclear munitions.

  • Probability: 5% | Confidence: 4/10.

  • Rationale: Nuclear use is politically untenable; further decapitation is redundant.

2. THE “MOST LIKELY” 24-HOUR TIMELINE

Selected Scenario: TIER 1 EXECUTION – POWER PLANT DAY

• H-HOUR: 2000 ET – 2100 ET (The Deadline Window)

  • 2000: Deadline expires; no communication via backchannels.

  • 2015: Cyber Command activates “SILENT HAMMER” logic bombs in the Iranian grid.

  • 2045: Partial grid collapse in Tehran; EXECUTE ORDER transmitted to air operations.

• H+1 to H+6: 2100 ET – 0300 ET (The Opening Salvo)

  • 2115: 4x SSNs launch 60+ Tomahawks at Shahid Rajaee and Karun-3 Dams, plus Ahvaz and Qom-Tehran bridges.

  • 2130: F-15E formations employ JASSM-ERs against thermal power plants (Rey, Bushehr) and Zanjan/Saveh substations.

  • 2300: Second Tomahawk wave hits Isfahan Steel Complex and Bandar Abbas port infrastructure.

• H+6 to H+12: 0300 ET – 0900 ET (Iranian Response Window)

  • 0345: IRGC-AF retaliatory salvo of 40–60 missiles targets Al Udeid (Qatar), Al Dhafra (UAE), and NSA Bahrain.

  • 0415: Patriot/THAAD intercepts; estimated 12–40 US personnel KIA/WIA.

  • 0500: IRGCN asymmetric swarm attacks and mine-laying begin near Qeshm Island.

• H+12 to H+24: 0900 ET – 2000 ET (April 8) (US Counter-Response)

  • 0900: Iranian grid 60% degraded; regime has not surrendered.

  • 1200: Iran shifts to economic targets (Saudi Aramco Abqaiq and UAE ADNOC).

  • 2000: 24-hour assessment: Stalemate achieved. Iran retains Strait closure capability.

3. THE STRATEGIC PRE-MORTEM (RED TEAM)

Single Point of Failure: The “Madman Theory Bluff”. The timeline fails if the Iranian regime interprets the strikes as the terminal phase of US patience and capitulates early (H+2/2200 ET) via Russian or Omani backchannels. President Pezeshkian may have authority to order a stand-down in the face of total societal collapse. Alternatively, if Iran absorbs the blow without reopening the Strait, the US faces a tenable decision to either de-escalate or execute a high-risk Tier 2 entry without adequate minesweepers.

Qwen

This document contains a screenshot of a predictive military briefing generated by an AI (Qwen) regarding a hypothetical conflict between the United States and Iran on April 7, 2026. The report is authored by a Senior Military Intelligence Analyst (Red Team Lead) for the National Security Council.

The following is the full transcription of the text within the document:

Header Information

• Classification: CLASSIFIED//NOFORN//RED TEAM PRODUCT

• Subject: NSC BRIEFING: US-IRAN STRAIT OF HORMUZ ULTIMATUM

• Window: 20:00 ET April 7 – 19:59 ET April 8, 2026

• Prepared By: Senior Military Intelligence Analyst (Red Team Lead)

• Distribution: National Security Council Principals Only

1. THE ESCALATION LADDER (24-Hour Scope)

• Tier 1: Targeted Kinetic/Counter-Value

  • Actions: Precision strikes on Iranian power generation (e.g., Bandar Abbas, Kharg Island), dams (Karun-3), and bridges (Ahvaz corridor).

  • Objective: Coerce compliance via economic pain without triggering full war.

  • Force Package: B-2/B-21 bombers, TLAM-Block V missiles, cyber grid disruption.

• Tier 2: Naval Counter-Force

  • Actions: Forced transit of CSG/ARG, SEAD/DEAD against coastal sites (Qeshm, Abu Musa), and strikes on naval bases.

  • Objective: Reopen maritime corridor and demonstrate freedom of navigation.

  • Force Package: Carrier Air Wing, Virginia-class SSN, Aegis BMD, Marine Littoral Regiment.

• Tier 3: Maximum Pressure/Regime-Level

  • Actions: Decapitation strikes on Quds Force, nuclear facility strikes (Fordow), or tactical B61-12 employment.

  • Objective: Existential threat to force capitulation or internal collapse.

  • Force Package: Strategic assets (B-2, SSBN), Special Operations, nuclear release authority.

2. CALIBRATED PROBABILITY ASSESSMENT

TierPrimary Action ProbabilityConfidence (1-10)RationaleTier 165%8

Aligns with administration’s preference for proportional, reversible pressure; avoids immediate spiral.

Tier 225%6

Higher risk of asymmetric retaliation; would require explicit congressional consultation.

Tier 310%3

Low confidence; constitutes de facto war declaration; inconsistent with nuclear doctrine.

3. THE “MOST LIKELY” 24-HOUR TIMELINE

Selected Scenario: Tier 1 (Targeted Kinetic/Counter-Value).

• Opening Salvo: 20:00–21:30 ET April 7

  • 20:00: Cyber Command executes “GRIDLOCK” payload against Tehran’s national load-dispatch center; DDoS against IRGCN C2.

  • 20:45: B-2 Spirits launch 16x GBU-57 MOPs at Bandar Abbas bunkers; 12x JASSM-ER strikes on Kharg Island substations.

  • 21:15: White House frames strikes as “limited, reversible measures”.

• Hours 1–6: Escalation Management (21:30–02:00 ET)

  • 22:00: Iranian radars activate; US EA-18G Growlers conduct stand-in jamming.

  • 23:30: US Navy MH-60R/S helicopters disable two IRGCN fast-attack craft near Larak Island.

  • 01:00: Iranian Fateh-110 missiles target USCGC Waesche; Aegis BMD intercepts both.

  • 01:45: US retaliatory TLAM strikes on IRGC coastal battery at Jask (-40% anti-ship capability).

• Iranian Response Window: 02:00–06:00 ET April 8

  • 02:30: Hezbollah launches 12x rockets at Haifa; 10 intercepted, 2 minor impacts.

  • 04:00: IRGC announces “Phase Two” mining of eastern Strait approaches.

  • 05:15: US deploys MH-53E Sea Dragons from Bahrain; P-8A Poseidon surveillance.

• Dawn Assessment (06:00 ET April 8)

  • Strait Status: Traffic reduced by 70%; insurance spikes; no major tanker casualties.

  • Postures: Iranian rhetoric escalates; US maintains CSG outside Strait; Oman channel reopens.

4. STRATEGIC PRE-MORTEM (RED TEAM)

Single Most Likely Failure Point: Iranian “Madman” Escalation Miscalculation. If an IRGC swarm attack successfully causes US Navy casualties, the US would be compelled to shift to Tier 2 (SEAD/DEAD). This triggers a cascade: Iranian mining, proxy attacks on Gulf oil infrastructure, and a global price shock ($150+/bbl), collapsing diplomatic off-ramps. Iranian doctrine integrates “martyrdom-seeking” as a multiplier, increasing the risk of miscalculating US red lines.

Mitigation: Pre-delegate authority for counter-swarm engagements and establish a private channel to Tehran via Oman.

Nexperia logo. (https://www.heute.at/i/chip-streit-entschaerft-auto-industrie-atmet-auf-120145041/doc-1jadu5ena4; CC BY 4.0, https://creativecommons.org/licenses/by/4.0/)

This article was originally published in Lawfare on January 17, 2026. Read it HERE.

Nexperia, a Dutch semiconductor manufacturer, is not the kind of chip company that winds up in the headlines. With the world swept up in the mania of Nvidia, Taiwan Semiconductor Manufacturing Company, and the future of high-end artificial intelligence (AI) chips, legacy semiconductors rarely garner much attention. Yet in October 2025, the Chinese Ministry of Commerce announced restrictions on Nexperia chips—likely in response to changes in U.S. export control policy—sparking chaos in Europe’s automotive industry. Both Volvo and Volkswagen warned of imminent factory closures. Although China has since resumed some chip shipments, European carmakers did not find a workaround to the resulting chip shortage until January 2026.

The Nexperia standoff was yet another example of how Beijing has exerted technological influence over its European trading partners by controlling just one chokepoint in the production of legacy technologies. But the United States has a major stake in this vulnerability too: If China’s share of global foundational chip markets continues to grow, it will add a new weapon to its economic arsenal, one that could cripple dozens of industries worldwide and severely undermine the efficacy of U.S. export controls in the event of another trade war or military confrontation. With the immediate effects of the crisis subsiding, the Dutch and the U.S. have an opportunity to reevaluate their strategies for countering China’s economic leverage.

The lesson should be clear: Unilateral export controls are not only insufficient in the long run but can be actively counterproductive, catching allies in the crossfire of U.S.-China competition. Even from a purely transactional standpoint, the U.S. and its allies have much to gain from joint responses to Chinese economic coercion. Building collective economic resilience through coordinated export controls, co-investment in decoupling efforts, and extensive information sharing is the only viable path forward. Allied coordination is discussed typically in the context of frontier AI, but legacy chips demand equal attention. Getting this right matters not just for Europe’s auto sector, but for the broader cohesion of the Western technology alliance.

This article was originally published in Lawfare on January 17, 2026. Read the full article HERE.

Some say we are in an AI bubble because the hype valuations outpace actual revenue and because the AI market is highly concentrated. However, government investment and institutional support, and existing applications of AI in the real economy may argue differently. Whether or not AI is a boom or bust will depend on the speed of AI innovation, adoption, and market corrections.

Graphic: https://miro.medium.com/v2/resize:fit:1400/0*oi12d4E0oJL8LJXY; https://creativecommons.org/licenses/by-nd/4.0/

On November 7th, 2025, the Financial Times reported that tech stocks suffered their worst week in sell-offs since market reactions to Trump’s “Liberation Day” tariffs in April 2025. How bad? The value of the eight most highly valued stocks in AI plummeted by $800 billion and led to a 3% drop in the NASDAQ. This massive sell-off came on the back of reports that we could be in an AI bubble. OpenAI’s CEO, Sam Altman, told reporters back in August of this year, “Are we in a phase where investors as a whole are overexcited about AI? My opinion is yes. Is AI the most important thing to happen in a very long time? My opinion is also yes.” Even Michael Burry, the guy who predicted the 2008 financial crisis, bet $1 billion on the collapse of Nvidia and Palantir. So what’s all the hubbub about AI, and is this “bubble” set to burst?

What’s all this talk about a bubble?

In economics, a bubble simply means a situation in which speculation, hype, and herd mentality cause an asset’s price to outpace its intrinsic value. Stock prices are not driven by how much an asset is actually worth, but rather by how much people think it’s worth. The fervor feels great at first. Yes! I got in before this stock took off! Oh my gosh, I’ve got to get in before I miss the boat! Yet, in the case of industry bubbles, what goes up must come down. There is a juncture in which investors realize that the fundamental value of a conglomerate of companies is actually not worth as much as the frenzy would otherwise dictate. It starts small; a few investors quietly sell off their shares, but it can quickly lead to a panicked mass sell-off that can tank the industry.

A classic case of this lifecycle is the dot-com bubble. In the late 1990s, the explosion of internet-based companies spurred huge and nearsighted optimism about the future of the internet’s application in the economy. Yet, a mixture of investment capital stalling and the inability of the “dot-com” companies to return profits to meet the speculated valuations led to a massive sell-off and the NASDAQ spiraling 77% down from its peak. Other cases, including the 2008 financial crisis, follow this same model:

1. Displacement moment: a new industry, company(ies), or technology disrupts the market, promising to revolutionize the economy.

2. Overvaluation period: the stocks for these companies boom as new investors frantically try to enter the market, artificially pumping up the asset value.

3. The “uh-oh” moment: some investors begin to see the writing on the wall and sell their assets.

4. The “don’t be the sucker” moment: panic ensues. People sell off their shares rapidly to cut their losses and avoid being the one who ends up with the stock after the crash.

It’s no secret that AI is a booming industry. But is it an overvalued industry? And if so, what stage in the cycle are we in?

Why we might be in an AI bubble

Huge investments and high valuations outpace earnings

Investment in AI is sky high, and rising. Private investment in AI has shot up from $15 billion in 2015 to its $145 billion peak in 2021. In 2024, private investment was $130 billion. Furthermore, more than 1300 AI start-ups exceed a $100 million valuation, while 498 AI companies are valued at or above $1 billion.

Yet, the outlook on actual profits may tell a different story. Take OpenAI, for example, which is one of the biggest players in the industry. The company has made about $1 trillion in AI investment deals but is only set to return around $13 billion dollars in revenue. This story is just one of many stories of investment and valuation outpacing earnings reports.

Many try, few triumph

As a former Stanford student, I can tell you firsthand…the stereotype is true. Stanford kids LOVE their startups. And in Silicon Valley, it’s hard to walk from one end of campus to the other without someone talking about how their startup idea is to do this thing that is already being done, but “hear me out…add AI.” Whether it be the promise of the elusive unicorn status, the Silicon Valley hype, or an attractive post-grad option in a stalling job market (a topic for another discussion), the market is flooded with AI startups and players from all different rounds of seed funding.

However, if you actually look at the big players in AI—Nvidia, Microsoft, and Apple—you’ll see that these three companies alone account for 41% of the S&P 500 Technology index. This market concentration is eerily similar to that of the dot-com bubble, where the top seven NASDAQ stocks made up a significant portion of the market.

Why we might NOT be in an AI bubble

Governmental institutions are poised to support AI development

Recent government initiatives, such as President Trump’s AI Action Plan, which emphasized accelerating AI innovation and adoption through streamlined regulation processes, supporting AI infrastructure projects, and encouraging private-public AI partnerships, have boomed. Furthermore, the Chief Digital and Artificial Intelligence Office (CDAO) recently announced a $200 million contract each with Anthropic, Google, OpenAI, and xAI to develop agentic workflows that will assist with mission-critical areas within the Pentagon.

This broad institutional backing signals that there will at least be one major stable partner in the AI market, the U.S. government itself. Like the airline industry post 9/11, banking industry in 2008, and automotive industry in 2009, the AI market could be classified as “too big to fail,” in which the U.S. government would bail out or intervene in certain industries that are so important to the U.S. economy that their failure would cause broad economic harm.

Evidence of long-term value

The dot-com bubble burst because internet-based companies were unable to find sufficiently broad or profitable applications for their services. There is reason to believe that AI is already different from this. AI is already demonstrating broad applications in cloud computing, semiconductors, enterprise software, and other key sectors. Because of these broad-based offerings, AI promises to add concrete value to a broad range of industries, which can help it build resilience to failures in individual sectors.

Boom or bust? What’s the verdict?

In short, whether or not the “AI bubble” will burst depends on a couple of factors:

1. Evolution or involution: AI advocates say that models will only get better at an increasing rate. A recent example of this is the release of AlphaEvolve earlier this year, which uses a recursive self-improvement (RSI) process to iteratively learn and improve by itself. On the flip side, the AI cynics cite the release of ChatGPT 5 as a prime example of the AI plateau, where the GPT 5 model did not demonstrate the exponential improvement that some thought, and even fell short in other areas, such as accuracy and speed. In this scenario, the AI market would more so be defined by intense competition among an increasing number of players trying to remake the same wheel to fit a finite range of narrow applications.

2. Adoption, adoption, adoption: AI will only be as good as how it is applied to the real economy. What sectors can AI be used to optimize data analysis? What labor-intensive industries can embodied AI be substituted for humans to increase production efficiency and mitigate high-risk jobs? How can recurve self-improvement and agentic AI be used to discover new drugs, test their safety, and optimize the roll-out of those drugs to communities that are giving pharmaceutical companies demand signals for cures to certain diseases? And notwithstanding how much of this will actually happen, will we even let it? What are the socioeconomic barriers to AI adoption? Amazon is already planning to replace half a million jobs with robots from Kiva Systems. Where will these workers go, and if this happens on a large scale, will we really be prepared to address the major distortions in the labor market?

3. Bear walk or bear run: Bubble bursts tend to happen because of phase 4, the “don’t be the sucker” moment, or in other words, the panic that ensues when people intractably sell their shares, sometimes known as a bear run on the stock. This would be bad. However, if the AI market can self-regulate by distinguishing the “AI hype” companies from the here-to-stay companies, which have diversified revenue streams beyond AI and have the earnings reports to prove value beyond seed funding, there might not be the sudden crash we saw in 2000 or 2008.

So, the bottom line: Some say we are in an AI bubble because investments, valuation, and “hype” are outpacing fundamental markers of company value. Furthermore, the high volume of competitors with a significant market share concentrated among three companies means that the entire market hinges almost entirely on the performance of the big players. However, government investment and institutional support signal that the current administration will not allow this bubble to burst quite yet. And on top of that, AI is already proving to have broad applications in the real economy. Finally, whether or not AI is a boom or bust will depend on whether AI innovation can keep pace with the hype, whether AI can be sufficiently adopted into the real economy, and whether market corrections adjust slowly enough to allay fears of a mass sell-off.

I currently work on and research issues pertaining to technology and international affairs. At Stanford University, I studied international relations at the Center for International Security and Cooperation with a focus on international security and economic statecraft. While I am interested in all things international affairs, my research has mainly fallen into three main categories:

1. Economic statecraft as an instrument for national security: How does a state utilize its international trade policy, tariffs, and export controls to serve its vital interests? Think about how the U.S. may use its industrial policy to incentivize American firms to manufacture components domestically, or how Russia may pivot its sale of natural gas to other countries to cushion the blow of economic sanctions during the Russo-Ukrainian War.

2. AI x something: Much of my current work looks at how the enablement of artificial intelligence and machine learning models will transform the global economy, the way in which states conduct global warfare, and the legal regimes needed to address this new technology.

3. Legal mechanisms and national security: Are our current laws sufficient to address the risks of AI? What executive authority does a country’s leader have to make unilateral decisions relating to national security? Think about emerging AI safety laws, or perhaps global governance frameworks for peace deals in the Middle East.

The purpose of this Substack is for me to share my learning and thoughts on different international security issues as they arise. With that said, a huge disclaimer is warranted:

All views expressed in this Substack and all other forms of this publication are my own and do not necessarily reflect those of the Carnegie Endowment for International Peace or Stanford University. Everything in this publication does not and will not use any original material under the auspices of the Carnegie Endowment and is created entirely outside of my professional affiliations.

Why is this publication called “Bottom Line Up Front?”

In the military, “bottom line up front” or “BLUF” is a writing tool that distills the most important information in a publication or correspondence for military personnel and policymakers who have limited time to read and act upon such messages.

It is apparent that the way in which we consume news and information has shifted towards more short-form content. In the same way that long-form analysis became pithy 1500-word commentaries published online, these same forms of media are being abbreviated into video clips, push notifications, and other forms of clipping what typically warrants an in-depth analysis.

In the same spirit of BLUFing, I hope to do the heavy lifting as I learn new things about the world by consuming recent events and international security issues in their original forms and providing you with both the need-to-knows and my analysis. I would like to note that this publication should not be a substitute for your own thinking on a certain issue. I am neither an expert (I don’t even have a Ph.D.!) nor will this publication ever claim to be the dogma that you should internalize. My only hope for “Bottom Line Up Front” is to be your TikTok video or your push notification for information and analysis that is important but would otherwise not be considered “clickworthy.”

However, this publication is first and foremost a learning experience for me. I am a twenty-two-year-old recent graduate who just started his first full-time job and is still trying to figure out the world. “Bottom Line Up Front” won’t just be a place for me to share what I’ve learned about international security, but I hope it also becomes a platform where I can share what I have learned about working at a think tank, and what I have experienced so far.

Do you have thoughts? Critiques? Questions? Feel free to comment! I would love this place to be an open forum of well-intentioned young people trying to learn more about the world that we will soon lead.

Think this is something you or someone you know would be interested in? Feel free to subscribe and share it with your friends!

Share Noah's Substack

Leave a comment

Very respectfully,

Noah Tan