Yes, the “Two Presidents” Scenario Could Really Happen

My recent post about two “Presidents” with the power to launch nuclear attacks sounds technologically very difficult, but it’s not impossible. Even biometric modification can happen if an adversary has enough money.

Grok.

But as is true with anything, the technology is easy. The business part is the difficult part.

And most would argue that there is absolutely no way that a scam like this could be pulled off, especially since it would require inside cooperation.

Perhaps you’d better sit down.

August 9, 1974

Washington, DC was in a very confused state on August 9, 1974. When the day began, Richard Nixon was President and Gerald Ford was Vice President. Several hours later Ford would be President and there was no Vice President. (If Ford had suddenly died, Speaker of the House Carl Albert would have become President. If you thought the events of 1973 and 1974 were wild enough, imagine if Albert had become President.)

The morning of August 9 was carefully choreographed, but I am going to concentrate on two events involving Richard Nixon, Alexander Haig, and Henry Kissinger.

  • The first occurred at about 10:35 am when President Richard Nixon’s helicopter lifted off from the South Lawn, headed toward what was then Andrews Air Force Base.
  • The second occurred later, at about 11:35, when White House Chief of Staff walked into the office of Henry Kissinger, in Kissinger’s capacity as Secretary of State. Haig’s arrival was expected, as was the signed letter that he bore from President Nixon (en route to California). The letter was short.

“I hereby resign the Office of President of the United States.”

Kissinger indicated his receipt of the resignation and maintained communications with critical people, including Vice President Gerald Ford.

But there was one other critical person: the Secretary of Defense, James Schlesinger.

And there was one very important part of the choreography that wasn’t mentioned publicly that day.

Back to the Helicopter

I don’t know if “biscuits” existed in 1974, but footballs certainly did. And certainly the concept of continuity hadn’t yet matured to the Carter-Mondale level. But everyone agreed that according to the Constitution, on that day Richard Nixon remained President of the United States until he didn’t.

But according to reality, Nixon was…stressed.

“Schlesinger feared that the president, who seemed depressed and was drinking heavily, might order Armageddon. Nixon himself had stoked official fears during a meeting with congressmen during which he reportedly said, “I can go in my office and pick up a telephone, and in 25 minutes, millions of people will be dead.” Senator Alan Cranston had phoned Schlesinger, warning about “the need for keeping a berserk president from plunging us into a holocaust.””

And Schlesinger acted. When a liberal Democratic Senator demands action from a conservative Administration, sometimes things happen.

While some of the 1974 actions of Schlesinger, Kissinger, and Haig during the “final days” are murky, there is general agreement that Schlesinger gave a rather unusual order to the military.

“[I]n the final days of the Nixon presidency he had issued an unprecedented set of orders: If the president gave any nuclear launch order, military commanders should check with either him or Secretary of State Henry Kissinger before executing them.”

This is entirely against the Constitution. If the Vice President and Cabinet doubted the sanity of the President, the proper avenue was a 25th Amendment removal—not an inferior official disobeying the instructions of the Commander-in-Chief.

However, in those strange days, in which many things happened in secret, one can understand why Schlesinger did what he did.

But there was one other critical decision that was made on August 9.

Remember when President Nixon boarded the helicopter?

“[T]he most critical tool of the modern presidency had already been taken away from him. He never noticed it, but the nuclear “football” didn’t travel with him as he boarded the helicopter, and later, Air Force One for his flight back to California.”

Yes, the football. The thing that was ALWAYS with the President because the USSR could launch a nuclear attack at any moment.

Remember that Nixon was still President an hour after boarding the helicopter, when Kissinger received a visit from Haig. But if the U.S. had been attacked during that hour, the President couldn’t respond.

And the Vice President didn’t have the power to respond.

The football appears to have been in the custody of military aides outside the East Room, awaiting the moment that Gerald Ford would take the oath of office. (Although he was already President once Kissinger indicated his receipt of the resignation letter.)

But…who controlled the football?

Schlesinger?

Kissinger?

Carl Albert?

In the end nothing bad happened, but it could have.

And it’s therefore entirely possible that the aforementioned “two Presidents” scenario could happen.

Two Footballs, Two Biscuits, Two Presidents: A Cybersecurity Nightmare.

Last year I wrote about a biscuit and a football, but I wasn’t talking about the snack spread on game day.

Google Gemini.

I was talking about the tools the United States President uses (as Commander-in-Chief) for identity verification to launch a nuclear attack.

But sometimes you have to pass the football. If the President is temporarily or permanently incapacitated in an attack, the Vice President also has a football and a biscuit. Normally the Vice President’s biscuit isn’t activated, but when certain Constitutional criteria are met it becomes operative.

Other than this built-in redundancy, the system assumes one football, one biscuit, and one President.

If you’re a cybersecurity expert, you know this assumption is the assumption of a fool.

  • It is not impossible to have duplicate functional footballs and duplicate functional biscuits.
  • And it is not impossible to have duplicate functional Presidents, with identical face, voice, finger, and iris biometrics. Yes, it’s highly unlikely, but it’s not impossible. If the target is important enough, adversaries will spend the money.
Grok.

And most of us will never know the answer to this question, but how do government cybersecurity experts prevent this?

The March 3, 2026 List (Probably Still Inaccurate) of PAD 3 Conforming Solutions

Update to the February 27 version. Added Incode.

VendorModalityConfirming LabLink/Date
AwareFaceBixeLabNovember 2025
FaceTecFaceBixeLabOctober 2025
IncodeFaceiBetaFebruary 2026
ParavisionFaceIngeniumSeptember 2025
YotiFaceiBetaJanuary 2026

Visa Overstays and Biometric Exit

Two facts about Nawaf al-Hazmi:

  • He’s dead. al-Hazmi died at the Pentagon on September 11, 2001 afterr hijacking a plane.
  • He had overstayed his visa. al-Hazmi’s visa expired in January 2001.

This fact, and other irregularities in the visas and passports of the 9/11 hijackers, directly led to the mandate that the U.S. implement biometric exit…which has been delayed more often than REAL ID.

In theory, enforcement of visa expirations with biometric exit is simple.

  • If you can tell who has entered a country and who has left a country, then you can identify people who have NOT left the country, but whose visas have expired.
  • And you can tell entries and exits via biometrics, as long as a person’s biometrics are acquired through the passport and/or visa process.

So if biometric exit had existed in January 2001, then a (theoretically) quick check could show that al-Hazmi had NOT left the United States and was still here on an expired visa. He could have been kicked out of the country and barred from returning, and therefore wouldn’t be on a plane on September 11.

The only problem is that EVERYONE needs to be processed when leaving the country for the system to work. At a minimum, anyone who cannot prove U.S. citizenship would have to have their biometrics captured. Or just make it easy and capture everyone’s biometrics as they leave the United States.

Some express the belief that current biometric exit practices exceed the mandate:

“The coalition—led by the Electronic Frontier Foundation, the American Civil Liberties Union and the Canadian-U.S. cross-border group OpenMedia—contends that capturing images of lawful permanent residents exceeds DHS’s statutory mandate and creates a de-facto travel dossier vulnerable to data breaches.”

Back in 2017, it was alleged that pilot programs even captured biometric exit data for U.S. citizens.

Concerns about overreach fall into two categories:

  • That the captured data would be used for things other than visa overstays.
  • That the captured data could be hacked, exposing the travelers’ personally identifiable information.

So the theory of tracking people as they enter and leave a country can get messy when put into practice.

I know.

So I Tried Vibe Coding

Vibe coding is real…and you can do it yourself for free. Since I’m on the Google platform, I used Google Gemini to guide me through the steps.

Specification

I started informally:

Online analysis of the chief biometric news from the last seven days, sorted into finger, face, iris, voice, DNA, and other.

Google then formalized a Product Requirements Prompt for Build Mode for Gemini AI Studio (which I had never used before). It made all the UI choices, which I didn’t change (although I haven’t used green on black since the DOS days).

PRODUCT REQUIREMENTS PROMPT (PRP): “BIOMETRIC PULSE 2026”

1. VISION & VIBE

You are building “Biometric Pulse 2026,” a high-frequency, automated data dashboard and visualization tool.

The Vibe: Minimalist, data-dense, dark mode (matrix-green and stark white accents), 1980s retro-futurist ‘terminal’ aesthetic. High information density with zero clutter. The app must feel intelligent, real-time, and analytical.


2. FUNCTIONAL SPECIFICATIONS

The application is a full-stack automated news and regulation analyzer. It must perform the following tasks without user input:

Phase 1: Data Ingestion (Automation)

  1. Source Strategy: Use a hybrid approach:
    • Google Search API (Real-time): Schedule a request every 4 hours for the query "biometrics industry news" OR "facial recognition technology" OR "iris scanning update" OR "voice biometrics market" OR "DNA border control policy" OR "biometric regulation". (Grounding is required).
    • Web Scraper (Targeted): Target specific domain feeds for deeper insights (e.g., BiometricUpdate.com, SecurityInfoWatch, specialized legal/regulatory feeds). If you cannot build the scraper, mock this data with realistic data from the last 7 days.
  2. Date Filtering: Automatically filter all results to only include data from the last 7 calendar days (using the current date dynamically).

Phase 2: AI Classification & Analysis

  1. Categorization: Use Gemini 3 Flash to analyze the title/snippet of every news item and classify it into one or more of these 6 buckets:
    • finger
    • face
    • iris
    • voice
    • dna
    • other (Regulation, Business Mergers, Multi-modal)
  2. Contextual Tagging: Assign secondary sentiment/type tags (e.g., [Surveillance], [Privacy Win], [Market Growth], [New Tech]).

3. UI/UX REQUIREMENTS (THE DASHBOARD)

The main view is a single-page, real-time updated dashboard.

Component A: The Pulse Feed (Primary View)

  • A vertically scrolling list of news items.
  • Items must be chronologically sorted (newest first).
  • Card Design: Every card must have:
    1. A clear category icon/tag (e.g., [ 👤 FACE ] in bright green).
    2. An automated, one-sentence summary (using Gemini).
    3. The primary source link, relative date (“2 days ago”).
    4. Sentiment analysis tags.

Component B: Filter Terminal (Left Sidebar)

  • A stack of minimalist buttons for the 6 primary categories.
  • Show the live “count” of articles found in the last week next to each (e.g., [ 👤 FACE (14) ], [ 🧬 DNA (3) ]).
  • Clicking a category filters the Pulse Feed instantly.

Component C: “The Weakly Pulse” Chart (Right Sidebar)

  • A stacked bar chart visualization.
  • X-Axis: The 6 modalities (Face, Finger, etc.).
  • Y-Axis: Number of news events reported this week.
  • Color Code: The bars should show sentiment (e.g., red for surveillance/privacy concern; green for innovation/market growth).

4. TECHNICAL ARCHITECTURE & STACK

  • Model: Gemini 3 Flash (required for continuous analysis and low latency).
  • Integration: Google AI Studio Build Mode.
  • Runtime: Node.js (Vite server for the frontend).
  • Package Needs: react-query (or simple useEffect for data fetching), chart.js (for the weekly pulse chart), and a minimalist CSS framework or Tailwind (but customized to the dark terminal look).
  • Deployment: Pre-configure for One-Click deployment to Google Cloud Run.

Use

So there it is. I went into Google AI Studio and used Build to build the thing, and without publishing it, I ended up with something that looked like this.

Biometric Pulse 2026, as of the afternoon of March 2, 2026.

It certainly has the retro user interface…but if you look carefully at the data, there isn’t any. I don’t know if I have to wait four hours for the data to auto-refresh, or if I actually have to publish it to have it generate data. Or buy tokens or something.

But if I can get this to actually work, I’ll have proven that you can easily specify simple tasks using modern tools.

But as I noted in my earlier post, I can’t maintain the code.

Yeah, I wrote this…sorta.

If I play with this more I’ll provide an update.

But you can save yourself the heartache and just ask someone like Silicon Tech Solutions to code your app. They know what they’re doing.

Let’s Talk Hype With Gartner on Generative AI

Gartner’s article “Latest Hype Cycle for Artificial Intelligence Goes Beyond GenAI” was written in July 2025, but even many months later it’s still illustrative. At the time, author Haritha Khandabattu said the following:

“…GenAI enters the Trough of Disillusionment as organizations gain understanding of its potential and limits. 

“AI leaders continue to face challenges when it comes to proving GenAI’s value to the business. Despite an average spend of $1.9 million on GenAI initiatives in 2024, less than 30% of AI leaders report their CEOs are happy with AI investment return. Low-maturity organizations have trouble identifying suitable use cases and exhibit unrealistic expectations for initiatives. Mature organizations, meanwhile, struggle to find skilled professionals and instill GenAI literacy.”

To see and download Gartner’s pretty pictures, go to the article.

Since the article was published, IBM has tripled entry-level hiring rather than assume that generative AI can perform ALL entry-level jobs.