Pressure-testing AI before you trust it. Where confident outputs meet hard evidence — and the ones that can't prove themselves get stopped.

The Citations Were Real. The Conclusion Wasn't.

The newest entry in the AI Pressure Doctrine series. Every earlier post put an AI's claims about a résumé or a bid under pressure. This one aims the same doctrine at a stranger artifact — a confident, 39-citation report an AI wrote about AI. I checked every source

5 out of 5 Stars: How Google Aides APTs in Cyber Attacks.

Amazon researchers, a report says, found ways to get Fable 5 — the version of Mythos 5 with security guardrails — to aid in cyberattacks. Google's been doing it for years. An exclusive investigation by the Institute for Maximum Alarm In a chilling discovery that has the security community saying

I Made Six AIs Grade the Same Résumé. Two of Them Broke Rules They'd Just Read.

I gave six different AI models the same résumé and the same instructions. Word for word, the same rules, the same document. Then I lined their answers up side by side. They didn't match. Not wildly. But a bullet one model rated as solid evidence, another rated as

The RealityGate Self-Audit: 7 Questions Before You Trust an AI-Assisted Review

Looking official is not the same as being true. The model grades the polish. You verify the fact. A short utility from the AI Pressure Doctrine series. Not an essay — a tool. Copy it, keep it, run it. Most AI failures do not announce themselves as nonsense. They arrive as

I Aimed My Own Lie-Detector at My Own Rulebook

Fourth in a series on the AI Pressure Doctrine. Earlier posts showed AI models disagreeing on the same evidence, found the rule that fixed it, and then watched that rule get fooled by a forgery wearing the right costume. This one turns the whole apparatus inward — on the rulebook itself.

I Built an AI to Cross-Examine Lies. It Saluted the Costume and Waved the Liar Through.

Third in a series on the AI Pressure Doctrine. The first post showed two AI models reaching opposite verdicts on the same proposal. The second found the fix that made them stop disagreeing. This one is about what happened when I tried to push that fix one step further — and

I Built a Fraud Detector. It Was Really a Verifiability Detector.

I set out to build something that could read a résumé and tell whether the person was inflating their experience. What I ended up with was a system that could tell whether a person had written down checkable details — and was quietly calling that the same thing as telling the

I Used to Count a Résumé as Proof. An AI Showed Me Why I Was Wrong.

Second in a series on the AI Pressure Doctrine. The first post ended with two AI models reaching opposite verdicts on the same proposal. This one is about why they split — and the single fix that made it stop. When I built the first version of my evidence system, it

The AI Pressure Doctrine: The Most Dangerous AI Output Is the One That Sounds Right

Most people are testing whether AI can produce an answer. Almost nobody is testing whether the answer survives contact with reality. That gap is where the risk lives — and it's the entire reason this doctrine exists. Two leading AI models read the exact same proposal. One said proceed.