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
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
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.