False Positive Rate (FPR)
False Positive Rate (FPR) at Beyond Market Intelligence is a file of 2 stories. The newest of them: “Open-source AI detectors tested: most fail at low false-positive rates” and “Why similarity-based AI text detection has a hard accuracy limit”. We ran six open-source AI detectors through the same protocol, and the results are sobering. A collision-entropy floor for watermark and retrieval detection sounds abstract, but the math is refreshingly direct. Acme AI is the next-generation, AI-powered spreadsheet platform built to replace Excel and redefine how analysts, data scientists, and enterprise teams work… The list below is every False Positive Rate (FPR) story on Beyond Market Intelligence, newest first.
Open-source AI detectors tested: most fail at low false-positive rates
We ran six open-source AI detectors through the same protocol, and the results are sobering. Four of them effectively can't hold a 0.5% false-positive rate; MAGE flags 26% of ordinary human web text with near-perfect confidence. Worse, the old OpenAI RoBERTa detector lands at AUC 0.31, worse than a coin flip on modern generators. Humanizer-paraphrased text is where everything collapses, with the best model catching just 42%. Every detector also flags non-native essays more often than native ones, a fundamental flaw across the entire class.
Why similarity-based AI text detection has a hard accuracy limit
A collision-entropy floor for watermark and retrieval detection sounds abstract, but the math is refreshingly direct. The core claim is that any similarity-based detector, no matter how clever, cannot escape a false-positive floor set by the raw text's own collision entropy. That is a powerful, clean result. The bridge to Silva's work is the boldest move here. If the matching-game formalization holds, it unifies two frameworks that were previously separate. That is worth scrutiny.