Why AI Text Gets Detected - The Linguistics Behind It

I've been building an AI text humanizer and spent weeks studying how AI detection actually works. The results surprised me - it's not about grammar, vocabulary, or even factual accuracy. It's about statistical patterns that humans produce naturally but language models don't. Here's what I found. The Three Metrics That Matter AI detectors primarily measure three properties: 1. Perplexity Perplexity measures how predictable the next word is given the previous context. Lower perplexity = more predictable text. Language models generate text by selecting the most probable next token. This produces consistently low perplexity. Human writing has higher perplexity because we make unexpected word choices - idioms, slang, unusual metaphors, sentence fragments. Think of it this way: if you can easily predict what word comes next, it was probably written by AI. 2. Burstiness Burstiness measures the variation in sentence complexity across a piece of text. AI text has low burstiness - sentences hove