# How AI text detection works today > Seven ways to check a text for AI, what limits each, and why an honest result is an estimate with caveats, not a percentage of AI authorship. - URL: https://authortext.com/en/articles/how-detection-works - Language: en - Published: 2026-10-11 - Site: AuthorText (https://authortext.com/) - Other languages: [ru](https://authortext.com/ru/articles/how-detection-works.md), [uk](https://authortext.com/uk/articles/how-detection-works.md), [pt](https://authortext.com/pt/articles/how-detection-works.md) We asked four different AI assistants about this and compared the answers. They agree: there is no single test, and the answer is always a probability. ## Seven approaches 1. **Statistics**: perplexity (how predictable the words are) and burstiness (how uneven the sentence rhythm is). Fast and clear, but polished human text is predictable too. 2. **Zero-shot probability methods** (DetectGPT, Binoculars): compare the likelihood of a text with that of its rewrites. Paraphrasing or swapping look-alike characters weakens them badly. 3. **Stylometry**: vocabulary variety, sentence length, connectives, punctuation. Transparent and more robust to edits, but depends on genre and language. 4. **Trained classifiers** (RoBERTa and similar): the core of commercial systems. Accurate on familiar data, quickly outdated when new models appear. 5. **Watermarks**: a signal planted at generation time. Works only if the generator added one, and disappears when the text is rewritten. 6. **Writing process**: drafts, edit history, pauses and pastes. The most direct evidence, but you need access to the process. 7. **Ensembles**: several signals plus human review. More reliable, but costlier. ## Where all the sources agree - A detector estimates a **probability**, not a fact of authorship. - It is weakest on **mixed texts**, where a human edits AI or AI edits a human. In the studies cited, accuracy dropped to roughly 54-71%. - **False positives** remain the main risk. Formal and academic writing and non-native writers suffer most. - **Paraphrasing and "humanizers"** sharply reduce accuracy. - Vendor-claimed figures (99% and up) and independent tests differ noticeably. ## The percentage: what can honestly be said If all you have is the finished text, you cannot reconstruct how it was written. So it is more accurate to say "65% of the text shows signs of machine generation" than "AI wrote 65%". A person's ideas and edits do not show up in that number. A good system also: - treats false positives on human text as the main error; - calibrates thresholds per language, genre and length; - shows **which passages** raised suspicion, with uncertainty bounds; - says "not sure" when the text is short or the language is poorly studied. ## Languages English is the best studied. Russian has a lot of formal text that is "smooth" on its own and triggers false alarms. Ukrainian has the least open data, so reliability is lower. Portuguese is in better shape here. ## What we already have Here is how that maps to the seven approaches above: - **Stylometry.** Our core method: variation in sentence and paragraph length, connectives, lexical diversity, punctuation, and three tiers of AI phrases in Russian, Ukrainian, Portuguese and English. - **Explainability.** Not just a number: specific passages with line numbers, quotes and a note on why the signal matters. That is where the field is heading, according to the studies. - **Fragment-level view and hints.** You can see which stretches are monotonous or templated, and how to fix them. Rules, no neural networks. - **Hidden characters.** We find and remove the invisible characters sometimes used to mark text (259 kinds) and normalize typography. These are literal characters, not a statistical watermark in the words themselves. - **Honest limits.** We abstain on short texts and warn about smooth genres (news, business writing, promo) where humans often look "machine-like". - **Measurement.** Validation on a corpus with confidence intervals and breakdowns by language and length. The sample is still small: threshold 50 on 34 AI texts and 20 human ones gave 0% false positives, but that is not final accuracy. ## What we want to add - **A bigger corpus**: at least 600 human texts per language, plus non-native writers, paraphrases and mixed texts. Every detector is weakest on exactly these today. - **Calibration by language and length.** "Human / uncertain / AI" zones from corpus distributions instead of hand-picked thresholds. - **A range instead of one number.** A result with an uncertainty band and a "no data" mark when no conclusion is possible. - **Share by fragments.** "This part of the text shows signs of generation" instead of one overall percentage. - **"What if".** Compare the score of a passage before and after an edit. - **Text type** (news, review, post, article) with its own thresholds, once genre corpora exist. - **An optional language-model signal** of the Binoculars class, but only if evaluation shows a clear gain, for example on non-native writers and paraphrases. Otherwise we leave it out. We do not promise "indistinguishable from human" and we are not building a tool to evade checks: the goal is livelier text and a more honest assessment. Treat the result as a hint about where to reread more carefully, not as a verdict. ## What to read next Start with [how to tell if a text was written by AI](https://authortext.com/en/articles/signs-of-ai-text) for the signs you can see yourself, then [why modern AI detectors get it wrong](https://authortext.com/en/articles/why-detectors-err) for the limits. For recent research see [what is new in AI detection](https://authortext.com/en/articles/detection-news-2026). To try it on a text, open the [checker](https://authortext.com/en/). [Check a text](https://authortext.com/en/#editor)