Cheat sheet for the video [How AI Detectors Work: Why One Essay Can Score 100% and 0%](https://www.youtube.com/watch?v=hv53RUw07w0) · [read the full page](https://kuzscotech.github.io/kush-exe/how-ai-detectors-work/)

An AI detector scores your finished text for patterns that resemble AI writing, not how you wrote it. The result is a statistical estimate. Turnitin and GPTZero say it is not a verdict.

## What the detector actually measures

- **Predictability (early tools).** Perplexity is how surprising text is to a language model. Low perplexity leaned AI. [Ars Technica](https://arstechnica.com/information-technology/2023/07/why-ai-detectors-think-the-us-constitution-was-written-by-ai/)'s example: "a cup of coffee" is low perplexity, "a cup of spiders" is high.
- **Burstiness.** GPTZero defined it as how much writing patterns and perplexity vary across a document.
- **Learned patterns (now).** [GPTZero](https://gptzero.me/news/perplexity-and-burstiness-what-is-it/) says it moved to deep learning in autumn 2023, though the same page still calls both one of seven indicators. [Turnitin](https://guides.turnitin.com/hc/en-us/articles/28477544839821-Turnitin-s-AI-writing-detection-capabilities-FAQs) says its model is not explicitly programmed for either, but still explains detection through word probability.
- **A threshold.** Turnitin scores each sentence from 0 to 1. The document percentage is the share over its threshold.

## What the evidence says

| Myth | Evidence |
|---|---|
| ChatGPT's maker has a working detector | [OpenAI's classifier](https://openai.com/index/new-ai-classifier-for-indicating-ai-written-text/) caught 26% of AI text and wrongly flagged 9% of human text in its 2023 test, then was withdrawn that July for low accuracy. |
| Detectors mostly flag human writing | A [2025 working paper](https://www.nber.org/papers/w34223) put GPTZero's false positive rate at about 0.7% and Pangram's near zero. Not peer reviewed, no student essays, and its authors expect an arms race. |
| Few false alarms means AI gets caught | In a small, peer-reviewed [2026 test](https://link.springer.com/article/10.1007/s40979-026-00226-w), Turnitin, GPTZero and Copyleaks failed on fully AI papers from ChatGPT Deep Research. |
| A 1% error rate is harmless | [Vanderbilt](https://www.vanderbilt.edu/brightspace/2023/08/16/guidance-on-ai-detection-and-why-were-disabling-turnitins-ai-detector/) estimated Turnitin's claimed 1% would have meant about 750 of Vanderbilt's 75,000 papers from 2022 wrongly labelled: a projection, not a count. |

## What it cannot tell

- **Predictable human writing.** In 2023, GPTZero said part of the US Constitution was likely written entirely by AI. People write predictably too, especially in formal styles such as law.
- **Non-native writers.** In a 2023 Stanford study, seven detectors averaged about 61% false positives on 91 TOEFL essays. That finding is contested, and GPTZero self-reports 1.1% false positives on TOEFL texts.
- **Short or mixed text.** Detection weakens sharply on short texts and joint human-and-AI essays.
- **The trade-off.** Within one detector, fewer false positives means more missed AI text, and the reverse.

## If your work is flagged

- Turnitin says its percentage should not be the sole basis for action and does not determine misconduct.
- Researchers say a flag should be paired with drafting history, so keep drafts and version history.
- Detectors can disagree on the same essay, which you can raise in a dispute.