Guides to AI text detection

Plain answers about AI detectors, each built on our own test results.

• How accurate are AI detectors? What our test of 900 texts shows
  Free AI detectors caught between 9.5% and 68.1% of AI text in our test while flagging real human writing. What the numbers mean if you have to judge a text.
• Should teachers use AI detectors? What our test data says
  The most careful free detector we tested flagged 6.3% of human texts. What that means for grading, and how to use a detector without accusing an honest student.
• Falsely accused of using AI? What the detector data shows
  AI detectors flag real human writing. In our test, 117 of 126 human texts were flagged by at least one of seven detectors. How to respond with evidence.
• Can AI detectors detect Claude? Test results for four Claude models
  We ran 504 texts from four Claude models through seven free AI detectors. A majority caught between 38.9% and 77.0% of them, depending on the model.
• Paragraph breaks can change an AI detector's verdict
  We scored the same texts with and without line breaks. One detector went from flagging 100.0% of multi-paragraph human texts to 25.7%. Results for seven detectors.
• How AI detectors work, and why they flag human writing
  AI detectors either learn the style of AI text or measure how predictable each word is. Both approaches flag predictable human writing. Examples from our tests.
• Perplexity and burstiness in AI detection, explained
  Perplexity measures how predictable a text is to a language model; burstiness how much that varies. Why both flag human writing, with results from our tests.
• How to run a free AI detector on your own computer
  Run Desklib, the most careful detector in our test, locally with Python. Working code, speed on a laptop, and how to read the score.
• What AUROC means for AI detectors, explained with real results
  AUROC measures how well a detector's scores separate AI from human text, from 0.5 (chance) to 1 (perfect). Our seven detectors scored between 0.579 and 0.877.
• Which AI detectors flag human writing?
• Does editing AI text fool detectors?
• Do AI detectors flag famous texts?
• Compare AI detectors head to head
• Best AI detector for academic writing (tested)
• Best AI detector for encyclopedia and Wikipedia-style articles (tested)
• Best AI detector for fiction and creative writing (tested)
• Best AI detector for forum posts and Q&A answers (tested)
• Best AI detector for long texts of 300 words or more (tested)
• Best AI detector for news articles (tested)
• Best AI detector for short texts under 200 words (tested)