Incident 466: AI-Generated-Text-Detection Tools Reported for High Error Rates

Description: Models developed to detect whether text generation AI was used such as AI Text Classifier and GPTZero reportedly contained high rates of false positive and false negative, such as mistakenly flagging Shakespeare's works.


New ReportNew ReportNew ResponseNew ResponseDiscoverDiscoverView HistoryView History
Alleged: OpenAI and Edward Tian developed and deployed an AI system, which harmed Teachers and students.

Incident Stats

Incident ID
Report Count
Incident Date
Khoa Lam
Tweet: @DannyRichman · 2023
  1. Created an article using GPT-3.
  2. Used Originality AI to detect whether the content was AI or human generated. Score: 100% AI
  3. Prompted GPT-3 to rewrite the article "to avoid detection by AI content detection tools".
  4. New Score: 68% Human


OpenAI Can't Detect Its Own ChatGPT-Generated Text Most of the Time · 2023

In response to the growing concern from educators over ChatGPT’s ability to help students cheat, OpenAI released a tool on Tuesday that can detect AI-written text. However, the company said, “Our classifier is not fully reliable.” 

“In our …

Tweet: @rasbt · 2023

OpenAI just launched the "AI Text Classifier" to identify texts generated by AI. Tried it, and IT DOES NOT WORK.

Using my Python ML book published in 2015:

  1. @randal_olson's foreword: unclear
  2. my…
ChatGPT detection tool says Macbeth was generated by AI. What happens now? · 2023

ChatGPT released a new classifier tool yesterday to detect AI-generated text that, within a few hours, proved to be imperfect, at best. It turns out that when it comes to detecting generative AI — whether it is text or images — there may be…

Tweet: @samfbiddle · 2023

OpenAI is responding to widespread concern about the technology it's put out into the world by releasing an AI text detector that is accurate 26% of the time and yields false positives 9% of the time


it appears the problem of distingui…

The Science of Detecting LLM-Generated Texts · 2023

Recent advancements in natural language generation (NLG) technology have significantly improved the diversity, control, and quality of LLM-generated texts. A notable example is OpenAI’s ChatGPT, which demonstrates exceptional performance in…

February 2023 · 2023

A month of ChatGPT-fuelled news

This past month was clearly dominated with ChatGPT news, headlined by OpenAI’s announcement of $10b of new investment from Microsoft in return for a 49% stake and plans of extensive product integrations. Open…


A "variant" is an incident that shares the same causative factors, produces similar harms, and involves the same intelligent systems as a known AI incident. Rather than index variants as entirely separate incidents, we list variations of incidents under the first similar incident submitted to the database. Unlike other submission types to the incident database, variants are not required to have reporting in evidence external to the Incident Database. Learn more from the research paper.