AI-written text cannot be reliably detected today, neither by people nor by tools. AI detectors give a probability, not proof: independent studies show that they wrongly flag human texts as AI and often miss AI texts that have been reworked. OpenAI, the company behind ChatGPT, switched off its own detection tool in 2023 because its accuracy was too low.
I work with Claude every day. My fourteen AI employees run on Claude Team, some also on open models or through the API. I have not run a detector test of my own. The figures in this article come from published studies and from OpenAI itself, all retrieved on 27 October 2026. All the basics about AI are collected on my AI Basics page.
How AI detectors work
There are two common designs. One is an AI model itself, trained on many pairs of human-written and AI-written texts; for a new text it estimates which group the text fits better. That is how OpenAI describes its own detector. The other measures how predictable a text is for a language model.
This measure is called perplexity: the more expected the word choice, the lower the value, and the more likely the detector is to treat the text as machine-written. The problem: people write predictably too, for example in a foreign language, on forms or in very factual texts.
A third approach is watermarking. Here the maker of the language model marks the text while it is being written, with an invisible pattern in the word choice. Google DeepMind has published such a method for text, called SynthID. A watermark only helps with texts from models that actually apply it, and Google itself writes that confidence can drop sharply when a text is thoroughly rewritten or translated.
What studies show about accuracy
The following results come straight from the publications:
Source
What was tested
Result
OpenAI, 2023
its own detector, English test texts
26% of AI texts correctly identified, 9% of human texts wrongly labelled as AI; switched off on 20 July 2023
Liang et al., 2023 (Stanford)
seven detectors, 91 essays by people for whom English is a foreign language
on average 61.22% wrongly labelled as AI; 89 of the 91 essays flagged as AI by at least one detector
Weber-Wulff et al., 2023
14 tools, two of them commercial
all below 80% accuracy, only five above 70%; for machine-paraphrased AI texts only 26% accuracy
Dugan et al., 2024 (RAID)
twelve detectors, over 6 million texts
easily fooled by targeted changes, different generation settings and unseen models
The second finding matters most in practice. The same detectors identified essays by US school students as human almost without error. For people writing in a foreign language, on the other hand, they were mostly wrong. The researchers attribute this to simpler, more predictable word choice. When they had ChatGPT polish the language of the same essays, the error rate fell to 11.77%. They therefore explicitly caution against using detectors in evaluative or educational settings.
For context: the studies test tools from 2023 and 2024. Newer versions may do better or worse. According to the authors of the RAID study, many vendors advertise accuracy of 99% or more, but very few detectors are tested on shared, challenging benchmark data. An advertised figure is no substitute for an independent test.
OpenAI lists further limits for its detector that illustrate the principle well: very unreliable on short texts under 1,000 characters, significantly worse in languages other than English, and AI text can be edited so that the detector no longer recognises it.
How people spot AI texts, and why that is not enough either
Even without a tool there are clues. My own list for business emails includes these patterns, which are among the most obvious traces in AI drafts:
an opener such as "I hope this message finds you well",
every sentence and paragraph the same length,
three adjectives in a row where two would have done,
"not only …, but also …" several times in the same text,
enthusiasm with no concrete reason,
a closing summary that only repeats what is above.
The full list is in Can AI Write Emails in My Voice?. Such patterns are clues, not proof. People sometimes write exactly like this, and if you give the AI a few of your own texts as a model, you get drafts without these traces. The Stanford researchers show the same for tools: a simple instruction to ChatGPT was enough to get past the detectors.
A more reliable clue than style is wrong or invented facts: a source that does not exist, a quote that appears nowhere. How to spot such inventions is explained in AI Hallucinations: Why AI Makes Things Up. But even that only proves the text is wrong, not who wrote it.
What this means for your business
No verdict based on a detector. When you review an application, a report or a text delivered by someone else, a high AI score is no reason for an accusation. Talk to the person, ask for drafts or have them explain the content.
If you have requirements, say so up front. If you want texts from a contractor without AI, put it in the brief. It cannot be reliably checked afterwards.
For your own texts, a different question counts. Not "will anyone notice?", but: is every detail correct, and does the text sound like you? How to get there is in Writing with AI: A Beginner's Guide.
Not accurate enough to rely on. In the study by Weber-Wulff and colleagues, all 14 tools tested were below 80% accuracy. OpenAI switched off its own detector after it identified only 26% of AI texts and wrongly flagged 9% of human texts.
Can a detector wrongly accuse a person?
Yes. It hits people writing in a foreign language especially often: on essays by non-native speakers, seven detectors wrongly labelled an average of 61.22% as AI. OpenAI writes about its detector that it sometimes labels human text as AI incorrectly but confidently.
Do detectors work on texts in other languages?
Most studies test English texts. OpenAI writes that its detector performs significantly worse in other languages. In the Weber-Wulff study, accuracy for human texts machine-translated into English from other languages dropped by 20%, according to the authors. My conclusion: for non-English texts, expect more errors rather than fewer.
Do AI texts have a watermark?
It is possible, but you cannot see it: only the matching detection method finds a watermark. Google has published such a method for text with SynthID. After thorough rewriting or translation, detection can become much less certain, according to Google.
Can an AI tell whether a text was written by an AI?
Not reliably. A chat such as ChatGPT or Claude is not built as a detector, and even specialised detectors are often wrong, as the studies above show. So do not ask the AI whether a text came from it; check whether the text is correct.
Where to go from here
Next time you write a text with AI, give it two of your own texts as a model and then strike the patterns from the list above. Then read the text aloud: does it sound like you? How to turn your content into a presentation with AI is in How to Create a Presentation with AI. If several people on your team write with AI, a few shared rules pay off; what belongs in them is in AI Usage Policy for Small Teams. How others handle AI texts in their business is what we discuss in my community Claude Practitioners.
Kevin Welter
Developer, IT architect, author of technical books (Kubernetes, cloud infrastructures) and speaker. Runs his business with an AI workforce of fourteen AI employees and shows solo business owners in his community how to hire their first AI employee.
