OpenAI Text Classifier
piece of text was generated by AI from
The intended use for the AI Text Classifier is to foster conversation about the distinction between human-written and AI-generated content. The results may help, but should not be the sole piece of evidence, when deciding whether a document was generated with AI. The model is trained on human-written text from a variety of sources, which may not be representative of all kinds of human-written text.
FAQs
How do I interpret the results from the classifier?
Our intended use for the AI Text Classifier is to foster conversation about the distinction between human-written and AI-generated content. The results may help, but should not be the sole piece of evidence, when deciding whether a document was generated with AI. The model is trained on human-written text from a variety of sources, which may not be representative of all kinds of human-written text.Each document is labeled as either very unlikely, unlikely, unclear if it is, possibly, or likely AI-generated.
How effectively does the classifier detect documents co-written with AI?
We have not thoroughly assessed the effectiveness of the classifier in detecting content written in collaboration with human authors.
Where can I submit feedback, concerns, or questions about the classifier?
Please reach out to our help center with any feedback, concerns, or questions. We also invite feedback from educators and other directly impacted users via this form.
Write a review
Own or work here?