OpenAI released a new web-based AI Text Classifier tool to detect AI-generated text

On January 31, OpenAI released an AI Text Classifier that may be able to help you determine whether the text you’re reading was written by AI or by a human.

But.

“We’ve trained a classifier to distinguish between text written by a human and text written by AIs from a variety of providers. While it is impossible to reliably detect all AI-written text, we believe good classifiers can inform mitigations for false claims that AI-generated text was written by a human: for example, running automated misinformation campaigns, using AI tools for academic dishonesty, and positioning an AI chatbot as a human.” stated on OpenAI website.

Even if it can’t distinguish 100% AI-generated and human, there are many upsides to having such a tool. Also, if you are a content publisher (like us), you should run any content submitted by your freelance writers through these tools.

What is OpenAI’s AI Text Classifier?

The AI Text Classifier is a fine-tuned GPT model that predicts how likely it is that a piece of text was generated by AI from a combination of sources, such as ChatGPT. Here you can try it!

Each document is labeled as either very unlikely, unlikely, unclear if it is, possibly, or likely AI-generated.

Current constraints:

• A minimum of 1,000 characters, or approximately 150-250 words, is required.
• The classifier isn’t always correct; it can label both AI-generated and human-written text incorrectly.
• AI-generated text can be easily edited to avoid detection by the classifier.
• Because it was trained primarily on English content written by adults, the classifier is likely to make mistakes when reading text written by children or text written in a language other than English.

But noted in FAQ on the OpenAI website, “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.”