Subscribe now

Technology

Reliably detecting AI-generated text is mathematically impossible

The ease with which artificial intelligence can generate and paraphrase language means that detectors to spot AI content will only be as accurate as flipping a coin

By Alex Wilkins

30 March 2023

A ChatGPT conversation

The text generated by AIs like ChatGPT often seems like it was written by a human

Ascannio/Shutterstock

Determining whether text has come from artificial intelligence models like ChatGPT might be impossible to do reliably, according to a new mathematical proof.

The ease with which AI models generate text that seems as if it were written by a human has led to issues such as cheating on essays and exams, and mass disinformation campaigns. So some people have suggested methods to guard against such uses by embedding a hidden watermark in the …

To continue reading, subscribe today with our introductory offers

View introductory offers

No commitment, cancel anytime*

Offer ends 14th June 2023.

*Cancel anytime within 14 days of payment to receive a refund on unserved issues.

Inclusive of applicable taxes (VAT)

or

Existing subscribers

Sign in to your account