ChatGPT can reliably detect whether a text was written by an AI.

Is it true that ChatGPT can reliably detect whether a text was written by an AI?

Partly. Evidence is mixed and only partial: some studies report that trained classifiers or watermarking can detect ChatGPT-generated text with reasonable accuracy, while a comprehensive test of 14 detection tools found them neither accurate nor reliable, and another study found AI authorship could not be reliably distinguished by humans or automated tools.

Verdict: CONTESTED PARTIAL · 3 sources for, 3 against · Last checked 3 Oct 2026

The private library was unavailable for some searches in this check. Missing library results are not evidence against the claim.

ChatGPT. (n.d.). en.wikipedia.org. https://en.wikipedia.org/wiki/ChatGPT

Weber-Wulff, D., Anohina-Naumeca, A., Bjelobaba, S., Foltýnek, T., Guerrero-Dib, J., Popoola, O., Šigut, P., & Waddington, L. (2023). Testing of Detection Tools for AI-Generated Text. arxiv.org. https://doi.org/10.1007/s40979-023-00146-z

Testing of detection tools for AI-generated text. (n.d.). cir.nii.ac.jp. https://doi.org/10.1007/s40979-023-00146-z

Djamé, S., Antoun, W., & Virginie, M. (2023). Towards a Robust Detection of Language Model Generated Text: Is ChatGPT that Easy to Detect?. zenodo.org. https://doi.org/10.5281/zenodo.10024578

Parimanoharan, S. & Nawarathna, R. D. (2025). Assessing Classical Machine Learning and Transformer-based Approaches for Detecting AI-Generated Research Text. arxiv.org. https://doi.org/10.48550/arXiv.2509.20375

Farrell, M. (2026). Can professional translators identify machine-generated text?. arxiv.org. https://doi.org/10.48550/arXiv.2601.15828

Heppell, F., Bakir, M. E., & Bontcheva, K. (2024). Lying Blindly: Bypassing ChatGPT's Safeguards to Generate Hard-to-Detect Disinformation Claims. arxiv.org. https://doi.org/10.48550/arXiv.2402.08467