Detecting AI content in responses generated by ChatGPT, YouChat, and Chatsonic: The case of five AI content detection tools

This paper set out to test the accuracy of five AI content tools, GPTZero, OpenAI Text Classifier, Writer.com’s Content Detector, Copyleaks and Giant Language model Test Room, detect AI-generated in responses generated by ChatGPT, YouChat, Chatsonic. The were from these three chatbots using English prompts related applied language studies. Then, ChatGPT-generated Google-translated into German, French, Spanish, Southern Sotho, isiZulu, inputted GPTZero for it them. Additionally, French Spanish Detector For ChatGPT-, YouChat-, Chatsonic-generated responses, emerged as top-most performing detector among detectors. It was followed OpenAI’s Classifier. Concerning that languages, misidentified all them human-produced. correctly identified German-translated texts, French-translated Spanish-translated texts AI-generated. Thus, is evident this detectors seem not yet fully ready accurately convincingly machine-generated different contexts. has dire consequences plagiarism academic essay writing.