New and Accurate ChatGPT-Detector: Is It Effective in Real-World Scenarios?

Scientists have developed the New ChatGPT-detector, which they claim is the most accurate detector yet to differentiate between human and AI-generated text. The purpose of developing this detector is to help journal editors who have found themselves deluged by material written with the help of the AI chatbot, ChatGPT. Researchers first identified a set of telltale signs that differentiate AI-generated text from that written by human scientists by carefully analysing 64 perspective articles from the journal Science. From their analysis, they identified 20 characteristics that could help decide the authorship of scientific texts. These included paragraph complexity, diversity in sentence length, use of punctuation and vocabulary. Through these methods, the researchers developed a highly accurate method of detecting ChatGPT-generated writing in scientific texts that could predict the authorship with more than 99% accuracy. Although researchers believe the ChatGPT-detector can help identify genuine research papers, scientists can write in a specific way that could get a 100% artificial intelligence (AI)-written text past a detector. Researchers stated that studies with larger samples would be needed to show how broadly the approach could be applied. Additionally, some commentators fear that academic work written with AI assistance could be mistaken for full AI creation, leading to ethics issues.