They’re on to me! 😉 According to an article, AI chatbots have telltale quirks and researchers can spot them with 97% accuracy!

As discussed in Fast Company (wait for it!) (AI Chatbots have telltale quirks. Researchers can spot them with 97% accuracy, written by Chris Stokel-Walker and available here), researchers at four U.S. universities have taken a rigorous approach to identifying linguistic fingerprints that reveal which large language model (LLM) produced a given text.

“All these chatbots are coming out every day, and we interact with them, but we don’t really understand the differences between them,” says Mingjie Sun, a researcher at Carnegie Mellon University and lead author of the study, which was published in Cornell University’s preprint server arXiv. “By training a machine learning classifier to do this task, and by looking at the performance of that classifier, we can then assess the difference between different LLMs.”

Sun and his colleagues developed a machine learning model that analyzed the outputs of five popular LLMs, and was able to distinguish between them with 97.1% accuracy. Their machine learning model uncovered distinct verbal quirks unique to each LLM.

ChatGPT’s GPT-4o model, for instance, tends to use “utilize” more than other models. DeepSeek is partial to saying “certainly.” Google’s Gemini often prefaces its conclusions with the word “essentially,” while Anthropic’s Claude overuses phrases like “according to” and “according to the text” when citing its sources.

xAI’s Grok stands out as more discursive and didactic, often reminding users to “remember” key points while guiding them through arguments with “not only” and “but also.”

“The writing, the word choices, the formatting are all different,” says Yida Yin, a researcher at the University of California, Berkeley, and a coauthor of the paper.

So, according to the article, remember to keep track of what words you utilize, not only if you’re using an AI model to help with your writing, but also certainly if you’re writing without assistance, essentially to avoid being accused of using the model to do your writing. See what I did there? 🤣

So, what do you think? Have you noticed any tell tale signs from AI-generated content? Asking for a friend. 😉 Please share any comments you might have or if you’d like to know more about a particular topic.

Image created using GPT-4o’s Image Creator Powered by DALL-E, using the term “robot writer looking at a desktop computer screen with a magnifying glass and seeing the word ‘certainly’”.

Disclaimer: The views represented herein are exclusively the views of the author, and do not necessarily represent the views held by my employer, my partners or my clients. eDiscovery Today is made available solely for educational purposes to provide general information about general eDiscovery principles and not to provide specific legal advice applicable to any particular circumstance. eDiscovery Today should not be used as a substitute for competent legal advice from a lawyer you have retained and who has agreed to represent you.