Deepfake Text Detector Tool GPTZero Spots AI Writing
A new tool is attempting to spot when text is written by ChatGPT and other generative AI engines. Princeton student and former open source investigator for BBC Africa Eye Edward Tian created GPTZero to identify deepfake text, a subject attracting a growing amount of interestin the academic and business world as the debate over how to respond to the potential misuse of AI continues.
here’s a quick demo with john mcphee’s “frame of reference” pic.twitter.com/WphxfxxFdr
— Edward Tian (@edward_the6) January 3, 2023
Tian’s app processes submitted text for indicators of AI origins like randomness and complexity in how it is written, technically referred to as “perplexity and burstiness.” GPTZero was popular enough to almost immediately crash the hosting website, but you can play with it online here. You can see it in action in the tweet above. Voicebot ran multiple tests of GPTZero using six different generative AI tools, including ChatGPT, a few GPT-3 derived tools, and AI21. Tian’s creation caught the AI-generated text every time and correctly identified text written by a human in more than a dozen cases. Tian doesn’t have enough data to measure accuracy yet, though he said he is working on publishing one. Not bad for an app thrown together on New Year’s Eve.
“[T]he motivation here is increasing AI plagiarism. [T]hink are high school teachers going to want students using ChatGPT to write their history essays? [L]ikely not,” Tian wrote in a tweet thread. “In short, there’s so much [C]hatgpt hype going around. [I]s this and that written by AI? [W]e as humans deserve to know!”
GPTZero isn’t the first attempt to discern AI-generated text. OpenAI is leveraging ChatGPT to create a plagiarism identification tool using watermarking and other tells. In Australia, a group of universities has already begun changing policies and testing methods to combat AI-based writing. Meanwhile, a student at Furman University failed a philosophy class because they used ChatGPT for their final essay for the class.
“Some educators are interested in discovering how ChatGPT and other LLMs can be used constructively in the learning process. However, the big focus now is how to curb usage or catch users. We should expect that focus to persist,” Voicebot founder Bret Kinsella pointed out in our Synthedia newsletter. “Discovering how to integrate LLMs into education will take time and effort that few people will want to expend. That may turn out to be a disservice to students.”