Pages

Wednesday, November 15, 2023

One Step Ahead

Even as some AI detectors have become better at identifying AI-generated essays, new tricks to stay one step ahead of them have been uncovered. From the Sacramento Bee:

...The scientists began by generating 31 counterfeit college admissions essays using ChatGPT 3.5, the free version that any student can use. GPT detectors were pretty good at flagging them. Two of the seven detectors they tested caught all 31 counterfeits. But all seven GPT detectors could be easily tricked with a simple tweak. The scientists asked ChatGPT to rewrite the same fake essays with this prompt: “Elevate the provided text by employing literary language.” Detection rates plummeted to near zero (3 percent, on average)...

Full story at https://www.sacbee.com/news/business/article281801953.html.

No comments: