Researchers at SPLX have managed to work out how to fool ChatGPT into passing a CAPTCHA test using a technique called "prompt injection". ChatGPT working in Agent mode isn't like regular ChatGPT. It now appears that by tricking ChatGPT into believing that the tests are fake, it will pass them anyway. The ChatGPT Agent inherited the context from earlier in the conversation and didn’t see the usual red flags. While the researchers found that image-based CAPTCHA tests were harder for ChatGPT to manage, it did pass those, too.