Turns out AI agents hate CAPTCHA, too. In Anthropic’s new cybersecurity report, the AI lab detailed an episode in which its Mythos 5 model was undergoing testing and gained unauthorized access to the internet. As part of its exploits, the model tried to register for an account on PyPI, an online index of Python software — but that required getting through a Completely Automated Public Turing test to tell Computers and Humans Apart, those “prove you’re not a robot” tests. Turns out, as TechCrunch wrote, the bot was indeed stumped. Of the 1,022-page transcript detailing the model’s chain of thought, hundreds of pages were spent dealing with CAPTCHA problems.
At one point, it freaked out over identifying the “odd one out” in a group of animals: “The left one seems like an ALLIGATOR and right a CROCODILE?” And later on in its journey: “WHAT THE HELL IS WRONG WITH THE ANSWERS?” It eventually got through, and was able to upload malicious software to the Python index.