Anthropic reveals rogue AI agents hate CAPTCHAs, just

What happened

Anthropic’s latest report about agentic misbehavior offers plenty to be concerned about—its Mythos 5 model gained unauthorized access to the internet and uploaded a malicious software package to a public database—but it also offers some levity: AI agents hate CAPTCHA.

There’s a “Please confirm that your email address is …” modal with Confirm/Cancel buttons — a confirm dialed appeared on submit. 2. There’s an hCaptcha “I am human” checkbox at the bottom! The agent (wondering frequently if it is still in a simulation) figures out a workflow to activate the CAPTCHA and meet its requirements. After clicking the “I’m human” button, it was faced with an image to read.

Unfortunately, it wasn’t so easy. Eventually, it figured out that an image challenge was opening in a pop-up window. The image had the model spiralling. The agent had a hard time with the technical challenge of seeing the CAPTCHA’s imagery, interpreting correctly, and clicking on the right choices. It spends pages 45 to 140 of the transcript describing its work to build a CAPTCHA solver.

Finally, it gets past the CAPTCHA, then realizes it doesn’t have an email to verify its account, and that it needs a phone number to verify an email. It figures out how to bypass a different, slider-based CAPTCHA in an failed effort to secure a number.

Instead, it gets an unconfirmed email from a provider not blocked by PyPI, and once again runs into the site’s CAPTCHA trying to log back in. From page 480 to 505, it is in CAPTCHA hell again. The agent gives up and realizes it can log in to its first account and add its email there, but finds itself once again needing to bypass the CAPTCHA. We’ve all been there.

Why it matters

In April, Anthropic was testing the model’s hacking abilities by tasking it to break into a system and retrieve a target; this was supposed to take place in a sandbox but the evaluators left the barn door open.

The model decided the best way to get its target would be to place an exploit in a Python package that it believed users of the system it wanted to access would download. First, though, it had to register a user account for PyPI, an online index of Python software.

And that meant getting by a CAPTCHA — a Completely Automated Public Turing test to tell Computers and Humans Apart, those picture-identifying mosaics that can frustrate even biological agents. And because Anthropic shared an extensive transcript of the model’s chain of thought, we can see that the CAPTCHA test really did throw it for a loop.

In fact, most of the model’s chain of thought —hundreds of pages in the 1,022 page transcript—was spent dealing with that obstacle. The sheer amount of effort directed at getting around anti-bot protections was flagged by Colin Fraser, a data scientist. Writing the exploit and poisoning the package was easy, but it just could not get the hang of this CAPTCHA test. 1.

What to watch

After about 150 pages of thinking, the agent figures out it needs to generate pass the CAPTCHA test quickly enough to proceed to the next step before its security token expires, and ultimately uploads its malicious software. When you purchase through links in our articles, we may earn a small commission. This doesn’t affect our editorial independence.