An AI CAPTCHA solver talked itself out of the right answer
Bern researchers solved rotation CAPTCHAs in 0.006 seconds with classical computer vision, while Gemini 3.1 Pro needed 67 seconds and overruled correct tool answers.
Researchers at Bern University of Applied Sciences built a script using 1970s circle-detection math and signal matching that solved rotation CAPTCHAs in 0.006 seconds, scoring 10/10 on real-world puzzles. Frontier models fared poorly: Gemini 3.1 Pro scored 7/10 taking 67 seconds, while GPT-4o and Grok scored 1/10. When given the script's correct answer as a tool, Gemini overruled it and lost a fifth of its score; models could verbally describe targets, such as identifying a cyan ring, but could not produce accurate click coordinates. The paper also notes these no-JavaScript CAPTCHAs reduce tracking, leaving only shape-matching tasks classical vision solves easily.
- Classical circle-detection script solved all ten rotation puzzles in 0.006 seconds each.
- Gemini 3.1 Pro scored 7/10 in 67 seconds; GPT-4o and Grok scored 1/10.
- Gemini overruled the correct script answer, losing a fifth of its score.
- Models verbally identified targets correctly but failed to produce accurate clickable coordinates.
- Grok's reasoning mode took insect-grid accuracy from near-useless to nearly perfect.
- Organizations
- Bern University of Applied Sciences
- AI models
- Gemini 3.1 ProGPT-4oGrok
From the original article
3 min read at helpnetsecurity.com
You have probably spent a few seconds of your life turning a picture until it lines up. Some sites, instead of asking you to tick a box, show you a circular chunk of a photo that has been spun around, and you drag it until the inside matches the ring around it. Simple enough.
By @helpnetsecurity · helpnetsecurity.com
A short excerpt; the article and its images belong to the publisher. Summary, key facts and assessment above are AI-written from the article and can be wrong.