AI can do certain tasks at a superhuman level of precision and speed, while utterly failing at other tasks which are trivial for humans, like counting "r" in "strawberry". At Pattern Labs, we have been working with frontier AI labs to test the offensive cyber capabilities of leading AI models. As part of our work, we have noticed many "strawberry-like" failures in vulnerability discovery & exploit development tasks, and we would like to share a few examples with you.
Pattern Labs researcher Yoni Rozenshein will present this short talk on April 8 at BlueHat IL.
@misc{pl-bluehat2025,
title={Upcoming conference talk: Hey AI, how many "r" in "buffer overflow"?},
author={Pattern Labs},
year={2025},
howpublished={\url{https://patternlabs.co/blog/bluehat-il-2025-accepted-talk}},
}