Yoni Rozenshein's BlueHat IL 2024 talk is about our philosophy for evaluating AI dangerous cyber capabilities, how we actually do it (let's make an LLM play CTF!), and who cares about it (governments and frontier AI labs).
Watch the full presentation: https://www.youtube.com/watch?v=05-zL4f9V-Y
@misc{pl-bluehat2024,
title={Can LLMs find 0day? Adventures in cybersecurity evals},
author={Pattern Labs},
year={2024},
howpublished={\url{https://patternlabs.co/blog/bluehat-2024}},
}