Replying to @wolf480pl@mstdn.io
@wolf480pl @drwhax
Often open source LLMs that you can run on your own computer find the same bugs with the appropriate tools and instructions. It's mostly hype based on fear or as Lee Vinsel named it: «criti-hype»
https://aisle.com/blog/ai-cybersecurity-after-mythos-the-jagged-frontier
AISLEAI Cybersecurity After Mythos: The Jagged FrontierWhen AISLE tested Mythos's showcase vulnerabilities on small, cheap, open-weights models, most found the same bugs. Here's what that means for cyber.