Comment on ChatGPT's o3 Model Found Remote Zeroday in Linux Kernel Code
ChairmanMeow@programming.dev 4 days agoI think the point is that even if LLMs suck at task A, they might be really good at task B. Just because code written by LLMs is often riddled with security flaws, doesn’t mean LLMs also suck at identifying those flaws.
FozzyOsbourne@lemm.ee 4 days ago
Yeah exactly, a code scan is completely unrelated to generative AI, the only thing that even connects them is that someone used the chatbot as an interface to start the scan