Post #3471850

RE: https://infosec.exchange/@mttaggart/116830015225440372 "Attack memorization is inherently brittle; it only works against attacks the LLM already knows [...] In contrast, role perception is the robust alternative. All the LLM needs to do is recognize that the command is in a role like tool that inherently lacks authority to give orders. But we'll show that LLMs cannot perceive roles accurately." TL;DR: they CANNOT be made secure. This is not a technology that should be taken seriously outside of a laboratory. #AI