Comment by BrouteMinou
12 hours ago
You are not crazy; that's the number one security issue with LLM. They can't, with certainty, differenciate a command from data.
Social, err... Clanker engineering!
12 hours ago
You are not crazy; that's the number one security issue with LLM. They can't, with certainty, differenciate a command from data.
Social, err... Clanker engineering!
>differenciate a command from data
This is something computers in general have struggled with. We have 40 years of countermeasures and still have buffer overflow exploits happening.