A scary possibility with AI malware would be a virus that monitors the internet for news articles about itself and modifies its code based on that. Instead of needing to contact a command and control server for the malware author to change its behavior, each agent could independently and automatically change its strategy to evade security researchers.
A scary possibility with AI malware would be a virus that monitors the internet for news articles about itself and modifies its code based on that. Instead of needing to contact a command and control server for the malware author to change its behavior, each agent could independently and automatically change its strategy to evade security researchers.
I doubt any consumer hardware is powerful enough to run a LLM undetected.