News for hackers. Stuff that matters.
Re:ZombAIs: From Prompt Injection to C2 with Claude Computer... by throwaway290 on Sunday October 27, 2024 @02:23AM (#41960264)
> The fundamental flaw people make is assuming that LLMs (i.e. a single inference) are a lone solution when in-fact they're just part of a larger solution.

A solution to what problem?

Re:ZombAIs: From Prompt Injection to C2 with Claude Computer... by Terr_ on Sunday October 27, 2024 @05:06PM (#41965680)
Creating BS cheaply at scale. :p

(Or perhaps not quite that cheaply, given the way some companies are racking up debt.)