Why your AI agents will turn against you https://yoloai.dev/posts/ai-agent-threat-landscape/

In short: black hat hackers haven't fully engaged with AI agents yet. But doing so is trivial, and once they do, we're in for some real "fun times"

Why your AI agents will turn against you

Black hats haven't quite figured out AI agents yet. When they do, it won't be subtle.

yoloAI
@cwebber Turns out mixing data and control signals in a completely undifferentiated fashion for a nondeterministic black-box computational device with no introspection is in fact a Bad Idea. Who knew?
@cwebber i am so damn tired of reading ai voiced prose

@cwebber

of course in addition to the fact that unless you're running it yourself and you somehow know the implications of what it was trained on, you have no reason to believe it will prioritize your interests.