AI Dynamics

Global AI News Aggregator

Real-world AI attacks remain limited beyond screenshots and prompt leaks

There have been a bunch of research/demo attacks, but I haven't seen a real-world malicious attack that caused actual damage yet – beyond producing embarrassing screenshots or leaking system prompts

→ View original post on X — @simonw,

Commentaires

Leave a Reply

Your email address will not be published. Required fields are marked *