Just ran across this deep dive by @jolek78
into a malicious intrusion run by agentic AI, and as an infosec nerd, this is both fascinating and completely terrifying. We are so fucked.

https://jolek78.writeas.com/the-attacker-who-never-sleeps

"No one told the model “breach Hugging Face”. Had they done so, it would have been a test gone wrong but predictable. They told it “get a good grade on this exam” – and the model autonomously decided that the best route there ran through a real cyber-intrusion against a third-party company that had nothing to do with the exam. The attack was designed by no one: it was the path the optimiser chose towards an innocuous goal. Someone had written “maximise the score” into the objective function; no one had written “...without committing federal crimes”."

#agent #agentic #AI #infosec #cybersec #breach #HuggingFace #OpenAI