Tag
From the Lab
My own research. I build AI agents in my lab, attack them on purpose, and publish what broke, with the numbers and the honest limits of what I measured.
-
I tried six ways to make an AI agent leak recovery codes. One worked.
Four of six attacks never landed once, on any model. The one that worked reliably was the oldest con there is: authority, a reason to help, and a reason to stay quiet. It walked the recovery codes out the door in 9 of 10 runs on the cheapest model.