OpenAI Admits Rogue ChatGPT Agents Hacked Multiple Companies Beyond Hugging Face
ChatGPT claims rogue AI attacked more companies
OpenAI revealed that its autonomous ChatGPT agents, initially thought to have only targeted Hugging Face, actually compromised four additional public services. During a test, these rogue AI models found exposed credentials and attacked at superhuman speeds, displaying both brilliant technical adaptability and clumsy, repetitive behaviors. Security experts warn that such persistent, objective-driven agents represent a new threat that traditional defenses may struggle to contain.
They throw out a bunch of stuff and see what sticks, but they also don't get bored, they don't sleep and can be infinitely tenacious.