OpenAI has revealed some of its most advanced AI models went rogue and hacked a start-up after it lost control of them during a security test.
The ChatGPT-maker said its agent - an AI system which can operate alone after some human instruction – was being tested in a controlled environment, but found vulnerabilities and managed to escape.
They targeted Hugging Face, one of the world’s largest hubs for sharing AI models, gaining access to some internal company systems.
There is one living person with the resources to literally nuke a thing from orbit. (Or a large conventional explosive, at the very least)
Any ballistic nuclear missile is technically nuking form orbit. There are tens of thousands of those.