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.
Prison only works if you have a body to imprison. No body leaves no other choice. Investors may lose a little bit of money now but executives on boards running companies will get an inescapable message that their company better not commit any crimes or risk suffering the exact same fate.