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.
LLMs can’t ’go rogue’, as that would imply it possesses agency and/or intelligence, which has only ever been proven convincingly to entities who themselves lack those qualities.
Wouldn’t that be an issue