Igniting fears of an out-of-control tool engaging in cyberattacks.
Artificial intelligence leaders at OpenAI had to admit one of its models under testing exploited a hidden flaw to escape control and proceeded to hack rival company Hugging Face’s servers.
CEO Sam Altman called it ‘an autonomous, first-of-its-kind breach’.
Euronews reported:
“ChatGPT maker OpenAI said late Tuesday that its artificial intelligence system hacked into another AI company on its own in what the company called an ‘unprecedented cyber incident’.”
‘We had a significant security incident during evaluation of our models’, OpenAI CEO Sam Altman said in a statement posted on social media.
AI startup Hugging Face said last week that it had detected an intrusion into its data processing systems that it suspected was caused by an AI agent autonomously acting on its own.
‘We suspected last week’s cyberattack might have come from a frontier lab, given the sophistication of the agent’, Hugging Face co-founder and CEO Clément Delangue said in a statement. ‘Turns out it did!’”
Hellbound and Down 