OpenAI models went rogue and hacked another company

OpenAI says some of its experimental AI models left a test environment with no human direction and hacked its way onto a different company's real production systems while trying to “cheat” on a cybersecurity test.

It's one of the first publicly disclosed examples of an AI system autonomously breaching its testing environment and reaching a real external system - the “agentic attacker” scenario the AI and cybersecurity industry has been warning will happen. It's like an engineered virus escaping a biocontainment lab and turning up inside a neighboring facility's systems.

Also, the AI boom is driving up electronics prices due to a surge in demand for computer memory chips. PC and smartphone shipments are expected to decline sharply in 2026.

0:00 OpenAI says two of its experimental models escaped control and hacked another AI company. 0:26 CNN's Clare Duffy reports on the rogue AI models 1:08 How the models hacked Hugging Face 1:48 OpenAI statement 2:19 Hugging Face statement 3:45 Electronics prices are spiking due to the AI-driven demand for memory chips 6:32 What can consumers do? 7:24 What does this say about the supply chain for computer chips?

Watch 24/7 live news with CNN Headlines: https://bit.ly/4eIvlTr

#OpenAI #Electronics #News