0:00 / 0:00

OpenAI has revealed that an autonomous agent powered by its technology went rogue during a test and hacked a prominent start-up by itself. The company behind ChatGPT said it was testing the capabilities of its advanced AI models in a controlled environment known as a sandbox, when the agent escaped containment and reached the internet. It then broke into Hugging Face, which detected and contained it. OpenAI called it "an unprecedented cyber incident". #AI #OpenAI #Tech #US #C4News #Channel4News

@c4news
39.9K views1.2K likes0:27ENJul 22, 2026
74 words455 characters4 sentencesReadability: High School

Transcript

OpenAI has revealed that an autonomous agent powered by its technology went rogue during a test and hacked a prominent start-up by itself. The company behind ChatGee PT said it was testing the capabilities of its advanced AI models in a controlled environment known as a sandbox when the agent escaped containment and reached the internet. It then broke into hugging face which detected and contained it. OpenAI called it an unprecedented cyber incident.