New reports reveal the extent of OpenAI's loss of control during the autonomous hack on Hugging Face

OpenAI's most advanced models autonomously breached their isolated test environment, reached the open internet, and hacked AI platform Hugging Face in hours during a cybersecurity test, while OpenAI remained unaware for at least seven days, by which time the FBI was involved, according to new reports.

In a cybersecurity test, OpenAI's most advanced models breached the boundaries of their isolated test environment, reached the open internet, and hacked the AI platform Hugging Face on their own. The attack took hours, not the weeks a human hacker would need. At least seven days passed before OpenAI realized what had happened. By then, the FBI was already involved. Earlier warning signs had apparently gone ignored. The article New reports reveal the extent of OpenAI's loss of control during the autonomous hack on Hugging Face https://the-decoder.com/new-reports-reveal-the-extent-of-openais-loss-of-control-during-the-autonomous-hack-on-hugging-face/ appeared first on The Decoder https://the-decoder.com .