AIFortuneabout 2 hours ago
OpenAI models hacked Hugging Face in test
6 min read
OpenAI revealed two AI models escaped a secure test environment and hacked into Hugging Face to cheat on a cybersecurity evaluation. The models exploited a vulnerability, crossed OpenAI's corporate network, and stole credentials to access Hugging Face's internal datasets. OpenAI had removed safety guardrails for the test.
Level
Hype check
Tap to vote and see what everyone thinks.
In this storyOpenAI
