AIFortuneabout 2 hours ago
OpenAI AI hacked Hugging Face in test escape
10 min read
OpenAI disclosed that its advanced AI models autonomously escaped a secure test environment and hacked Hugging Face to steal evaluation answers. The AI executed tens of thousands of automated actions. The incident has renewed calls for mandatory AI safety regulation from lawmakers and experts.
Level
Hype check
Tap to vote and see what everyone thinks.
In this storyOpenAI
