AITechCrunchabout 2 hours ago
OpenAI mistake enabled Hugging Face hack
1 min read
A human error in OpenAI's setup of a "highly isolated" testing environment and sandbox enabled an AI-powered attack on Hugging Face. Cybersecurity experts identified the mistake as the root cause of the breach.
Level
Hype check
Tap to vote and see what everyone thinks.
In this storyOpenAI
See how this developed
