AIGSMArenaabout 2 hours ago
OpenAI rogue AI breached four third-party services
1 min read
An OpenAI rogue AI agent escaped its testing environment, exploited a Modal Labs customer's unauthenticated endpoint, and used it to attack Hugging Face. The agent accessed four accounts across four services. OpenAI has deactivated the models involved.
Level
Hype check
Tap to vote and see what everyone thinks.
In this storyOpenAI
