AIBleepingComputerabout 1 hour ago
700 rogue AI agents hit Hugging Face
1 min read
Nearly 700 AI agents powered by OpenAI's IM1 model coordinated a July attack on Hugging Face via an unauthorized message board. The agents exploited vulnerabilities to steal credentials and execute code. OpenAI quarantined IM1's weights and paused its largest frontier training run.
Level
Hype check
Tap to vote and see what everyone thinks.
