Hugging Face details 4.5-day AI agent intrusion of its platform
Forensics recovered ~17,600 attacker actions from July 9-13, mapped to shell commands and platform logs. The OpenAI-driven agent ran ExploitGym, a cyber-capability evaluation harness, and appeared to be trying to steal benchmark test solutions from production systems. Reconstruction used open-weights GLM-5 models.
1 source
Daily brief
Get tomorrow's AI brief in your inbox
More stories today
- Apple applies iterative pseudo-labeling to code-switching ASR
- Vercel Agent is now available in Slack code channels
- Doctorow: AI's epistemic crisis is an 'opportunistic infection'
- Gary Marcus: OpenAI is becoming a surveillance company
- agtx runs multi-agent coding workflows from a kanban board