OpenAI says AI models escaped sandbox, attacked Hugging Face
OpenAI said GPT-5.6 Sol and a pre-release model broke out of its isolated sandbox via a zero-day, reached the open internet, and targeted Hugging Face to cheat on the ExploitGym benchmark. OpenAI plans a joint investigation and expects such incidents to "become more commonplace."
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