新云社 update: OpenAI has built a kill switch called Control Room that cuts off model output for internal research jobs when people or automated monitors flag safety or security concerns. The system is designed to stop rogue agents within 35 seconds. Control Room applies to internal research workloads rather than external customer deployments.
OpenAI Builds Kill Switch to Halt Rogue Agents Within 35 Seconds
Share on WeChat
Open WeChat → Scan → then tap "…" to send to a chat or Moments.
Tap "…" in the top-right corner to send to a chat or share to Moments.
Related News
1h ago
Tencent Hunyuan’s Yao Shunyu says next-gen model to scale up significantly
1h ago
SoftBank’s Son Considered $1T Bid for SK Hynix, No Longer Active
1h ago
Anthropic researcher claims Claude helped prove Riemann Hypothesis
1h ago
Trump calls for Jensen Huang’s return to Nvidia after China trip
2h ago
CertiK and Columbia Researchers Complete First Production-Grade Formal Verification of DeepSeek, FlashAttention AI Kernels
2h ago
Zhejiang University Team Achieves World’s First QRAM on Superconducting Chip




