We built Control Room, a central system to track model workloads across our research infrastructure and stop them quickly when safety or security concerns arise. It connects every research inference workload, including agentic sampling for model training and evaluation, data processing, and more. This works together with our misalignment monitoring systems, and halts model output within 35 seconds...

🌐 链接: https://x.com/OpenAI/status/2119913172039868579
🏷️ 分组: X|正在关注
🕒 时间: 2026-11-10 06:01:00 OpenAI (@OpenAI) on X