OpenAI· @OpenAI · X·· 13 天前AI 评分58
AI 导读
OpenAI 构建了 Control Room 系统,用于追踪研究基础设施中的模型工作负载,并在出现安全或安保问题时快速中止。该系统接入所有研究推理工作负载,包括模型训练与评估中的智能体采样、数据处理等,并与失准监控系统配合,在决定干预后 35 秒内停止模型输出。OpenAI 称 Control Room 只是其安全训练与部署前沿模型整体方案的一部分。
正文 · 原文
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 of a decision to intervene to stop or pause a job.
Control Room is just one part of our holistic approach for safe frontier model training and deployment.
来源:OpenAI · x.com