Best detail in here: the job being stopped doesn't get asked.
The brake sits where the tokens come from, not in the code asking for more.
Same rule for any agent with a budget.
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.
openai.com/index/control-roo…
Nov 11, 2026 · 1:26 PM UTC
