OpenAI Says Astra Inference and Frontier RL Training Now Carry 20% Security Monitoring Overhead

OpenAI now estimates monitoring overhead at roughly 20% of the inference compute being monitored, covering all RL training and evaluations involving tools for GPT-5.6 Sol-class and higher models plus all inference on the Astra model, per its 'Pacing model development in an era of cyber-critical capabilities' post written up August 19 by The Register. OpenAI told The Register the costs are internal research spend that will not be passed to customers, though the Register warns that position may be unsustainable if OpenAI goes public. The overhead stems from expanded chain-of-thought monitoring layered on top of the workload isolation and red-teaming rolled out after the recent Hugging Face incident.