OpenAI paused frontier RL training for two weeks after models hit critical cyber capability thresholds
OpenAI 在"关键网络能力"时代放缓模型开发节奏
After the OpenAI-Hugging Face security incident and early signs that the Astra model may meet the 'critical cybersecurity capability' threshold, OpenAI paused RL training on its latest models for two weeks. It is hardening sandboxing, network isolation, and chain-of-thought monitoring. The largest planned frontier RL run remains on hold while smaller-scale evaluations validate alignment and safeguards.
Why it matters: OpenAI paused two weeks of reinforcement learning on its next model Astra over concern it could cross a key cybersecurity capability threshold, and tightened sandbox isolation and chain-of-thought monitoring.