Comment by Microsoft

Microsoft’s most advanced models are assessed for leading indicators of the framework’s tracked high-risk capabilities. [...] The leading indicator assessment is run during pre-training, after pre-training is complete, after post-training, and prior to deployment to ensure a comprehensive assessment as to whether a model warrants deeper inspection. [...] Any model demonstrating frontier capabilities is then subject to a deeper capability assessment to provide strong confidence about whether it has a tracked high-risk capability and to what level, informing mitigations. [...] Models assessed as having a high or critical risk are subject to further review and safety and security mitigations prior to deployment.