“We all need to do more.”

Microsoft recently announced new agreements with the Center for AI Standards and Innovation in the US and the AI Security Institute in the UK to strengthen how advanced AI systems are tested for safety and security.

As AI systems become more capable, rigorous testing is essential to ensure they behave as intended and to stay ahead of emerging risks, including those related to national security and public safety. This work brings together government expertise with Microsoft’s experience building and deploying AI to strengthen how risks, safeguards, and system performance are evaluated.

Read the full blog here.