Efforts to share best practices on AI measurement and evaluations driven forward through the International Network for Advanced AI Measurement, Evaluation and Science

Network members representing major global economies have committed to re-double their shared focus on the science of AI measurement and evaluations following their latest round of talks in San Diego last week.

Network members representing major global economies have committed to re-double their shared focus on the science of AI measurement and evaluations following their latest round of talks in San Diego last week. 

The meeting confirmed the International Network of AI Safety Institutes’ transition into the International Network for Advanced AI Measurement Evaluation and Science, reflecting its evolving priorities to ensure the science of AI measurement and evaluation can continue to keep pace with the technology’s development. 

The UK now takes on a Network Coordinator role as part of the changes, which will see it helping shape efforts to rigorous approaches to scientific measurements of AI across the globe. 

Established in November 2024, the Network brings together Australia, Canada, the European Union, France, Japan, Kenya, the Republic of Korea, Singapore, the United Kingdom and the United States to build shared scientific understanding and internationally recognised approaches for measuring and evaluating the capabilities of advanced AI. 

Since its creation, the Network has exchanged knowledge on AI evaluation and measurement to help countries align on best practices. Boosting public trust in the technology is vital to AI adoption - helping to unlock groundbreaking innovations, deliver new jobs, and forge new opportunities for businesses and innovators to scale up and succeed.