AI Safety Institute releases new AI safety evaluations platform

Global AI safety evaluations are set to be enhanced as the UK AI Safety Institute’s evaluations platform is made available to the global AI community today, paving the way for safe innovation of AI models.

After establishing the world’s first state-backed AI Safety Institute, the UK is continuing to drive global collaboration on AI safety evaluations with the release of the AI Safety Institute’s homegrown Inspect evaluations platform. This will be the first time that an AI safety testing platform spearheaded by a state-backed body has been released for wider use.

By making Inspect available to the global community, the Institute will accelerate the work on AI safety evaluations being carried out across the globe, leading to better safety testing and the development of more secure models for a consistent approach to AI safety evaluations around the world.

AI Safety Institute Chair Ian Hogarth said: 

“Successful collaboration on AI safety testing means having a shared, accessible approach to evaluations, and we hope Inspect can be a building block for AI Safety Institutes, research organisations, and academia. We hope to see the global AI community using Inspect to not only carry out their own model safety tests, but to help adapt and build upon the open source platform so we can produce high-quality evaluations across the board. We have been inspired by some of the leading open source AI developers which all have publicly available training data and OSI-licensed training and evaluation code, model weights, and partially trained checkpoints.”