Korabench
Intro
KORA builds the first non profit, independent and open-source benchmark for AI child safety, measuring how today's AI systems behave with children, against 26 child-specific risks, and publish everything openly, so that families, builders and policymakers have the evidence to act, and safer products get built. The project is led by Mathilde Colin, CEO of La Licorne Front, and Stéphie Herlin, with whom I collaborate on the design of the platform.
