Actor Ryan Gosling plays a science teacher in Project Hail Mary. Credit: Shutterstock/lev radin Let’s be honest here. If you’re a scientist — or, in our case,…

Credit: NIST On March 23, 1916, officials and citizens gathered in Washington, D.C., to celebrate a new era in the nation’s ability to measure. Secretary of Commerce William…

Authored by Drew Keller, Ryan Steed, Stevie Bergman, and the Applied Systems Team at CAISIBuilding gold-standard AI systems requires gold-standard AI measurement science – the scientific study…

Thank you to everyone who participated in the Cybersecurity Framework Profile for Artificial Intelligence (Cyber AI Profile) Workshop in January! The input we received on the Preliminary…

By Maia Hamin and Benjamin EdelmanAI evaluations are designed to assess and compare how AI models perform on different tasks. Developers, users, and independent evaluators — like…

In December, CAISI published a write-up on how AI models can cheat on agentic evaluations, including lessons from our experience building and using AI-enabled transcript analysis tools…

AI security red-teaming competitions – in which participants compete to develop new attacks against AI models and defenses – provide a unique way to assess how secure…

Credit: iStock/alvarez Manufacturing is a fast-paced, constantly evolving, and dynamic environment, and the supply chain is at its heart. For small and medium-sized manufacturers (SMMs), navigating the…