At Waymo, an AI project isn't ready until its evals are — not when the model performs well

Few companies face higher stakes when deploying AI than Waymo, the self-driving car company under Alphabet that spun out of Google. Its models do not merely generate text or automate back-office tasks: They help vehicles navigate unpredictable streets, respond to human drivers and make split-second decisions in the physical world.But the methods Waymo uses to manage those risks — continuous evaluation, carefully cur…