Google DeepMind(@GoogleDeepMind):In an industry first, we’re piloting double-blind evaluations for frontier AI. By creating a secure environment where neither test prompts nor model weights are revealed, we can ensure external safety and performance evaluations of our models remain private, robust, and trustworthy. →

Google DeepMind

@GoogleDeepMind

The engine room of @Google. Building AI safely and responsibly to solve the world’s most complex problems. Join us:

参加 January 2016

269 フォロー中 1.5M ファン

Google DeepMind@GoogleDeepMind

2026.08.27 13:05

In an industry first, we’re piloting double-blind evaluations for frontier AI. By creating a secure environment where neither test prompts nor model weights are revealed, we can ensure external safety and performance evaluations of our models remain private, robust, and trustworthy. →