SafetyPage

Lab research on the web · Blog post · Google DeepMind

Piloting the world's first double-blind AI evaluations

Read at deepmind.google ↗Read at sourceAll rights reserved

Outline · 13 paragraphs

  1. Piloting the world's first double-blind AI evaluations¶1
  2. How double-blind evaluations work¶8
  3. A novel approach to building trust in model evaluations¶11