shipfeedAI news, curated daily

03:32:37 CET
12 OCT03:32:37shipfeed⋯
pull to refreshlast sync
Just in — 30 new
§ evals · storyline

Piloting the world's first double-blind AI evaluations

Piloting the world's first double-blind AI evaluations

Aug 27 · · primary fetch2 sourcesupdated Aug 27 ·

Piloting the world's first double-blind AI evaluations

read full article on deepmind.google ↗
§ sources2 publications · timeline below
  1. deepmind.googlePiloting the world's first double-blind AI evaluationsprimary
  2. deepmind.googleGoogle launches a pilot of double-blind AI evaluations, keeping external evaluations in a cryptographic "box" to stop benchmark contamination and protect IP (Google DeepMind)

§ how this story moved

  1. primary — Google DeepMind — Blog publishes the launch post.
  2. Google DeepMind picks up coverage.