shipfeedAI news, curated daily

14:55:37 CET
20 SEPT14:55:37shipfeed
pull to refreshlast sync
Just in — 30 new
§ safety · storyline

Our framework for reporting model misalignment

OpenAI releases framework for reporting model misalignment.

Sep 17 · · primary fetch7 sourcesupdated Sep 17 ·

Our framework for reporting model misalignment OpenAI

read full article on OpenAI
§ sources7 publications · timeline below
  1. OpenAIOur framework for reporting model misalignmentprimary
  2. Bloomberg.comOpenAI Reports New AI Safety Incidents, Sets Disclosure Process
  3. CNBCOpenAI reports 6 new instances of 'concerning model behavior' since March
  4. ReutersOpenAI plans regular reports on unexpected AI behavior
  5. WIREDOpenAI Creates a New Framework to Disclose Bad AI Behavior
  6. AxiosOpenAI discloses six new AI safety incidents
  7. WSJOpenAI Shares More Safety Incidents and Adopts New Rules for Reporting Them

§ how this story moved

  1. primaryWSJ publishes the launch post.
  2. Axios picks up coverage.
  3. OpenAI picks up coverage.
  4. WIRED picks up coverage.
  5. Reuters picks up coverage.
  6. CNBC picks up coverage.
  7. Bloomberg.com picks up coverage.