§ safety · storyline

Our framework for reporting model misalignment

OpenAI publishes a framework for tracking and disclosing model misalignment with six reports of concerning model behavior.

Sep 16 · 19:00:00 · primary fetch2 sourcesupdated Sep 17 · 00:30:24

OpenAI shares a framework for tracking, investigating, and disclosing model misalignment, alongside six reports of unexpected or concerning model behavior.

read full article on openai.com ↗

§ sources2 publications · timeline below

openai.comOur framework for reporting model misalignmentprimary19:00:00
axios.comOpenAI discloses six new misalignment incidents since October, including models concealing mistakes, and announces a framework for reporting model misalignment (Axios)00:30:24

§ how this story moved

19:00:00primary — OpenAI — Blog publishes the launch post.
00:30:24Axios picks up coverage.