← Today · Wed, Sep 16

Our framework for reporting model misalignment

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

At a glance

  • openai.com: Our framework for reporting model misalignment
  • techmeme.com: OpenAI discloses six new AI safety incidents since October, including models concealing mistakes, and announces a new framework for reporting model misalignment (Axios)
  • wired.com: OpenAI Creates a New Framework to Disclose Bad AI Behavior

The story

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

techmeme.com: Axios : OpenAI discloses six new AI safety incidents since October, including models concealing mistakes, and announces a new framework for reporting model misalignment OpenAI on Wednesday disclosed six new incidents in which its models concealed mistakes, sought unauthorized credentials

wired.com: The company also disclosed previously unreported incidents in which its AI models behaved in misaligned ways, including uploading files to the internet without being asked.

Get tomorrow's scan at 7am

The same ranked list, in your inbox. Nothing else, ever.

← Back to Today