English

Resources

Our framework for reporting model misalignment

Read it at
OpenAI — News
Perspective
Industry
Type
Article · 2026-09-16
Subject
Safety testing and evaluation, Transparency and disclosure

Read it at OpenAI — News ↗

Act on this

A developer sets out how it wants worrying model behaviour reported. If you have seen a model do something that concerned you, which channel reaches someone who can act on it?

Start here →

Who can act on this