Français

Ressources

Our framework for reporting model misalignment

À lire sur
OpenAI — News
Point de vue
Industry
Type
Article · 2026-09-16
Sujet
Safety testing and evaluation, Transparency and disclosure

À lire sur OpenAI — News ↗

Agir

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?

Commencer ici →

Qui peut agir à ce sujet