We’ve updated the Model Spec, our public description of how we want our models to behave. This revision makes clearer what we want from models as they take on more autonomous work in the world and become capable of helping us in new ways. 🧵 openai.com/index/updated-mod…
An updated Model Spec for more capable and beneficial AI

An updated Model Spec for more capable and beneficial AI

OpenAI’s updated Model Spec outlines five core values to guide more capable AI toward sound judgment, human agency, and faithfulness to human intent.

openai.com
90
102
72
824
212,232
Nice! Do you have any data about how much the models follow (or disobey) this spec?
1
1
325
we haven't put out anything since alignment.openai.com/model-s…, but hope to follow up on this soon

Oct 30, 2026 · 5:23 AM UTC

3
321