OPENAI · 2026-10-29 17:02 UTC

An updated Model Spec for more capable and beneficial AI

OpenAI updated its Model Spec, a public description of how its AI models should behave, reorganizing guidance around five core values: faithfulness to human intent, harm minimization, honesty and transparency, human agency, and care. The update aims to help models understand and apply human values in unfamiliar situations while remaining faithful to human intent, with clearer explanations of existing principles and new guidance on context, oversight, and agency.

Loading the story on Tree News…