An updated Model Spec for more capable and beneficial AI

OpenAI has updated its Model Spec, the public document describing how it wants its AI models to behave. The revision reorganizes guidance around five underlying values: faithfulness to human intent, harm minimization, honesty and transparency, facilitating human agency, and care. This reflects the goal of value alignment—enabling models to understand and apply human values in unfamiliar situations while remaining faithful to human intent. The update adds guidance on context, oversight, and agency, adjusts some behavioral defaults, and retires much of the detailed style guidance. It introduces a new section on faithfulness to human intent, including an updated chain of command and a subsection on considering context carefully. The Spec now refers to the model as "GPT" rather than "the assistant." OpenAI is also exploring new training methods to help models learn these core values and apply the Spec's principles in new situations. The update is a first step toward making the values and reasoning behind the Spec more explicit, and OpenAI invites public feedback.

(Source：OpenAI)