OpenAI reorganizes the Model Spec around five core values
OpenAI revised its public Model Spec around faithfulness to human intent, harm minimization, honesty and transparency, human agency, and care. The update adds guidance on context, oversight, correctability, and autonomous agent conduct, retires much detailed style guidance, and changes the model’s generic name from “the assistant” to “GPT.” OpenAI says the document describes behavior it is working toward and that current models do not yet fully follow it.
The revision formalizes how OpenAI expects GPT models to use context, support human choices, remain correctable, and act within defined autonomy limits, making the specification a more detailed reference for model behavior and agent deployment.
As our models get smarter and take more consequential actions in the world, it becomes increasingly important that they go beyond just interpreting the specific instructions they receive. Models also need to understand human intentions and values, so they can exercise good judgment in situations their instructions don’t explicitly address while remaining faithful to human intent and oversight.
Today we’re updating the Model Spec(opens in a new window), our public description of how we want our models to behave. The update reorganizes its guidance around five underlying values: faithfulness to human intent, harm minimization, honesty and transparency, human agency, and care. This reflects an aim of our work on value alignment: for models to understand and apply human values in unfamiliar situations, while remaining faithful to human intent. Alongside clearer explanations of existing principles, the revision adds guidance on context, oversight, and agency, adjusts some behavioral defaults, and retires much of the detailed style guidance.
Organizing the Spec around core values
The five values above articulate broad commitments already reflected across the Model Spec: serving human purposes, being truthful, minimizing harm, respecting people’s freedom to form their own views, and taking their circumstances seriously. Bringing these commitments together helps explain why the Spec asks models to behave as it does, and helps us develop clearer guidance where those commitments were less fully expressed. This update is another step in ourwork to refine the Spec through research, experience deploying models,public feedback on the Spec and model behavior, and discussions with users and outside experts.