The Model Spec Feedback

On February 12, 2025, we shared updates made to our Model Spec⁠(opens in a new window), a document that specifies our approach to shaping desired model behavior and how we evaluate tradeoffs when conflicts arise. The Model Spec includes 6 key sections:

• Chain of command: Defines how the model prioritizes instructions from the platform (OpenAI), developer, and user in order. 
• Stay in bounds: Explains how the model balances user autonomy with precautions to avoid facilitating harm or abuse. 
• Seek the truth together: Like a high-integrity human assistant, our models should empower users to make their own best decisions. 
• Do the best work: Sets basic standards for competence, including factual accuracy, creativity, and programmatic use.
• Be approachable: Describes the model’s default conversational style—warm, empathetic, and helpful—and how this style can be adapted.
• Use appropriate style: Provides default guidance on formatting and delivery. 

The Model Spec will continue to change over time. We invite you to share your feedback on the spec in the form below. This form will be open until March 10th.