OpenAI rewrote its chatbot rulebook around five values — and admits its models don't follow it yet

OpenAI published an updated Model Spec on October 29, reorganizing its public description of how its models should behave around five values: faithfulness to human intent, harm minimization, honesty and transparency, human agency, and care. Faithfulness to human intent is the foundation — what people value is primary, and instructions are ordinarily the clearest signal of those values.

The revision adds guidance on context, oversight and agency, including a new section on considering context carefully, and retires most of the Spec's detailed style guidance. The model is now called 'GPT' rather than 'the assistant,' and style is supposed to adapt to what people prefer in aggregate and individually.

OpenAI is explicit about the gap: the Spec describes the behavior it is working toward, and its models do not yet fully reflect it. The company says it is exploring new training methods to teach models the values, not just the rules, and will share results in future updates.