OpenAI updates Model Spec, adjusting model behavior guidelines around five values
An updated Model Spec for more capable and beneficial AI
OpenAI updated the Model Spec, reorganizing model behavior guidance around five values: being faithful to human intent, reducing harm, honesty and transparency, promoting human agency, and care. The new version adds guidance on context, oversight and agency, adjusts some default behaviors, and removes most detailed style guidelines, while changing "assistant" in the spec to "GPT." OpenAI says it is exploring new training methods to help models understand these values and apply them in new situations, and will publish results later; the Spec describes the behavior it is working toward, which models do not yet fully achieve.
The new Model Spec consolidates behavior guidance into five values and adds provisions on context, oversight and agency, offering a way to observe how OpenAI defines the boundaries of model judgment in situations not covered by instructions.