OpenAI restructures Model Spec around five core values
What happened
OpenAI updated its Model Spec on October 30, reorganizing model behavior rules around five core values: staying true to human intent, reducing harm, honesty and transparency, human autonomy, and care. The revision updates the instruction hierarchy, adds guidance on context, human autonomy and social norms, and expands requirements on side-effect control and communication. Most detailed style guidance is removed. OpenAI says it is exploring training methods for the spec but that current models do not yet fully reflect it.
Written by AI from the coverage · updated 1 hour ago
Coverage
Follow the reports to see the story from different sides.
- OpenAI NewsPickOpenAI updates Model Spec, organizing model behavior around five core values
OpenAI has updated its Model Spec, regrouping the rules for model behavior around five core values: following human intent, reducing harm, honesty and transparency, human autonomy, and care. The revision updates the instruction hierarchy, adds guidance on context, human autonomy and social norms, expands requirements on side-effect control and communication, and removes most detailed style guidance. OpenAI says it is exploring training methods to match, but states plainly that current models do not yet fully reflect the spec.
Heat over time
Not enough continuous observations to draw a trend yet.