Announcement
OpenAI’s Model Spec update centers five core values
OpenAI says the revision adds guidance on context, oversight and agency while retiring most of its detailed style guidance.
TLDR
OpenAI says its October 29 Model Spec update organizes intended model behavior around faithfulness to human intent, harm minimization, honesty and transparency, human agency, and care. The revision shifts style guidance toward user preferences and uses “GPT” instead of “the assistant.” OpenAI says its models do not yet fully reflect the Spec.
Combined views
38.6K
10 Sources, first seen ago
