Sharing the latest Model Spec

OpenAI published an updated Model Spec on Feb 12, 2025 and released it under a CC0 public-domain license for free reuse and adaptation. The update centers on chain of command, truth-seeking, boundaries, and style; OpenAI says adherence improved versus its best system from last May, but the post does not disclose scores, eval size, or model names. The key point is that OpenAI writes intellectual freedom into the spec while keeping platform-level refusal boundaries.

Why it matters: OpenAI's latest Model Spec matters because HKR-K and HKR-R both land, and the official source gives this policy update real weight. The score stays at the low end of featured because the post gives principles and mechanisms, but no eval scores, test scale, or model-level rollout.