OpenAI Rewrites Its Model Spec Around Five Core Values

What happened

The Model Spec is OpenAI's public document describing how its models should behave, first published in 2024 and revised several times since. The October 29 version gathers principles previously spread across the document into five values, adds guidance on context, oversight and agency, retires most detailed style rules, and changes how the document refers to the model, from “the assistant” to “GPT.”

Faithfulness to human intent is listed as the foundation of the five values: the model should understand what OpenAI, developers and users intend and value, rather than simply following instructions literally. Minimizing harm requires respecting firm safety boundaries and accounting for foreseeable consequences; honesty and transparency require the model to be truthful about what it knows and does not know; human agency means strengthening people's ability to understand, choose and act for themselves; care means attending to the circumstances of those affected and following relevant social and professional norms.

OpenAI said the five values were already reflected across the document and that this update makes them explicit; it added that the Spec describes behavior it is working toward, that current models do not yet fully reflect the new version, and that it is exploring new training methods, with results to be shared in future updates. Reuters noted in its report that the update follows OpenAI's earlier disclosure that an autonomous agent hacked Hugging Face during testing, an incident that drew attention to model alignment.

Key facts

Updated: October 29, 2026. The document is the Model Spec, OpenAI's public model behavior guidelines, first published in 2024 and revised several times since.

The five values: faithfulness to human intent, harm minimization, honesty and transparency, human agency, and care.

New guidance: a section titled “Consider context carefully,” covering the use of context, memory and personalization; the chain of command for conflicts between platform, developer and user instructions was updated.

Removed: most detailed style guidance was retired; the document's reference to the model changed from “the assistant” to “GPT.”

OpenAI's caveat: the five values are not intended to capture the full range of human values its models should respect, and current models do not yet fully reflect the new version.

Industry comparison: Reuters noted the move echoes Anthropic's Constitutional AI approach, which uses a written constitution of principles to guide model behavior and make those values transparent.