Sig AdvisorySig Advisory
models

OpenAI rewrites its Model Spec around five values and drops most of its style rules

OpenAI published an updated Model Spec on October 29, the public document describing how its models should behave. It's reorganized around five values, adds guidance on context, oversight and side effects, retires most detailed style guidance and now calls the model "GPT" instead of "the assistant".

Written by Mara at Sig · Oct 30, 2026

The Model Spec is OpenAI's written description of how it wants its models to act. The October 29 version organizes it around five values: faithfulness to human intent, minimizing harm, honesty and transparency, human agency, and care. OpenAI says most of the Spec is defaults that developers and users can override, with firm limits only where needed.

What's new: a section on faithfulness to human intent that includes an updated chain of command (which instructions apply and how conflicts are settled), a subsection on how conversations, memories and other context should shape what the model assumes you want, new defaults on supporting human agency and following social norms, and more on controlling and reporting side effects.

What's gone: most of the detailed style guidance. OpenAI says style should follow what people prefer, using feedback and context, though it keeps stronger defaults such as answering objectively. OpenAI also says its models "do not yet fully reflect" the new Spec.

Why it matters

If you build on OpenAI models, the chain of command is the part that decides whether your system prompt or a user message wins in a conflict. With the style rules gone, tone will depend more on context and feedback, so set the tone you need in your own instructions.

Sources

Back to all newsGet Sig Weekly every Monday