OpenAI Model Spec update: 5 core values for how GPT should behave
Why it matters
OpenAI updated its Model Spec on 29 October 2026, the public description of how it wants its models to behave. The update reorganizes the guidance around five underlying values: faithfulness to human intent, harm minimization, honesty and transparency, human agency, and care. OpenAI says models need to understand human intentions and values so they can exercise good judgment in situations their instructions don't explicitly address, while remaining faithful to human intent and oversight. The revision adds guidance on context, oversight and agency (including a new 'consider context carefully' subsection), adjusts some behavioral defaults, retires most of the detailed style guidance, and now refers to the model as "GPT" rather than "the assistant". OpenAI notes that its models do not yet fully reflect the Spec.
Read the source: openai.com (opens in a new tab)
All hits from 30 Oct 2026More ModelsGet the daily hits by email