--- title: An updated Model Spec for more capable and beneficial AI description: OpenAI has updated its Model Spec, the public document describing how its models should behave. The revision reorganizes guidance around five values:... canonical: https://daily.dev/posts/an-updated-model-spec-for-more-capable-and-beneficial-ai-vfobw4biq twitter:card: summary_large_image twitter:site: @dailydotdev og:type: website og:site_name: daily.dev og:title: An updated Model Spec for more capable and beneficial AI | daily.dev og:description: OpenAI has updated its Model Spec, the public document describing how its models should behave. The revision reorganizes guidance around five values:... og:url: https://daily.dev/posts/an-updated-model-spec-for-more-capable-and-beneficial-ai-vfobw4biq og:image: https://api.daily.dev/og/posts/vFOBw4BiQ.png og:image:alt: An updated Model Spec for more capable and beneficial AI og:image:width: 1200 og:image:height: 630 og:locale: en --- > ## Documentation Index > Fetch the complete documentation index at: https://daily.dev/llms.txt > Use this file to discover all available pages before exploring further. # An updated Model Spec for more capable and beneficial AI **[OpenAI](https://daily.dev/sources/openai)** · 7 min read · 0 upvotes · 0 comments ## Summary OpenAI has updated its Model Spec, the public document describing how its models should behave. The revision reorganizes guidance around five values: faithfulness to human intent, harm minimization, honesty and transparency, human agency, and care. It adds guidance on context, oversight, and agency, including a new subsection on 'consider context carefully' and defaults on 'supporting human agency' and 'controlling and communicating side effects'. Most detailed style guidance is retired in favor of adapting to user and cultural preferences. The document now refers to the model as 'GPT' instead of 'the assistant'. OpenAI says models do not yet fully reflect this behavior. ## Full article daily.dev links to this article rather than hosting it. Read it at the original source: ## Questions this post answers ### What are the five core values in OpenAI's updated Model Spec? The five values are faithfulness to human intent, harm minimization, honesty and transparency, human agency, and care. Faithfulness to human intent is described as the foundation, meaning understanding what OpenAI, developers, and users intend rather than just following instructions literally. The other four values make explicit considerations like safety boundaries, truthfulness, user capability, and attention to circumstances. _Developers shaping AI product behavior can track how OpenAI's own guidance evolves on daily.dev._ ### Does OpenAI's Model Spec still include detailed style guidance for how models should write? No, OpenAI is retiring most of the Model Spec's detailed style guidance, letting style adapt to user and cultural preferences based on feedback and context instead. Some stronger defaults remain, such as approaching questions objectively; users and developers can explicitly request a particular perspective, but the model should not infer that preference just from what it thinks they want to hear. _Anyone building on GPT models can follow spec changes like this on daily.dev before they hit production behavior._ ### Why does OpenAI's Model Spec now call the model 'GPT' instead of 'the assistant'? OpenAI changed the terminology to reflect the increasing breadth of its models' use cases and deployment settings, since referring to it only as 'the assistant' no longer captured how broadly the models are deployed. This is a naming change within the October 2026 Model Spec update, alongside reorganized guidance around five core values. _Teams tracking terminology and behavior shifts across OpenAI's models can keep up via daily.dev._ ## Similar posts on daily.dev - [OpenAI adds new teen safety rules to ChatGPT as lawmakers weigh AI standards for minors](https://daily.dev/posts/openai-adds-new-teen-safety-rules-to-chatgpt-as-lawmakers-weigh-ai-standards-for-minors-b7rcb0wwa) · TechCrunch · 0 upvotes · 0 comments --- Tags: [#openai](https://daily.dev/tags/openai), [#ai-safety](https://daily.dev/tags/ai-safety), [#gpt](https://daily.dev/tags/gpt), [#ai-governance](https://daily.dev/tags/ai-governance) [View this post on daily.dev](https://daily.dev/posts/an-updated-model-spec-for-more-capable-and-beneficial-ai-vfobw4biq) ```json {"@context":"https://schema.org","@graph":[{"@type":"Organization","@id":"https://daily.dev/#organization","name":"daily.dev","url":"https://daily.dev","logo":{"@type":"ImageObject","url":"https://daily.dev/apple-touch-icon.png","width":180,"height":180},"sameAs":["https://twitter.com/dailydotdev","https://github.com/dailydotdev","https://www.linkedin.com/company/daily-dev-ltd"]},{"@type":"WebSite","@id":"https://daily.dev/#website","url":"https://daily.dev","name":"daily.dev","publisher":{"@id":"https://daily.dev/#organization"},"potentialAction":{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https://daily.dev/search?q={search_term_string}"},"query-input":"required name=search_term_string"}}]} {"@context":"https://schema.org","@type":"TechArticle","headline":"An updated Model Spec for more capable and beneficial AI","url":"https://daily.dev/posts/an-updated-model-spec-for-more-capable-and-beneficial-ai-vfobw4biq","mainEntityOfPage":{"@type":"WebPage","@id":"https://daily.dev/posts/an-updated-model-spec-for-more-capable-and-beneficial-ai-vfobw4biq"},"datePublished":"2026-10-29T17:47:08.158Z","dateModified":"2026-10-29T18:29:14.174Z","description":"OpenAI has updated its Model Spec, the public document describing how its models should behave. The revision reorganizes guidance around five values:...","image":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/2ec509f5a857083882fb92dc29428512?_a=AQAEuop","thumbnailUrl":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/2ec509f5a857083882fb92dc29428512?_a=AQAEuop","isAccessibleForFree":true,"articleSection":"OpenAI","inLanguage":"en","publisher":{"@type":"Organization","name":"daily.dev","url":"https://daily.dev","logo":{"@type":"ImageObject","url":"https://daily.dev/apple-touch-icon.png","width":180,"height":180}},"author":{"@type":"Organization","name":"OpenAI","logo":"https://media.daily.dev/image/upload/t_logo,f_auto/v1/logos/984b3632316f4afaa3d5213d5c64fe65","url":"https://daily.dev/sources/openai"},"commentCount":0,"discussionUrl":"https://daily.dev/posts/an-updated-model-spec-for-more-capable-and-beneficial-ai-vfobw4biq","interactionStatistic":[{"@type":"InteractionCounter","interactionType":{"@type":"LikeAction"},"userInteractionCount":0},{"@type":"InteractionCounter","interactionType":{"@type":"CommentAction"},"userInteractionCount":0}],"keywords":"openai,ai-safety,gpt,ai-governance","timeRequired":"PT7M"} {"@context":"https://schema.org","@type":"BreadcrumbList","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https://daily.dev"},{"@type":"ListItem","position":2,"name":"OpenAI","item":"https://daily.dev/sources/openai"},{"@type":"ListItem","position":3,"name":"An updated Model Spec for more capable and beneficial AI"}]} {"@context":"https://schema.org","@type":"FAQPage","@id":"https://daily.dev/posts/an-updated-model-spec-for-more-capable-and-beneficial-ai-vfobw4biq#faq","mainEntity":[{"@type":"Question","name":"What are the five core values in OpenAI's updated Model Spec?","acceptedAnswer":{"@type":"Answer","text":"The five values are faithfulness to human intent, harm minimization, honesty and transparency, human agency, and care. Faithfulness to human intent is described as the foundation, meaning understanding what OpenAI, developers, and users intend rather than just following instructions literally. The other four values make explicit considerations like safety boundaries, truthfulness, user capability, and attention to circumstances. Developers shaping AI product behavior can track how OpenAI's own guidance evolves on daily.dev."}},{"@type":"Question","name":"Does OpenAI's Model Spec still include detailed style guidance for how models should write?","acceptedAnswer":{"@type":"Answer","text":"No, OpenAI is retiring most of the Model Spec's detailed style guidance, letting style adapt to user and cultural preferences based on feedback and context instead. Some stronger defaults remain, such as approaching questions objectively; users and developers can explicitly request a particular perspective, but the model should not infer that preference just from what it thinks they want to hear. Anyone building on GPT models can follow spec changes like this on daily.dev before they hit production behavior."}},{"@type":"Question","name":"Why does OpenAI's Model Spec now call the model 'GPT' instead of 'the assistant'?","acceptedAnswer":{"@type":"Answer","text":"OpenAI changed the terminology to reflect the increasing breadth of its models' use cases and deployment settings, since referring to it only as 'the assistant' no longer captured how broadly the models are deployed. This is a naming change within the October 2026 Model Spec update, alongside reorganized guidance around five core values. Teams tracking terminology and behavior shifts across OpenAI's models can keep up via daily.dev."}}]} ```