# OpenAI 更新 Model Spec,围绕五项核心价值观重组模型行为准则
> 原标题:An updated Model Spec for more capable and beneficial AI
- 来源:OpenAI:官网动态
- 发布时间:2026-10-29T17:00:00.000Z
- AIHOT:https://aihot.news/items/rccreyesa3aeph7jasj5spv29
- 原文:https://openai.com/index/updated-model-spec
## 摘要
OpenAI 更新其公开的 Model Spec,将指导原则重组为五项核心价值观:忠实于人类意图、最小化伤害、诚实透明、促进人类自主和关怀。更新新增了关于上下文理解、监督和自主性的指导,调整了部分行为默认值,退出了大部分详细风格指南,并将模型称呼从 the assistant 改为 GPT。
## 推荐理由
原文列出五项核心价值观及新增与退出的具体章节,读者可据此比较对齐框架的实际变化。
## 正文 · 中文译文
## 更强大的模型需要更完善的模型规范,以造福人类
[阅读更新后的规范(在新窗口打开)](https://model-spec.openai.com/2026-10-29.html)
加载中…
[音频 1](https://openai.com/index/updated-model-spec)
分享
随着我们的模型越来越智能,在现实世界中采取的行动也越来越有分量,它们不能只停留在理解收到的具体指令上,这一点正变得愈发重要。模型还需要理解人类的意图和价值观,这样才能在指令没有明确覆盖的情况下做出良好判断,同时始终忠于人类意图并接受人类监督。
今天我们更新了[模型规范(在新窗口打开)](https://model-spec.openai.com/2026-10-29.html),这是我们公开说明希望模型如何行为的文件。此次更新围绕五项基本价值重新组织了规范内容:**忠于人类意图**、**尽量减少伤害**、**诚实与透明**、**尊重人的自主性**以及**关怀**。这体现了我们在[价值对齐](https://openai.com/index/an-alien-mind/)方面的工作目标:让模型在陌生情境中理解并运用人类价值观,同时始终忠于人类意图。除了对现有原则作出更清晰的解释,本次修订还新增了关于情境、监督和自主性的指引,调整了一些默认行为,并删去了大部分详细的风格指引。
## 围绕核心价值组织规范
上述五项价值阐明了模型规范中早已体现的广泛承诺:服务于人类目的、保持真实、尽量减少伤害、尊重人们形成自身观点的自由,以及认真对待人们的处境。把这些承诺汇聚在一起,有助于解释规范为何要求模型以特定方式行事,也帮助我们在这些承诺表达得不够充分的地方制定更清晰的指引。此次更新是我们[完善规范工作](https://openai.com/index/our-approach-to-the-model-spec/)的又一步,依托于研究、部署模型的经验、[公众对规范及模型行为的反馈](https://openai.com/index/collective-alignment-aug-2025-updates/),以及与用户和外部专家的讨论。
我们希望 AI 造福于一个由不同需求、价值观和对未来期望的人们组成的世界。
**忠于人类意图**是这一方法的根基:理解并帮助人们追求对他们重要的事情。OpenAI 负责撰写规范、设定边界,并训练模型遵守这些边界;开发者在这一边界内指导应用;用户则在上述约束下指导模型的工作。我们的模型应当[拓展人们塑造自身生活的能力](https://openai.com/index/built-to-benefit-everyone-our-plan/),帮助他们理解世界、发现可能性、追求自己选定的目标,同时认真对待这种协助对他人造成的影响。忠于人类意图与其余四项价值共同构成了规范的组织框架,指导模型如何权衡它们面临的一些最重要取舍。这些价值并不意在涵盖模型应当尊重并帮助人们追求的全部人类价值。
忠实意味着不止于字面执行指令,而是深入理解 OpenAI、开发者和用户的意图与价值取向,并在这种理解不完整时做出明智判断。它还意味着要认识到人们的信念和价值观会变化,帮助他们以自己认可的方式反思和成长,而不是悄悄引导他们或替他们做选择。例如,在帮人比较工作机会时,模型可以援引对方此前分享过的优先考虑——比如希望工作时间可预测——同时把这些假设摆到明面上,方便对方纠正。
我们的使命是确保通用人工智能造福全人类。这要求我们不仅考虑某人当下的意图,还要考虑其长远利益以及对他人造成的影响。另外四项价值观把这些考量明确表达出来:
- **尽量减少伤害**,意味着遵守明确的安全边界,并考虑模型行为可预见的后果。
- **诚实与透明**,意味着如实说明模型知道什么、做了什么、对什么不确定,让人们能够理解和评估它的推理与工作。
- **促进人的能动性**,意味着增强人们理解、选择和自主行动的能力。
- **关怀**,意味着关注受影响者的处境,遵循相关的社会与职业规范,并让人们可以信赖模型的工作。
《模型规范》把这些价值观转化为可操作的指引:在需要保护人和社会的地方设定明确边界,其余部分大多以默认规则的形式呈现,用户和开发者可以覆盖。
在更新《模型规范》的同时,我们一直在探索新的训练方法,帮助模型学习这些核心价值观,更好地理解和遵循规范中的具体行为原则。目标是让模型理解这些原则为何重要,以及如何在新情境中运用它们:_做正确的事_,_出于正确的理由_。我们希望这种理解能支撑模型在重大决策上做出合理判断,在日常决策中保持审慎——这些日常决策累积起来,可以[为人和社会带来持久益处(在新窗口打开)](https://alignment.openai.com/beneficial-rl/)。我们会在后续更新中分享这项训练工作的成果和经验。
## 新增与停用的章节
这次重组还帮助我们找出了哪些地方需要补充指引,据此制定新原则,并按需修订或停用原有指引。
新增的“忠实于人类意图”一节,出发点是:人们所看重的东西是第一位的,而指令通常是这些价值最清晰、最重要的信号。这一思路借鉴了对齐研究中的“协助博弈”框架(参见[早期工作(在新窗口打开)](https://arxiv.org/abs/1606.03137)和[后续综述(在新窗口打开)](https://www.amacad.org/publication/daedalus/if-we-succeed))。该节纳入了更新后的[指令链(在新窗口打开)](https://model-spec.openai.com/2026-10-29.html#chain_of_command),说明哪些指令适用、冲突如何解决。新增小节[仔细考虑上下文(在新窗口打开)](https://model-spec.openai.com/2026-10-29.html#consider_context_carefully)则说明对话、记忆和其他上下文证据应如何帮助模型理解人们的意图和偏好。
我们还为[支持人的能动性(在新窗口打开)](https://model-spec.openai.com/2026-10-29.html#support_human_agency)和[遵循相关社会规范(在新窗口打开)](https://model-spec.openai.com/2026-10-29.html#follow_social_norms)补充了默认要求,并扩充了关于[控制并沟通副作用(在新窗口打开)](https://model-spec.openai.com/2026-10-29.html#control_side_effects)的现有指引。这些原则涵盖了其余价值观在模型行为中体现的更多方式——它们往往细微却重要:考虑工作成果对他人的影响、增强用户的能力、产出人们可以信赖的成果,同时尊重用户的目标和指令。
与此同时,我们删去了规范中大部分详细的风格指引。风格应当顺应人们的偏好——既包括语言和文化层面的整体偏好,也包括每个人的个人偏好——而用户反馈和具体情境则为这些偏好提供依据。规范保留了更强的默认要求,例如[客观地探讨问题(在新窗口打开)](https://model-spec.openai.com/2026-10-29.html#assume_objective_pov)。用户和开发者可以明确要求模型采取特定视角,但模型不应仅仅因为觉得对方想听什么,就推断出这种偏好。
最后,考虑到模型用例和部署场景日益广泛,我们在规范中现在称模型为“GPT”,而不再称“助手”。
## 接下来
随着模型能力不断增强,本次更新是让规范背后的价值观和推理更加明确的第一步。模型规范描述的是我们努力实现的行为,我们的模型尚未完全体现这一点。我们将从研究、实际使用和反馈中不断学习,持续改进规范与模型。
我们想知道你认为规范中哪些部分有说服力、哪些地方你不认同其权衡取舍,以及它忽略了什么或哪些地方表述不清。关于价值观、权衡取舍和具体措辞的反馈,能帮助我们改进规范。欢迎阅读[更新后的模型规范(在新窗口打开)](https://model-spec.openai.com/2026-10-29.html)并[分享你的看法(在新窗口打开)](https://model-spec-feedback-2026.openai.chatgpt.site/)。
- [对齐](https://openai.com/news/?tags=alignment)
## 作者
OpenAI
## 正文 · 原文
## An updated Model Spec for more capable and beneficial AI
[Read the updated Spec(opens in a new window)](https://model-spec.openai.com/2026-10-29.html)
Loading…
[Audio 1](https://openai.com/index/updated-model-spec)
Share
As our models get smarter and take more consequential actions in the world, it becomes increasingly important that they go beyond just interpreting the specific instructions they receive. Models also 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.
Today we’re updating the [Model Spec(opens in a new window)](https://model-spec.openai.com/2026-10-29.html), our public description of how we want our models to behave. The update reorganizes its guidance around five underlying values: **faithfulness to human intent**, **harm minimization**, **honesty and transparency**, **human agency**, and **care**. This reflects an aim of our work on [value alignment](https://openai.com/index/an-alien-mind/): for models to understand and apply human values in unfamiliar situations, while remaining faithful to human intent. Alongside clearer explanations of existing principles, the revision adds guidance on context, oversight, and agency, adjusts some behavioral defaults, and retires much of the detailed style guidance.
## Organizing the Spec around core values
The five values above articulate broad commitments already reflected across the Model Spec: serving human purposes, being truthful, minimizing harm, respecting people’s freedom to form their own views, and taking their circumstances seriously. Bringing these commitments together helps explain why the Spec asks models to behave as it does, and helps us develop clearer guidance where those commitments were less fully expressed. This update is another step in our[work to refine the Spec](https://openai.com/index/our-approach-to-the-model-spec/) through research, experience deploying models,[public feedback](https://openai.com/index/collective-alignment-aug-2025-updates/) on the Spec and model behavior, and discussions with users and outside experts.
We want AI to benefit a world of people with different needs, values, and hopes for the future.
**Faithfulness to human intent** is the foundation of this approach: understanding and helping people pursue what matters to them. OpenAI writes the Spec, sets boundaries, and trains models to respect them; developers direct applications within those boundaries; and users direct the model’s work subject to those constraints. Our models should[expand people’s ability to shape their own lives](https://openai.com/index/built-to-benefit-everyone-our-plan/) by helping them understand the world, discover possibilities, and pursue the goals they choose, while taking seriously how that assistance affects others. Faithfulness to human intent and the remaining four values organize the Spec and guide how our models should navigate some of the most important trade-offs they face. They are not intended to capture the full range of human values our models should respect and help people pursue.
Faithfulness means going beyond following instructions literally to deeply understanding what OpenAI, developers, and users intend and value, and acting wisely when that understanding is incomplete. It also means recognizing that people’s beliefs and values can change, and helping them reflect and grow in ways they would endorse without quietly steering them or overriding their choices. For example, when helping someone compare job offers, the model might draw on priorities they have shared before—such as predictable hours—while making those assumptions visible and easy to correct.
Our mission is to ensure that artificial general intelligence benefits all of humanity. This requires considering not only someone’s immediate intentions, but also their longer-term interests and the effects on others. The other four values make these considerations explicit:
- **Minimizing harm** means respecting firm safety boundaries and accounting for the foreseeable consequences of the model’s actions.
- **Honesty and transparency** mean being truthful about what the model knows, does, and is uncertain about so people can understand and evaluate its reasoning and work.
- **Facilitating human agency** means strengthening people’s ability to understand, choose, and act for themselves.
- **Care** means attending to the circumstances of those affected, following relevant social and professional norms, and doing work people can rely on.
The Spec turns these values into practical guidance, with firm boundaries where needed to protect people and society, and otherwise mostly takes the form of defaults that users and developers can override.
Alongside this Model Spec update, we’ve been exploring new training methods to help our models learn these core values and better understand and follow the Spec’s specific behavioral principles. The aim is to build an understanding of why those principles matter and how to apply them in new situations: to do the _right things_ _for the right reasons_. We want that understanding to support sound judgment in consequential decisions and care in everyday decisions that can add up to [lasting benefits for people and society(opens in a new window)](https://alignment.openai.com/beneficial-rl/). We’ll share results and lessons from this training work in future updates.
## New and retired sections
This reorganization also helped us identify where additional guidance was needed, develop new principles to address it, and revise or retire existing guidance as needed.
The new section on faithfulness to human intent starts from the idea that what people value is primary, and instructions are ordinarily the clearest and most important signals of those values. This approach borrows from the assistance-games framing of alignment (see[early work(opens in a new window)](https://arxiv.org/abs/1606.03137) and a[later overview(opens in a new window)](https://www.amacad.org/publication/daedalus/if-we-succeed)). The section incorporates an updated [chain of command(opens in a new window)](https://model-spec.openai.com/2026-10-29.html#chain_of_command), which explains which instructions apply and how conflicts are resolved. A new subsection, [consider context carefully(opens in a new window)](https://model-spec.openai.com/2026-10-29.html#consider_context_carefully), explains how conversations, memories, and other contextual evidence should inform the model’s understanding of people’s intentions and preferences.
We’ve also added defaults on[supporting human agency(opens in a new window)](https://model-spec.openai.com/2026-10-29.html#support_human_agency) and[following relevant social norms(opens in a new window)](https://model-spec.openai.com/2026-10-29.html#follow_social_norms), and expanded existing guidance on[controlling and communicating side effects(opens in a new window)](https://model-spec.openai.com/2026-10-29.html#control_side_effects). These principles capture additional, often subtle but important ways the remaining values should surface in model behavior: considering the effects of the work on others, strengthening users’ capabilities, and producing work people can rely on, while respecting the user’s goals and instructions.
At the same time, we’re retiring most of the Spec’s detailed style guidance. Style should adapt to what people prefer—in aggregate, within languages and cultures, and for each person—with user feedback and context providing evidence about those preferences. The Spec retains stronger defaults, such as [approaching questions objectively(opens in a new window)](https://model-spec.openai.com/2026-10-29.html#assume_objective_pov). Users and developers can explicitly ask the model to take a particular perspective, but the model should not infer that preference merely from what it thinks they want to hear.
Finally, reflecting the increasing breadth of our models’ use cases and deployment settings, we now refer to the model as “GPT” rather than “the assistant” in the Spec.
## What comes next
This update is a first step in making the values and reasoning behind the Spec more explicit as models become more capable. The Model Spec describes the behavior we are working toward; our models do not yet fully reflect it. We will keep improving both the Spec and the models as we learn from research, real-world use, and feedback.
We want to hear which parts of the Spec you find compelling, where you disagree with the balance it strikes, and what it overlooks or leaves unclear. Feedback on the values, trade-offs, and specific language can help us improve it. We invite you to read the [updated Model Spec(opens in a new window)](https://model-spec.openai.com/2026-10-29.html) and [share your perspective(opens in a new window)](https://model-spec-feedback-2026.openai.chatgpt.site/).
- [Alignment](https://openai.com/news/?tags=alignment)
## Author
OpenAI