面向更强大、更有益 AI 的更新版模型规范

随着我们的模型变得越来越智能，并在现实世界中采取影响越来越重大的行动，它们就越来越需要超越对所接收的具体指令的单纯解读。模型还需要理解人类的意图和价值观，以便在指令未明确涉及的情境中作出合理判断，同时忠实于人类的意图并接受监督。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.

今天，我们更新了 Model Spec（在新窗口中打开），这是我们对模型应如何表现的公开说明。此次更新围绕五项根本价值重新组织了相关指导：忠实于人类意图、尽量减少伤害、诚实与透明、维护人类自主权，以及关怀。这体现了我们在价值对齐方面的目标：让模型能够在陌生情境中理解并践行人类价值观，同时忠实于人类意图。除了更清晰地阐释现有原则外，此次修订还新增了关于情境、监督和自主权的指导，调整了部分行为默认设置，并废除了大部分详尽的风格指导。Today we’re updating the Model Spec⁠(opens in a new window), 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: 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.

上述五项价值观阐明了《模型规范》中已体现的广泛承诺：服务于人类福祉、保持真实、尽量减少伤害、尊重人们形成自身观点的自由，并认真看待他们所处的具体情境。将这些承诺汇集起来，有助于解释《规范》为何要求模型以这样的方式行事，也有助于我们针对那些尚未得到充分阐释的承诺，制定更明确的指导原则。此次更新是我们持续完善《规范》的又一步；这项工作以研究、模型部署经验、公众对《规范》和模型行为的反馈，以及与用户和外部专家的交流为基础。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 through research, experience deploying models, public feedback on the Spec and model behavior, and discussions with users and outside experts.

我们希望人工智能能够造福世界各地的人们，满足他们不同的需求、价值观和对未来的期望。We want AI to benefit a world of people with different needs, values, and hopes for the future.

忠实于人类意图是这一方法的基础：理解人们，并帮助他们追求对自己重要的事物。OpenAI 编写规范、设定边界，并训练模型遵守这些边界；开发者在这些边界内指导应用；用户则在这些约束下指导模型的工作。我们的模型应帮助人们了解世界、发现可能性并追求自己选择的目标，从而增强他们塑造自身生活的能力，同时认真考虑这种帮助会如何影响他人。忠实于人类意图以及其余四项价值观构成了规范的框架，并指导我们的模型如何应对它们面临的一些最重要的权衡。这些价值观并非旨在涵盖我们的模型应予以尊重并帮助人们追求的全部人类价值。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 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.

忠实性意味着不只是照字面遵循指令，还要深入理解 OpenAI、开发者和用户的意图与重视之处，并在这种理解不完整时明智地采取行动。它也意味着认识到人们的信念和价值观可能会改变，并帮助他们以自己认可的方式反思和成长，而不是暗中引导他们或凌驾于他们的选择之上。例如，在帮助某人比较工作机会时，模型可以参考对方此前分享过的优先考虑因素——比如工时稳定——同时明确说明这些假设，让对方可以轻松更正。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.

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的眼前意图，还要考虑其长远利益以及对他人的影响。其他四项价值观明确体现了这些考量：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:

• 最大限度地减少伤害，意味着尊重严格的安全边界，并考虑模型行为可能造成的可预见后果。

  Minimizing harm means respecting firm safety boundaries and accounting for the foreseeable consequences of the model’s actions.

• 诚实与透明意味着如实说明模型知道什么、做了什么以及对什么不确定，让人们能够理解并评估其推理和工作。

  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.

• 促进人的自主性，意味着增强人们理解、选择并自主行动的能力。

  Facilitating human agency means strengthening people’s ability to understand, choose, and act for themselves.

• 关怀意味着关注受影响者的具体处境，遵循相关的社会规范和职业规范，并做出值得人们信赖的工作。

  Care means attending to the circumstances of those affected, following relevant social and professional norms, and doing work people can rely on.

《规范》将这些价值观转化为切实可行的指导方针，在保护个人和社会所必需之处设定明确界限；除此之外，主要以用户和开发者可以覆盖的默认规则形式呈现。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.

除了此次 Model Spec 更新，我们还一直在探索新的训练方法，以帮助模型学习这些核心价值观，更好地理解并遵循 Spec 中具体的行为准则。我们的目标是让模型理解这些准则为何重要，以及如何将其应用于新的情境：出于正确的理由做正确的事。我们希望这种理解能支持模型在影响重大的决策中作出可靠判断，并在日常决策中体现关怀；这些日常决策累积起来，能够为人们和社会带来持久的益处⁠（在新窗口中打开）。今后的更新中，我们会分享这项训练工作的成果与经验。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). We’ll share results and lessons from this training work in future updates.

这次重组也帮助我们发现了哪些方面需要补充指导，制定了新的原则来应对这些需求，并根据需要修订或废止现有指导内容。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.

关于忠实于人类意图的新章节，立足于这样一种观点：人们珍视什么才是首要因素，而指令通常是这些价值观最清晰、最重要的信号。这种方法借鉴了对齐的“协助游戏”框架（参见早期研究（在新窗口中打开）和后来的综述（在新窗口中打开））。本节纳入了更新后的指令层级（在新窗口中打开），解释哪些指令适用以及如何解决冲突。新增的小节“仔细考虑上下文”（在新窗口中打开）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。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) and a later overview⁠(opens in a new window)). The section incorporates an updated chain of command⁠(opens in a new window), which explains which instructions apply and how conflicts are resolved. A new subsection, consider context carefully⁠(opens in a new window), explains how conversations, memories, and other contextual evidence should inform the model’s understanding of people’s intentions and preferences.

我们还新增了关于支持人类自主性（在新窗口中打开）和遵循相关社会规范（在新窗口中打开）的默认指导，并扩展了现有的关于控制和沟通副作用（在新窗口中打开）的指导。这些原则体现了其余价值观还应以其他方式体现在模型行为中；这些方式往往微妙，却很重要：考虑工作对他人的影响，增强用户的能力，并产出值得人们信赖的成果，同时尊重用户的目标和指示。We’ve also added defaults on supporting human agency⁠(opens in a new window) and following relevant social norms⁠(opens in a new window), and expanded existing guidance on controlling and communicating side effects⁠(opens in a new window). 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.

与此同时，我们将取消《规范》中大部分详细的风格指导。风格应根据人们的偏好进行调整——既要考虑整体偏好、不同语言和文化中的偏好，也要考虑每个人的偏好；用户反馈和上下文则可作为判断这些偏好的依据。《规范》仍保留更有力的默认要求，例如客观地看待问题（在新窗口中打开）。用户和开发者可以明确要求模型采取某种特定视角，但模型不应仅仅因为认为用户想听什么，就推断用户有这种偏好。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). 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.

最后，鉴于我们的模型在应用场景和部署环境方面日益广泛，我们现在在规范中将该模型称为“GPT”，而非“助手”。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.

这次更新是让随着模型能力不断增强，《模型规范》背后的价值观和推理过程变得更加明确的第一步。《模型规范》描述了我们致力于实现的行为；我们的模型目前尚未完全体现这些要求。随着我们从研究、实际应用和反馈中不断学习，我们将持续改进《模型规范》和模型本身。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.

我们想了解 Spec 中哪些部分让你觉得有说服力，哪些地方你不同意它所采取的平衡，以及它忽略了什么或有哪些表述不够清楚。你对其中的价值观、权衡取舍和具体措辞提出的反馈，都能帮助我们改进它。欢迎阅读更新后的 Model Spec（在新窗口中打开），并分享你的看法（在新窗口中打开）。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) and share your perspective⁠(opens in a new window).