更新型号Spec，用于更有能力和更有利的AI

更新型号Spec，用于更有能力和更有利的AI

随着我们的模式变得更加聪明，在世界上采取更多的相应行动，它们必须超越仅仅解释它们收到的具体指示。 模式也需要理解人类的意图和价值，这样，在他们的指示没有明确涉及的情况下，他们就可以做出良好的判断，同时忠于人类的意图和监督。

现今我们正在更新模型Spec(在新窗口打开)，该更新围绕五个基本价值观重新调整了指导：对人类意图的忠诚、尽量减少伤害、诚实和透明度、人的能力和关心。 这反映了我们在价值观协调方面的工作的一个目标：使模式在不熟悉的情况下理解和运用人类价值观，同时忠于人类意图。 除了对现有原则作出更明确的解释外，修订版的新增关于上下文，监督和代理的指导，调整了一些行为默认，并取消了许多详细的风格指导。

上述五项价值观阐明了整个示范体系中已经体现的广泛承诺：为人类服务、诚实、尽量减少伤害、尊重人们形成自己观点的自由以及认真对待他们的情况。 将这些承诺汇集在一起有助于解释《光谱》为什么要求模式照样行事，并帮助我们在这些承诺表述不够充分的地方制定更明确的指南。 这一更新是我们通过研究，经验部署模型，公众对Spec和模型行为的反馈，以及与用户和外部专家的讨论来完善Spec的又一步骤。

我们希望AI有利于一个有不同需求、价值观和对未来希望的人的世界。

对人类意图的忠诚是这种方法的基础：理解和帮助人们追求对他们重要的事物。 OpenAI写作Spec，设定界限，并训练模型以尊重它们；开发这些界限内的直接应用程序；用户在这些限制下指导模型的工作。 我们的模式应该通过帮助他们了解世界、发现各种可能性并追求他们所选择的目标来扩大人们塑造自己生活的能力，同时认真对待这种援助如何影响他人。 对人类意图和其余四个价值观的忠诚度组织Spec，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。 它们的目的不是要体现我们的模式应该尊重和帮助人们追求的各种人类价值观。

忠诚意味着超越从字面上遵循指示来深刻理解OpenAI，开发者，用户的意图和价值，并在该理解不完整时明智行事。 这也意味着承认人们的信仰和价值观可以改变，帮助他们以他们不会悄悄地引导他们或压倒他们的选择的方式反映和发展。 例如，在帮助某人比较工作机会时，该模式可能利用他们以前共享的优先事项，如可预测的时间，同时使这些假设变得明显和容易纠正。

我们的任务是确保人工一般情报造福全人类。 这就不仅需要考虑某人的直接意图，而且还需要考虑其长期利益和对他人的影响。 其他四项价值观明确了这些考虑：

- 尽量减少损害意味着尊重严格的安全界限和说明模型行动的可预见后果。

- 诚实和透明意味着要诚实地了解模型的知识、行为和不确定性，以便人们能够理解和评价其推理和工作。

- 促进人类机构意味着加强人们了解、选择和为自己采取行动的能力。

- 照顾是指按照相关的社会和职业规范照顾受影响者，从事人们可以依赖的工作。

Spec将这些价值观转化为实用指导，在需要保护人和社会的地方有坚实的界限，否则大多采取用户和开发商可以超越的默认形式。

除了这个模型Spec更新之外，我们一直在探索新的训练方法，帮助我们的模型学习这些核心价值，目的是了解这些原则为何重要，以及如何在新的情况下适用这些原则：出于正确的理由做正确的事情。 我们希望这种理解能够支持对相应决定的正确判断和对日常决定的关心，从而给人民和社会带来持久的惠益(在一个新的窗口打开)。 我们将在将来的更新中分享这项培训工作的成果和教训。

这一重组还帮助我们确定需要哪些额外指导，制定新的原则加以解决，并根据需要修订或废除现有指导。

有关对人类意图的忠诚的新一节的出发点是，人们所珍视的是首要的，指示通常是这些价值观的最清楚和最重要的信号。 这种办法借用了对齐的协助游戏框架(见早期工作(在新窗口打开)和后来的概述(在新窗口打开))。 本节包含更新的命令链(在新窗口打开)，说明适用哪些指令以及如何解决冲突。 一个新的小节，仔细考虑背景(在新窗口打开)，解释对话、记忆和其他背景证据应如何使模型了解人们的意图和偏好。

我们还增加了关于支持人体机构(在新窗口打开)和遵循相关社会规范(在新窗口打开)的默认，并扩大了关于控制和沟通副作用(在新窗口打开)的现有指导。 这些原则捕捉到其他的、往往是微妙的、但很重要的价值观在模式行为中应该浮现出来：考虑作品对他人的影响，加强用户的能力，以及制作工作的人可以依赖的工作，同时尊重用户的目标和指示。

与此同时，我们即将废除斯佩克的大部分详细风格指导。 风格应该适应人们所喜欢的东西——在语言和文化中，对于每个人来说——用户的反馈和背景可以提供这些偏好的证据。 Spec保留了较强的默认值，例如客观地接近问题(在新窗口打开). 用户和开发者可以明确要求模型采取特定视角，但模型不应仅仅从它认为他们想听到的内容推断出这种偏好。

最后，由于我们模型使用的案例和部署设置日益广泛，我们现在将模型称为 " GPT "，而不是Spec中的 " 助手 "。

这一更新是随着模型能力增强，使Spec背后的价值观和推理更加清晰的第一步。 模型Spec描述了我们正致力于的行为；我们的模型还没有充分反映它。 我们将不断改进Spec和模型学习研究、现实世界的使用和反馈

我们想听听你认为有说服力的斯佩克的哪一部分，你不同意它所达到的平衡，以及它忽略了什么或留下了不明确的地方。 对价值、取舍和具体语言的反馈可以帮助我们改进它。 我们邀请您阅读更新的 Model Spec( 在新窗口打开) 并分享您的观点( 在新窗口打开)。

本文由 AI图鉴自动抓取并翻译，版权归原作者所有；如需查看原文请点下方链接。

An updated Model Spec for more capable and beneficial AI

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), 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.

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.

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 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). We’ll share results and lessons from this training work in future updates.

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) 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.

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.

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.

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.

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) and share your perspective(opens in a new window).

Auto-fetched and translated by AI Atlas. All rights belong to the original author.