Muse Creates Detailed Profiles of All Your Friends and Family
Muse Creates Detailed Profiles of All Your Friends and Family
Muse 为你的所有亲友创建详细档案
Meta’s new personal assistant, Muse, has become a viral hit, with millions downloading the AI agent, connecting it to bank accounts, messages, or health data, and allowing it to complete tasks for them. But as Muse takes off among consumers, data from inside the app is providing insight into how it organizes and presents information to users.
Meta 推出的全新个人助理 Muse 已成为现象级应用，数百万用户下载了这款 AI 智能体，将其连接到银行账户、消息或健康数据，并授权其代为完成任务。随着 Muse 在消费者群体中走红，应用内部的数据也揭示了它如何组织并向用户呈现信息。
In recent days, multiple researchers have extracted Muse’s internal files and dumped the agent’s operating instructions, providing a glimpse of how the system was built and behaves. Meta has maintained that it intended for these files to be accessible in the interest of transparency, and they do provide insight into how Muse responds to prompts and questions about, for example, highly politicized or sensitive topics.
近日，多位研究人员提取了 Muse 的内部文件并导出了该智能体的操作指令，让我们得以一窥该系统的构建方式及其运行逻辑。Meta 坚称，出于透明度考虑，这些文件本就应是可访问的。这些文件确实让我们深入了解了 Muse 如何响应有关高度政治化或敏感话题的提示和提问。
Independent AI safety and security researcher Karan Joshi was able to extract an extensive array of Muse instructions and system prompts by using the regular chat interface to essentially ask Muse to copy and share its own software files. Joshi then shared his findings with WIRED.
独立的 AI 安全研究员 Karan Joshi 通过常规聊天界面，诱导 Muse 复制并分享其自身的软件文件，从而提取出了一系列详尽的 Muse 指令与系统提示词。随后，Joshi 将其发现分享给了《连线》（WIRED）杂志。
One of Muse’s instructions appears to be the ability for it to create “a page for every person in the user’s life.” This hourly process involves compiling data on family, partners, friends, colleagues, “collaborators,” and people you “follow,” the instructions say.
Muse 的其中一项指令似乎是为“用户生活中的每个人创建一个页面”。指令显示，这一每小时运行一次的流程涉及汇总有关家人、伴侣、朋友、同事、“合作者”以及你所“关注”的人的数据。
The general idea is that Muse can use its “memory” (aka structured text files) to collect information about your relationships and the important people in your life. It can then make suggestions, like giving pointers on how to improve particular relationships or, say, where to take a coffee-loving friend for breakfast. Of course, it’s not unusual for AI chatbots to track social information in general—people have been asking ChatGPT for relationship advice for years now. But it’s interesting to see how Muse is set up given Meta’s history and vast access to social network data.
其核心理念是，Muse 可以利用其“记忆”（即结构化文本文件）来收集有关你的人际关系以及生命中重要人物的信息。随后，它能提供建议，例如如何改善特定关系，或者建议带一位爱喝咖啡的朋友去哪里吃早餐。当然，AI 聊天机器人追踪社交信息并不罕见——多年来，人们一直都在向 ChatGPT 寻求情感建议。但考虑到 Meta 的过往历史及其对社交网络数据的庞大访问权限，Muse 的这种设置方式显得尤为引人关注。
“What it seemed like to me—from all these prompts, system skills data, and things that they’re feeding into Muse—is that they want to understand your relationships that you have with real people,” says Joshi. “They’re trying to know you like a friend, which is honestly pretty creepy.”
“从所有这些提示词、系统技能数据以及他们输入给 Muse 的内容来看，他们似乎想要了解你与现实中人们的关系，”Joshi 说道，“他们试图像朋友一样了解你，老实说，这相当令人毛骨悚然。”
Muse’s documentation says that a page may start “sparse” and then be filled out over time, potentially including sections like Facts, History, The relationship, In common, Open threads, and Strengthening. Meta’s instructions say Muse should only use the “evidence” it has available, and that invented details are worse than an empty page.
Muse 的文档显示，一个页面最初可能很“稀疏”，但会随着时间推移逐渐完善，可能包含事实、历史、关系、共同点、待办事项（Open threads）以及关系强化等板块。Meta 的指令要求 Muse 只能使用现有的“证据”，并强调编造细节比页面空白更糟糕。
“Where they live, what they do, the threads that recur (the apartment move, the shared savings goal),” the instructions say. They add, too, that the model could record the “dates that matter,” such as birthdays or anniversaries. A person’s history could include backstory like “the trip in March, the argument that got resolved, the milestone last week.”
指令写道：“他们住在哪里，从事什么工作，反复出现的话题（搬家、共同的储蓄目标）。”指令还补充说，该模型可以记录“重要的日期”，例如生日或纪念日。一个人的历史记录可能包括背景故事，如“三月份的旅行、已解决的争吵、上周的里程碑事件”。
The instructions also focus on recording relationship details such as “how close they are, what it is built on, how they act with each other, and what it seems to need right now.” The Strengthening section suggests ways a relationship could be improved, including, “A reason to call, a date worth remembering, something they said to circle back on, a way to be there for them that matters.”
指令还侧重于记录人际关系细节，例如“关系的亲疏程度、建立的基础、彼此的互动方式，以及目前似乎需要什么”。“强化”板块则建议了改善关系的方法，包括：“打电话的理由、值得纪念的日子、他们提到过需要后续跟进的事情，以及一种对他们而言重要的陪伴方式。”
“We are giving AI systems much more information about us than we are getting information from them,” says Carissa Véliz, an associate professor at Oxford’s Institute for Ethics in AI. “It’s not only what we explicitly tell them, but what they can infer from us—correctly or incorrectly, both concerning for different reasons—and what they can piece together from other sources of data.”
牛津大学 AI 伦理研究所副教授 Carissa Véliz 表示：“我们提供给 AI 系统关于我们自身的信息，远多于我们从它们那里获得的信息。这不仅包括我们明确告诉它们的内容，还包括它们能从我们身上推断出的信息——无论推断正确与否，出于不同原因都令人担忧——以及它们能从其他数据源拼凑出的信息。”
Muse is architected so each individual user has their own dedicated virtual machine, which stores user data and context. This VM is inaccessible to other agents and users can wipe memories or disconnect external services at any time. Meta says that Muse is also designed to seek human confirmation before completing actions like sending an email or making a purchase, and that it has an audit log where users can see all of the agent’s activity and future plans.
Muse 的架构设计为每个用户拥有独立的虚拟机，用于存储用户数据和上下文。其他智能体无法访问该虚拟机，用户可以随时清除记忆或断开外部服务。Meta 表示，Muse 在执行发送电子邮件或进行购买等操作前，会寻求人工确认，并且拥有审计日志，用户可以在其中查看智能体的所有活动和未来计划。
“For any agent to be useful and actually help you achieve your goals, it needs to have context about you and those you interact with,” Meta spokesperson Daniel Roberts told WIRED in a statement. “Muse gathers that based on public information and from what you’ve chosen to share, which is how it remembers the person who sent you an invoice is in fact the plumber who you previously hired to complete work in your bathroom or which flowers your spouse said they liked best.”
Meta 发言人 Daniel Roberts 在给《连线》的声明中表示：“任何智能体若想发挥作用并真正帮助你实现目标，都需要了解你以及与你互动的人的背景信息。Muse 基于公开信息和你选择分享的内容来收集这些信息，这就是它为什么能记住给你发账单的人其实就是你之前雇来修浴室的水管工，或者记住你配偶说过最喜欢哪种花。”
It’s become common for AI assistants to incorporate some sort of memory feature designed to allow greater personalization in responses and activity. Miranda Bogen, the director of the Center for Democracy and Technology’s AI Governance Lab, says Muse appears to have more emphasis on relationships and personal contacts than rivals’ systems. In general, these tools tend to offer some transparency and editing capabilities, and Muse does as well. If anything, though, Bogen notes that agents and assistants encourage people to proactively share more data with them versus focusing on culling data.
AI 助手集成某种记忆功能以实现更个性化的响应和活动，已成为常态。民主与技术中心（CDT）AI 治理实验室主任 Miranda Bogen 指出，与竞争对手的系统相比，Muse 似乎更强调人际关系和个人联系。总体而言，这些工具往往提供一定的透明度和编辑功能，Muse 也不例外。不过，Bogen 指出，这些智能体和助手更多是在鼓励人们主动分享更多数据，而非专注于精简数据。
“These [AI assistant] tools are actively soliciting users to plug their whole lives in—their emails, calendars, financial institutions, everything in order to be helpful assistance,” Bogen says. “That’s dramatically more information than people might have otherwise given to some of these companies. The breadth of access to information that these tools have will lead to a ballooning of what they know about users.”
“这些（AI 助手）工具正在积极诱导用户接入他们的整个生活——电子邮件、日历、金融机构，一切为了提供所谓的‘有益协助’，”Bogen 说道，“这比人们原本可能提供给这些公司的数据量要多得多。这些工具所拥有的信息访问广度，将导致它们对用户了解程度的急剧膨胀。”