模型硬件标准预览
原题Previewing the Model Hardware Standard
推荐理由Anthropic 发布 Model Hardware Standard 研究预览，用读取、写入、标签和编排等通用原语，让 Agent 安全操作显微镜、移液设备、机械臂与量子激光系统。原本需要数周甚至数月的设备集成，可以缩短到数小时或数分钟。MHS 像是面向物理世界的 MCP：能力不再停留在屏幕里，但每台设备的状态、权限、安全联锁与可追踪性，也因此成为比模型调用更稀缺的基础设施。六个科研与制造案例让这项标准不只停留在概念层，尤其适合关注实验自动化和具身系统的读者。
读前速览
Anthropic 正在推出模型硬件标准（MHS），这是一种共享规范，允许 AI 代理安全地操作物理设备，并且正在向一组科学研究实验室和高级制造商开放 MHS 的研究预览。
MHS 允许 AI 代理同时操作多个实验室和制造仪器。
MHS 将集成工作减少到几小时或几分钟，并帮助研究人员和工程师更容易地编排自动化、全天候的实验和工作流程。
MHS 旨在与任何具有可编程接口的设备兼容。
该标准使用一组简单的原语，例如“读取”和“写入”命令，任何硬件设备都可以理解和执行。
MHS 帮助 AI 代理了解如何使用它从未见过的设备。
MHS 驱动程序包含标签，允许用户编写有关设备特性的信息，例如它可以测量什么和将执行什么安全限制。
MHS 允许通过单行代码编排多个设备。
代理可以跨设备序列步骤，监控结果，并根据条件的变化实时调整参数。
完整摘要
模型硬件标准（MHS）是一种标准化的驱动程序，允许 AI 代理同时操作多个实验室和制造仪器，并执行从常规药物发现实验到量子计算机激光校准等复杂任务。MHS 将集成工作减少到几小时或几分钟，并帮助研究人员和工程师更容易地编排自动化、全天候的实验和工作流程。该标准旨在与任何具有可编程接口的设备兼容。
目录 · 10 节
实验室或制造设施通常需要数周甚至数月，才能完成硬件的安装与集成。大多数设备彼此无法通信，因此需要专家专门构建定制集成方案。MHS 将这项集成工作缩短至数小时甚至几分钟。通过将 AI 融入这些工具，MHS 还帮助研究人员和工程师更轻松地编排全天候自主运行的实验和工作流程；智能体能够逐步推理实验中的每个环节、实时更新参数，并在某些情况下无需人工干预即可从硬件故障中恢复。It typically takes a lab or manufacturing facility weeks, if not months, to set up and integrate their hardware. Most devices don’t communicate with each other, instead requiring specialists to build bespoke integrations. MHS reduces this integration work to hours or minutes. And by incorporating AI into these tools, MHS also helps researchers and engineers more readily orchestrate autonomous, round-the-clock experiments and workflows, with agents able to reason through each step in an experiment, update parameters in real time, and, in some cases, recover from hardware errors without intervention.
我们正在与科学、机器人、电子和制造领域的合作伙伴分享 MHS 的早期版本，以便在将该标准开源之前，携手构建安全评估，并为操作物理设备的 AI 系统制定最佳实践。MHS 适用于任何具有可编程接口的设备。它也与模型无关，任何智能体运行框架都可以通过标准协议（例如 Model Context Protocol）访问它。请前往此处申请访问研究预览版。We’re sharing an early version of MHS with partners across science, robotics, electronics, and manufacturing so we can collaborate to build safety evaluations and develop best practices for AI systems operating physical equipment, ahead of making the standard open source. MHS works with any device that has a programmable interface. It is also model-agnostic, and any agent harness can access it using standard protocols, such as the Model Context Protocol. To apply for access to the research preview, head here.
MHS 的工作原理How MHS works
让实验室或工厂车间里的多台设备彼此通信可能颇具挑战，即使不考虑将 AI 集成到整个系统中所带来的额外难度也是如此。每台设备往往都有自己的编程接口，迄今还没有标准化的集成方式。而且，即使设备已经连接起来，也没有通用的方法让它们与 AI 智能体共享数据，或让智能体安全地操作这些设备。Getting multiple devices in a lab or on a factory floor to communicate with one another can be challenging, even setting aside the added difficulty of integrating AI into the setup. Each device tends to have its own programming interface, and so far there has been no standardized way to integrate them. And once the devices are connected, there is no common way for them to share data with an AI agent, nor to let the agent operate them safely.
MHS 通过引入标准化驱动程序来应对这些挑战：这是一种在计算机操作系统与硬件设备之间进行转换的软件。MHS 驱动程序使用一组简单的基本操作——例如“读取”（如“获取温度”）或“写入”（如“设置温度”）等命令——任何硬件设备都能理解并执行这些命令。它还会以标准格式让每台设备都可被发现，因此设备和智能体能够在网络中彼此查找并进行通信，无需在中间另行编写专用的“翻译器”程序。MHS addresses these challenges by introducing a standardized driver: software that translates between a computer’s operating system and a hardware device. The MHS driver uses a simple set of primitives—commands like “read” (for example, “get temperature”) or “write” (for example, “set temperature”)—that any hardware device can understand and act on. And it makes each device discoverable in a standard format, so that devices and agents can find each other and communicate across networks without needing a bespoke “translator” program in between.
MHS 驱动还能帮助 AI 智能体了解如何使用从未见过的设备，向它提供仅凭代码可能无法辨识的机器特性信息（例如机械臂的重量，这对了解如何安全地操纵它至关重要）。迄今为止，这类信息大多存储在纸质手册、用户的电脑中，或以隐性知识的形式存在。但 MHS 驱动包含一些标签，用户可以通过这些标签直接用自然语言编写此类信息（用户可以自行编写，也可以与智能体聊天，由智能体询问其硬件配置）。利用这些标签中的信息，MHS 驱动会自动生成一份参考文件，介绍设备的一般特性，例如它能测量什么、可以调整什么，以及将执行哪些安全限制。这份文件为智能体提供了操作设备所需的一切信息。The MHS driver also helps an AI agent understand how to use a device it has never seen before, giving it information about machine characteristics that may not be discernable from code alone (for example, the weight of a robot arm, which is important for knowing how to manipulate it safely). To date, much of this information has been stored in paper manuals, on a user’s computer, or as tacit knowledge. But the MHS driver contains tags that let the user write this information directly in natural language (users can either do this themselves, or by chatting to an agent that interviews them about their hardware setup). With the information from these tags, the MHS driver then automatically produces a reference file with information about a device’s general characteristics, such as what it can measure, what can be adjusted, and what safety limits will be enforced. This file gives the agent everything it needs to know to operate the device.
设备连接完成且代理知道如何使用每台设备后，还需要一种控制硬件的方式。对于 MHS，有三种这样的机制：MCP、命令行界面和代码文件（API）。它们协同工作，只需一行代码即可编排多台设备。After the devices are connected and the agent knows how to use each one, the agent needs a way to control the hardware. For MHS, there are three such mechanisms: MCP, the command line interface, and code files (APIs). These work together to enable orchestration across multiple devices via a single line of code.
一旦智能体能够控制这些设备，就可以接收每台设备的运行数据，并从高层次上监督和指导工作。智能体可以安排各仪器的操作步骤、监控结果，并根据条件的实时变化调整参数。当智能体需要执行长时间运行的任务，或以高于其在线推理速度的节奏操作设备时，可以在代码文件中串联一个或多个设备的驱动程序命令。这样，设备就能自行执行操作，而无需智能体在每一步都进行推理。Once the agent can control the devices, it’s able to receive operating data from each one and supervise and direct the work at a high level. The agent can sequence steps across instruments, monitor results, and adjust parameters as conditions change in real time. When the agent needs to execute long-running tasks or operate devices faster than its online reasoning would allow, it can chain together driver commands from one or more devices in code files. This allows the devices to carry out operations themselves, without the agent needing to reason at every step.
在测试 MHS 的过程中，我们发现 Claude 会像科学家一样，以探索性的方式与实验和硬件互动。例如，我们观察到 Claude 调整激光器，通过摄像头观察结果，以评估这次调整如何改变激光束的位置，然后重复这一过程，试图理解事件发生的先后顺序。随后，Claude 将学到的内容整理成代码文件，编写了一个确定性脚本，使它无需在每一步都进行推理就能校准激光器，从而让整个过程可以通过一条命令运行。As we’ve tested MHS, we’ve found that Claude interacts with experiments and hardware in an exploratory manner, much as a scientist would. For example, we observed Claude make an adjustment to a laser, observe the results through a camera to assess how its adjustment moved the laser beam, and repeat the process, seeking to understand the sequence of events. Claude then packaged what it learned into code files, writing a deterministic script that let it align the laser without having to reason at each step, so the whole process could run as a single command.
MHS 的早期示例Early examples from MHS
我们才刚刚开始看到人们能够借助前沿模型和 MHS 做些什么，但我们希望，这项标准能够帮助研究人员、工程师及其他从业者，加快任何使用可编程接口设备的领域中的发现与实验进程。We are only just beginning to see what people can do with frontier models and MHS, but our hope is that the standard can be of use to researchers, engineers, and other practitioners in speeding up the process of discovery and experimentation in any domain that uses devices with a programmable interface.
在开发 MHS 的过程中，我们与生物技术、机器人、量子计算及其他领域的几家实验室和硬件制造商分享了它。在这些早期项目中，我们发现，MHS 缩短了设备集成所需的时间，让团队能够在各种实验环境中更快地迭代，并协助机器实时运行和进行故障检测。下面，我们的合作伙伴将介绍他们早期使用 MHS 开展的一些项目详情。As we developed MHS, we shared it with a handful of labs and hardware manufacturers in biotech, robotics, quantum computing, and other fields. Across these early projects, we saw MHS reduce the time it took to integrate devices, make it possible to iterate faster in a variety of experimental settings, and assist with the live operation of machines and real-time fault detection. Below, our partners share the details of some of their early projects involving MHS.
基因泰克：为实验室自动化实施 MHSGenentech: Implementing MHS for lab automation
基因泰克的研究人员实施并测试了 MHS，将其作为自动化 BCA 蛋白质测定的概念验证。BCA 蛋白质测定是一种测量样品总蛋白浓度的标准流程，需要协调液体处理器、机械臂和酶标仪协同工作。Researchers at Genentech implemented and tested MHS as a proof of concept for automating the BCA protein assay, a standard procedure to measure total protein concentration in a sample, which requires coordinating across a liquid handler, a robotic arm, and a plate reader.
华盛顿大学 Baker 和 Pinglay 实验室：将 AI 智能体带到实验台前University of Washington Baker and Pinglay labs: Bringing AI agents to the bench
华盛顿大学 Baker 和 Pinglay 实验室的博士生宋子豪利用 MHS 构建了一个仪表板，用于远程监控他的仪器；还构建了一个由 AI 智能体监督的 qPCR 系统（通过反复加热和冷却来扩增目标 DNA 序列），该系统会监测扩增曲线，并在适当时机停止实验；此外，他还实现了机械臂与液体处理器的集成，使它们能够无碰撞地交接微孔板。Zihao Song, a PhD student in the University of Washington Baker and Pinglay labs, used MHS to build a dashboard to remotely monitor his instruments; an AI agent-supervised qPCR (which copies a target DNA sequence through repeated cycles of heating and cooling) that watches amplification curves and halts the procedure at the right moment; and an integration between a robotic arm and a liquid handler for collision-free plate handoffs.
卡内基梅隆大学：通过快速自动化确定剂量-反应曲线Carnegie Mellon University: Determining dose-response curves through rapid automation
卡内基梅隆大学的研究人员利用 MHS 开展系列稀释剂量-反应实验，速度约为以往的三倍。实验过程中，一个 AI 智能体协调液体处理器、酶标仪、机械臂和监控摄像头；这些设备分布在三台计算机上，且接口从根本上彼此不兼容。Researchers at Carnegie Mellon University used MHS to run serial dilution dose-response experiments about three times faster than before, with an AI agent orchestrating a liquid handler, a plate reader, a robotic arm, and monitoring cameras spread across three computers with fundamentally incompatible interfaces.
HHMI Janelia：利用 MHS 加速显微学研究HHMI Janelia: Using MHS to accelerate microscopy research
在 HHMI Janelia 研究园区，研究人员正利用 MHS 加快推进各类显微成像相关项目。在这里，Ahrens 实验室的科学家 Virginie Ruetten 研究睡眠如何帮助身体从压力中恢复，并分享了她如何利用 MHS 整合并协调一套此前需要使用七种不同厂商软件、且彼此没有共享界面的设备系统。At HHMI Janelia Research Campus, researchers are using MHS to speed up a range of microscopy-related projects. Here, Virginie Ruetten, a scientist in the Ahrens lab who studies how sleep helps the body recover from stress, shares how she used MHS to unify and orchestrate a rig that previously involved seven different vendor programs without a shared interface.
QuEra Computing：在量子激光器稳频中使用 MHSQuEra Computing: Using MHS in quantum laser stabilization
QuEra 是一家使用中性原子构建量子计算机的公司，它利用 MHS 让 AI 智能体能够控制其量子计算机内部激光系统的部分组件。该智能体开发了一种控制器，无需人工干预，就能在 99.3% 的情况下重新锁定激光器的频率——也就是激光器必须保持的、用于与原子相互作用的超高精度频率。QuEra, a company that builds quantum computers using neutral atoms, used MHS to give an AI agent control over parts of the laser system inside its quantum machines. The agent developed a controller that recovers the laser’s “lock”—the ultra-precise frequency the lasers must hold to interact with the atoms—99.3% of the time without human intervention.
Tetsuwan Scientific：利用 MHS 进行 qPCR 检测，分析本地污染情况Tetsuwan Scientific: Using MHS to run qPCRs to profile local pollution
Tetsuwan 的研究人员将 MHS 集成到其自动化生物实验室平台 ResearchOS 中。MHS 协助协调了一项 qPCR 工作流程，为公民科学项目提供支持，以分析加利福尼亚州圣佩德罗溪的污染情况。Researchers at Tetsuwan integrated MHS with its automated biology lab platform, ResearchOS. MHS helped orchestrate a qPCR workflow to contribute to citizen science efforts to characterize pollution in California’s San Pedro Creek.
硬件供应商及为其提供支持的软件公司也在其设备中加入 MHS 支持，以便 AI 代理更轻松地发现和操作这些设备。例如：Hardware vendors and the software companies that support them are also building MHS support into their equipment so AI agents can more easily discover and operate their devices. For example:
- Amazon Web Services 将通过 Strands Robots（用于连接 AI 智能体与物理设备的库）为 MHS 提供支持。在 MHS 研究预览期间，AWS 将向参与者提供 Strands Robots 软件包的私有预发布版本。Amazon Web Services will support MHS through Strands Robots, the library for connecting AI agents to physical devices. AWS will provide participants a private, pre-release version of the Strands Robots package for the duration of the MHS research preview.
- Automata 正在为其实验室自动化平台 LINQ 添加 MHS 支持，以便在自主实验室中对仪器进行智能错误处理。Automata is adding MHS support to LINQ, their lab automation platform, to perform intelligent error handling of instruments in autonomous labs.
- 丹纳赫和 Anthropic 正在积极探索，MHS 支持的能力如何赋能其智能仪器和自主实验室，助力扩大生物医学研究与开发的规模。Danaher and Anthropic are actively exploring how MHS-supported capabilities could enable its smart instruments and autonomous laboratories to scale biomedical research and development.
- 斗山机器人正在使用其机械臂测试 MHS，包括执行自动化质量检测以及协调多台机器人的任务。Doosan Robotics is testing MHS with their robotic arms, including to perform automated quality assurance and coordinate tasks across multiple robots.
- MBF Bioscience 正在为 ScanImage 开发 MHS 驱动程序。ScanImage 是一款用于运行激光扫描显微镜的软件，服务于全球数百家神经科学实验室。此举旨在将 AI 智能体集成到实时数据分析和实验中。MBF Bioscience is building an MHS driver for ScanImage, the software that runs laser-scanning microscopes in hundreds of neuroscience labs worldwide, to integrate AI agents into real-time data analysis and experiments.
- QIAGEN 正在其核酸纯化平台 QIAsymphony Connect 上开展 MHS 的概念验证，展示 AI 智能体如何帮助实验室更快地排查仪器问题、指导操作人员恢复仪器运行，并在降低生物样本风险的同时提高仪器正常运行时间。QIAGEN is experimenting with MHS through a working proof of concept on its nucleic acid purification platform, QIAsymphony Connect, showing how AI agents could help laboratories troubleshoot instrument issues faster, guide operators through recovery, and improve instrument uptime while reducing risk to biological samples.
- Tecan 正在为其 Fluent 液体处理平台添加 MHS 支持，使 AI 智能体能够直接发现并操作这些平台。Tecan is adding MHS support for their Fluent liquid handling platforms so AI agents can discover and operate them directly.
- Universal Robots 已提前获得 MHS 的使用权限，并计划在其机器人平台中增加对 MHS 的支持。Universal Robots has had early access to MHS and plans to add support to its robotics platform.
加入研究预览版Joining the research preview
合作伙伴取得的这些早期成果令人鼓舞，但在将这项标准开源之前，我们还有更多工作要做。作为一种大型语言模型，Claude 通过文本和图像了解物理世界，这意味着它在空间推理和物理推理方面存在局限，仍需要专家监督。例如，在处理蛋白质样本时，基因泰克的研究人员必须引导 Claude 认识到，样本起泡导致的错误属于物理故障，而非软件缺陷，只能通过采取适当的物理措施来缓解。These early results from our partners are encouraging, but we have more work to do on the standard before we open-source it. As a large language model, Claude learns about the physical world through text and images, meaning its spatial and physical reasoning have limitations that still require expert oversight. When working with protein samples, for example, Genentech researchers had to guide Claude to recognize that errors caused by foaming in samples were physical failures, not software bugs, that could only be mitigated through the appropriate physical corrections.
MHS 目前也尚不支持缺少编程接口的硬件，因此我们正在与这类设备的制造商合作，为设备构建 MHS 驱动程序。许多开发者已经在使用 Claude Code 操作各类实体设备；在 MHS 的下一阶段，我们希望扩大该标准的覆盖范围，支持更多开发者所构建的设备。早期采用者包括 Hugging Face，他们正在其机器人库 LeRobot 中添加 MHS 支持；以及 Raspberry Pi，他们在使用 Camera MHS Driver 成功完成测试后，正为旗下多款产品启用 MHS 集成。MHS also doesn’t yet work with hardware that lacks a programming interface, so we’re working with the manufacturers of such devices to build in MHS drivers. Many developers already use Claude Code to work with individual pieces of physical equipment; for the next phase of MHS, we hope to expand the standard to cover more of the devices developers build on. Early adopters include Hugging Face, who are adding MHS support in LeRobot, their robotics library, and Raspberry Pi, who are enabling MHS integration across a number of their products following successful tests using their Camera MHS Driver.
我们还将利用研究预览版，与我们的发布合作伙伴共同开展更多安全评估，并加强对人工智能在现实物理世界中应用的保护措施。我们正在制定一份物理安全路线图，以进一步完善我们的防护政策和执行覆盖范围，降低技术遭滥用的风险。开源 MHS 时，我们将把研究预览版的发现作为安全部署该标准的指导内容一并发布。We will also use the research preview to build additional safety evaluations with our launch partners and strengthen protections for the use of AI in the physical world. We are developing a physical safety roadmap to further bolster our safeguards policy and enforcement coverage against the risk of misuse. When we open-source MHS, we will release findings from the research preview as part of our guidance for deploying the standard safely.
我们邀请各行业的利益相关者加入 MHS 研究预览版的候补名单。如果您有意参与，请在此提交申请。We’re inviting stakeholders across industries to join the waitlist for our research preview of MHS. If you’d like to participate, submit your interest here.
致谢Acknowledgments
MHS 最初是 Anthropic 有益部署团队的 Alek Kemeny 与 HHMI 珍利亚研究园区博士后科学家 Arco Bast 合作开展的项目。Bast 使用一套设备进行复杂的脑成像实验，其中集成了来自不同供应商的激光器、电动调焦器和专用相机，却没有通用接口。为了加快实验进度，他开发了一种共享内存字典，使这些仪器能够以内存速度彼此通信。Kemeny 和 Bast 携手将 AI 模型集成到这一接口中。MHS began as a collaboration between Alek Kemeny on Anthropic’s Beneficial Deployments team and Arco Bast, a postdoctoral scientist at HHMI Janelia Research Campus. Bast was running complex brain-imaging experiments on a rig that combined lasers, motorized focusers, and specialized cameras from different vendors with no common interface. To speed up his experiments, he developed a shared memory dictionary that enabled the instruments to communicate with one another at memory speed. Kemeny and Bast worked together to integrate AI models into that interface.
我们感谢迄今为止为这项工作作出贡献的所有人，其中包括但不限于 Aaron Boswell、Ben Arthur、Boaz Mohar、Gagan Bhat、Mark Kittisopikul、Nadine Yasser、Nick Purcell、Takashi Kawase 和 Virginie Ruetten。我们期待与行业合作伙伴携手推进 MHS，并很快与开源社区共同推动其发展。We thank everyone who has contributed to this work so far, including, but not limited to, Aaron Boswell, Ben Arthur, Boaz Mohar, Gagan Bhat, Mark Kittisopikul, Nadine Yasser, Nick Purcell, Takashi Kawase, and Virginie Ruetten. We look forward to moving MHS forward with our industry partners and, soon, with the open-source community.