跳到正文

Anthropic 测试 Claude 设计真实电子硬件:三款设备原型一次成型

Testing Claude on real-world electronics design

摘要

Anthropic 与电路板设计公司 Diode Computers 合作,让 Claude Fable 5.2 仅凭简单提示词完成扬声器电话、语音助手中枢和掌上电子宠物三款设备的设计,包括规格、原理图、PCB 布局布线、3D 打印外壳、固件和物料清单,Diode 按设计文件直接制造并组装出可正常工作的原型。

摘要由模型根据原文撰写,以原文为准。

入选理由

Anthropic 与 Diode 用 Claude Fable 5.2 从提示词走到可运行硬件原型,展示了模型在电路板布局与制造约束上的进展边界。

正文 · 双语对照

中文 · AI 翻译原文

大约一年前,我们开始测试 Claude 设计基础电子电路的能力。我们与 Diode Computers 合作,1这家公司设计和制造电路板,我们用它来训练 Claude 完成简单任务——例如,阅读芯片的数据手册,并弄清楚芯片运行需要哪些部件。当时我们试验的模型无法可靠地布局电路板;它们也难以设计出能够相互配合的组件。现在,Claude 能够从头到尾设计和制作电子硬件的原型。

A little over a year ago, we began testing how well Claude could design basic electronic circuits. We collaborated with Diode Computers,1 a company that designs and manufactures circuit boards, to train Claude on simple tasks—for example, on reading a chip’s datasheet and working out which parts a chip needs in order to run. The models we experimented with back then couldn’t reliably lay out a circuit board; they also struggled to design components that fit together. Now, Claude can both design and prototype electronic hardware from start to finish.

设计电子设备需要处理许多复杂的步骤和实际约束。你不仅要设计和仿真电路板,还要推理电路板的物理布局及其行为方式,对机械组件建模,并编写固件——同时还要跟踪哪些部件容易获得,以及工厂具备什么样的生产能力。

Engineering an electronic device requires working through many complex steps and practical constraints. You have to not only design and simulate a circuit board, but also reason about the board’s physical layout and how it will behave, model the mechanical components, and write firmware—all while keeping track of which parts are readily available and what a factory is set up to build.

为了了解更新的 Claude 模型在这一领域的进步,我们再次与 Diode 合作,这次让 Claude Fable 5.2 设计三款电子设备:免提扬声器、语音助手中枢和手持虚拟宠物。只需极少的提示,Claude 就能运用几何推理来布局每块电路板,预判制造约束,并确保其设计能在这些约束下正常工作。它修改了自己的工作,在计算机辅助设计(CAD)软件中为设计建模,最后指导人类工程师制作出无需对电路做任何修复就能工作的原型。

To see how newer Claude models have improved in this area, we collaborated with Diode again, this time asking Claude Fable 5.2 to design three electronic devices: a speakerphone, a voice-assistant hub, and a handheld virtual pet. With minimal prompting, Claude was able to use geometric reasoning to lay out each circuit board, anticipate manufacturing constraints, and make sure its designs would work within them. It revised its own work, modeled its designs in computer-aided design (CAD) software, and, finally, directed human engineers to build prototypes that worked without any fixes to their circuitry.

对于每个设计,我们首先给 Claude 一个简单的提示,概述要构建的设备类型及其主要硬件要求。例如,免提扬声器的提示要求“一个通过 USB-C 插入电脑的圆盘形设备,包含麦克风和扬声器,支持带 PCB 天线的蓝牙。”Claude 随后编写了设备规格,绘制了清晰的视觉原理图,选择了组件在印刷电路板(PCB)上的放置位置,布线了它们之间的铜连接,设计了可 3D 打印的外壳,编写了固件,并准备了物料清单。Diode 在 Claude 的指导下组装了电路板并运行了固件。最终结果是一个免提扬声器原型,在使用数周后仍然正常工作。

For each design, we began by giving Claude a simple prompt that outlined what kind of device to build and its main hardware requirements. The prompt for the speakerphone, for example, asked for “a puck that plugs into a computer over USB-C and includes microphones and a speaker, supporting Bluetooth with a PCB antenna.” Claude proceeded to write the device’s specifications, draw clean visual schematics, choose where to place the components on a printed circuit board (PCB), route the copper connections between them, design a 3D-printable enclosure, code the firmware, and prepare a parts list. Diode assembled the circuit boards and ran the firmware, under Claude’s direction. The final result was a prototype of a speakerphone that still works after weeks of use.

Claude 经历了类似的过程来构建语音助手中枢和虚拟宠物,两者也仍然处于良好的工作状态。由于这些设备是早期原型,我们尚不知道它们在持续使用下的表现如何,也不知道它们能否通过商业认证。

Claude went through a similar process to build the voice-assistant hub and the virtual pet, and both are also still in good working order. Because the devices are early prototypes, we don’t yet know how they’ll hold up with continued use or whether they would pass commercial certifications.

通过几何问题进行推理

Reasoning through geometric problems

Fable 5.2 与我们早期测试中使用的模型之间最实质性的差异,在于 Fable 5.2 对复杂几何问题的推理能力,例如在电路板上放置组件的位置,以及如何布线它们之间的铜连接。

The most substantial difference between Fable 5.2 and the models we used in our earlier tests was in how well Fable 5.2 reasoned through complex geometric problems, such as where to place components on a circuit board and how to route the copper connections between them.

早期的模型难以决定如何安排基本元件——例如,把支撑部件放得离它们所服务的芯片太远,或者连接器方向错误。相比之下,Fable 5.2 生成的布局更紧凑、更实用。它优先布线最重要的连接:那些传输高速信号或大电流、或对噪声敏感的连接。例如,对于语音助手中枢,Claude 首先布线 USB 和以太网连接,这些连接通过成对的走线——电路板上的细铜条——传输信号。它一次布线一对走线,保持每对中两条走线长度相同且间距正确。它还添加了调谐图案——使走线变长以便信号同时到达的小锯齿形——并安排电源的各个部分以提高效率。

Earlier models had struggled to decide how to arrange basic components—placing supporting parts too far from the chips they served, for example, or orienting connectors incorrectly. Fable 5.2, by contrast, produced more compact, practical layouts. It routed the most important connections first: those that carry high-speed signals or high currents, or that are sensitive to noise. For example, for the voice-assistant hub, Claude started by routing the USB and Ethernet connections, which transmit signals along pairs of tracks—thin strips of copper on the board. It routed one pair of tracks at a time, keeping the two tracks in each pair the same length and correctly spaced. It also added tuning patterns—small zigzags that lengthen a track so that signals arrive at the same time—and arranged the parts of the power supply to make it more efficient.

为了展示 Fable 5.2 在电路板布局方面比早期模型好多少,我们让 Diode 运行 PCB Gym——一个内部基准测试,根据模型在移除布局的电路板设计上放置元件和重新布线连接的能力来评分。Fable 5.2 在该基准测试中得分 69%,而 Fable 5 为 25%(图 2)。它在 BenchCAD 2.1 上也表现更好,这是一个公开基准测试,测试模型能否根据工程图纸和渲染图像重建 3D 零件、装配体和电路板。Fable 5.2 得分 83.5%,几乎是其前身 Claude Fable 5.1 得分的两倍。

To demonstrate how much better Fable 5.2 is than earlier models at laying out circuit boards, we asked Diode to run PCB Gym—an internal benchmark that scores models based on how well they can place components and reroute connections on board designs whose layouts have been removed. Fable 5.2 scored 69% on the benchmark, compared with 25% for Fable 5 (Figure 2). It also performed better on BenchCAD 2.1, a public benchmark that tests whether models can rebuild 3D parts, assemblies, and circuit boards from engineering drawings and rendered images. Fable 5.2 scored 83.5%, nearly double the score of its predecessor, Claude Fable 5.1.

修改设计

Revising designs

早期模型在设计 PCB 布局时很少修改自己的工作,即使很明显它们的放置选择永远无法完成连接布线。在过去一年里,Diode 用这些模型设计了许多电路板,完成度达到 95% 但仍不可用。

Earlier models rarely revised their own work when designing PCB layouts, even when it became clear that their placement choices would never let them finish routing the connections. Over the past year, Diode designed many boards with these models that were 95% complete but still unusable.

当 Claude 注意到它的某个设计不奏效时,它会主动改变方向,无需提示。例如,在设计免提电话的电路板(有四层铜)时,它把信号重新分配到两个芯片的不同引脚上。这使得免提电话触摸感应控件下方的走线可以保持在单层上而不会相互交叉。后来,当电路板背面变得过于拥挤时,Claude 交换了可互换引脚上的信号,并重新布局了电路板的整个角落,而不是用额外的层间跳线来修补问题。

When Claude noticed one of its designs wasn’t working, it would change course without being prompted to do so. For instance, when designing the speakerphone’s circuit board, which has four layers of copper, it reassigned signals to different pins on two of the chips. This allowed the tracks under the speakerphone’s touch-sensitive controls to stay on a single layer without crossing one another. Later, when the back of the board became too crowded, Claude swapped the signals on interchangeable pins and laid out a whole corner of the board again, rather than patching the problem with extra jumps between layers.

在语音助手中枢的设计文件中放置走线时,Claude 注意到铜连接“变得太乱,无法目视追踪”,并推理道:“我应该把这些走线[轨道]撕掉,重新开始。”它随后删除并重新布线铜连接数十次,直到找到可行的排列。

And when placing tracks in its design file for the voice-assistant hub, Claude noticed that the copper connections were “getting too tangled to trace visually” and reasoned, “I should just rip these traces [tracks] and start fresh.” It proceeded to delete and reroute copper connections dozens of times until it found an arrangement that worked.

使用软件和文档

Using software and documentation

当某个设备的设计决策取决于特定零件的细节时,Claude 经常查阅该零件的数据表——制造商发布的技术文档。当被问及手持宠物在没有电池的情况下能否工作时,Claude 阅读了充电器的数据表,并回答说它可以靠 USB 供电运行,但预测充电指示灯会闪烁,因为充电器会不断给替代电池的小电容充电。2

When a design decision for one of the devices depended on the details of a particular part, Claude often checked that part’s datasheet—a technical document published by the manufacturer. When asked whether the handheld pet would work without a battery, Claude read the charger’s datasheet and answered that it would run on USB power but predicted that the charging light would flicker, because the charger keeps recharging a small capacitor in the battery’s place.2

为了在语音助手中枢上布线,Claude 从 Diode 提供的设计软件入手,该软件让它能够运行 KiCad 内置的布线器(一种用于绘制走线的工具),KiCad 是一款广泛使用的电路板设计程序。KiCad 的布线器一次只能在 Claude 选定的两点之间绘制一条走线。但该中枢有从 100 针连接器引出的长走线,Claude 判断逐条布线将需要过多的逐步指导。

To route the connections on the voice-assistant hub, Claude started with the design software Diode provided, which let it run the router (a tool for drawing tracks) built into KiCad, a widely used circuit board design program. KiCad’s router drew one track at a time between two points Claude chose. But the hub had long tracks running from a 100-pin connector, and Claude judged that routing these one by one would take too much step-by-step guidance.

于是,Claude 编写了自己的布线器:一种将电路板划分为网格并搜索网格、为每条走线找到清晰路径的算法。在大约半小时内,Claude 就有了一个布线器,可以大约一秒布好每条长走线。当 Claude 发现一条音频时钟走线离以太网走线太近时,它调整了布线器,在敏感走线周围留出更多空间。

Instead, Claude wrote its own router: an algorithm that divides the board into a grid and searches it to find a clear path for each track. Within about half an hour, Claude had a router that could lay each long track in roughly a second. When Claude spotted an audio clock track running too close to the Ethernet tracks, it adjusted the router to leave more room around sensitive tracks.

跟踪约束条件与下游影响

Keeping track of constraints and downstream effects

设计中某一部分做出的决策会产生下游影响,Claude 对此进行了跟踪。在设计每个设备的外壳时,它编写代码来检查电路板的 3D 模型能否装入外壳内而不会发生任何元件碰撞。例如,它发现扬声器电话的电路板无法直接向下放入外壳,因为静音开关会撞到后壁。Claude 算出,如果在安装时倾斜约 25 度,电路板就能装进去。它在 3D 模型中测试了这一点,并将该步骤加入了装配说明。

Decisions made in one part of a design have downstream effects, which Claude kept track of. While designing each device’s enclosure, it wrote code to check that a 3D model of the circuit board would fit inside the enclosure without any components colliding. For example, it found that the speakerphone’s board couldn’t be lowered straight into the enclosure, because the mute switch would hit the back wall. Claude worked out that the board would fit if it was tilted by about 25 degrees during installation. It tested this in its 3D model and added the step to the assembly instructions.

在设计语音助手中枢的外壳时,Claude 计算出 25 毫米长的麦克风端口——让声音到达麦克风的开口——会在接近 3.4 kHz 处产生共振。它推断,这“正好位于语音频段内”,“虽不理想,但对语音助手用途仍可使用。更好的方案是采用后部较高、前部阶梯式降低的楔形外壳。”楔形设计将端口缩短至约 10 毫米,从而将共振频率提高到约 8.9 kHz,正好处于语音所用频段的边缘。Claude 还为扬声器电话编写了固件,在音频变响时调暗其 LED 灯环,以使设备保持在 Claude 为电路板设计的电流限制之内。

When designing the enclosure for the voice-assistant hub, Claude calculated that a 25 mm-long microphone port—the opening that lets sound reach the microphone—would resonate near 3.4 kHz. That is “right in the voice band,” it reasoned, “which is not ideal though still usable for voice assistant purposes. A better approach is a wedge-shaped enclosure that’s tall at the rear and steps down low at the front.” The wedge shape shortened the ports to about 10 mm, which raised the resonant frequency to about 8.9 kHz, at the very edge of the range used for speech. Claude also wrote firmware for the speakerphone that dims its ring of LED lights as the audio becomes louder, to keep the device under the electrical current limit Claude had designed into the board.

面向真实世界制造的设计

Designing for real-world manufacturing

在电子设计中,工程师必须在现实世界的约束内工作。也就是说,他们必须确保工厂确实能够制造出他们想要构建的东西。他们通过运行两类检查来做到这一点:可制造性设计(DFM)检查,将电路板的几何形状与工厂的制造限制进行比较;以及采购检查,确认其分销商有零件库存。

In electronics design, engineers have to work within the constraints of the real world. That is, they have to make sure a factory can actually make the thing they want to build. They do this by running two kinds of checks: design-for-manufacturing (DFM) checks, which compare a circuit board’s geometry with the factory’s manufacturing limits, and sourcing checks, which confirm that their distributors have the parts in stock.

Claude 自己运行了这些检查,并将结果分为需要修复的问题和可以忽略的标记。它对语音助手中枢的检查标记出六处阻焊层(电路板上的保护涂层)薄片过薄而无法制造。Claude 通过加宽阻焊层中的开口来修复它们,而没有移动任何零件。检查还将两个地(电流的共享回流路径)之间的连接标记为错误,因为自动检查器没有识别出该连接是有意为之。Claude 正确地推断出它不会影响性能,并忽略了该标记。

Claude ran these checks itself and sorted the results into problems that needed fixing and flags it could ignore. Its checks for the voice-assistant hub flagged six slivers of solder mask (the protective coating on a circuit board) as too thin to manufacture. Claude fixed them by widening the openings in the solder mask, without moving any parts. The checks also flagged a connection between two grounds (shared return paths for electrical current) as an error, because the automated checker hadn’t recognized that the connection was deliberate. Claude correctly reasoned that it wouldn’t affect performance and ignored the flag.

Diode 直接依据 Claude 的设计文件制造了全部三块电路板,没有就调整进行任何来回沟通。工厂和工程师通常需要经历多轮制造变更,而 Diode 团队告诉我们,他们惊讶地发现使用 Claude 时无需这样做。

Diode manufactured all three boards directly from Claude’s design files, without any back-and-forth over adjustments. Factories and engineers often have to work through multiple rounds of manufacturing changes, and the Diode team told us they were surprised that they didn’t have to do this with Claude.

局限性与后续步骤

Limitations and next steps

这三款设备都仍是原型:它们尚未经过电气验证、天线调谐、热测试或认证,也不是为量产而设计的。由于 Claude 并未连接测试设备或制造和组装电路板的机器,Diode 的工程师不得不亲手搭建并测试这些原型。即便如此,在过去一年里,Claude 在元件布局与布线决策的推理方面已有大幅提升,现在它能在极少人工指导下设计电子产品,并帮助人们搭建原型。其他模型也在这一领域取得进展:OpenAI 最近撰文介绍了使用其模型设计一款手持设备的情况。这类工作有望帮助工程师更快地构建和测试新的硬件设计。

All three of these devices are still prototypes: they haven’t been through electrical validation, antenna tuning, thermal testing, or certification, and they weren’t designed for mass production. Since Claude wasn’t connected to test equipment or to the machines that make and assemble circuit boards, engineers at Diode had to physically build and test the prototypes. Even so, over the past year, Claude has improved substantially at reasoning through decisions about component placement and routing, and it can now design electronics with minimal human guidance and help people build the prototypes. Other models are making progress here, too: OpenAI recently wrote about using its models to design a handheld device. Work like this could help engineers build and test new hardware designs faster.

接下来,我们计划研究 Claude 能否设计更密集、更快速、更复杂的电路板,在仿真中对其进行检查,并从成品设备上采集的测量数据中学习。

Next, we plan to investigate whether Claude can design denser, faster, and more complex boards, check them in simulation, and learn from measurements taken on the finished devices.



注意转载授权 · 阅读原文。中文正文为 AI 翻译,请以原文为准。

注意转载授权 · 阅读原文

来源:Anthropic Research · anthropic.com

引用原文

Anthropic Research. Testing Claude on real-world electronics design[EB/OL]. (2026-11-09)[访问日期]. https://www.anthropic.com/research/claude-electronics-design.