PULSE
AI 认知方法 HOWTO重要度 52

50美元开发板复刻Meta Muse Charm

The Verge AI · 2026-10-31 · 原题《I built an AI Tamagotchi before Meta could》 · 原文约 6 分钟 · 阅读原文 ↗
50美元复刻 Muse Charm 核心:可自由编程 = 专用硬件的真正价值 起点 Waveshare 开发板 ESP32-S3 1.75C 约 50 美元 Meta 推荐套件 外观近似 Charm 默认固件局限 音频当转写而非指令 响应慢 · 无语音输出 静态 Jolly 头像 无法自动发现家居 缺少远程快门 Claude Code 逐项修补 对话历史页 ElevenLabs 语音 远程拍照 蓝牙低画质预览 养成小游戏 进一步扩展 多级饥饿/无聊/脏污 · 怀表 · 视频 隐私权衡 无编程经验 · 不信任代理 结论:可自由编程才是专用硬件的真正价值 设备放访客 Wi-Fi · 曾泄露评测者住址
作者用50美元的Waveshare开发板加Claude Code,复刻了Meta的AI挂件Muse Charm,并认为可自由编程才是专用硬件的真正价值。

做法与步骤

  1. 作者购买Waveshare ESP32-S3 1.75C开发板,这是Meta官方推荐的Muse Gadget开发套件之一,外观类似Muse Charm。
  2. 初始设置简单:连接电脑、指向Meta的GitHub、配对Muse手机应用,但设备最初把音频当转写而非指令,响应慢且无语音输出。
  3. Meta的默认固件功能有限:只有一个静态Jolly头像、不能自动发现智能家居设备、缺少远程快门按钮。
  4. 作者用Claude Code逐项修补:增加对话历史页、接入ElevenLabs语音、实现远程拍照和蓝牙低画质预览。
  5. 作者还让Claude添加了类似Tamagotchi的养成小游戏、多级饥饿/无聊/脏污状态,以及可用的怀表表盘和视频播放器。
  6. 作者无编程经验,不信任Meta或Muse代理的隐私安全(曾泄露评测者家庭住址),因此将设备放在访客Wi-Fi上。

对实践的启示

对AI应用开发者而言,专用硬件的价值不在于内置AI本身,而在于可自由编程以扩展手机做不到的功能;同时,隐私安全仍是采用第三方AI云服务时的关键顾虑。

作者承认的反方与局限

作者承认自己不懂代码,无法判断生成的代码质量,也不确定对有编程经验、愿意承担更大风险的人来说Muse Charm是否实用;且Meta服务器延迟仍存在。

原文摘引

The reason to have a dedicated piece of hardware is to do things you can’t do on the phone that’s already in your pocket, like coding the entire gadget to do whatever you want.
I want you to understand I have no coding experience, and so I have no idea if any of this code is good.
Nor do I trust Meta or its Muse agent with my email or my home network, particularly after hearing how it leaked one reviewer’s home address.
▸ 展开原文全文(22 段,抓取自 The Verge AI)

Mark Zuckerberg’s Meta made AI look so stinking cute by giving it a squishy little face — and this holiday season, he wants to sell you a Muse Charm so you can carry your jolly AI helper around like a Tamagotchi.

But I won’t be buying one, because we have Muse Charm at home. It cost just $50, and I’ve decided the learning experience was worth it.

[Media: https://www.tiktok.com/@verge/video/7702862550014168333]

My version doesn’t sport cameras or a 5G cellular radio, but it really talks to Muse and has cute avatars, too! It doubles as a pocket watch and a remote camera viewfinder, and it can (theoretically) control my smart home.

Or at least it can if you inject a lot of extra vibe code.

Weeks ago, I paid $50 to get a 1.75-inch touchscreen computer pendant drop-shipped from China — specifically the Waveshare ESP32-S3 1.75C. Not only does the push-to-talk AI devkit look a lot like the Muse Charm, but it’s officially sanctioned by Meta. It’s one of the company’s first suggestions if you want to build a “Muse Gadget,” a device that uses Meta’s open-source code and tokens to directly connect to its Muse AI cloud.

When the silver metal pocket watch arrived, it felt pretty useless to start. Setup was easy enough — I just plugged it into my PC and pointed Claude at Meta’s GitHub, then paired it to the Muse phone app. But even after I put Meta’s keys on the device, Muse originally thought I was sending it audio clips to transcribe rather than commands. After I cleared that up, Muse’s responses were still slow, and it didn’t answer me out loud. It was hard to tell what it was saying since it only showed a few words onscreen at a time, with no place to read full messages unless I whipped out my phone with its own Muse app.

Meta’s build also only came with a single Jolly avatar that mostly just sat there and looked cute, and it wouldn’t automatically discover smart home gadgets like Amazon Echo or Google Home devices do. (This gadget really didn’t do anything useful after my initial install.) And though Meta AI software engineers Anant Narayanan and Jeremy Payne include a neat sample app showing how Muse Gadgets can stream video from your phone camera, the lack of a remote shutter button made it not so useful for taking photos.

[Image: https://platform.theverge.com/wp-content/uploads/sites/2/2026/10/verge-sean-hollister-muse-gadget-331A2570-01-2.jpg?quality=90&strip=all]

But a few sessions of Claude Code filled in almost all those holes. All I had to do was plug the Waveshare back into my PC, then ask Claude to reprogram each thing I wanted.

When I complained to Claude that I couldn’t properly read or hear Muse’s replies to my asks, issues that others have mentioned as well, Claude built a conversation history page so I can swipe right to read what it said, and I plugged in a British AI voice from ElevenLabs that speaks its answers out loud. (The voice was the least soul-sucking of the ones in ElevenLabs’ free tier, my wife and I agree, even if it doesn’t match the Muse avatars’ cuddly vibe at all.)

[Image: https://platform.theverge.com/wp-content/uploads/sites/2/2026/10/verge-sean-hollister-muse-gadget-331A2576-01.jpg?quality=90&strip=all]

Thanks to Claude, I can now press a button to make my phone take a picture from across the room with a high-quality live preview, and my phone’s front-facing camera no longer displays upside down. Claude made fairly short work of adding a low-quality camera preview over Bluetooth, too, so I don’t need to be on home Wi-Fi to get photos from creative angles.

[Image: https://platform.theverge.com/wp-content/uploads/sites/2/2026/10/DJI_20261030134230_0857_D-1.jpg?quality=90&strip=all]

[Image: https://platform.theverge.com/wp-content/uploads/sites/2/2026/10/Muse_20261030_134155.jpg?quality=90&strip=all]

I asked Claude to make a whole batch of different avatars like the ones Meta showed off during Meta Connect, and to add a Tamagotchi-like minigame where they need food, play, sleep, and a bath. When the game seemed too simple to capture any attention, I had it add four different levels of hunger, boredom, and dirt. I decided treats should make a crunchy mess and get avatars dirtier when they eat them, and that too much play should tire out a pet. My wish was Claude’s command.

When I noticed I was accidentally letting go of the push-to-talk button too soon and making Muse choke on almost-empty audio, vibe coding fixed it minutes later by sending only audio over one second in length. The only obvious lag I’m seeing now is from Meta’s own servers — sometimes they’re responsive, sometimes they lag quite a bit.

[Image: https://platform.theverge.com/wp-content/uploads/sites/2/2026/10/verge-sean-hollister-muse-gadget-331A2577-01.jpg?quality=90&strip=all]

It was so easy to let Claude reprogram the pendant that I asked it to build a few features specifically for this video in this story, including a working pocket watch face with three hands that actually tells the time. (That took it 15 minutes; now, when I say the hardware looks like a pocket watch, you can see what I mean!) It even found, downloaded, trimmed, and loaded video clips of Zuck introducing the Muse Charm and installed a video player so I could play those clips on the Waveshare.

I want you to understand I have no coding experience, and so I have no idea if any of this code is good. It might be fatally flawed. Nor do I trust Meta or its Muse agent with my email or my home network, particularly after hearing how it leaked one reviewer’s home address. (I put it on guest Wi-Fi from the get-go as a precaution.)

That means I don’t really know how useful a Muse Charm may or may not be for those who do know how to code and are willing to take a bigger leap of faith. But after nearly dropping a bulky little silver pendant a couple of times, one with no more Muse functionality than my phone (and quite a bit less without additional code), I’m thinking Muse itself isn’t the reason to buy a dedicated compute pocket watch.

The reason to have a dedicated piece of hardware is to do things you can’t do on the phone that’s already in your pocket, like coding the entire gadget to do whatever you want. Which makes me wonder: Will the actual Muse Charm be this freely programmable, or would the kind of people who’d buy one be better off with a development kit? I guess we’ll see when it ships.