晓

Co-founder of @midscene_ai. The maintainers of Module Federation.

[晓 @codingzx]

从工程角度提供了各种优化 Agent 的不确定性思路，从而提升产品体验。赞！

[艾略特 @elliotchen100]

https://t.co/tbFOumjC6r

[晓 @codingzx]

@chenchengpro 学习了，有帮助

[heal @2hea1]

MCP Apps lets AI hosts render interactive UI in conversations. But most solutions bundle UI into the MCP Server — rebuild + redeploy every time anything changes.

We built @module-federation/mcp-apps: point a JSON at your existing MF remotes, and your components show up in Claude. Zero separate builds.

🔗 GitHub: https://t.co/pRJav4VmYg
⭐ Star the repo if this looks useful — issues and PRs very welcome.

[晓 @codingzx]

@Soon_Iter Agent 下一个大的技术突破点和技术方向 memory

[晓 @codingzx]

@rccoders 这么牛批，我的特斯拉全手动驾驶

[晓 @codingzx]

@geekplux vibe coding 之后要保证测试的输入和输出是能够清晰看懂的

[Midscene @midscene_ai]

🎉 We've surpassed 10,000 stars! A huge thank you to our community!

Now, we're launching Midscene v0.27! 🚀

Building on 0.26's Rslib integration, 0.27 makes a major refactor, making it incredibly easy to add new devices & AI operations. Now is the perfect time to contribute!

[Midscene @midscene_ai]

Midscene 0.24 is released

1. 🚀 MCP for Android Automation
2. 🌐 Web Optimization
3. 🔧 Development Experience

BTW, The new report now supports viewing the AI token consumption(Pic 2)

#AI #Automation #Playwright #Puppeteer #BrowserUse #VibeCoding #AIAutomation #Midscene

[leeight @leeight]

We're hiring a Web Architect to shape the future of https://t.co/67IXEgXsyC.

If you're passionate about large-scale systems, performance, and elegant architecture (React / TS / Node), we want to hear from you.

Let’s build the best web platform, together.

DM is open.

cc @Huxpro @ScriptedAlchemy @octogonz_ , please RT.

[晓 @codingzx]

@atian25 LLM 产品，快是唯一的护城河😁

[晓 @codingzx]

赞同，人类是存在“物质幸福适应感的”动物，在住到更大的房子、获得更好的薪水后，幸福感会随着时间的递增而逐渐递减，而后回到达到和物质提升前略微提升的水平且达到稳定状态，能够找到自我实现的事业和自由是长久的追求

[晓 @codingzx]

@jait_chen 感觉随着传统互联网应用的资本热潮过去，开始把更多的资源投入在 ai 上，这些原来的开源社区非盈利性的平台，问题会越来越多，除非找到新的盈利方式，才能够投入资源来保证平台的可用性，降低这种事件出现的可能性并快速响应

[晓 @codingzx]

新版报告超酷的，执行任务每一步花了多少 token， GUI 自行回放动画也更精细了！

[Midscene @midscene_ai]

Midscene 0.23 is released

1. 📊 New Report Style
2. ⚙️ YAML Script Ability Enhancement

Changelog: https://t.co/caMaqWEq7Q
Star the GitHub for timely updates: https://t.co/sgv1lwTxDO

#AI #Automation #Playwright #Puppeteer #BrowserUse #VibeCoding #AIAutomation #Midscene

[晓 @codingzx]

Qwen 团队太赞了，有效打破 claude 模型在 code 领域的垄断地位，开发者狂喜😍

[Qwen @Alibaba_Qwen]

>>> Qwen3-Coder is here! ✅

We’re releasing Qwen3-Coder-480B-A35B-Instruct, our most powerful open agentic code model to date. This 480B-parameter Mixture-of-Experts model (35B active) natively supports 256K context and scales to 1M context with extrapolation. It achieves top-tier performance across multiple agentic coding benchmarks among open models, including SWE-bench-Verified!!! 🚀

Alongside the model, we're also open-sourcing a command-line tool for agentic coding: Qwen Code. Forked from Gemini Code, it includes custom prompts and function call protocols to fully unlock Qwen3-Coder’s capabilities. Qwen3-Coder works seamlessly with the community’s best developer tools. As a foundation model, we hope it can be used anywhere across the digital world — Agentic Coding in the World!

💬 Chat: https://t.co/V7RmqMaVNZ
📚 Blog: https://t.co/syL1hsSGKq
🤗 Model: https://t.co/1LWwUKMrBN
🤖 Qwen Code: https://t.co/qqwj5nAO3Z

[晓 @codingzx]

@Soon_Iter 现在一些业务团队已经开始把 infra oncall 当成新人培训的一个地方了🙃

[辛宝Otto-Web Worker Podcast @xinbao965]

新一期节目来啦，欢迎收听，鼓励在小宇宙上互动，你的互动对我有很大帮助❤️ https://t.co/CmL8pKoJ2v

[晓 @codingzx]

习惯用 ts、tsx 开发后，改用 js、jsx 和 vibe coding，感觉开发效率提升了很多。相比之下，ts 的类型限制有时会影响模型效率，而用 js、jsx 开发更灵活顺畅。

[晓 @codingzx]

支棱起来了，参数太大了不然自己部署个玩玩

[Kimi.ai @Kimi_Moonshot]

🚀 Hello, Kimi K2! Open-Source Agentic Model!
🔹 1T total / 32B active MoE model
🔹 SOTA on SWE Bench Verified, Tau2 & AceBench among open models
🔹Strong in coding and agentic tasks
🐤 Multimodal & thought-mode not supported for now

With Kimi K2, advanced agentic intelligence is more open and accessible than ever. We can't wait to see what you build!

🔌 API is here: https://t.co/EOZkbOwCN4
- $0.15 / million input tokens (cache hit)
- $0.60 / million input tokens (cache miss)
- $2.50 / million output tokens

🔗 Tech blog: https://t.co/2RP7U3iakZ
🔗 Weights & code: https://t.co/4ukcXB0iP6
🔗 Github: https://t.co/B2bA4SfXBl
Try it now at https://t.co/85jA71X9gw or via API!

[晓 @codingzx]

@_ulivz @agent_tars So cool!

[晓 @codingzx]

那如何避免掉队？

保持好奇： 把 LLM 当成自己能力的延伸，而不是对手。
培养共情： 懂产品、懂用户，比任何时候都重要。
强化工程： 你的架构设计、质量控制、系统整合能力，现在是王牌。

[晓 @codingzx]

别信那些贩卖焦虑的，程序员不会被 AI 替代。恰恰相反，我们将和 LLM 一起“吞噬世界”。

这是一场软件革命，核心是从“指令驱动”变为“意图驱动”。我们不是被淘汰者，而是新范式的定义者。