samzong

🌟 Dropped out of high school, but never stopped learning. My career has been a series of actively choosing the “harder path”: - Started with self-taught programming and became a tech evangelist and training instructor - Built a full-channel customer service product from 0 to 1, bootstrapped it to profitability, and successfully got acquired - Developed intelligent e-commerce customer service robots covering all platforms except Taobao (including cross-border) - Pivoted into containerization, and now fully focused on large model training and inference acceleration Continuous learning is my core foundation. My obsession and passion for technology is the only driving force behind every transformation. I’m not a traditional Product Manager — instead, I bring a strong Founder mindset: business-savvy, SaaS builder with deep user empathy, always hands-on in product definition and delivery. I love open source — my GitHub is my real resume. Currently Committer of vllm-project/semantic-router Contributor to Kueue / Karmada / Kubernetes / HAMi and more What I’ve always been seeking are creative, high-challenge projects and people. Because what truly sets my heart on fire is: The hope to make a real difference in this world. If that resonates with you, feel free to DM me directly.

Your coding workflows don’t have to stay inside your IDE. Mosoo moves them to the cloud as reusable agents. In this demo, one avatar becomes a full Codex Pet pack—just copy the “Instruction for LLM” into Codex, and it integrates Mosoo with your product backend automatically. 👇

@mosooagent nice job!

@XchenEvan @0xblacklight gmc task is base om tmux session control

@0xblacklight Codex is smart

giving an agent tools to manage background bash processes is popular but wrong force your agent to use tmux - it is a much-better-shaped harness for managing processes and stdin and stdout and sending signals and stuff than anything you're gonna come up with

Something I have been thinking about: in the past, the best engineers I knew spent a lot of time automating their work in various ways. Better vim/emacs automations, writing lint rules to catch repeat code issues, building up a suite of e2e tests so they don't need to smoke test the app manually. These kinds of things were the highest leverage activities an engineer could do, because it multiplied their own output, which in turn meant they could build more things. I think many of these automations have become even more important now. This is true for a number of reasons. First, infra and DevX automation speeds you up. And if you are running an army of agents, each of those agents will be sped up also. More automation == more output per unit of time. Second, moving things to code improves efficiency. Your agent could fix an issue every time it sees that issue happen, but that uses tokens and might miss cases. If Claude instead writes a lint rule, CI step, or routine, that class of issue can be fully automated forever. This is really what people are talking about when they talk about loops -- it's about automating entire types of busywork rather than solving them one off. This isn't a new idea at all. Engineers have been doing this for a long time! Third and most importantly, automation makes it possible for others to contribute to the codebase more easily. Increasingly what I am seeing is engineers are contributing to codebases on day one because Claude can navigate the codebase for them, and that non-engineers are able to contribute to a codebase as effectively as engineers can. What gets in the way of both of these is domain knowledge that lives in peoples' heads rather than in automation -- the stuff you used to have to learn when ramping up. What has changed thanks to agents is the domain knowledge that can be encoded as infrastructure is no longer limited to what is expressible in lint rules and types and tests; it can now capture nearly all domain knowledge, encoded as code comments and skills and CLAUDE.md rules and memories. If I put up a PR for an iOS codebase I don't know and a code reviewer rejects it because it doesn't use the right framework, or if a designer builds a new feature and it gets rejected because it doesn't follow the right architectural patterns, these are failures of automation. Every team should be writing the CLAUDE.md's, REVIEW.md's, skills, and docs that enable agents to productively work in their codebase with zero additional context from the prompter. This sounds crazy, and at the same time is a natural extension of the stuff engineers have always done: automate, and encode domain knowledge as infrastructure. As the model gets smarter and as the harness matures, this task becomes easier. In the meantime, it is on every team to look for ways to convert their domain knowledge to infra so that Claude can write code better, so that code review catches issues automatically, and so the next person working on your codebase can contribute more easily.

@wey_gu 恭喜大佬

So honored to continue being invited as a #MicrosoftMVP this year 🥰🫡

@aiandcloud @MVPAward 恭喜大佬

续任成功！ 😁 Thank you! @MVPAward #mvpbuzz

@xuanwo @aiandcloud 我记得当年锤子好像买了个t.tt

@aiandcloud 再买个t.it 吧

telegram 的事情解决了，不仅 t.me 恢复了，还买了 t.you 😂

@XchenEvan 在使用 5.6 之后我才开始认真思考这个问题，经过一天的体验，我把全局 AGENTS.md 砍掉了2/3 的约束。

在 5.6 和 Fable 发布之后，每个人都应该用 Checkup 的 slash command 去检查一下你开发环境当中没有被使用的 MCP 或 Skill，减少它们的上下文占用。 还有一些过分的安全带

And I got review this code is staff-grade / production-ready

The crazy is I used GPT-5.6 Sol in Codex, Push my Rust AI gateway to its real latency floor and yeah it cooked: - 1750 concurrent SSE streams stable under 1ms - 50k events/s at ~0.6ms p99 keep default <1ms gate green, and only keep TCP_NODELAY + optional spinner slowkey that why I switched. this is the agentic coding loop I actually want. @ChatGPTapp @thsottiaux

Gmail 积压了很多邮件，现在睡觉，明天处理

深度沉浸一周打造一个产品，刚刚我发布了 v0.0.1-beta1 ，其中有一个我很喜欢的模块。 期待和大家见面的一天。

This is why I’m staying use Raycast @raycast

MAXXXXING !

@turingou 我正在构建 @mosooagent 这也是我们想解决的问题

想象一下，现在构建一个新的 AI app： 1. 核心是围绕对话框的 agent 2. 对话框的 agent 需要支持所有业务 API 的调用 3. 对话框的 agent 需要广泛调用不同的 tools（连接器） 4. 对话框的 agent 还需要在其他的聊天框中可用（比如 codex 或者 claude code）意味着你需要把业务包装成 MCP/Skill 5. 对话框的 agent 需要生成符合我们产品风格的 UI，并且还需要在其他聊天框中也生成类似的 UI。 6. 毫无疑问，这个以对话框 agent 为核心的产品还需要跨平台可用。 你能想象到完成上述功能最好的框架是什么？如果你只是把这些文字复制给 coding agent，多半过了一段时间之后，产品功能变得复杂后就很难维护了。

@XchenEvan @Jiaxi_Cui 应该是下午吧

@Jiaxi_Cui 会在今天吗

出门吃饭 散步 健身，写个文章，然后等待 gpt 5.6 的到来

Good morning. Agent work has a threshold. Below it: keep it simple. Above it: you need a lifecycle. We call it Mosoo. mosoo.ai/blog/the-journ…

@frankekn haha 我老板会看到，我有很认真在工作哦，只不过并发比较高

@samzong_ 你有沒有認真上班

MacMusicPlayer: A clean, lightweight music player for macOS. producthunt.com/products/macmu…