在台灣做軟體工程十多年，帶過團隊。寫 AI 時代的工程系統與延續性問題。
Taiwan
Joined April 2008
- Tweets4.8K
- Following493
- Followers644
- Likes3.7K
AWS Community Day 2026 辦在實踐大學，總是很愛大學的建築與校園設計有大學的味道。雖然最近都在用 Google Cloud、給 AI 操作 gcloud 指令，還是來感受、呼吸一下熟悉的氣圍與 infra，見識一下最近 AWS 的發展
可以看到 AI 不只是讓工程師的產出增加倍，而是整個工作的分工、流程，甚至哪些事情值得做，都在重新定義。
在 AI 愈快 one-shot 完成的年代，決定要做什麼、如何驗證，以及承擔的後果，也都更快實現了。
#AWSCommunityDay #AIAgents #SoftwareEngineering
Haowen Huang 分享了產業到 2030 Agent Economy Functions Like a Neural Network。
2026 三月前與之後的不同、沒有 10x 也有 5~6 倍的績效，整個工作流的改變。
Fox 講到一人公司配 AI 上架短影片到各平台，人仍需要嘗試不斷迭代與修正。
也都提到文藝復興與工業革命 💭
Keith Yang retweeted
Ubuntu 26.10 #StonkingStingray is now available.
Read our announcement for more details: ubuntu.com/blog/canonical-re…
#Ubuntu #Linux #OpenSource
感覺似曾相識地，最近參加了 Omarchy Taipei 初次聚會。簡單三個小心得：
一．有人一起玩真好。更好的是有人辦社群聚會。
二．We can fix everything. It's just that so many things needed to be fixed.
三．參加活動前升到 4.0.6 後炸了要重灌，真是不意外。
例如請 AI 從系統移除 Hey、Basecamp。我也燒了一些 Fable 與 Sol token 來讓 xdg-desktop-portal-hyprland 支援 remote-desktop 讓 Deskflow 能操作 Omarchy 的桌面，但要讓 PR 合進 main 就不是那麼容易了。
Keith Yang retweeted
皆様に、今夜に対応して頂きたい大至急のお願いです。
多くのウェブサイトで使用されているPHPに関し、PHPのセキュリティチームが、重大な２件の脆弱性に関する注意喚起を行っています。
公開しているウェブサイトでPHPを使用しているか確認し、今夜、10月21日午後11時（日本時間）に公開される修正パッチについて、可及的速やかに適用できるよう準備をお願いします。
修正パッチを速やかに適用することが困難な場合は、例えばウェブサイト等を一時的に停止させることも、リスクを低減させるための有効策の一つと考えられます。
国家サイバー統括室のXアカウントでも関係する情報を発信していますので、そちらも参考にして下さい。
国家サイバー統括室(注意・警戒情報)（@cyber_forecast） / X
Keith Yang retweeted
🚀 November scisprint Taipei is coming!
Got unfinished tasks or tech you want to explore further? Let's pick up where we left off! Continue contributing to sciwork's open-source projects or bring your own side project.
Newcomers are welcome too! See you at scisprint Taipei.
Keith Yang retweeted
OpenBSD 8.0 is out now! See what's new: openbsd.org/80.html
今年只參加到 PyCon Taiwan 2026 第二天，但仍然收穫滿滿。
Max Lai 分享醫院導入 AI Coding 與團隊轉型的故事，很多台灣公司熟悉的人情世故，都很有共鳴。
Panel 裡也有個蠻喜歡的觀點：「跟人有關的事，都變成更明顯的瓶頸。」
AI 工具一直在變，但（是我無法推開生命的改變 🎶）回到社群跟人交流，依然是研討會最有價值的部分。
期待 2027！
yang.keitheis.org/blog/pycon…
Keith Yang retweeted
AI was supposed to make us work less
I've never been this tired in my life
most days I have up to 10 agents running at the same time. one fixing a bug, one writing pages, one refactoring something I already forgot I asked for, 3 other I have no idea what they are doing but i suppose i ask it?
and I jump from conversation to conversation all day
compared to 5 years ago, I probably context switch 100x more
by the end of the day my brain is fried. completely toasted. nothing left, not even for the people I love
I call it the fried brain effect
thought it was just me but almost every founder I talk to lately says the exact same thing
we got superpowers, and somehow the pressure only went up. if you can ship 10x more, you feel like you have to ship 10x more. every single day
I don't have a solution
honestly I have no idea where this goes from here
anyone else feeling this?
Another simple trick: ask a frontier model to generate your repo-native SDLC governance principles, then have another frontier model review them
"Put them in SDLC-Governance-Principles.md, reference it from AGENTS.md, and optimize for principles that survive better models—not today's agent quirks."
Keith Yang retweeted
We are making Markdown files work natively across Google Drive and Docs.
You can now preview .md files in Drive, open them in Docs, edit them, comment on them, and collaborate without converting the file into a Google Doc!
After actually using ChatGPT Dot, I can feel the difference between a lobster someone else has properly seasoned and served in a real work setting, versus one you casually cook at home in your spare time.
A few impressions 🧵
Most of these things were already possible with Codex or Claude Cowork / Code.
But the mindset feels quite different.
With agents today, I usually move into the right context — the right project, the right repo — and give fairly precise instructions.