大家晚安,今天晚上的活動連結在這裡哦~~ https://meet.google.com/mng-xndh-jpq

Channel
GDG Taichung Channel
@gdg_taichung
On this record: Topic · Growth · Engagement · Posts · Cite this entry
153subscribers
-2 since we began measuring on 7 August 2026
Risers and fallers across the register · movement among entries of Under 1,000.
Register entry
| Telegram ID | -1001246360789 |
|---|---|
| Type | Channel |
| Username | @gdg_taichung |
| Created | Between 1 March 2018 and 31 August 2021 — estimated from Telegram’s id allocation, not measured. How this range is calculated. |
| First recorded | 8 August 2026 |
| Last confirmed live | 8 October 2026 |
| Measurements held | 4 |
| Confirmed unchanged | 2 times, most recently 8 October 2026 |
| On Telegram | t.me/gdg_taichung |
Topic
Technology — a classification, not a measurement. An on-box language model (Qwen3.6-35B-A3B-FP8, prompt version 1) read this channel’s own recent posts on 25 September 2026 and assigned it the closest of 31 fixed categories, at 99% confidence. This is a model’s judgement about what the channel is likely to be about, not a fact this register measured the way a subscriber count or a view count is measured — it can be revised on a later pass, and it carries no weight anywhere else on this page. How this classification works, and why it has no browse page of its own yet.
Growth
| Measured (UTC) | Subscribers | Change |
|---|---|---|
| 29 Sept 2026, 03:18 | 153 | -1 |
| 15 Sept 2026, 18:41 | 154 | -1 |
| 8 Aug 2026, 18:45 | 155 | no change |
| 7 Aug 2026, 21:13 | 155 | first reading |
Engagement
20 posts held, back to 22 October 2025 — the reader has not yet reached the start of this channel’s public history, so older posts may sit further back, unread. Read across 1 page of Telegram’s post history, 20 posts per page.
Nothing published in the last 30 days. ERR and ER are rolling 30-day measures, so there is nothing to compute — we hold 20 posts for this entry, the most recent from 17 July 2026. An engagement rate over an empty window would be a number about nothing.
Recent posts
❇️【線上懶人包】Google I/O Extended 2026 Taichung 前哨站 Jul 17, 7:30 – 9:30 PM https://gdg.community.dev/e/m4xufa/ 難得的線上活動,歡迎邀請各地的人一起來參與!
今天晚上返鄉場的 Build with AI - 新手友善場 19:15 開始報到 剛巧最近 AI Stduio 大更新,今天會由 Developer Ecosystem Regional Lead - Eric 來帶大家認識這個新介面 歡迎大家一起來「年末相聚」! https://gdg.community.dev/e/m9t9wv/
突然就來到 12 月底了,1 月份活動安排好啦 !!! 活動主題:Build with AI - Vibe SQL 實戰分享/Antigravity 活動講者:Abi / Ahdaa 活動時間:2026/01/10 (六) 14:00-17:00 活動地點:Monospace 共同工作空間 活動報名:https://gdg.community.dev/e/mvxg3m/
DevFestTaichung2025 講題介紹 - Vibe Coding全新進化:使用Gemini CLI 與 SDD 重新定義 AI 協作開發 在 AI 編程時代,開發者常陷入「Vibe Coding」的困境,與 AI 對話像猜謎、程式碼品質不穩定、專案意圖難以追溯。本次議程將介紹 如何使用 Gemini CLI 實踐規格驅動開發(Spec-Driven Development)。 活動報名:https://gdg.community.dev/e/m8ypnx/
DevFestTaichung2025 講題介紹 - 用 Gemma3 打造全地端 Agent 系統 簡介全地端 Agent 系統,地端佈署 LLM、自建 MCP server,從單 Agent 到多 Agent 協同作戰,讓 AI 不只能聊天,更能實際執行任務,同時確保隱私資訊不外流。 活動報名:https://gdg.community.dev/e/m8ypnx/
DevFestTaichung2025 講題介紹 - 從錯誤到準確的距離:AI Agent 如何重新定義開發流程的「第一次」 傳統開發仰賴人與流程的協作,但每一次修改、溝通與回饋都意味著成本。AI Agent 不只是輔助,它能「學習上下文」、「調用知識」、「協調任務」,最終讓整個製造鏈具備自我修正與預測能力。這不只是自動化,而是 精準化與智慧協作的新時代。 活動報名:https://gdg.community.dev/e/m8ypnx/
🚀【DevFestTaichung 2025 倒數報名 !!】 想親手實作 AI Lab、體驗最前線技術?當天開場就教你領取免費 Google Credit,直接上手做 Lab!💻參加工作坊還可以拿到限量紀念小提袋 🎁~數量有限,先到先得! 這是一場結合 AI × Cloud × 開發者精神的年度盛會,完全免費參加!馬上報名,卡位 DevFest 2025,別等別人炫技時你還沒入場!👉 https://gdg.community.dev/e/m8ypnx/
DevFestTaichung2025 講題介紹 - Firebase 帶你進入 Client-Side AI 時代 開發 AI 應用最擔心的就是 API Key 外洩造成高額費用。Firebase 讓開發者可以「安全、簡單、原生地在前端直接呼叫 Gemini API」,透過 App Check 與 AI Logic 的機制,在無需後端的情況下打造低延遲、高互動的 Client-Side AI 體驗,讓生成式應用的開發變得更輕量、更即時、更安全。 活動報名:https://gdg.community.dev/e/m8ypnx/
DevFestTaichung2025 講題介紹 - 利用 Gemini CLI 與 ADK 開發 Agentic 應用 本議程將為您提供一份完整的實戰指南。我們將展示如何以 Gemini CLI 作為開發起點,來實作遵循 ADK 概念的 AI Agent。 大綱 Outline 1. 開場:Agentic 應用的開發挑戰 2. Gemini CLI 與 Agent Dev Kit (ADK) 介紹 3. 用 Gemini CLI 加速本地 Agent 開發 4. 將 Agent 部署至雲端並實現可觀測性 5. 總結與未來:從 ADK 到 A2A (Agent-to-Agent) 協作 活動報名:https://gdg.community.dev/e/m8ypnx/
DevFestTaichung2025 講題介紹 - 整合 Google AI 與開源生態系的個人化微調工作流 現在 Colab 上可以很方便取得的 A100 80G, 不但可以拿來當私人的 AI Inference Server,能應付現在越來越大的開源模型。也適合客製化微調 AI 模型,不管是上用 Unsloth 極速微調最新的 LLM ,還是客製化自己的 AI 影片模型都能游刃有餘。 活動報名:https://gdg.community.dev/e/m8ypnx/
DevFestTaichung2025 講題介紹 - [工作坊] 透過 Google Gemini 與 ADK 工具來製作 AI Agent 應用 生成式 AI 正在快速推進,如何從模型走向「能實際執行任務的 Agent」是企業導入的關鍵。本場工作坊將示範如何透過 Google Gemini 結合 ADK (Agent Development Kit),快速構建具備感知、推理與行動能力的 AI Agent。參與者將了解 Agent 的核心設計思維、實作流程與應用案例,並掌握如何將生成式 AI 技術落地到真實商業場景。 活動報名:https://gdg.community.dev/e/m8ypnx/ 當天會提供 Credit 讓大家參予工作坊,還有機會獲得可愛小禮品喔!!
Showing the 12 most recent of 20 posts we hold for @gdg_taichung. View and reaction counts are the latest single reading for each post, not a live figure, and a recent post is still accumulating both. A view count marked ≈ was rounded by Telegram before we ever saw it — t.me prints views in full below 1,000 and to three significant figures above, so ≈1,200,000 means somewhere between 1,150,000 and 1,249,999. Unmarked counts are exact. Text is reproduced from the public post preview and truncated for length.
Cite this entry
A live page changes as we take new readings, so a citation should name the measurement it is based on, not just the URL. The line below cites the subscriber count as measured 29 September 2026 — this entry's latest reading, not the date you are reading this.
“GDG Taichung Channel” (@gdg_taichung), 153 subscribers as measured 29 September 2026. Telegram Register, tgregister.com/channel/gdg_taichung.
Full measurement history, CC BY 4.0. Every reading this register holds for this entry, not just the latest one, as a dated, downloadable record: CSV · JSON. Free to use with attribution to tgregister.com. Each file carries its own generation timestamp, which is the figure to cite for exactly when the data was retrieved.