Claude Code Vibe Coding 開發手冊 第 2 版

 

（點此前往博客來購書）

即使不像對岸因高失業率引發的各行各業「內捲」那般慘烈，在台灣，近年來資訊科技相關工作的日子，也越來越不輕鬆自在了。除了像 Claude Code 這類強大的 Vibe Coding 工具緊追在後之外，IT 技術本身的突破與迭代速度也快得令人措手不及。以前可能學個 COBOL，就能安穩地寫二十年的銀行系統；學個 SQL，也能在中小企業的 MIS 部門一路做到退休，這種好日子已經一去不復返。現在資訊技術的保鮮期，多則不到兩年；像 AI 領域更誇張，新東西可能不到半年就過時，又得重新學起。

以這本《Claude Code Vibe Coding 開發手冊 第 2 版》為例，上市日期是 2026/06，離今天大概也才一個月。書中提到建立 subagent 的 /agents 指令，就已經被原廠停用、廢棄了。雖然就學習、使用的角度來說，這並不會造成太大的困擾，依舊能改用口語式指令操作，但對出版社、作者等教學方而言，撰寫、出版 AI 技術書籍的性價比肯定不高。畢竟，相較於討論底層核心觀念、歷久彌新的電腦書，這類 AI 熱門主題書如果不能在出版當年賣掉，大概也只能被秤重回收了。所以看電腦書，尤其是主題偏向 AI 實作時，近來得出的心得是：有需要再買，買了就馬上看，千萬不要積書！

由於我才剛看過這本書的第一版，因此能很明確地比對出新增加的章節內容。整體而言，基本概念與操作方式變化不大，實作練習則略有增加，翻閱時本質上比較像是在看別人做習題。因此，本書真正有價值的地方，在於 Claude Code 新功能的介紹，像是將特定執行流程 SOP 化的 Skills，以及跨平台的遠端操控功能。另外，內建 MCP 的 Claude in Chrome，也讓我眼睛一亮，更確切地體認到，在 AI 工具的協助下，未來的網路環境中，爬蟲機器人將會是再也無法阻擋的必然存在。還是那句老話，程式開發人員已經不能不懂 Vibe Coding。來一本吧！

Even though Taiwan is not facing the same serious "involution" as China, where high unemployment has made competition much tougher, working in the IT industry here has also become more stressful in recent years. Powerful Vibe Coding tools like Claude Code are moving forward very quickly. At the same time, new IT technologies are changing faster than ever. In the past, you could learn COBOL and spend twenty years writing banking systems. If you learned SQL, you could also work in the MIS department of a small or medium-sized company until retirement. Those days are gone. Today, many IT skills stay useful for less than two years. The AI field changes even faster. A new technology may become old in less than six months, and then you have to learn something new again.

Take this book, *Claude Code Vibe Coding Developer's Guide, 2nd Edition*, as an example. It was published in June 2026, only about one month ago. However, one command for creating a subagent has already been removed by the official developer. Luckily, this does not cause much trouble for readers. We can still do the same thing by using natural language commands instead. Still, for publishers and authors, writing AI books is probably not a very good business. Unlike classic computer books that teach basic ideas and stay useful for many years, AI books can become outdated very quickly. If they do not sell soon after publication, they may end up being recycled. Because of this, I have learned one important lesson about computer books, especially AI books: buy them only when you really need them, and read them right away. Don't let them sit on your bookshelf for too long.

I finished the first edition not long ago, so it was easy for me to see what had changed in this new edition. Overall, the basic ideas and operations are almost the same. There are a few more hands-on exercises, but reading them feels a little like watching someone else solve homework problems. The most valuable part of this book is its introduction to Claude Code's new features. For example, it explains Skills, which can turn common workflows into standard operating procedures (SOPs). It also introduces remote control across different platforms. Another feature that impressed me was Claude in Chrome, which comes with a built-in MCP. It helped me realize that, with the help of AI, web-crawling bots will become an unavoidable part of the future Internet. As I always say, software developers can no longer ignore Vibe Coding. Go get a copy of this book!

勇者鬥惡龍 達伊的大冒險 各自的道路(全)

 

（點此前往博客來購書）

以日本電玩《勇者鬥惡龍》的世界觀為舞台的漫畫《達伊的大冒險》，雖然已經完結多年，但一直以來都是我的最愛。有別於現在許多漫畫充斥著各種沉重、灑狗血的情節，以及灰暗、走極端的角色設定，二、三十年前日本《週刊少年 Jump》上的連載漫畫，幾乎都是以友情、努力和勝利為核心來創作。在三觀正確的前提下所描繪出來的《達伊的大冒險》，絕對是一部能讓家長放心買給小朋友閱讀的少年漫畫。

2026年的當下，以達伊的老師阿邦打倒魔王哈德拉/巴特拉為故事主題的前傳《勇者鬥惡龍 達伊的大冒險 勇者阿邦與獄炎魔王》仍在連載中。而早已完結多年的正傳，則是以輕小說的形式推出了這本《勇者鬥惡龍 達伊的大冒險 各自的道路》，用來補完冒險故事中一些細微的橋段。本書以阿邦的五位弟子達伊/小呆、波普/何布、瑪姆、休葛爾和蕾歐娜，各自的一篇短篇小說，串接起漫畫中的重要章節，形成一個巧妙的補充。

原作漫畫我看了不下十次，因此對於角色的個性與能力可說是倒背如流。即便如此，我還是對日本輕小說的文字創作功力感到相當驚豔。僅憑文字描寫，就能讓我在腦海中浮現宛如漫畫原著般的畫面；情節的鋪陳和人物的刻畫，也都沒有脫離原作，進行任何不必要的二次創作。相對地，輕小說中的故事內容補足了漫畫中沒有機會著墨的日常篇章，讓讀者能以更和緩的節奏，深入理解阿邦五位弟子的人格特質與成長歷程。推薦給每一位曾經拿著掃把，練習過阿邦式快速劍的朋友們。

*Dragon Quest: The Adventure of Dai* is a manga set in the world of the famous Japanese video game *Dragon Quest*. Even though it ended many years ago, it has always been one of my favorite manga series. Unlike many modern manga, which are full of dark stories, over-the-top drama, and extreme characters, most manga in *Weekly Shonen Jump* twenty or thirty years ago were created around three important ideas: friendship, hard work, and victory. Because of these positive values, *The Adventure of Dai* is a manga that parents can feel comfortable giving to their children.

As of 2026, the prequel manga *Dragon Quest: The Adventure of Dai – The Brave Avan and the Hellfire Demon King* is still being serialized. It tells the story of Dai's teacher, Avan, and his battle against the Demon King Hadlar. The original manga ended many years ago, but a light novel called *Dragon Quest: The Adventure of Dai – Their Paths* was later published. It fills in some of the small but meaningful moments that were not shown in the manga. The book contains five short stories, each focusing on one of Avan's students: Dai, Pop, Maam, Hyunckel, and Leona. Together, these stories connect important parts of the original manga and add more depth to the adventure.

I have read the original manga more than ten times, so I know the characters and their abilities very well. Even so, I was still amazed by the author's writing. With only words, the novel brought scenes from the manga to life in my mind. The story and the characters stayed true to the original work, without adding unnecessary changes or fan fiction. Instead, the novel focuses on everyday moments that the manga did not have time to show. It lets readers learn more about the personalities and growth of Avan's five students at a slower and more relaxing pace. I highly recommend this book to everyone who once picked up a broom and practiced the "Avan Strash."

LangChain 奇幻旅程：OpenAI x Gemini x 多模態應用開發指南

 

（點此前往博客來購書）

AI 浪潮席捲而來的當下，軟體工程師若想不被大浪滅頂，勢必得將它視為助力而非阻力。唯有動心起念、善加運用，才能立於不敗之地。而對第一線的程式開發者來說，面對 AI 可以學習的方向，大致可分成兩個主題：一是人工智慧的 Vibe Coding 開發工具，增益自身的開發能量；二是探索與實作 AI 應用程式，將 LLM（大語言模型）的大腦融入不同的應用情境，開發出新世代的智慧程式。

在軟體開發的過程中，程式框架（Framework）具有將重複性需求規格化、模組化的優點，框架優先的觀念早已在 Web 應用開發中根深蒂固。在 LLM 應用的領域裡，LangChain 則是最具知名度的程式框架，其核心理念是透過它所提供的抽象層，達成不受制於單一 LLM 平台或業者的設計。這本《LangChain 奇幻旅程》不僅讓讀者學到 LangChain 框架的基礎，更進一步介紹 AI 應用開發會觸及的相關技術，像是本地端模型的 Hugging Face、Ollama、RAG 的觀念與實作、LINE Bot 對話機器人，以及極具價值的 Qdrant 向量資料庫基礎運用。

書中不偏袒地將 OpenAI 與 Gemini 這兩個 LLM 領頭羊的實作一併收錄，不論讀者原本採用的是哪一家的方案，都可以直接從書中學到具備即戰力的開發技能。可惜的是，AI 技術一日千里，即便這本書出版至今才約一年半（2024 年 10 月出版），LangChain 的版本已經歷多次更新，書中的程式碼也大多已經過時，得自行花時間查找新版的寫法。幸好身處 AI 時代，在 ChatGPT 這類工具的協助下，相信都能迎刃而解。

不過，對於 AI 應用的開發是否非得採用 LangChain 這樣的框架，目前我還是有點遲疑。以我比較熟悉的 GCP Vertex AI 為例，有一些平台專屬的功能，像是格式化輸出（Structured Output）、Grounding 等，都不包含在 LangChain 基本類別的設定值裡。換言之，如果想使用這些強大的 LLM 功能，就得客製化框架的程式碼；然而，一旦這麼做，就很難再切換到其他 LLM 平台，如此一來，採用框架所追求的平台無關性（Platform Agnostic）也就不復存在了。

With the AI wave sweeping across the software industry, developers who don't want to be left behind need to see AI as an opportunity rather than an obstacle. The key is to embrace it and learn how to use it effectively. For software developers, there are two main directions for learning AI. The first is using AI-powered development tools, such as Vibe Coding, to boost productivity. The second is exploring and building AI applications by integrating the "brain" of LLMs (Large Language Models) into different use cases to create the next generation of intelligent software.

In software development, frameworks help standardize and modularize common requirements, making development more efficient. As a result, the "framework-first" mindset has become deeply rooted in modern web development. In the world of LLM applications, LangChain is probably the best-known framework. Its core idea is to provide an abstraction layer so developers are not tied to a single LLM platform or vendor. This book, LangChain 奇幻旅程 (The Fantastic Journey of LangChain), not only teaches the fundamentals of the LangChain framework, but also introduces many important technologies used in AI application development. These include local models with Hugging Face and Ollama, the concepts and implementation of RAG, LINE Bot development, and the basics of using the Qdrant vector database.

The book presents examples for both OpenAI and Gemini without favoring either one. No matter which LLM platform you are currently using, you can learn practical development skills that are immediately useful. The downside is that AI technology evolves incredibly fast. Although the book was published only about a year and a half ago (October 2024), LangChain has already gone through multiple major updates. Much of the sample code is now outdated, so readers will need to spend some time figuring out the new APIs and coding style. Fortunately, with AI assistants like ChatGPT, updating the code is much easier than it used to be.

That said, I'm still not completely convinced that AI applications must be built on a framework like LangChain. Take GCP Vertex AI as an example. It provides several platform-specific features, such as Structured Output and Grounding, that are not covered by LangChain's standard abstractions. In other words, if you want to take advantage of these advanced LLM features, you'll need to customize the framework. Once you do that, however, switching to another LLM platform becomes much more difficult. As a result, the platform-agnostic design that frameworks like LangChain aim to provide starts to lose its value.

台灣小妹，美國大姊

 

（點此前往博客來購書）

人的一生說長不長，再加上時空、地理等外在因素的侷限，每個人能經歷的人生體驗總是有限。然而，透過閱讀，我們就能在極短的時間內，瀏覽、品鑑別人一生的起落與故事。這本由邱瀟君所寫的《台灣小妹，美國大姊》，和前陣子看過的《偽魚販指南》同屬一類，是相當私人的家書型作品；內容卻更貼近家庭與生活，而書中的文章也都曾刊載於《聯合報》。

這本書記載著她大半輩子走過的悲歡離合，時間軸幾乎橫跨一家三代的日常點滴。而她的故事也展現了一種外省第二代子女的典型：上一代原本在對岸家世良好、生活無憂，卻因國共內戰而流亡來到台灣。長輩在經濟困苦的環境下拉拔子女成長，並受惠於一併帶來的中華文化中尊師重道的傳統教育思維，這群外省第二代多半在學業、事業上都小有成就，更有不少人憑藉優異成績赴海外留學，最後直接移居美國、加拿大。

這樣的一群人一住就是數十年，在異國生活的時間，甚至比待在台灣還長。台灣對他們而言，只是生命中如過客般的一個逗點；人生最重要的奮鬥與美好，反而都建立在美、加的旅居歲月裡。不過，當年他們為了移居海外，忍受外國人的歧視，放棄年少時的夢想，只為了生存而從事各種工作。等同於耗費大半生的光陰，只為了在海外獲得一方安身立命的天地。這正是許多第一代移民的寫照。最後受惠的，則是那些一出生便擁有綠卡的第二代移民，他們甚至已經不認得台灣在哪裡。

如果常去百貨公司美食街用餐，或是在星巴克裡喝咖啡，偶爾聽見幾位白髮蒼蒼的老太太茶餘飯後聊天，說著外省人口音字正腔圓的國語，忽然冒出一句：「我在溫哥華……怎樣怎樣。」說不定，她就是移居海外多年，最後因為年紀大了，覺得回台灣看病比較方便，而返國定居的僑胞呢。

A person's life is not all that long. With the limitations of time, place, and circumstance, the range of life experiences any one of us can have is naturally limited. Reading, however, allows us to witness the rise and fall of someone else's life in a very short time. Through books, we are able to explore and appreciate stories that took others a lifetime to live. *Taiwanese Little Sister, American Big Sister*, written by Chiu Hsiao-chun, belongs to the same category as *A Fake Fishmonger’s Guide*, which I read not long ago. Both are highly personal works, almost like collections of family letters. This one, however, focuses even more on family life and everyday experiences. The essays in the book were originally published in the *United Daily News*.

The book records the joys and sorrows of the author's life over several decades, covering the everyday lives of nearly three generations of her family. Her story also reflects the typical experience of many second-generation mainlander families in Taiwan. Her parents' generation once enjoyed comfortable lives on the Chinese mainland, but the Chinese Civil War forced them to flee to Taiwan. Despite growing up in poverty, they worked hard to raise their children while passing on the traditional Chinese values of respecting teachers and valuing education. As a result, many people of this generation achieved success in both academics and their careers. Quite a few also earned opportunities to study abroad because of their excellent academic performance, eventually settling permanently in the United States or Canada.

Many of them stayed overseas for decades, spending more years abroad than they had ever lived in Taiwan. For them, Taiwan gradually became little more than a brief pause in life, while their greatest achievements and happiest memories were built during their years in North America. Of course, moving overseas was never easy. They endured discrimination, gave up the dreams of their youth, and accepted whatever jobs they could find simply to survive. Many devoted the better part of their lives to building a place where they could finally call home. Their stories represent the experiences of countless first-generation immigrants. The greatest beneficiaries, however, were their children—the second generation, many of whom were born with permanent resident status or citizenship. Some of them have grown so distant from Taiwan that it has become little more than the place where their parents once came from.

If you often eat at department store food courts or enjoy a coffee at Starbucks, you may occasionally overhear a group of elderly ladies chatting after a meal. Speaking flawless Mandarin with the distinctive accent of Taiwan's mainlander generation, one of them might suddenly say, "Back when I was in Vancouver..." Chances are, she is someone who spent decades living overseas before returning to Taiwan in old age, finding it a more convenient place to receive medical care and spend her retirement.

Java程式設計師應該知道的97件事：來自專家的集體智慧

 

ISBN：9789865027148

我自從約15年前因為專案需要實作訊息佇列，開始著手研究 Apache ActiveMQ 這個開源產品後，程式開發的重心也從微軟的 .NET 平台轉向 Java。而後又更進一步採用 Apache Camel 這個開源框架打造訊息交換平台，接著步入 Hadoop 大數據開發領域等因緣際會下，就此熟悉並喜愛 Java／Apache 相輔相成的軟體生態系。想當然耳，看到這本《Java程式設計師應該知道的97件事》的書名，毫無遲疑地就會買來翻閱，想瞧瞧所謂專家們的智慧。

這本書的編輯形式相當獨特，它匯集了97位頂級的 Java 開發人員，請他們各自以一篇文章分享自身認為 Java 程式設計人員最該關注的事情。由於書後的附錄收錄了這群人的經歷簡介，可以發現他們每一位都足以被稱為大神的頂尖工程師，不論是出身正統科班的 IT 博士、開源專案的貢獻者、資訊書籍的作者，還是服務於大型企業的顧問、講師。來自四面八方的宗師級人物，依據他們各自深切關心的議題，文章探討的內容也因此五花八門，從 Java 語法細節、JVM 效能工具、非 Java 的 JVM 語言，到軟體測試、專案管理、參與社群等等。內容可說是超乎想像地豐富，但又名副其實地淺嘗即止。

所謂人多口雜，此書的缺點也輕而易舉地浮現，連書籍編輯都直接在序言中提出，97位專家的建言肯定會有相互衝突的部分，而且很多文章的重點可能放在非常枝微末節的語法問題，因此會產生一種奇妙的認知悖論：如果你讀了能產生共鳴，那表示你早就懂了；如果你的程度還不夠，看了也形同嚼蠟。整體來說，閱讀這本書的過程，既沒有學習到具體技能的成就感，也沒有獲得實用新知的充實感。對現階段的我而言，讀起來如同雞肋，只是多了一本曾經讀過的電腦書的回憶。

About fifteen years ago, I started working with Apache ActiveMQ, an open-source message broker, because I needed to implement a messaging queue for a project. Since then, my main development focus has gradually shifted from Microsoft's .NET platform to Java. Later, I adopted Apache Camel to build a message integration platform. Combined with my subsequent experience in Hadoop and big data development, I gradually became familiar with—and grew to appreciate—the Java/Apache ecosystem and the way its open-source projects complement one another. So when I came across the title *97 Things Every Java Programmer Should Know*, I didn't hesitate to pick it up. I was curious to see what insights these experts had to offer.

The format of this book is quite unique. It brings together 97 experienced Java developers, each contributing a short article about what they believe every Java programmer should know. The appendix includes a brief biography of each contributor, and it's clear that every one of them is a highly respected expert in the field. They include PhDs in computer science, contributors to open-source projects, authors of technical books, consultants, and trainers working for major companies. Because the contributors come from such diverse backgrounds, the topics covered are equally diverse. They range from Java language details, JVM performance tools, and JVM languages other than Java, to software testing, project management, and participating in open-source communities. The breadth of the content is impressive, but each topic is explored only briefly.

As the saying goes, "Too many cooks spoil the broth." The downside of this format becomes apparent as well. Even the editors mention in the preface that the advice from 97 experts is bound to contain conflicting opinions. In addition, many articles focus on extremely subtle language details. This creates an interesting paradox: if an article resonates with you, you probably already know the topic well. If you don't have enough background knowledge, however, the article may be difficult to appreciate or learn from. Overall, reading this book didn't give me the satisfaction of learning practical new skills, nor did it leave me feeling that I had gained many useful insights. At this stage of my career, the book felt somewhat underwhelming—neither bad nor particularly rewarding. In the end, it simply became another technical book that I can say I've read.

Claude Code Vibe Coding 開發手冊

 

ISBN：9789863128533

對於從事軟體開發工作的從業人員來說，看到新聞媒體不間斷地報導 AI（人工智慧）如何在資訊領域中高速成長、進化，間接讓矽谷網路、資通訊巨頭們有底氣大幅裁員、縮編，除了心裡不是滋味外，也總是抱持著懷疑：AI 真的能整合各種繁雜、混亂的系統知識，從無到有地生成零失誤的程式碼嗎？畢竟，以我使用 ChatGPT 的經驗，它在回答程式問題時，也時常答非所問，或充滿 AI 幻覺。這一切的疑惑，在看完這本《Claude Code Vibe Coding 開發手冊》後，就豁然開朗了。

Claude Code 是一個針對程式開發情境打造的 AI 大語言模型，而它的表現也讓我大為驚艷，更讓我直接體驗了什麼是 Vibe Coding（隨想編程）。藉由書中 Step by step 的引導，不論是哪個程度的程式開發者，都可以輕而易舉地踏入 LLM 協助開發的旅程。幾乎可以肯定，在 AI 模型進展到這個水準的情況下，未來軟體業的組織規劃、職務權責和工作形態，都將發生巨大的改變。

也因此，不論是上至 CTO（技術長）、IT 單位負責人，還是第一線實作的 PM（專案經理）、SA／SD（系統分析／系統設計）和 PG（工程師），都值得花點時間，親自淺嘗即止地使用 Vibe Coding 工具，絕對會讓自己開闊視野，並從另一個角度思考軟體產業未來的走向。Claude Code 這樣的 AI 開發工具，就像是運動場上的類固醇，能快速且無差別地強化使用者的程式開發能力。但「能力越強，責任越大」，沒有恰當的規範與管理，AI 工具所能造成的破壞也會等比例放大。工程師的誠信與敬業精神，在未來的軟體開發產業中，將會是無可取代的必要條件。畢竟，誰也不想把大規模殺傷性武器的按鈕，交到自己不信任的人手上吧？AI 程式開發工具，就有這樣的威力。

For people who work in software development, it is hard to ignore the news about how AI (Artificial Intelligence) is growing and improving at an amazing speed. Many reports also say that this gives big technology companies in Silicon Valley more confidence to cut jobs and reduce their workforce. Besides feeling uneasy about these changes, I always had one question in mind: Can AI really bring together all kinds of complex and messy system knowledge and create perfect code from nothing? From my own experience with ChatGPT, it often gives answers that miss the point or are affected by AI hallucinations when I ask programming questions. After reading Claude Code Vibe Coding Development Guide, however, all of my doubts disappeared.

Claude Code is a large language model designed especially for software development. Its performance truly surprised me and gave me a firsthand experience of what Vibe Coding is. With the book's step-by-step guidance, programmers of any skill level can easily begin their journey of developing software with the help of LLMs (Large Language Models). It is almost certain that, as AI models continue to improve, the software industry will go through major changes in its organization, job responsibilities, and ways of working.

For this reason, everyone—from CTOs and IT managers to PMs (Project Managers), SAs/SDs (System Analysts/System Designers), and programmers on the front line—should spend some time trying Vibe Coding tools for themselves. Even a short hands-on experience can broaden your perspective and help you think about the future of the software industry from a different point of view. AI development tools like Claude Code are much like steroids in sports. They can quickly and dramatically improve a programmer's development ability. But as the saying goes, "With greater power comes greater responsibility." Without proper rules and management, the damage caused by AI tools can also grow just as quickly. In the future, honesty and professionalism will become more important than ever for software engineers. After all, no one wants to put the button for a weapon of mass destruction into the hands of someone they cannot trust. AI programming tools have that kind of power.

哦NO！不要跟我去旅行

 

ISBN：9789573330950

國中時期，我因病在家休養了一年，在沒有課業壓力可以自我放飛的情況下，每天打著電視遊樂器配著廣播節目的悠閒日子，至今都是屬於我個人酸中帶甜的回憶。而在每天例行收聽的廣播節目，就以主持人羅懿芬的節目最令我喜愛和期待。也因為這個節目的緣故，認識到常被邀請的來賓侯文詠、施寄青和苦苓，更間接地讓我去購買、閱讀課外書籍，就此養成閱讀紙本書的習慣。在那個沒有網路、網紅和名嘴的年代，這四位廣播四人幫在節目中的對話、互動，不論是內容和娛樂性，都遠遠優於今日的網路內容。

許多年青人聽到苦苓，只會以為他是一位愛蹭議題，在臉書上大發議論的老人家。其實他真的是一位能寫、能說、能議論也能罵大街的全方位媒體人。更難得的是他還是位樂在旅遊，行遍全球的重度旅行家。《哦NO！不要跟我去旅行》全書便是他集結數年出國旅行的經驗與回憶，以他平實自然又帶點毒舌嘲諷的筆風，將自身遭遇過的酸甜苦辣，毫不保留地分享給讀者。

其實如果是認識苦苓，看過他上節目的老朋友們，看到那篇和老太太坐經濟艙的故事，肯定會翻白眼地大喊，這笑話我聽你講過八百次了！沒錯，全書裡描途的故事和片段，十有八九早就曾在各種傳播媒體上發表過了。畢竟人生的經驗就那些，他印象深刻覺得有趣的小故事當然有限。苦苓就像是一個專業的領隊般，在書中講著倒背如流的笑話和豆知識，娛樂著你我這些素不相識，只有一面之願的過客。好笑，就夠了。

When I was in junior high school, I had to stay home for a year because of an illness. Without the pressure of schoolwork, I was free to enjoy my days. I spent my time playing video games while listening to radio programs. Even today, those relaxing days remain sweet memories with a little sadness for me. Among all the radio programs I listened to every day, the one hosted by Lo Yi-fen was my favorite. Through her program, I got to know the regular guests, Hou Wen-yong, Shih Ji-ching, and Ku Ling. They also inspired me to buy and read books outside of school, and that was how I developed the habit of reading printed books. Back then, there was no Internet, no influencers, and no online commentators. The conversations between these four people on the radio were not only interesting but also very entertaining. In my opinion, they were much better than much of today's online content.

Many young people today only know Ku Ling as an old man who likes to comment on popular topics on Facebook. But in fact, he is a talented media personality. He can write, speak, discuss, and even criticize people with sharp words. What makes him even more special is that he loves traveling and has visited many countries around the world. In *Oh No! Don't Travel with Me*, he shares stories and memories from many years of traveling abroad. With his simple, natural, and slightly sarcastic writing style, he honestly tells readers about the happy and difficult moments he experienced during his journeys.

If you have known Ku Ling for a long time and have watched his TV shows before, you will probably roll your eyes when you read the story about sitting in economy class with an old lady. You might even say, "I've heard this story hundreds of times!" And that's true. Most of the stories in this book have already appeared in different kinds of media. After all, there are only so many unforgettable experiences in one person's life. Reading this book feels like joining a tour led by an experienced guide. Ku Ling tells the jokes and interesting facts he knows by heart, entertaining readers who may be strangers but happen to travel with him through this book. As long as it's funny, that's enough.