現代研究需要現代手段：研究工具彙整 / Modern Research Needs Modern Tools: A Compilation of Research Instruments

我在「現代研究需要現代手段：用知識管理和AI輕鬆做研究！」演講中使用了很多研究工具。為了方便讓大家找到這些工具，我把演講裡提到的工具都拉出來，額外放在下面進行介紹。這些工具包含了書籍、軟體、網站等等。有些是付費才能使用，有些是可以免費註冊帳號即可使用，使用之前請自行評估一下囉。

In my presentation, "Modern Research Demands Modern Tools: Leveraging Knowledge Management and AI for Effortless Research," I utilized a variety of research tools. For your convenience, I've listed those tools below with additional details. These resources include books, software, websites, and more. Some require payment while others offer free accounts. Please evaluate each option before using it.

現代研究需要現代手段：用知識管理和AI輕鬆做研究！ / Modern Research Demands Modern Tools: Leveraging Knowledge Management and AI for Effortless Research!

今年10月的時候我去南藝大為研究生們講述了活用圖書館資源、AI工具以及Zotero來撰寫研究論文的方法。有了內建大型語言模型資料庫的協助，例如Scopus、Semantic Scholar、Consensus、Elicit、SciSpace，現在作研究的方式已經有了很大的轉變了。投影片的內容分成了「研究搜尋篇」與「閱讀寫作篇」兩個部分，以下就來看看這次演講的投影片內容吧。

In October of this year, I gave a presentation at Tainan National University of the Arts to graduate students on how to leverage library resources, AI tools, and Zotero for research paper writing. With the help of databases incorporating large language models, such as Scopus, Semantic Scholar, Consensus, Elicit, and SciSpace, the way we conduct research has been significantly transformed. The presentation was divided into two parts: "Investigate Research" and "Reading and Writing." Let's take a look at the slides from the presentation below.

自行架設大型語言模式應用程式：Dify / Self-Hosting a Large Language Model Application: Dify

Coze開始收費之後，Dify會是更好的替代方案嗎？事情原來沒有我自己想象中的這麼簡單！

When Coze began to charge fees, what is the next solution for Large Language Model (LLM) application? Will Dify be a better alternative? The actual situation is not as simple as I had imagined!

從生成式AI到脈絡式AI：文學院AI人才培育的反思 / From Generative AI to Contextual AI: Reflections on AI Talent Development in the Faculty of Arts

這是我在2024年6月於「智慧人文沙龍」活動中演講的主題「從生成式AI到脈絡式AI：文學院AI人才培育的反思」。演講中我一邊回顧了在淡江任教時應用的「人工智慧」，一邊對於現今的「人工智慧」教育提出疑問，最後提出文學院培育AI的三個方向。

This is the topic of my speech at the "Smart Humanities Salon" event in June 2024, titled "From Generative AI to Contextual AI: Reflections on AI Talent Development in the Faculty of Arts." In this speech, I reviewed the application of "artificial intelligence" during my course at Tamkang University, questioned the current state of "artificial intelligence" education, and finally proposed three directions for AI talent development in the Faculty of Arts.

Fixed Short URL: http://l.pulipuli.info/24/tku/ai 

人工智慧的發展與應用 / The Development and Application of Artificial Intelligence

這是我在2024年7月演講主題中抽取一部分出來分享的投影片：「人工智慧的發展與應用」。講述人工智慧從專家系統、資料探勘、機器學習、深度學習、生成式AI與大型語言模型的發展歷程，以及他們在教育領域、產業領域、設計領域和軟體領域的應用實例。

Here is a slide extracted from my speech on "The Development and Application of Artificial Intelligence" in July 2024. I discussed the evolution of artificial intelligence from expert systems, data mining, machine learning, and deep learning to generative AI and large language models. I also covered their applications in the fields of education, industry, design, and software.

使用Coze建置聊天機器人的經驗 / Experience in Building Chatbots With Coze

我在2024年5月為2024淡江大學數位轉型暨淨零轉型成果觀摩展建置的「希希助教 in TKU DILS 2024MS3AP」後，陸陸續續使用Coze建置了許多聊天機器人，並探索RAG與知識庫等現今LLM領域的重要議題。然而因為Coze的收費政策調整，現在這些機器人已經不能用了。

After establishing "Sissi Assistant in TKU DILS 2024MS3AP" in May 2024, I gradually used Coze to build many chatbots and explored important topics in the current LLM field like RAG and knowledge bases. However, due to changes in Coze's pricing policy, these chatbots are no longer usable.

請ChatGPT幫我改Blog的文章 / ChatGPT Reviews My Blog Articles

有時候有用，有時候跑不出來。最終的結果還是跟餵給ChatGPT的資料格式有很大的關係吧。

AI老師教教我！用AI改報告 / How to Get Report Revision Suggestions from Chat-based AI?

你想請ChatGPT這種聊天機器人幫你改報告，但是報告內容太長、還有表格等格式，導致你的複製貼上讓AI也看不懂，怎麼辦好呢？這時候不妨試著用我做的「AI改報告提問器」來產生適合的提問內容吧。

新的圖片索引工具：CLIP Interrogator / Can CLIP Interrogator be an AI Indexer?

要如何用文字來描述一張圖片，這是一項非常困難的任務。現在有許多用提示詞產生圖片的AI繪圖，那自然也有用圖片來產生提示詞的AI圖片介紹囉。

以圖製圖的AI外掛：Synthesys X / Synthesys X: Generate New Images based on the Original Image

大家知道的AI製作圖片，大多都是要輸入合適的描述詞，再請模型根據描述詞來產生圖片。但如果我只有圖片，連要怎麼描述都不知道的話，有辦法用AI產生圖片嗎？