Agent 很慢、LLM 不夠聰明——什麼時候該用多步驟處理？
LLM 一次回答不完整，Agent 又跑很久還常卡住——單次呼叫、CoT、RAG、Agent 到底怎麼選？一張光譜圖 + 5 個問題幫你判斷。
LLM
Single Call vs Agent: A Spectrum of LLM Strategies
Single LLM calls miss details. Agents take forever and get stuck. What are the options in between? A visual spectrum + 5 questions to help you decide.
AI Outputs ‘用户’ ‘调用’? One Command to Convert to Taiwan Chinese
LLM-generated Chinese often mixes terminology from different regions. Taiwan readers stumble over Mainland terms like ‘用户’ and ‘调用’. The zhtw tool lets you localize with one command—supporting CLI, Python integration, and batch processing.
AI 輸出『用戶』『調用』？一個指令轉成台灣用語
LLM 生成的中文內容常混合不同地區用語，台灣讀者看到『用戶』『調用』會出戲。zhtw 工具讓你一個指令完成在地化，支援 CLI、Python 整合、批次處理。
下一代 QA：在大型 Java 既有專案中實現 AI 驅動的自主多輪驗收測試
深度解析如何利用 LangChain4j、GPT-4o 與 Playwright 打造 AI 測試代理人。本文詳細探討在缺乏文檔的大型 Java 遺留系統中，如何透過「探索、診斷、穩定性」三重迴圈機制，實現超越傳統自動化的自主驗收測試，並提供完整的實作代碼與導入路線圖。
Next-Gen QA: Implementing AI-Driven Multi-Turn Autonomous Acceptance Testing in Legacy Java Projects
A complete technical implementation plan: Building an AI Testing Agent using LangChain4j, GPT-4o, and Playwright. Includes full code concepts, prompt engineering, state machine architecture, CI/CD integration, and a concrete adoption roadmap.