- Published on
探討 AI 應用程式中評估（evals）的重要性與方法，基於 Vercel 工程師 Ido Pesok 的演講內容，說明評估與傳統單元測試的差異，以及如何建立有效的評估機制
Evaluation
All Posts
- java (46)
- aspnet-core (44)
- spring-boot (40)
- ithome2024 (39)
- c (29)
- aspnet-mvc (20)
- ai (19)
- ubuntu (17)
- ef (15)
- js (13)
- database (11)
- sql (10)
- postgresql (9)
- murmur (8)
- course (8)
- jenkins (8)
- rider (8)
- test (8)
- ef-core (7)
- git (7)
- react (7)
- claude-code (7)
- mac (5)
- nodejs (5)
- security (5)
- event (4)
- aop (4)
- package (4)
- testing (4)
- heroku (4)
- shell (4)
- programming (4)
- nginx (4)
- actionfilter (3)
- mediatr (3)
- skype-bot (3)
- parse (3)
- jetbrains-plugin (3)
- mongodb (3)
- springboot (3)
- tool (3)
- vscode (3)
- hook (3)
- tdd (3)
- kent-beck (3)
- api (2)
- exception (2)
- firebase (2)
- jwt (2)
- vue (2)
- convert (2)
- datetime (2)
- cmd (2)
- ideavim (2)
- movie (2)
- mindset (2)
- bot (2)
- book (2)
- python (2)
- refactor (2)
- editorconfig (2)
- nextjs (2)
- 軟體工程 (2)
- ali-abdaal (2)
- productivity (2)
- youtube (2)
- kiro (2)
- coding (2)
- software-development (2)
- running (1)
- android (1)
- android-studio (1)
- di (1)
- middleware (1)
- clean-architecture (1)
- cqrs (1)
- html (1)
- miniprofiler (1)
- markdown (1)
- 日劇人生 (1)
- kanban (1)
- everntoe (1)
- 動畫人生 (1)
- jetbrains (1)
- github (1)
- slack (1)
- 看書人生 (1)
- monolisa (1)
- azure (1)
- integromat (1)
- raycast (1)
- scrum (1)
- retro (1)
- ted (1)
- webstorm (1)
- typescript (1)
- warp (1)
- 漫畫人生 (1)
- websocket (1)
- windows (1)
- winform (1)
- transaction (1)
- meetup (1)
- enummap (1)
- enum (1)
- lombok (1)
- equalsandhashcode (1)
- function (1)
- composition (1)
- cloudflare-pages (1)
- env (1)
- resttemplate (1)
- configuration (1)
- transactional (1)
- 網站安全 (1)
- 機器人防禦 (1)
- 網路安全 (1)
- 技術債 (1)
- 程式碼品質 (1)
- 最佳實踐 (1)
- 學習 (1)
- 技術觀點 (1)
- 軟體開發 (1)
- 個人成長 (1)
- audiobook (1)
- learning (1)
- knowledge (1)
- creator (1)
- entrepreneurship (1)
- motivation (1)
- tsumiki (1)
- ai-coding (1)
- hooks (1)
- agent (1)
- worktrees (1)
- design (1)
- llm (1)
evaluation (1)
- tidy-first (1)
- xp (1)
- sdd (1)
- spec-driven-development (1)
- 職涯發展 (1)
- 社群經營 (1)
- prompt-engineering (1)
- claude (1)
- anthropic (1)
- 產品開發 (1)
- 快速迭代 (1)
- 用戶反饋 (1)
- agile (1)
- remote-development (1)
- vibe-tunnel (1)
- ssh (1)
- logging (1)
- swagger (1)
- validation (1)
- cors (1)
- actuator (1)
- deployment (1)