[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"tag-模型比較":3},{"tag":4,"articles":10},{"id":5,"name":6,"slug":6,"article_count":7,"description_zh":8,"description_en":9},"4b413fc6-0651-4005-9031-1453c2b57a32","模型比較",3,"模型比較關注不同 AI 模型在基準測試、上下文長度、授權條款、推理能力與產品整合上的差異。對開發者來說，重點不只是哪個分數高，還包括自架成本、提示穩定性，以及在聊天、搜尋、工作流程中的實際表現。","Model comparison focuses on how AI systems differ in benchmarks, context length, licensing, reasoning quality, and product integration. For developers, the key question is not just which model scores higher, but how it behaves in self-hosting, prompting, and real workflows such as chat, search, and office tools.",[11,20,28,35],{"id":12,"slug":13,"title":14,"summary":15,"category":16,"image_url":17,"cover_image":17,"language":18,"created_at":19},"a87c5406-ba2d-4f16-92cc-c59d738b4126","local-llm-vs-claude-for-coding-zh","本地 LLM vs Claude 寫程式","本地 LLM 適合重視隱私、固定成本與大量例行寫碼；Claude 在除錯、跨檔推理與複雜修改上更強。","industry","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1778753447706-5r1g.png","zh","2026-05-14T10:10:29.999545+00:00",{"id":21,"slug":22,"title":23,"summary":24,"category":25,"image_url":26,"cover_image":26,"language":18,"created_at":27},"3ba89b24-d855-41d2-b316-6fe26be48bee","openai-vs-deepmind-models-apps-2026-zh","OpenAI 與 DeepMind 2026 對決","到 2026 年，OpenAI 和 DeepMind 的差距不只在模型分數，也在產品體驗。ChatGPT 仍靠 app 生態守住日常使用，Gemini 則靠搜尋與 Workspace 整合搶場景。","model-release","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1775165090367-2hzj.png","2026-04-02T21:24:33.429824+00:00",{"id":29,"slug":30,"title":31,"summary":32,"category":25,"image_url":33,"cover_image":33,"language":18,"created_at":34},"710ff4cc-d333-4bd8-b50a-e5522d430161","open-source-llm-comparison-2026-zh","2026 開源 LLM 誰領先","Qwen 3.5、GLM-5、DeepSeek R1、Llama 4 讓開源 LLM 進入實戰。這篇整理 2026 年主流模型的 benchmark、上下文長度、授權條款與自架表現。","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1775131800331-8pqc.png","2026-04-02T12:09:39.445524+00:00",{"id":36,"slug":37,"title":38,"summary":39,"category":40,"image_url":41,"cover_image":41,"language":18,"created_at":42},"af9c46c3-7a28-410b-9f04-32b3de30a68c","prompting-in-2026-what-actually-works-zh","2026 提示工程，真正有用的是什麼","2026 年的提示工程更吃模型差異。資料顯示，38.5% 對話要靠反覆修正才成功。真正有效的方法不是花式 wording，而是把提示寫成精簡規格，配合限制條件、格式要求與驗證流程。","tools","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1774517388287-tt7a.png","2026-03-26T08:08:12.453028+00:00"]