[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"tag-長上下文":3},{"tag":4,"articles":10},{"id":5,"name":6,"slug":6,"article_count":7,"description_zh":8,"description_en":9},"87866137-c0da-4bc0-a289-aca4b3445de2","長上下文",7,"長上下文指模型能在同一次推理中保留更多文件、程式碼、對話與工具輸出，從 128K、256K 到百萬級 token 都是重點。它影響長文件分析、跨檔案編輯、代理式工作流與記憶壓縮策略，也直接牽動成本、延遲與幻覺風險。","Long context refers to models that can keep far more text in a single run, from 128K and 256K windows to million-token APIs. It matters for codebases, long documents, agent workflows, memory compression, and the tradeoffs between cost, latency, and reliability.",[11,20,27,35,42,49,56,63,70,77,85,92],{"id":12,"slug":13,"title":14,"summary":15,"category":16,"image_url":17,"cover_image":17,"language":18,"created_at":19},"66ce4542-3c93-4a0c-ab52-5e6f90a36212","minimax-m3-kai-fang-quan-zhong-xie-cheng-shi-reng-neng-ying-zh","MiniMax M3 證明開放權重在寫程式上仍能贏","MiniMax M3 證明開放權重模型不只可以追上前沿，還能在寫程式、長上下文與成本控制上形成優勢。","model-release","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1780968786191-lele.png","zh","2026-06-09T01:32:30.829528+00:00",{"id":21,"slug":22,"title":23,"summary":24,"category":16,"image_url":25,"cover_image":25,"language":18,"created_at":26},"409fc126-8ed2-42e3-bec3-9d114c4aca23","why-minimax-m3-matters-long-context-model-zh","為什麼 MiniMax M3 比又一個長上下文模型更重要","MiniMax M3 的重要性不在於它又把上下文做大，而在於它把長上下文、多模態與代理控制綁成一個可用系統。","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1780755468369-c0ia.png","2026-06-06T14:17:20.522361+00:00",{"id":28,"slug":29,"title":30,"summary":31,"category":32,"image_url":33,"cover_image":33,"language":18,"created_at":34},"bef47dbc-b0b4-439e-bae9-abe9473a321c","wei-shen-me-tether-ba-ben-di-ai-ji-yi-tui-jin-ri-chang-zhuan-zh","為什麼 Tether 把本地 AI 記憶推進日常裝置是對的","TurboQuant 的價值不在於更快，而在於把長上下文 AI 從資料中心拉回手機、筆電與邊緣裝置，讓本地 AI 真正可用。","tools","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1780542170805-opi6.png","2026-06-04T03:02:19.599329+00:00",{"id":36,"slug":37,"title":38,"summary":39,"category":16,"image_url":40,"cover_image":40,"language":18,"created_at":41},"06774dfe-08eb-4a53-a8f7-36389b462c2b","llama-3-1-70b-specs-benchmarks-deployment-zh","Llama 3.1 70B：規格與部署","Meta 的 Llama 3.1 70B 仍是 128K 長上下文的自架文字模型，適合內部聊天、RAG 與 API 編排，重點在成本控制與部署自主性。","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1780395481064-5yri.png","2026-06-02T10:17:33.072306+00:00",{"id":43,"slug":44,"title":45,"summary":46,"category":32,"image_url":47,"cover_image":47,"language":18,"created_at":48},"2f8b506f-91a9-4d0c-9171-303301c4d23a","why-claude-code-should-use-deepseek-v4-for-1m-context-zh","為什麼 Claude Code 應該用 DeepSeek v4 來處理 1M …","Claude Code 在長上下文程式工作上，應優先路由到 DeepSeek v4，因為 1M context 比品牌偏好更能決定實際產出。","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1777867842186-4psy.png","2026-05-04T04:10:18.556889+00:00",{"id":50,"slug":51,"title":52,"summary":53,"category":16,"image_url":54,"cover_image":54,"language":18,"created_at":55},"b875d3ed-f892-43a8-a51e-920729e85b1e","gpt-5-4-benchmarks-2026-scores-rankings-zh","GPT-5.4 知識測驗拿 97.6 分","GPT-5.4 在 BenchLM 知識與理解拿到 97.6 分，總榜暫列第 2，還有 1.05M token 長上下文。這篇拆解它適合哪些工作、和其他模型怎麼比。","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1776082194973-cyii.png","2026-04-13T12:09:40.301446+00:00",{"id":57,"slug":58,"title":59,"summary":60,"category":32,"image_url":61,"cover_image":61,"language":18,"created_at":62},"99c0866d-50f9-4a93-a282-b092f9d298df","claude-code-compaction-context-management-zh","Claude Code壓縮機制怎麼省上下文","Claude Code 用多層壓縮處理長對話上下文，避免 200K 到 1M token 被文件、Shell 輸出和編輯記錄吃光。","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1775629324817-9lcw.png","2026-04-08T06:21:46.65172+00:00",{"id":64,"slug":65,"title":66,"summary":67,"category":16,"image_url":68,"cover_image":68,"language":18,"created_at":69},"fad499f8-512b-4d92-8110-7a4aaac4801f","grok-41-xai-quieter-upgrade-matters-zh","Grok 4.1 低調升級，卻很有料","xAI 的 Grok 4.1 把幻覺率從 12.09% 降到 4.22%，還加入 Fast 與 Thinking 兩種模式，支援 256k context 與 2M token API，對開發者很實際。","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1775175345966-349k.png","2026-04-03T00:15:29.860687+00:00",{"id":71,"slug":72,"title":73,"summary":74,"category":16,"image_url":75,"cover_image":75,"language":18,"created_at":76},"f0fb0635-5207-4fc5-b913-a4ab205ebb66","grok-420-xai-flagship-model-explained-zh","Grok 4.20 怎麼看","xAI 的 Grok 4.20 主打 200 萬 token 長上下文、多代理推理與 API 價格。這篇拆解它的定位、規格、競品差異與開發者該注意的坑。","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1775175176314-zyny.png","2026-04-03T00:12:37.401835+00:00",{"id":78,"slug":79,"title":80,"summary":81,"category":82,"image_url":83,"cover_image":83,"language":18,"created_at":84},"ff021fab-7330-4e01-8187-ca099f7c31f4","claude-vs-chatgpt-copilot-gemini-enterprise-2026-zh","Claude、ChatGPT、Copilot、Gemini…","Claude 擅長長上下文與程式工作；ChatGPT、Copilot、Gemini 則靠分發、整合與工作流吃香。企業 2026 年該怎麼選，重點不是誰最強，而是誰最適合你的資料、流程與控管。","industry","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1775153757367-xo7r.png","2026-04-02T18:15:40.452457+00:00",{"id":86,"slug":87,"title":88,"summary":89,"category":16,"image_url":90,"cover_image":90,"language":18,"created_at":91},"5a3c6417-77a9-4526-bee5-c355979576f2","gemini-3-1-pro-googles-top-model-in-numbers-zh","Gemini 3.1 Pro 數字看真實力","Gemini 3.1 Pro 以 77.1% ARC-AGI-2、94.3% GPQA Diamond、1M token 上下文登場，價格仍維持 Gemini 3。這次重點不是噱頭，而是長文檔、程式碼與 agent 工作流的實戰成本。","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1775153580311-vv9w.png","2026-04-02T18:12:41.777858+00:00",{"id":93,"slug":94,"title":95,"summary":96,"category":97,"image_url":98,"cover_image":98,"language":18,"created_at":99},"9d1ed0f2-aace-46ce-9b0a-0c0d8655e8e8","turboquant-wont-fix-memory-crunch-zh","TurboQuant 解不了記憶體荒","Google 的 TurboQuant 可把 KV-cache 記憶體用量降到 6 倍，但更長上下文、更多 agent 與更高吞吐，可能把 DRAM 和 NAND 需求繼續往上推。","research","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1775132150405-6fvw.png","2026-04-02T12:15:31.810812+00:00"]