[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"tag-agentic-coding":3},{"tag":4,"articles":11},{"id":5,"name":6,"slug":7,"article_count":8,"description_zh":9,"description_en":10},"9739b73b-e42a-4dc3-a906-b1f97a56db6f","agentic coding","agentic-coding",12,"Agentic coding 指的是讓模型不只回答程式問題，而是能規劃、修改、測試並反覆修正整個開發流程。這類工作流常牽涉工具呼叫、多代理協作、長上下文與高額 token 成本，也直接影響 SWE-bench、Claude Code 與開源模型部署策略。","Agentic coding refers to models that plan, edit, test, and iterate across a software task instead of answering a single prompt. It raises practical issues around tool use, multi-agent coordination, long contexts, token cost, and deployment choices for SWE-bench-style workflows and Claude Code-like setups.",[12,21,28,36,44,51,58,66],{"id":13,"slug":14,"title":15,"summary":16,"category":17,"image_url":18,"cover_image":18,"language":19,"created_at":20},"1d5fc6b1-a87f-48ae-89ee-e5f0da86eb2d","why-xiaomi-mimo-v25-pro-changes-coding-agents-en","Why Xiaomi’s MiMo-V2.5-Pro Changes Coding Agents More Than Chatbots","MiMo-V2.5-Pro matters because it is built for long, tool-heavy coding work, not chat.","model-release","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1778689848027-ocpw.png","en","2026-05-13T16:30:29.661993+00:00",{"id":22,"slug":23,"title":24,"summary":25,"category":17,"image_url":26,"cover_image":26,"language":19,"created_at":27},"cb6097c9-9b15-4ff5-860d-5d1b172035db","kimi-k26-qwen-36-open-source-frontier-gap-en","Kimi K2.6 and Qwen 3.6 Narrow the Gap","Kimi K2.6 and Qwen 3.6 are open-weight models that now rival closed models on coding and agent tasks.","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1777901475047-q3mm.png","2026-05-04T13:30:41.54989+00:00",{"id":29,"slug":30,"title":31,"summary":32,"category":33,"image_url":34,"cover_image":34,"language":19,"created_at":35},"904270f5-c35d-4938-915f-99b405511466","ai-agents-token-spending-coding-tasks-en","AI Coding Agents Burn 1000x More Tokens Than Chat","A study of SWE-bench Verified shows agentic coding can consume 1000x more tokens than chat, with costs driven by inputs and hard to predict.","research","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1777270014409-t6t5.png","2026-04-27T06:06:38.046891+00:00",{"id":37,"slug":38,"title":39,"summary":40,"category":17,"image_url":41,"cover_image":42,"language":19,"created_at":43},"674cce69-5be8-4c32-bfbd-32ab6fd2fcd7","qwen36-27b-open-source-coding-model-en","Qwen3.6-27B opens a smaller, sharper path to coding","Qwen3.6-27B is a 27B dense multimodal model that beats Qwen3.5-397B-A17B on key coding benchmarks while staying easier to deploy.","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1777260618061-cpw4.png","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Fskill-cover-qwen36-27b-en_-1777263004.png","2026-04-27T00:12:39.968514+00:00",{"id":45,"slug":46,"title":47,"summary":48,"category":17,"image_url":49,"cover_image":49,"language":19,"created_at":50},"2ab61916-02e3-47f5-8131-9d69cb770f03","claude-opus-4-7-release-workflow-vision-en","Claude Opus 4.7 发布：更会干活了","Anthropic发布Claude Opus 4.7，长任务、视觉理解和代码工作流更强，但Token消耗也更高。","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1776859438392-675v.png","2026-04-22T12:03:39.271461+00:00",{"id":52,"slug":53,"title":54,"summary":55,"category":17,"image_url":56,"cover_image":56,"language":19,"created_at":57},"26e34d8d-efd4-4253-a791-cca1b1803567","qwen36-35b-a3b-open-source-coding-model-en","Qwen3.6-35B-A3B: 35B Open Source Model Release","Qwen3.6-35B-A3B ships with 35B total params, 3B active params, and Anthropic API compatibility for Claude Code workflows.","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1776643430778-2if7.png","2026-04-20T00:03:37.697765+00:00",{"id":59,"slug":60,"title":61,"summary":62,"category":17,"image_url":63,"cover_image":64,"language":19,"created_at":65},"d23cd5f6-f875-49f5-b53b-1c5416d13d99","cursor-composer-2-agentic-coding-model-en","Cursor Composer 2 Bets on Agentic Coding","Cursor’s Composer 2 posts 61.3 on CursorBench and 61.7 on Terminal-Bench 2.0, with pricing aimed at high-volume coding teams.",null,"https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1774498610250-zp8n.png","2026-03-28T03:13:06.513673+00:00",{"id":67,"slug":68,"title":69,"summary":70,"category":17,"image_url":63,"cover_image":71,"language":19,"created_at":72},"f063d8d1-41d1-4de4-8ebc-6c40511b9369","xiaomi-mimo-v2-pro-1t-moe-agents-en","Xiaomi MiMo-V2-Pro: 1T MoE Model for Agents","Xiaomi’s MiMo-V2-Pro packs 1T parameters, 42B active, and 1M context, with SWE-bench results close to Claude Sonnet 4.6.","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1774619185536-iewn.png","2026-03-28T03:06:19.238032+00:00"]