[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"tag-agentic-coding":3},{"tag":4,"articles":11,"peer_article_count":160},{"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.",[12,21,29,36,44,51,58,65,73,80,87,94,101,108,115,123,131,138,145,153],{"id":13,"slug":14,"title":15,"summary":16,"category":17,"image_url":18,"cover_image":18,"language":19,"created_at":20},"03903663-658a-4f3d-8edb-735c19ddf897","devin-ai-review-2026-benchmarks-pricing-tests-en","Devin AI Review 2026: Benchmarks, Pricing & Tests","A developer guide to testing Devin AI, its benchmarks, pricing, and workflow limits.","tools","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1782362868557-ar7n.png","en","2026-06-25T04:47:27.72498+00:00",{"id":22,"slug":23,"title":24,"summary":25,"category":26,"image_url":27,"cover_image":27,"language":19,"created_at":28},"bae2c76d-53a2-468f-9451-32112f760733","spacex-shou-gou-cursor-bu-hua-suan-ai-bian-cheng-en","SpaceX收购Cursor不划算，AI编程能力应自己做","SpaceX花600亿收购Cursor并不划算，AI编程能力更该自建。","industry","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1781877772236-jpfj.png","2026-06-19T14:02:19.96906+00:00",{"id":30,"slug":31,"title":32,"summary":33,"category":17,"image_url":34,"cover_image":34,"language":19,"created_at":35},"1e01a6f4-3f54-407d-a775-f9147de8b911","8-cursor-alternatives-that-fit-how-you-work-en","8 Cursor alternatives that fit how you work","I break down eight Cursor alternatives, what each one is actually good for, and the template I’d start from.","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1781312598893-8ox5.png","2026-06-13T01:02:56.581668+00:00",{"id":37,"slug":38,"title":39,"summary":40,"category":41,"image_url":42,"cover_image":42,"language":19,"created_at":43},"435fc551-a461-444a-bf95-dbf5685cfac0","minimax-m3-open-weight-coding-win-en","MiniMax M3 Proves Open-Weight Can Still Win on Coding","MiniMax M3 makes a strong case that open-weight models can still lead on coding, context, and price.","model-release","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1780968781159-odhi.png","2026-06-09T01:32:31.256895+00:00",{"id":45,"slug":46,"title":47,"summary":48,"category":41,"image_url":49,"cover_image":49,"language":19,"created_at":50},"758b2a2e-2785-432e-b7c2-4947a7a078f3","why-minimax-m3-matters-long-context-model-en","Why MiniMax M3 matters more than another long-context model","MiniMax M3 is a real step forward because it pairs long context with multimodal and agentic control.","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1780755477727-j0go.png","2026-06-06T14:17:21.058476+00:00",{"id":52,"slug":53,"title":54,"summary":55,"category":26,"image_url":56,"cover_image":56,"language":19,"created_at":57},"e7d761e1-12cc-4b6e-9e90-88eb807e030f","5-github-explore-picks-for-builders-en","5 GitHub Explore picks for builders","5 GitHub Explore picks show what builders are shipping, from agentic coding tools to document parsers and open-source apps.","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1780067886267-cp6g.png","2026-05-29T15:17:37.867397+00:00",{"id":59,"slug":60,"title":61,"summary":62,"category":41,"image_url":63,"cover_image":63,"language":19,"created_at":64},"3dea00fc-0edf-4a95-8809-803f0bea1b35","gpt-5-model-comparison-5-0-to-5-5-en","GPT-5.0 to 5.5: Which ChatGPT Model Wins?","OpenAI’s GPT-5 family grew from a 400K-token baseline to 1M-token agentic models, with GPT-5.5 now leading benchmarks.","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1780007585568-qbtw.png","2026-05-28T22:32:39.599972+00:00",{"id":66,"slug":67,"title":68,"summary":69,"category":70,"image_url":71,"cover_image":71,"language":19,"created_at":72},"e84510d4-8387-4a7f-bf15-3bdcf575f6a0","why-devin-ai-is-overrated-software-engineer-en","Why Devin AI is overrated as a software engineer","Devin AI is impressive, but it is not the autonomous software engineer its launch implied.","ai-agent","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1779816964028-8nl0.png","2026-05-26T17:35:26.512611+00:00",{"id":74,"slug":75,"title":76,"summary":77,"category":17,"image_url":78,"cover_image":78,"language":19,"created_at":79},"839ae514-f64f-4cb4-9650-a318f5a64acf","sonar-acquires-gitar-ai-code-review-en","Sonar Acquires Gitar for AI Code Review","Sonar bought Gitar to add AI code review to SonarQube, pairing review with verification for agent-written code across CI workflows.","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1779761155350-ps06.png","2026-05-26T02:05:29.383535+00:00",{"id":81,"slug":82,"title":83,"summary":84,"category":70,"image_url":85,"cover_image":85,"language":19,"created_at":86},"198b2c7e-50d9-4805-a586-a77401d6de3d","zero-turns-compiler-errors-into-agent-ready-json-en","Zero turns compiler errors into agent-ready JSON","I break down Vercel Zero’s agent-first compiler design and give you a copy-ready template for structured diagnostics.","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1779744981645-urg4.png","2026-05-25T21:35:56.339171+00:00",{"id":88,"slug":89,"title":90,"summary":91,"category":26,"image_url":92,"cover_image":92,"language":19,"created_at":93},"b20531aa-2384-4e49-a03f-3dbe680ed74d","why-amazon-q-developer-is-wrong-future-coding-en","Why Amazon Q Developer is wrong about the future of coding","Amazon Q Developer is a strong AWS assistant, but it should not be treated as the future of software development.","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1779177246999-vh6i.png","2026-05-19T07:53:39.110344+00:00",{"id":95,"slug":96,"title":97,"summary":98,"category":41,"image_url":99,"cover_image":99,"language":19,"created_at":100},"3e183760-52e4-4491-8ea9-be02ccac1042","minimax-m2-open-source-agentic-coding-en","MiniMax M2 opens up cheap agentic coding","MiniMax open-sourced M2, a model for agents and code that costs $0.30 per million input tokens and is free for a limited time.","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1779077044155-be13.png","2026-05-18T04:03:38.169023+00:00",{"id":102,"slug":103,"title":104,"summary":105,"category":41,"image_url":106,"cover_image":106,"language":19,"created_at":107},"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.","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1778689848027-ocpw.png","2026-05-13T16:30:29.661993+00:00",{"id":109,"slug":110,"title":111,"summary":112,"category":41,"image_url":113,"cover_image":113,"language":19,"created_at":114},"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":116,"slug":117,"title":118,"summary":119,"category":120,"image_url":121,"cover_image":121,"language":19,"created_at":122},"904270f5-c35d-4938-915f-99b405511466","ai-agents-token-spending-coding-tasks-en","How AI Agents Spend Your Money: 1000x Tokens on SWE-bench","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":124,"slug":125,"title":126,"summary":127,"category":41,"image_url":128,"cover_image":129,"language":19,"created_at":130},"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":132,"slug":133,"title":134,"summary":135,"category":41,"image_url":136,"cover_image":136,"language":19,"created_at":137},"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":139,"slug":140,"title":141,"summary":142,"category":41,"image_url":143,"cover_image":143,"language":19,"created_at":144},"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":146,"slug":147,"title":148,"summary":149,"category":41,"image_url":150,"cover_image":151,"language":19,"created_at":152},"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":154,"slug":155,"title":156,"summary":157,"category":41,"image_url":150,"cover_image":158,"language":19,"created_at":159},"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",18]