[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"tag-gpt-4":3},{"tag":4,"articles":11},{"id":5,"name":6,"slug":7,"article_count":8,"description_zh":9,"description_en":10},"2f2707ca-cd6d-43e9-9abe-e74fafcd8198","GPT-4","gpt-4",3,"GPT-4 是 OpenAI 的大型語言模型系列代表，常被拿來討論參數規模、推理品質、延遲與成本之間的取捨。相關話題也延伸到 GPT-4o、模型蒸餾、工具呼叫與 agent 工作流程，反映生成式 AI 的工程實作重點。","GPT-4 refers to OpenAI’s flagship language model family and the tradeoffs it brought into focus: model size, reasoning quality, latency, and cost. The topic also connects to GPT-4o, distillation, tool use, and agent workflows, all central to how developers ship generative AI systems.",[12],{"id":13,"slug":14,"title":15,"summary":16,"category":17,"image_url":18,"cover_image":18,"language":19,"created_at":20},"4ed4aff6-7cc8-49a7-aa35-3f68e984135e","bytedance-deerflow-2-0-47k-stars-en","ByteDance's DeerFlow 2.0 Hits 47.3K Stars","ByteDance's DeerFlow 2.0 passed 47.3K GitHub stars and aims to make complex agent workflows easier to build and run.","ai-agent","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1775142414048-ba6h.png","en","2026-04-02T15:06:32.911177+00:00"]