[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"tag-gpt-4o":3},{"tag":4,"articles":11,"peer_article_count":8},{"id":5,"name":6,"slug":7,"article_count":8,"description_zh":9,"description_en":10},"42dd357a-eb7f-4178-a36d-e2813bcf47e9","GPT-4o","gpt-4o",3,"GPT-4o 是 OpenAI 的多模態模型，常被拿來討論參數規模、延遲、成本與推理品質之間的取捨。這個主題也延伸到語音、影像與 agent 工作流，適合關注模型部署與實際效能的開發者。","GPT-4o is OpenAI’s multimodal model, often discussed in terms of parameter scale, latency, cost, and reasoning quality. This tag also connects to voice, image, and agent workflows, making it relevant for developers evaluating real-world model trade-offs.",[12,21,29],{"id":13,"slug":14,"title":15,"summary":16,"category":17,"image_url":18,"cover_image":18,"language":19,"created_at":20},"354441d5-652c-4658-a446-14f101f5e084","rootly-benchmark-llama-4-trails-coding-models-en","Rootly benchmark: Llama 4 trails coding models","Rootly AI Labs says Llama 4 lagged coding-focused models on a Mastodon GitHub benchmark, with GPT-4o and Qwen2.5-Coder ahead.","research","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1782086567786-wz4t.png","en","2026-06-22T00:02:22.751682+00:00",{"id":22,"slug":23,"title":24,"summary":25,"category":26,"image_url":27,"cover_image":27,"language":19,"created_at":28},"8273152c-3c9d-4c52-8a91-237847a95d48","copilot-studio-gpt-41-default-gpt-4o-retirement-en","Copilot Studio shifts to GPT-4.1 by default","Microsoft is retiring GPT-4o in Copilot Studio for generative orchestration and making GPT-4.1 the default model starting Oct. 27, 2025.","model-release","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1779031439978-9fdm.png","2026-05-17T15:23:34.064168+00:00",{"id":30,"slug":31,"title":32,"summary":33,"category":17,"image_url":34,"cover_image":34,"language":19,"created_at":35},"280d30d6-b080-4de0-b89b-fd239d8775fc","claude-opus-45-gpt-parameters-estimate-en","How Big Are Claude Opus 4.5 and GPT Models?","Claude Opus 4.5 and GPT models are likely far smaller than people assume, with GPT-4o estimates landing around 200B-300B.","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1775207397088-173o.png","2026-04-03T09:09:29.085297+00:00"]