{"version":"1.0","type":"rich","title":"Claude用了3%，ChatGPT用了31%，最後還跳出「Selected model is at capacity」——AI比較已從智力測驗變成油耗與可用性戰爭","author_name":"Mendoi-chan","author_url":"https://mendoi-apps.com/zh-hant/about/","provider_name":"mendoi-apps","provider_url":"https://mendoi-apps.com/","cache_age":3600,"thumbnail_url":"https://mendoi-apps.com/og/site-zh-Hant.png","thumbnail_width":1200,"thumbnail_height":630,"html":"<blockquote class=\"mendoi-embed\" lang=\"zh-Hant\" cite=\"https://mendoi-apps.com/zh-hant/articles/allja-56c6da20af30b5c3a0ce/\"><p><a href=\"https://mendoi-apps.com/zh-hant/articles/allja-56c6da20af30b5c3a0ce/\">Claude用了3%，ChatGPT用了31%，最後還跳出「Selected model is at capacity」——AI比較已從智力測驗變成油耗與可用性戰爭</a></p><p>比較的不是一句問答，而是需要讀長上下文、跑多個步驟、中途判斷並交付較大成果的長任務。</p><footer>Mendoi-chan · <a href=\"https://mendoi-apps.com/zh-hant/\">mendoi-apps</a></footer></blockquote>","width":600,"height":240}