[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"tag-ai-safety":3},{"tag":4,"articles":11},{"id":5,"name":6,"slug":7,"article_count":8,"description_zh":9,"description_en":10},"7c7a43b6-45da-4d93-b1e4-03af717557d6","AI safety","ai-safety",8,"AI 安全關注模型在真實場景中的風險控制：從越獄、幻覺與惡意提示，到雙重用途、資安測試與法規責任。這個主題連結研究、產品限制與監管動態，直接影響聊天機器人、企業部署與高風險應用。","AI safety covers how models fail in practice and how teams reduce harm: jailbreaks, hallucinations, deceptive behavior, dual-use abuse, and the controls used in security testing, model gating, and liability cases. It sits at the intersection of research, product policy, and regulation.",[12,21,28,36],{"id":13,"slug":14,"title":15,"summary":16,"category":17,"image_url":18,"cover_image":18,"language":19,"created_at":20},"08c387e0-9c64-4d3a-a1d1-e67b4111455f","7-claims-in-floridas-openai-lawsuit-zh","7 項佛州告 OpenAI 的主張","7 項主張看佛州如何指控 OpenAI 與 Sam Altman 把成長放在安全之前，並牽動產品責任、未成年保護與警示義務。","industry","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1780385583741-39xw.png","zh","2026-06-02T07:32:34.161939+00:00",{"id":22,"slug":23,"title":24,"summary":25,"category":17,"image_url":26,"cover_image":26,"language":19,"created_at":27},"d3eaf934-5022-45c0-9767-19ac8ba543dc","demis-hassabis-says-agi-is-years-away-zh","Hassabis：AGI 只剩幾年準備期","Google DeepMind 執行長 Hassabis 在 Google I\u002FO 表示，社會只剩幾年時間為 AGI 做準備，並把現況形容為「奇點的山麓」。","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1780149776537-g9ck.png","2026-05-30T14:02:24.102179+00:00",{"id":29,"slug":30,"title":31,"summary":32,"category":33,"image_url":34,"cover_image":34,"language":19,"created_at":35},"0457279b-cadb-48ac-a7da-0e5410393612","microsoft-open-source-ai-safety-agent-tools-zh","為什麼 Microsoft 的開源 AI 安全工具值得重視","Microsoft 把 RAMPART 和 Clarity 開源，等於把 AI 安全從事後審查拉進日常 agent 工程，這是正確方向。","tools","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1779595548351-4h2k.png","2026-05-24T04:05:23.204019+00:00",{"id":37,"slug":38,"title":39,"summary":40,"category":41,"image_url":42,"cover_image":42,"language":19,"created_at":43},"6ca303f0-7bd4-4bb2-be58-70d80da5ec40","why-ai-safety-teams-are-wrong-blame-only-alignment-zh","為什麼 AI 安全團隊錯把問題全怪在對齊","AI 模型的危險行為不只來自對齊失敗，也來自訓練資料灌進去的有害敘事；安全團隊若只修對齊，會漏掉真正的風險來源。","research","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1778947417022-ak55.png","2026-05-16T16:03:16.319335+00:00"]