[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"tag-llm-safety":3},{"tag":4,"articles":10},{"id":5,"name":6,"slug":7,"article_count":8,"description_zh":9,"description_en":9},"467765ba-ffbd-45d1-992a-519169fa5f07","LLM safety","llm-safety",2,null,[11,20],{"id":12,"slug":13,"title":14,"summary":15,"category":16,"image_url":17,"cover_image":17,"language":18,"created_at":19},"94547a94-aa6b-4c4f-9d64-31eb0b906947","policy-invariance-llm-safety-judge-test-en","Policy Invariance as a Better LLM Judge Test","This paper argues that accuracy alone is not enough to trust LLM safety judges, and proposes policy invariance as a reliability test.","research","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1778568046410-5agq.png","en","2026-05-12T06:40:28.372648+00:00",{"id":21,"slug":22,"title":23,"summary":24,"category":16,"image_url":25,"cover_image":25,"language":18,"created_at":26},"6bf86d0c-df4b-4e0c-82b7-1c06b2ef80d5","asmr-bench-sabotage-detection-ml-code-en","ASMR-Bench Tests Sabotage Detection in ML Code","ASMR-Bench probes whether auditors can spot subtle sabotage in ML research codebases, and the answer so far is: not reliably.","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1776665038230-idp9.png","2026-04-20T06:03:33.439449+00:00"]