[{"data":1,"prerenderedAt":16},["ShallowReactive",2],{"notes-list":3},[4],{"path":5,"slug":6,"title":7,"lede":8,"authors":9,"date":14,"devOnly":15},"\u002Fresearch-notes\u002Flong-horizon-ai-rd-evals","long-horizon-ai-rd-evals","Update on our long-horizon AI R&D evaluations","CRUX 2 is testing whether AI agents can answer novel, open-ended AI research questions.",[10,11,12,13],"Sayash Kapoor","Peter Kirgis","Andrew Schwartz","Arvind Narayanan","2026-07-02",false,1783979437919]