CRUX Research Notes https://cruxevals.com/research-notes Rough research updates and observations from the CRUX team Wed, 19 Aug 2026 19:28:12 GMT https://validator.w3.org/feed/docs/rss2.html Nuxt + Feed for Node.js en All rights reserved 2026, CRUX <![CDATA[Why do our findings differ from Sakana’s AI Scientist?]]> https://cruxevals.com/research-notes/why-crux-2-differs-from-ai-scientist https://cruxevals.com/research-notes/why-crux-2-differs-from-ai-scientist Wed, 19 Aug 2026 00:00:00 GMT <![CDATA[Can AI agents conduct open-ended AI research? Early evidence from two case studies]]> https://cruxevals.com/crux/can-ai-agents-conduct-research https://cruxevals.com/crux/can-ai-agents-conduct-research Thu, 30 Jul 2026 00:00:00 GMT <![CDATA[Update on our long-horizon AI R&D evaluations]]> https://cruxevals.com/research-notes/long-horizon-ai-rd-evals https://cruxevals.com/research-notes/long-horizon-ai-rd-evals Thu, 02 Jul 2026 00:00:00 GMT