Research notes
Rough research updates and observations from the CRUX team
Why do our findings differ from Sakana’s AI Scientist?
By Stephan Rabanser, Peter Kirgis, Sayash Kapoor, and Arvind NarayananUpdate on our long-horizon AI R&D evaluations
CRUX 2 is testing whether AI agents can answer novel, open-ended AI research questions.
By Sayash Kapoor, Peter Kirgis, Andrew Schwartz, and Arvind Narayanan