Announcement
ScholarCatalyst benchmark draws on AI researchers’ accounts of what inspired their work
The announcement argues that AI can increasingly make progress on open problems, but defining new ones still relies on human research taste.
TLDR
A post introducing ScholarCatalyst describes a benchmark built from AI researchers’ firsthand accounts of what inspired their work. Its author argues that AI can increasingly make progress on open problems like Navier-Stokes, while defining a new problem still relies on human research taste.
Combined views
5.7K
3 Sources, first seen ago
