Prof. Matthew Schwartz describes BootLoops, a toolkit designed to align AI capabilities with scientific research needs. By identifying "Claude-shaped" problems—quantitative challenges suited to LLM strengths—Schwartz built an open-source harness that helped Claude discover connections across physics, ecology, genetics, and other fields, addressing the impedance mismatch between what scientists need and what current AI does well.
Prof. Matthew Schwartz describes BootLoops, a toolkit developed with Claude to identify and solve "Claude-shaped" problems—quantitative science questions best suited to current LLM capabilities. By working with domain experts across ecology, genetics, physics, and other fields, BootLoops discovered technical connections and made substantive advances by matching AI strengths to scientific needs rather than forcing AI to work like human scientists.