RESEARCH · RESEARCH · #1470
Harvard physicist Matthew Schwartz publishes BootLoops, an open-source AI harness for exact scientific calculations
Matthew Schwartz (Harvard; visiting researcher at Anthropic) developed BootLoops, an open-source harness that uses Anthropic's Claude to perform exact scientific calculations and bridge gaps between disciplines; the team generated 36 manuscripts across 18 fields and the code is available on GitHub. Schwartz reports novel results (e.g., computed integrals, a solved 20‑year ecological equation, population‑genetics signals) but warns models often misjudge completion, can draw incorrect conclusions from correct calculations, and require human verification.
KEY POINTS
- Matthew Schwartz (Harvard; visiting researcher at Anthropic) developed BootLoops, an open-source harness that uses Anthropic's Claude to perform exact scientific calculations and bridge gaps between disciplines; the team generated 36 manuscripts across 18 fields and the code is available on GitHub.
- Schwartz reports novel results (e.g., computed integrals, a solved 20‑year ecological equation, population‑genetics signals) but warns models often misjudge completion, can draw incorrect conclusions from correct calculations, and require human verification.
- BootLoops shows large language models can accelerate cross-disciplinary, exact scientific calculations and discover new results, but also highlights persistent reliability and oversight requirements.
WHY IT MATTERS
BootLoops shows large language models can accelerate cross-disciplinary, exact scientific calculations and discover new results, but also highlights persistent reliability and oversight requirements.