Claude-shaped science

gist

Matthew Schwartz says current language models are good at science but are not scientists, so he stopped treating Claude as the collaborator he wanted and looked for problems that fit it. He built BootLoops, an open-source harness for exact quantitative calculations, first on scattering amplitudes and then in ecology, genetics, and other fields. Early hits were often technically correct and scientifically uninteresting until domain experts redirected them. He argues the models can speed that loop without collapsing it, and that humans still decide what is worth doing.

ideas

• The mismatch is the method. Models know a lot and code fast, but Schwartz says they still need hand-holding to produce work a scientist would value.
• Hunt Claude-shaped problems. BootLoops is his harness for checkable quantitative work, starting with the semi-numerical S-matrix bootstrap rather than deep conceptual questions.
• Correct is not the same as interesting. Outside his field, experts often shrugged at the first result and then redirected the question.
• The loop does not collapse. Data still has to be acquired and checked. He sees no reason to replace the scientific method, and he wants humans credited for direction rather than typing.

quotes