He Gave Claude a List of His Lab Equipment and It Designed Experiments He Could Actually Do
A New Experiment Meta-Strategy
After reorganizing his cluttered home lab, an independent scientist fed a list of his gear and chemicals to Claude, asking for a QtPy app that maps the state space of possible experiments. The tool suggests tabletop experiments probing complex phenomena, ranks them by difficulty and setup time, and even provides protocols. He's now exploring convection oscillations with better temperature probes.
I wondered what would happen if I tried to flip this on its head and tried to come up with stuff based on what I had already. Would this allow me to do interesting science more cheaply?