# Claude Science

Working with Claude Science, Brice Ménard orchestrated a team of AI agents to gather public UV and multi-wavelength data from GALEX, Swift, FIMS/SPEAR, TD-1, Planck and Gaia, cross-calibrate and merge the surveys, inpaint roughly one third of the sky never observed in UV using learned multi-wavelength relations, and add UV estimates for more than 100 million individual stars, yielding the first complete UV map of the sky; in held-out tests the model estimated hidden UV data to within about 10% of real measurements.

Working with Claude Science, Brice Ménard orchestrated a team of AI agents to gather public UV and multi-wavelength data from GALEX, Swift, FIMS/SPEAR, TD-1, Planck and Gaia, cross-calibrate and merge the surveys, inpaint roughly one third of the sky never observed in UV using learned multi-wavelength relations, and add UV estimates for more than 100 million individual stars, yielding the first complete UV map of the sky; in held-out tests the model estimated hidden UV data to within about 10% of real measurements.

Physicist and science writer Matt von Hippel publicly challenged AI companies to solve a hard scattering-amplitude problem on an academic budget; Anthropic's Liam Fitzpatrick and Siddharth Mishra-Sharma used Fable 5.1 inside the Claude Science platform, gave Claude a single problem statement and then mostly just told it to keep going, and Claude computed the six-particle (hexagon) nine-loop amplitude in planar N=4 super Yang-Mills two different ways, via the original bootstrap and via the indirect form-factor route, with the bootstrap portion costing about $100, equivalent to running 96 CPUs for a week; Lance Dixon of SLAC then independently validated the result, and Song He's group at the Chinese Academy of Sciences had also computed the symbol piece of the nine-loop amplitude with GPT-6

Physicist and science writer Matt von Hippel publicly challenged AI companies to solve a hard scattering-amplitude problem on an academic budget; Anthropic's Liam Fitzpatrick and Siddharth Mishra-Sharma used Fable 5.1 inside the Claude Science platform, gave Claude a single problem statement and then mostly just told it to keep going, and Claude computed the six-particle (hexagon) nine-loop amplitude in planar N=4 super Yang-Mills two different ways, via the original bootstrap and via the indirect form-factor route, with the bootstrap portion costing about $100, equivalent to running 96 CPUs for a week; Lance Dixon of SLAC then independently validated the result, and Song He's group at the Chinese Academy of Sciences had also computed the symbol piece of the nine-loop amplitude with GPT-6