PERSON DIRECTORY
Brandon Anderson
Brandon Anderson appears in 4 indexed conversations across Latent Space. This directory brings every appearance, source, TL;DR, digest, and transcript into one searchable feed.
🔬 "The Most Innovative Diffusion Research Is Happening in Drug Discovery, Not Image Generation"
Brandon AndersonEvan FeinbergSergey Edunov
Genesis Molecular AI is applying diffusion and inference-time scaling to 3D molecular design, targeting roughly 1 Å protein-ligand accuracy because 2 Å can hide chemically fatal errors.Its prospective edge comes from Incyte and Insitro programs that connect models to synthesis and ADMET feedback, while OpenBind showed stronger unseen-target generalization and GPUs remain the scaling bottleneck.
🔬There Is No AlphaFold for Materials — AI for Materials Discovery with Heather Kulik
Brandon AndersonRJ HonickyHeather Kulik
Materials AI lacks an AlphaFold-like shortcut: variable bonding and sparse experimental ground truth make validation a central bottleneck.AI found a polymer-network design that made the material about four times tougher through electron rearrangement during molecular breakage.Active learning offers at least a hundred- to thousandfold speedup across seven direct-air-capture objectives, but reliable DFT replacement at two orders of magnitude greater speed and device-scale processing remain unresolved.
🔬 From Red Teaming GPT-4 to Automating Drug Discovery: The Future of AI in Science — Andrew White
RJ HonickyBrandon AndersonAndrew White
FutureHouse’s Cosmos turns scientific discovery into a closed loop linking literature, data analysis, experiments and an evolving world model, shifting the bottleneck toward laboratory state, reagent logistics and experiment turnaround.Robin’s dry-AMD work showed verification can beat expert enthusiasm, while Ether0 exposed adversarial verifier failures; scaling discovery will depend on provenance, cheap filtering and robust tests before wet-lab spending.