Chemistry

🔬There Is No AlphaFold for Materials — AI for Materials Discovery with Heather Kulik

Mar 24, 2026 · 35:15

Heather Kulik, MIT professor, demonstrates that AI can discover surprising new materials—such as a polymer made four times tougher via an unexpected quantum effect—but warns current models still fail basic chemistry tasks like generating a 22-atom ligand. She describes active learning with seven objectives to accelerate discovery of metal-organic frameworks for direct CO₂ capture, achieving hundred- to thousand-fold speedups per dimension. Kulik criticizes machine-learned potentials that 'look really good' but often produce nonsensical results, and notes that no large-scale experimental benchmark like CASP exists for materials. She calls for shared high-throughput cloud labs and standardized data reporting so published results are machine-learning-ready from day one. Her group's open-source tool MolSimplify (and MOFSimplify) generates transition-metal complexes and screens MOFs, and she invites feedback from users.

🔬Generating Molecules, Not Just Models

Feb 12, 2026 · 1:41:26

Gabriele Corso and Jeremy Wolwen, founders of Boltz, explain how their open-source models democratize biomolecular structure prediction and design, building on AlphaFold2's breakthrough in single-chain protein folding to model interactions with small molecules, RNA, and DNA. They recount how, after AlphaFold3 was kept closed by DeepMind, they built Boltz1 in months by training a single large model with mid-training bug fixes and limited compute. The conversation covers the shift from regression to generative diffusion models, the critical role of evolutionary multiple sequence alignments (MSAs), and the specialized pairwise triangular attention architecture that remains central. They detail Boltz2's addition of affinity prediction and BoltzGen's unified sequence-structure diffusion for designing proteins, nanobodies, and peptides, validated across 25 labs on targets with no known interactions. Boltz Lab provides an API and interface with optimized inference (10× faster small-molecule screening) and collaborative ranking tools, aiming to serve academia, startups, and enterprises while keeping core models open.

🔬 From Red Teaming GPT-4 to Automating Drug Discovery: The Future of AI in Science — Andrew White

Jan 28, 2026 · 1:13:56

Andrew White, co-founder of Future House and Edison Scientific, argues that automating the scientific method with LLM agents is now feasible, explaining how ChemCrow triggered White House briefings, how Kosmos uses a world model to generate and test hypotheses, and why EtherZero's reward hacking revealed the difficulty of verifiable chemistry tasks. He shifts from his academic work on molecular dynamics to building agents that enumerate and filter ideas, claiming scientific taste remains the frontier. White recounts the counterexample of D.E. Shaw Research's MD vs. AlphaFold, asserts that natural language is the universal bridge for scientific data, and predicts that automation will expand rather than eliminate scientific jobs.