Materials

🔬 RL with Verifiable Rewards, but the Verifier is a Lab — Lila Sciences

Jul 16, 2026 · 1:41:04

Andy Beam (CTO) and Rafa Gómez-Bombarelli (Co-founder & CSO of Physical Sciences) of Lila Sciences argue that science is an 'infinite token generator' for AI, using reinforcement learning with verifiable rewards where the wet lab acts as the verifier. They claim one general model trained on ~10 trillion experimentally-verified reasoning tokens across biology, chemistry, and materials outperforms domain-specific models—'breadth gives us depth.' Their AI Science Factories treat the lab as a data center, with instruments on a 'PCI bus' and humans 'below the API line.' Highlights include a CAR-T candidate designed in six months by two or three people, 'monster UTRs' achieving ~10x Moderna/Pfizer mRNA expression, and the 'zero-FTE startup' business model. They discuss RL pathologies like collapsed chains of thought and a model that 'swears,' and note why there is still no AlphaFold for materials due to the sim-to-real gap.

🔬 The Limits of AI in Science - Why We Need Self-Driving Labs — Joseph Krause, Radical AI

Jun 17, 2026 · 1:16:50

Joseph Krause of Radical AI argues that the bottleneck in materials science is experiments, not ideas, and his company's self-driving lab combines AI hypothesis generation with automated synthesis and characterization to produce alloys at unprecedented speed—1,200 in six months, with 300 novel compositions and 10 already in commercial development. Radical's closed-loop system runs research campaigns, not just automated tasks, overcoming challenges like sample manipulation at 3,000°C and tool vendors' software access. Krause details how their AI explores elemental families humans overlooked, why they open-source models like Matrix (the moat is experimental data, not models), and how they plan to compress discovery timelines from decades to 3–5 years for defense and space applications. He addresses the 10-year qualification process for aerospace, supply chain geopolitics (e.g., hafnium price up 10–15x due to Chinese dominance), and the need for public-private partnerships to accelerate U.S. R&D. Finally, he urges ML engineers to lean into their expertise rather than try to become material scientists.

🔬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.

🔬Max Welling: Materials Underlie Everything

Feb 25, 2026 · 34:14

Max Welling, a pioneer in variational autoencoders and equivariant neural networks, argues that materials underlie everything from GPUs to the energy transition, and AI can turn material discovery into a search engine. He traces his career from quantum gravity with Gerard 't Hooft to climate-focused AI, founding CuspAI to accelerate carbon capture materials. CuspAI’s platform combines generative models, multi-scale digital twins, and LLM-powered agents, but Welling insists chemists remain in the loop for the foreseeable future. He explains equivariance as hardcoding symmetry into neural networks to reduce data needs, though data augmentation often works better at scale. His upcoming book reveals the identical mathematics between diffusion models and stochastic thermodynamics, promising cross-fertilization between machine learning and physics.