Episode 88: Accelerating Materials Discovery with Microsoft

Aluminum may seem like a common metal today, but did you know it was once considered on par with silver? Taylor and Andrew sit down with Marat Latypov, a professor at the University of Arizona, to explore how aluminum went from a precious metal to one of the go-to metals of modern society. We talk about the discovery that collapsed the price from dollars to cents per pound and the patent dispute it caused. We explore how a metal so hungry for oxygen resists corrosion so well and how precipitation hardening was discovered after a weekend getaway. Finally, we look at more recent issues like the challenges of Ford's aluminum F-150, the fire hazards of 1970s aluminum house wiring, and why recycling scrap is harder than it sounds.

We have all seen the heat of atmospheric reentry depicted a thousand times in movies and TV shows, but how do we actually protect spacecraft from that danger? Taylor and Andrew sit down with Nate Olson, an aerospace engineer at NASA's Johnson Space Center, to explore the history of thermal protection systems. Nate unpacks the science of surviving atmospheric entry from the simple blunt-body design that made reentry physically possible, to the ~300,000 honeycomb cells hand-caulked with Avcoat on Apollo. We also touch on modern events like the Artemis I heat-shield anomaly and where he believes the technology could be headed.

What if a materials lab on Earth could screen a hundred alloys a day with little input from the scientist? Taylor and Andrew sit down with Joseph Krause, CEO and co-founder of Radical AI, to dig into what it takes to build a self-driving lab and why most of the field is still missing the hard part. From discovering that flagship SEM and XRD instruments ship with no real data access (and rebuilding their entire OS around the workaround), to MATRIX — their multimodal vision-language model that hones in on a target property in roughly 20 experiments — Joseph walks through the technical bets that got them here. He explains why they're using language-model embeddings to teach Bayesian optimization what "28% titanium" actually means, why "scientific intuition" has to be measured as a delta between human and AI annotations, and why Radical is going all the way to manufacturing instead of licensing compositions — because the real IP, and the only training data that matters, lives on the production floor.

What if you could know which batteries are worth building before you actually build them? Taylor and Andrew sit down with Dr. Qichao Hu, founder of SES AI, to explore how artificial intelligence is reshaping battery discovery and his experience in the field. From his decision to ditch solid state electrolytes and double down on liquid, to building a suite of simulation tools that map molecules all the way up to full cell performance. Dr. Hu lays out how SES went from lithium metal battery startup to offering their hard-won design tools as a platform for the rest of the industry.

The fanciest suit isn't on the runway, it's in orbit. In this follow-up episode, Taylor and Andrew bring back Kate Winning from Oxford Space Systems to dive into the world of space textiles. From the knitted gold-plated mesh antennas that fold up for launch and deploy to the size of a room, to the 14-layer suit that keeps astronauts alive. Learn why tungsten makes a better yarn than you'd expect, how ancient crafts still have a place in high tech manufacturing, and why the hardest part of a spacesuit might just be the gloves.