AI Summary
5 min readJoseph Krauss, CEO and co-founder of Radical AI, has a blunt message for competitors: “I’m gonna run you over. And if I miss you on the way going forward, I’m gonna hit you when I back up.” That tenacity reflects a company that started in 2024 and is now in its third year, having pivoted from bulk metallic glasses to high-entropy alloys and beyond. Radical AI is not selling software or recipes—it is selling actual materials, aiming to close the loop from discovery straight through to manufacturing. The core challenge, Krauss explains, is that “materials already have a problem of being a long industry. It takes decades to discover new material. You can't then come up with a new solution to solve the decades problem that takes decades.”
Speed as a Cultural Imperative
Continue reading the full summary in the app — free to try.
Read Full Summary →Free • No credit card required
Never miss an episode of Materialism: A Materials Science Podcast
Get every new episode summarized in your inbox — free, ~5 minutes to read.
No spam. Unsubscribe anytime.
What you'll learn
- 1 (02:18) **Company State & Core Thesis** - Joseph Krauss describes Radical AI's focus on closing the loop from discovery through to manufacturing, positioning the company as a platform for shrinking materials timelines.
- 2 (04:47) **Hardware Reality Check: The SDL Challenge** - Joseph admits the difficulty of building self-driving labs was far greater than anticipated, especially with tool vendors and system integration.
- 3 (06:11) **Speed & Culture as Competitive Moats** - Joseph explains that Radical AI's culture of shipping fast and embracing failure is the engine behind their rapid innovation, contrasting with academic timelines.
- 4 (09:39) **Concrete Failure: The SEM & XRD Integration** - A specific example of "moving fast and breaking things" where the team assumed modern lab equipment would have accessible data ports, only to find they did not.
- 5 (12:20) **The Discovery-to-Manufacturing Flywheel** - Joseph details why discovery cannot be separated from manufacturing considerations; microstructure changes at scale, altering properties.
- 6 (16:36) **Competition & The Technical Moat** - Joseph gives an unfiltered take on the competitive landscape: he doesn't care about competitors, but welcomes the ecosystem growth it brings.
- 7 (17:57) **In-Context Learning & The Matrix Model** - The breakthrough of using in-context learning to stabilize optimization, moving away from random search in Bayesian optimization loops.
+ Full timestamped outline available in the app
Show Notes
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.
Check out Radical AI here [LINK]
This episode of the Materialism Podcast is sponsored by Momentum Transfer. Visit their website for more details about their measurement services. [LINK]
The Materialism Podcast is sponsored by Materials Today, an Elsevier community dedicated to the creation and sharing of materials science knowledge and experience through their peer-reviewed journals, academic conferences, educational webinars, and more. [LINK]
Thanks to Kolobyte and Alphabot for letting us use their music in the show!
If you have questions or feedback please send us emails at [email protected] or connect with us on social media: Instagram, Twitter.
Materialism Team: Taylor Sparks, Andrew Falkowski, & Jared Duffy.
More from this podcast
Materialism: A Materials Science Podcast →