Many drugs work by binding to a specific target in the body and blocking or changing what it does. An important first step in the drug development process is designing a molecule that can bind tightly to its target. Traditionally, that's meant weeks or months of expert work per target, sifting through a large number of candidates to identify the few that work. We wanted to test if Claude could successfully design novel protein binders from scratch (also called de novo design). With a protein design prompt written by a human expert, Claude autonomously designed protein binders against 14 out of 15 targets. We then worked with Adaptyv Bio and Twist Bioscience, who independently built and tested the proteins Claude designed.

Sharing part of my commute with @josephfkrause keeps our decision-making moving fast. Tonight’s decision: @RadicalAI is hiring our first in-house brand designer. DM your portfolio if you want in on the most exciting company in NYC.

Nvidia and Eli Lilly are building a $1B lab for AI drug discovery in SF. Lilly CEO Dave Ricks talks about their data advantage: “Some scale [tech-bio] players…are just training on public data but they’re only 4,000 ever approved drugs. Lilly alone has 3 million failed drugs.”

What a time for U.S. manufacturers. Government is calling for innovative solutions to address some of America's most complex manufacturing and materials challenges relevant to the U.S. energy sector. Below is a list of top areas of interest. This isn't a surprise. The National Security Strategy, National Defense Strategy, and a slew of Executive Orders have signaled a surge in demand for these capabilities. For reindustrialization. To supercharge the defense industrial base. And now we're seeing the specific calls for innovation. One example: Department of Energy's HPC4EI initiative released a solicitation a few days ago. It's an opportunity for U.S. manufacturers to participate in collaborative projects with DOE national labs' supercomputing capabilities and technical expertise to strengthen domestic supply chains and enhance U.S. industrial competitiveness. Some of the solutions they are most interested in: - Overcoming qualification and certification barriers for advanced materials (time, cost) - Scaling and manufacturability / reducing cost and risk in scaling up advanced materials - Computational methods that reduce technical, cost, and supply chain risks for rare earth elements, battery materials, etc - Multifunctional materials w/ combined structural, thermal, and electrical performance - Advanced thermal management solutions for power electronics, semiconductors, computing systems - AI/ML driven materials informatics, end-to-end digital thread platforms, smart manufacturing approaches that enable faster development, reduced costs - Modeling of material systems that enable cost-effective domestic production -- e.g. rare-earth-free magnetic materials, substitutes for critical minerals - Advanced reactors, turbine systems, grid-scale storage - Simulation of advanced manufacturing methods Modeling of high-throughput machining, finishing, and forming technologies that deliver greater precision and reliability at scale - AI/ML and smart manufacturing platforms to optimize process control - Technologies that improve productivity optimization in energy-intensive industries - Chemicals and fuels -- process innovations, novel reactor and separation technologies, advanced materials development for chemical manufacturing - Iron and steelmaking, aluminum, and other metals -- innovative processes for primary metals production, methods to optimize productivity, methods to decopperize steel - Food and beverage products processing that optimize efficient recovery and reuse of waste energy, extend product shelf life, minimize waste - Cement and concrete, asphalt, and glass process innovations, alternative source materials, novel material composition, and solutions to reduce waste - Forest products, including novel dewatering or drying technologies and improved pulping and chemical recovery processes - Equipment and processes that improve industrial process heating, including reducing cost, improving efficiency, or enhancing product quality - Non-thermal processes for cost-competitive separations and treatments - Industrial technologies that can ensure grid reliability amidst industrial demand growth - Technologies that enable production of fit-for-purpose water -- e.g. reduce direct water consumption of data centers Concept papers due May 27.

You cannot buy a new gas turbine until 2030. Order books at GE, Siemens, and Mitsubishi stretch to 2029. Turbine prices have nearly tripled since 2019. Every AI data center needs power and every gas plant needs a turbine. And every turbine has one part that bottlenecks the entire industry: The blade. It has to survive in gas 500°C above the melting point of the metal it's made from and spin at up to 20,000 RPM under 10,000 g of centrifugal force. Each blade is grown as a single crystal of nickel superalloy, pulled through a vacuum furnace at 3 mm per minute. A set of blades costs $600,000 and takes 90 weeks to grow. The same metallurgy powers modern jet engines. Only 3 companies on Earth can build one. China spent $42 billion trying to catch up. They bought a Russian fighter engine, took it apart, and copied every part. Their copy ran 30 hours between overhauls versus 400 for the original. Modern Western engines run 4,000. You can reverse engineer the shape of a turbine blade. You cannot reverse engineer 60 years of metallurgy.