Finding a Path from “Promise” to “Performance”—Toward Realizing Novel Materials Predicted via Generative AI
The “need for speed” drives early adopters toward autonomous labs. But it can also trip up well-intentioned researchers and managers seeking to convert promise into reality. The phrase “欲速则不达” captures this well: to speed up, one must slow down and think.
I’ll present a hard-earned “thinking checklist,” drawing from a decadal effort to accelerate R&D by combining AI/ML, high-throughput experiments and simulation. Come listen if you’re keen to tackle meaningful grand challenges with patient, sustained R&D investment.
I’ll concentrate on the experimental realization of materials proposed by generative AI, covering the topics:
(1) selecting appropriate problems for “automated” and “autonomous” systems
(2) increasing the odds that materials predicted by generative AI are experimentally accessible
(3) ensuring reproducible, transferable and “scale-up-able” synthesis
(4) choosing whether to buy or build (home-built automation equipment)
(5) performing rapid phase identification to validate synthesis
(6) venturing beyond standard optimization to find novel “exceptional” materials
(7) the human side: lessons of leadership, teambuilding, resources, institutional culture and committing to courageous change
Come spend a moment to reflect, exhale and maybe share a knowing laugh with other people driving this R&D transformation.