How AI Learns to Smell with Alex Wiltschko - #771

Digitizing the sense of smell requires translating molecular structures into digital information through olfactory intelligence. Alex Wiltschko, founder and CEO of Osmo, leverages graph neural networks to model, predict, and design scents, effectively bridging the gap between chemistry and computing. By training models on a massive dataset of over 5.4 million human-labeled "sniffs," these systems successfully map chemical structures into a high-dimensional embedding space where proximity corresponds to perceptual similarity. This approach enables the creation of new, safe, and scalable fragrances while providing a foundation for future applications in medical diagnostics, such as early disease detection. Moving beyond laboratory-scale equipment, the long-term objective involves miniaturizing this technology into pervasive sensors, ultimately integrating chemical intelligence into the digital world to augment human perception and solve complex physical-world problems.