Explore the world of scent detection and creation with Alex Wiltschko, Founder and CEO of Osmo. From mapping smell using AI to scent prediction, Alex takes us on a scented journey. Discover the potential of capturing memories through smell and the power of scent detection in robotics and AI. Also, learn about Solonus and how it enables businesses to generate process intelligence with AI.
Read more
AI Summary
AI Chapters
Episode notes
auto_awesome
Podcast summary created with Snipd AI
Quick takeaways
Osmo's AI platform predicts the smell of molecules based on their structure, surpassing human predictions in scent Turing tests.
Osmo collaborates with the Gates Foundation to create safe and effective insect repellents using their scent AI platform.
Osmo's Scent AI platform has the potential to revolutionize human interaction with the olfactory world and can be applied in various industries, including robotics and environmental assessments.
Deep dives
Discovering New Fragrance Molecules
Osmo's artificial intelligence platform is utilized to discover new fragrance molecules that are pleasant, affordable, and safe. By leveraging graph neural networks, they can predict the smell of a molecule based on its structure, surpassing human predictions in scent Turing tests. Osmo focuses on constructing fragrance ingredients for a wide range of products, including perfumes, home care, and personal care items. The goal is to replace potentially unsafe or environmentally harmful molecules with superior alternatives that meet the rising standards of society.
Insect Repellents Powered by AI
Osmo collaborates with the Gates Foundation to create insect repellents using their scent AI platform. By analyzing the molecular structure of thousands of compounds, their AI system identifies molecules that repel mosquitoes. The ultimate aim is to design safe, effective, and pleasant-smelling repellents that can help combat insect-borne diseases. Osmo's platform, equipped with an extensive knowledge of scent and an advanced understanding of molecular properties, allows them to access the enormous space of potential molecules and discover novel solutions.
The Digital Future of Smell
Osmo is at the forefront of digitizing the sense of smell. By building an extensive odor map and AI platform, they aim to compress the timeline of olfactory digitization to benefit various areas, including entertainment, memory preservation, and even environmental monitoring. Through their Scent AI platform, they can predict the smell of molecules, facilitating the creation of natural language interfaces and expanding the possibilities for using scent in everyday life. This innovative approach holds promise for capturing, storing, and recreating smells, revolutionizing human interaction with the olfactory world.
Potential Applications with Chemical Sensors
Beyond fragrance-related applications, Osmo's Scent AI platform can be deployed in conjunction with chemical sensors. This partnership could yield advancements in electronic noses, as the platform has the potential to interpret complex signals from such devices. By combining cutting-edge sensor technologies with Osmo's AI capabilities, it becomes feasible to create compact scent detection systems for various industries, including robotics, safety monitoring, and environmental assessments.
Workflow Integration with Large Language Models
While Osmo's primary focus is capturing and predicting scent-related data, there's potential to integrate their AI platform with large language models (LLMs). By utilizing LLMs as a natural language interface to interact with Osmo's proprietary tools, productivity can be enhanced. LLMs could facilitate seamless communication and refining within the scent engineering workflow, allowing for easy incorporation of natural language queries and descriptions into the process of discovering, predicting, and synthesizing molecules.
This episode is sponsored by Celonis, the global leader in process mining. AI has landed and enterprises are adapting. To give customers’ slick experiences and teams the technology to deliver. The road is long, but you’re closer than you think. Your business processes run through systems. Creating data at every step. Celonis reconstructs this data to generate Process Intelligence. A common business language. So AI knows how your business flows. Across every department, every system and every process. With AI solutions powered by Celonis enterprises get faster, more accurate insights. A new level of automation potential. And a step change in productivity, performance and customer satisfaction Process Intelligence is the missing piece in the AI Enabled tech stack.
Go to https://celonis.com/eyeonai to find out more.
Explore the world of scent detection and creation with our special guest, Alex Wiltschko, Founder and CEO of Osmo. Alex is giving computers a sense of smell to improve the health and happiness of human life.
From discussing the complexities of mapping smell using artificial intelligence to the lexicon used by perfumers to standardize their work, Alex takes us on a scented journey that’s bound to whet your olfactory appetite. You’ll be intrigued by how olfactory sensory neurons express 350 distinct channels of information and how AI can predict smells based on the molecular structure.
Alex shares his insights about a unique project they’ve been working on with the Gates Foundation to create molecules that smell good to humans but repel insects. We dive into the prospect of finding safe, affordable, and great smelling molecules via AI, and how this can have a profound impact on products we use every day.
Finally, we shift the conversation to the use of large language models in creating natural language interfaces. Alex shares how Osmo is using AI to ‘open the window of computation to smells’ and how this technology can potentially make us healthier and happier.
(00:00) Preview (00:30) Celonis Sponsorship & introduction (03:30) Alex's Interest in Neuroscience and Scents (05:20) The Neuroscience of Wine Tasting (14:25) Mapping Smell With Artificial Intelligence (18:05) How AI Integrates with Smell & Molecules (21:43) Perfumers' Language Dictionary and Taxonomy (25:20) Completing the Double Blind Test For Scent (34:05) Discovering Safe and Effective Fragrance Molecules (44:23) The Future of Fragrance Technology (54:48) Large Language Models in Natural Language Interfaces
Get the Snipd podcast app
Unlock the knowledge in podcasts with the podcast player of the future.
AI-powered podcast player
Listen to all your favourite podcasts with AI-powered features
Discover highlights
Listen to the best highlights from the podcasts you love and dive into the full episode
Save any moment
Hear something you like? Tap your headphones to save it with AI-generated key takeaways
Share & Export
Send highlights to Twitter, WhatsApp or export them to Notion, Readwise & more
AI-powered podcast player
Listen to all your favourite podcasts with AI-powered features
Discover highlights
Listen to the best highlights from the podcasts you love and dive into the full episode