Menu
Sign In Search Podcasts Charts People & Topics Add Podcast API Blog Pricing
Podcast Image

The Neuron: AI Explained

Teaching Computers to Smell?! The AI That's Digitizing Scent

07 Nov 2025

Transcription

Chapter 1: What is the main topic discussed in this episode?

0.031 - 28.879 Corey Noles

So imagine if you could smell a photo, not just see it, but actually smell it. Like someone sends you a picture of fresh coffee and your phone releases that exact aroma. Sounds like sci-fi, right? Well, a company called Osmo just figured out how to teach AI about smell. Welcome, humans, to the latest episode of The Neuron Podcast.

0

28.979 - 36.39 Corey Noles

I'm Corey Knowles, editor of The Neuron, and we're joined, as always, by the writer of The Neuron Daily AI newsletter, Grant Harvey.

0

36.97 - 59.328 Grant Harvey

Today, we are talking about something truly wild, teaching computers to smell. Our guest is Alex Wilczko, founder and CEO of Osmo, the first company to digitize scent. They've created an AI that can predict what a molecule smells like, teleport scents across rooms, and design brand new fragrance molecules that have never even existed before. And this isn't just about making better perfumes.

0

59.588 - 66.742 Grant Harvey

Alex thinks this could actually help us detect diseases earlier and even fight malaria. That's wild. Alex, welcome to The Neuron.

0

66.762 - 67.804 Corey Noles

It's a pleasure to have you.

67.902 - 70.945 Alex Wiltschko

Corey Grant, it's awesome to be here. I'm excited to chat.

71.886 - 78.854 Corey Noles

Awesome. Well, I guess first question that everyone's going to be wondering, what does it mean to digitize smell?

79.955 - 99.818 Alex Wiltschko

So, I mean, let's talk in analogies. What does it mean to digitize sound, which is what we're all experiencing right now? There's three steps. Take the physical world, which is vibrating airwaves, and turn that into a digital signal. So that's what a microphone does. That had to get invented at one point, right?

99.858 - 124.977 Alex Wiltschko

Initially, that was literally changing those pressure waves into grooves of a needle carving into a piece of physical material. Step number two, encode and reason about and then decode that signal, right? So now we have MP3. It's a way of compressing and understanding audio. We've got audio editors. So first, you got to read the physical world, then you have to map it.

Chapter 2: What does it mean to digitize smell?

301.486 - 325.015 Alex Wiltschko

Boy, that's fair. But you don't choose your obsessions. They choose you. And then I watched a TED talk by a guy named Luca Turin when I was in I think I was in college. And the TED talk said two things. One is, you know, we really don't actually know why things smell the way that they do. And then number two is he had a solution for it.

0

325.996 - 349.5 Alex Wiltschko

Turns out, I think that it's mostly wrong, the solution, but oh my gosh, is there value in asking the right question? And this idea that like, you can tell me RGB and I can figure out what color that is. It seems trivial. We can't do that for smell. Like we can't talk about why something smells the way that it does. It's just random. And then I ended up going completely down that rabbit hole.

0

350 - 369.459 Alex Wiltschko

And I ended up, you know, I did my undergraduate in neuroscience. I got my PhD in olfactory neuroscience. And I learned that actually nobody knows the answer. Like you go to the very edge of human knowledge, at least in academic science, and there's no answer forthcoming for something that seems very basic. It drove me absolutely bananas.

0

370.14 - 373.123 Alex Wiltschko

And that's basically been my life's work since then is trying to figure this out.

0

374.858 - 400.106 Corey Noles

Hey everyone, today I'm excited to tell you about Flora, the AI canvas used by creative teams like Base Design and Pentagram. It makes it easier for designers to generate campaign visuals, treatments, and final deliverable assets in just minutes. Unlike mid-journey or runway, Flora gives full workflow control so creative teams can ideate, iterate, and refine with precision, all in one canvas.

400.626 - 431.681 Corey Noles

If you're a designer or an agency looking to scale ideas with a high degree of creative control, check out florafauna.ai. That's F-L-O-R-A-F-A-U-N-A dot A-I. Check them out today and tell them the neurons sent you. So in 2024, you achieved scent teleportation. That's right. It was a fresh cut plum, from what I understand. And what happened that day? What was that day like? How did the project go?

431.782 - 432.523 Corey Noles

Just kind of...

432.503 - 454.462 Alex Wiltschko

Walk us through it if you would. One of the wildest, most excellent days in my professional life was that first breakthrough. And it was really just a first step. Like it's not the top of Everest. It's like getting to base camp, but it's still so, so powerful and so vivid in my memory. So the team had been working for a while on the technology and the processes to do this.

454.542 - 477.03 Alex Wiltschko

And one day they said, Hey, look, I think we're ready. And they sat me down in the morning in front of 30 amber vials. And inside of these vials, blind to the entire team, been set up by somebody else, blind to the entire scent teleportation team, inside of it were fruits and vegetables and some flowers. And so they didn't know what I was going to choose.

Chapter 3: How does Osmo teleport scents?

1798.777 - 1817.994 Alex Wiltschko

So looking at like a new color is kind of weird. It's like, have I seen that? Have I not seen that? You know, the answer is like, no, you haven't seen it in these cases. Like they're actually totally new smells. The one that I like the most, Glossine, so it has a nice like kind of purple fruit floral smell. It's very kind of just pleasant.

0

1818.654 - 1836.032 Alex Wiltschko

What was amazing about it is you put that in a fragrance and it lasts an hour longer, like instantly. Wow. So we've got all these kind of interesting side benefits with some of the molecules that we've created. And the customers for these are just, they're the really big companies that can make use of proprietary molecules.

0

1836.172 - 1849.707 Alex Wiltschko

So you have to be a very, very big company to be able to make use of this kind of a product. So, you know, you probably won't buy a bottle of this stuff anytime soon. It's kind of a, it's a component that goes into, you know, really large global products.

0

1850.949 - 1851.169 Corey Noles

Yeah.

0

1851.189 - 1851.289

Yeah.

1852.383 - 1862.876 Corey Noles

That is interesting. So are major brands using these yet? Are we at a point where you've gotten some interest?

1862.976 - 1886.225 Alex Wiltschko

Yeah. So you can go to stores. I can't tell you exactly which ones and which brands because we kind of want to be in the background. But you can go to major stores you probably buy stuff in and you can buy products with fragrance that was made by olfactory intelligence. So it's not theoretical. It's working. The scents are beautiful. They're safe. They do the job.

1886.285 - 1904.867 Alex Wiltschko

They're affordable for the customers that buy them and ultimately build a product for their consumers. So this isn't, you know, if we talked a year ago, I'd be like, we probably can do this. And now it's like, no, we definitely can do it. And we've got to do a whole lot more of it because it's working and it's really beautiful.

1904.847 - 1918.763 Corey Noles

That's amazing. Well, you know, the, the fragrance industry is dominated by what? Four massive companies. Mostly. Yeah. Have, have you gotten their attention yet? Are they, I don't know.

Comments

There are no comments yet.

Please log in to write the first comment.