How AI is Reinventing Chemistry (From a Trailer Lab to a $32B Partnership)

14:42Albert Invent:Yeah, so we use all the foundational LLM models out there. We're not in the business of building LLM foundational models, but we're in the business of doing chemistry domain-specific foundational models. And so that's, again, where you have to pair these things up. And it's, you know, I think that a lot of the reason that this problem hasn't been tackled is because there hasn't been this like concerted efforts to go solve it for one domain. I think there's been a lot of people that are like, hey, science, let's go try to solve, you know, AI for science. And even that to me was too broad. Like we are just doing chemistry and materials.

15:11Albert Invent:So biotech, pharma, you know, then we might dabble a little bit in those types of areas, right? If there's like a butt up next to them. But for the most part, those are different, like a protein sequence is much different than a small molecule, which is much different than a DNA sequence. And so if you try to build some generic AI across all of it, you end up spreading the peanut butter, so to speak, and you don't get the value that the data actually can provide.

15:32Nick Talken:You think there might be a time where I assume, and we're seeing this in other industries as well, where industry leaders are coming together and like building this foundational approach that's hyper-specific. And I would assume that's going to happen or is happening in biopharma. That will be and is happening in physics. Do you feel like there is a time where having those models all able to talk to each other could be beneficial in the future?

15:59Albert Invent:I hope so, man. I hope so. Me too. I hate you.

16:03Nick Talken:Sorry, I went a little off the deep end there, but it was, yeah, I had to ask. Since we're talking off the deep end, as part of this, what are your thoughts on Cloud Labs as well? I'm curious. The idea of doing all the experiments completely autonomously, Like, yeah, just what are your thoughts? Yeah.

16:18Albert Invent:So I'll try to maybe I'll try to address both those. So I hope that the industry, the industry has not had a lot of urgency for many, many years, this industry that we serve. And now that's changing. We're starting to see urgency because of margin margin erosion, because of competitive pressures in other regions in the world. And because there's other companies now that are popping up that are doing fully autonomous laboratory work with high throughput lab testing that are competing with the more traditional chemical industry. And so I think as part of the solve to that, you know, companies like Albert are playing a role to help these companies jump, you know, into the future a little bit or jump maybe into the present from the past.

16:56Albert Invent:And so, you know, there is going to be a big role to play in cloud labs there, but it will never replace the actual experimental result. That, I think, is the beauty of science. There will never be a world where you will just purely be able to do science digitally, I think, or maybe we're so far away that it doesn't matter about talking about that. I think that you're going to do 95 % of the failed experiments, hopefully digitally. And then the ones that you actually go run are the ones that have that information density I was talking about that may not be the right answer, but they're at least going to test a space that you have no historical knowledge around.

17:26Albert Invent:And I like to give people an example just to kind of like put in perspective how challenging this problem is. If I give you guys a task today and I was like, okay, you've got a hundred different ingredients. I want you to make a recipe to make a cake. and all I want you to do is pick a set of those 10 ingredients so don't worry about the ratios and how much each one has to be how many unique sets of 10 ingredients out of 100 do you think

17:50Nick Talken:that there are that you could come up with well on the order of maggots like one to the 100th right it's it's 17 trillion um oh no no it's way off yeah so it's it's it's 17 trillion combinations

18:04Albert Invent:of just 10 ingredients now if you think about what the ratios of those ingredients should be then that blows up even bigger. And of course, there's way more than 10 ingredients that you can choose from as a scientist. And so the idea that you could even brute force this problem without having domain knowledge around it, it's just impossible. There's more possible combinations of chemistry than there are atoms in the universe. And so that's a super fun problem to work on because it's much different than other domains where you can kind of explore every possible route and just come up with this is the definitive best answer.

18:33Nick Talken:Is there any intention to save those that maybe don't make the cut? for experimentation right now, but maybe have a lower chance of success a little bit that maybe is whatever is below the threshold and still maybe have AI research those in some way in the future still to see if there aren't underlying opportunities that while less likely might still exist?

18:59Albert Invent:Yeah, I think that's the beauty of science, right? Because one failed experiment could be a successful experiment tomorrow um because the requirements change um and so yeah there's value there's value in all that data the key is if you're going to go put um if you're going to go into the real world you're going to go onto the benchtop and run that experiment you want that to

19:16Nick Talken:be the most valuable experiment for today's problem for sure right for sure right 100 it makes sense um well that that makes me think so if we're talking about a problem set that could potentially have 17 trillion possible, you know, areas to go. What type of like, are you competing with OpenAI for compute here? Like how much compute do you need for this type of stuff? Like, yeah.

19:39Albert Invent:Yeah, I think you want to try to not play that game as much as possible. Right. And I think that you're going to see and now I'm talking about stuff that I don't have a right to necessarily talk about. But I think even with the foundational LLM providers, like there is the laws of physics that you have to run. And like, you cannot have a data center the size of the planet Earth, right? And so at some point, you have to figure out, okay, like, how do we get more efficient about how we run some of these algorithms so that we can just, okay, there's 17 trillion combinations. How do you exclude 16.9 trillion of those right off the bat without having to simulate them?

20:10Albert Invent:So then you can focus on maybe just a billion. That is where scientific domain knowledge comes in. That's where the human comes into the problem. Their role is to say, okay, this is the infinite space. I know if I'm making a paint, it needs to have at least 50 % water. Okay, right there, you've now constrained that problem much more than any possible combination. And I know it needs to have these type of attributes. And it can't have 100 ingredients because I can't manufacture that reasonably. So the scientist comes in with the real world like constraint building, and they start to put constraints on it.

20:39Albert Invent:And that's how you first of all, solve the problem sooner. It's also how you reduce the amount of compute to go like brute force this problem. And I think it comes into, you know, the question we get all the time is, you know, are we replacing scientists? For sure, we're trying to replace a piece of the scientific process that they're going through. Are we trying to replace the entire scientist? Absolutely not, because the scientist still needs to come in and give those guardrails for how the AI should go approach the problem.

21:00Nick Talken:Yeah, we sort of landed on that, too, right, Corey, where it seems like it's specific tasks that are getting replaced, not jobs. Like at this point, no AI can replace any single job at this point. Yeah. I don't know that I would say it in an absolute like that. Fair enough. Fair enough. I'm worried when you're wrapping in an absolute. Yeah, that's fair. It seems unlikely. The general approach, yeah. I mean, that is what we're seeing.

21:27Albert Invent:If we're headed to a place of like huge amounts of prosperity, right, where we're starting to automate these tasks, you know, at some point we may get to a point where everyone's job has fully been replaced. So then the question isn't, you know, is that the inevitable end state at some point in the future? The question is like, what's the last job that's going to be out there, right? So I think like scientists and some of those types of fields, those are going to be some of the last jobs that are out there because they're very challenging roles to be in to just fully autonomous, fully automize the entire process.

21:58Albert Invent:And so I think if I was a scientist listening to this conversation, I wouldn't worry too much about it today. These generations, I think we're going to have a lot of cool tools to play with and not something that's just going to completely replace it.

22:07Nick Talken:Well, what are your thoughts on OpenAI's stance that they're basically saying now in 2026, they think that they're going to have, they're confident that we're going to have AI that can make like, I forget the exact phrasing that they said, but like meaningful small contributions to science. Novel scientific breakthroughs or something? Yeah, but then in 2028 or 2027, they're thinking that it'll have significant impact on novel breakthroughs. What are your thoughts? Do you think that those timelines make sense with what you've seen? What are your thoughts?

22:35Albert Invent:I think that if you look at the progress of technology on a XY axis where X is time and Y is progress, you know, you see that curve, that exponential ramp. And so if you look at it from that perspective, you say, well, shoot, two years, five years, my God, we're going to immediately jump to this next stage. If you zoom in, though, on that chart, it doesn't look smooth at all. It looks like a bunch of kind of flat and then a huge step change and then maybe a slow progress and then another step change. Because things like transformers, right, were that step change, right? Five years ago, would we have predicted where we are today if we had looked at the rate of technology improvement?

23:15Albert Invent:We wouldn't have. We actually are probably way ahead of where we were. So then, but I think it's also false to say if you assume that we're going to continue to progress at the current rate forever, right? There has to be another step change. And so there will be more step changes. Does it happen in two years by 2028? I have no idea. I think nobody has any idea. If they did, they would have done it today and we would have already had it. Right. Yeah, fair enough. And so I don't know the answer to that question. At some point, there will be incredibly meaningful, you know, advances because of AI.

23:43Albert Invent:But I think that you shouldn't discredit the humans that are controlling it, constraining it, guiding it and that type of stuff. And I think that you're going to see more and more, you know, Nobel Prizes in chemistry won by humans plus models versus just one or just the other.

23:57Nick Talken:would you would you list the model on the paper would you say like and and authored by you know me and grok or me yeah why not i think credit where credit's due right yeah yeah yeah i think so too and i think it would speak to the credibility too because you know two years down the road we might want to remember what model that was and understand what its limitations might have been and maybe it still requires you know further study and repetition yeah

24:27Albert Invent:Yeah, I think that's a good point. I mean, you got to set your sources, right? And these AI foundational models are becoming a source. And, you know, that's part of our long-term vision also as a company, right, is I would love to see us contribute significantly into the, you know, human knowledge sphere. but we're going to do that ultimately through our customers. Our customers are the ones that are going to make those innovations and we're just going to try to empower them with the best tools possible which I think makes us a multiplier in the industry which is that's fundamentally why I am doing this is it's the best place to be a multiplier.

25:03Nick Talken:So would you say that the Albert Invents models are agentic? Is any part of your system agentic? Like, how do you think of the way that people are working with that? Are they working with that as a co-scientist or as a specific tool? How do you look at it?

25:19Albert Invent:Yeah, so we look at our tech stack as three different components. We've got that system of record that we were kind of talking about before. How do we replace the paper notebook with something that you actually collect your workflow in? Then we look at our system of record that layers on top of that. And that's really where, like, the machine learning comes in. That's where the rule engines come in. I'd say the more traditional but still complex, you know, software engineering gets applied on top. And certain things like regulatory information, you don't want an agentic system guessing, you know, or guessing what the next token for like something that you're going to put on a passenger plane and ship around.

25:50Albert Invent:That's a discrete rule. You need to have that. Then we have our system of work, which is that third layer that's at the top. And that's where you've got the RAG LLM, the agentic network that sits on top of it. And that's where we're starting to do like fully automate, you know, certain parts of the work. So does people do people want to type data into a system? Nobody wants to type data into a system. OK, so you've got to get the data into Albert somehow. How do we put an agent there that maybe does that for you? It takes it from the machine and automatically puts it in there or takes it from a PDF on some online source and puts it in there in a clean and structured format.

26:20Albert Invent:And so there's a whole agentic layer of our platform that sits on top. And our real competitive advantage, I think, is that we're doing all three of those layers. We're not just an agentic layer. We have the system of record as a foundation underneath everything else.

26:33Nick Talken:And you have the neural network kind of in the middle. Exactly.

26:36Albert Invent:Exactly. Yeah.

26:37Nick Talken:Cool. Nice. I have a question kind of dealing with data around IP, for example. I know you mentioned it's been learning from some of Kenview's data. How does that work without compromising their IP, for example? I know companies are protective of that kind of stuff for ages and ages, formulation research and whatnot. How do you both use that to innovate and ensure that at the same time you're protecting, you know, valuable clients' IP?

27:11Albert Invent:Yeah, that's a foundational question that every single customer also asks us, especially in today's age. And our answer is super simple. Their data is their data. The models that are built on their data become their models. We would never share that data with anybody else. Now, could we scrape things from online public sources to use for everybody? Absolutely. And that's what we did with the 15 million chemical structures and that. But the moment you add your data into it and you start getting insights out of it, that becomes yours and you own it. And I think, you know, we couldn't do what we were doing without that.

27:39Albert Invent:Now, back to an earlier question you had is like, what about when companies want to start sharing information with each other? Right. We would love to facilitate that. But that has to be them kind of coming to us and the industry coming to us saying, hey, we want to share information more broadly. And then we set up ways to constrain that as well, where maybe it's only a very small subsegment of their IP that they've decided to make public for X, Y and Z purposes.

28:00Nick Talken:Not everything they've ever made. Exactly.

28:03Albert Invent:But that has to be a clear opt in. There can't be a default status for us.

28:07Nick Talken:That makes sense.

28:08Albert Invent:Yeah.

28:09Nick Talken:Speaking of Kenview, I mean, what type of stuff are you working on? Are you like, has any of your stuff that you've contributed to been productized yet? Yeah.

28:18Albert Invent:So, I mean, Kenview is, you know, one of the earlier or the more recent, you know, relationships that we have. We just publicly announced that just, I think, a month and a half ago or something at this point. Yeah. Congratulations.

28:28Nick Talken:Congrats. Thank you.

28:29Albert Invent:Yeah. They're an amazing, amazing company, you know, doing, making products that we all use every day. And so they're in the middle of a big digital transformation and we're a core piece of that. And so, you know, we are right now deploying Albert to every single laboratory inside of their entire facility. And, you know, by, you know, middle of next year, every product coming out of Kenview is going to be touched by Albert and we're going to be helping all those scientists with their innovation. And so, yeah, I think, you know, you should next year be able to go to a CVS or a Target. And, you know, I wish they would go for it.

28:59Albert Invent:But invented by Albert would be invented with Albert would be really cool to have on the bottle there.

29:04Nick Talken:So do you want to see Albert listed on papers that win the Nobel Prize? Or is that is that the goal?

29:10Albert Invent:That's not the goal. That would be a nice outcome. Right. That's not your feelings, though. Yeah, I think what would be the most meaningful thing is when a scientist, you know, reaches out to us and just says, like, thanks for making my life easier. Right. I've been struggling for a long time with paper, Excel, haven't been able to move as fast as I think I could. And now you guys are making my life easier. And we have that type of feedback all the time. And that's like I built this for myself. I was the first user of all of this in the Ken's trailer. And so that's why I built it. And to be able to share that with the rest of the world, that's really what we're here for.

29:43Nick Talken:Well, I'd like to ask a question or two about kind of your business model. Are you essentially, so you're not selling access to a specific model. You're helping them craft a model that is correct for them, essentially. Exactly.

29:58Albert Invent:So first we help them manage their data because without data, we can't do anything. So that becomes like objective number one. And then we help them and we're really helping their scientists build models for themselves every single day. And so, you know, we've had a last in the last 12 months, I think we've had something like 120 million simulated experiments running through our platform. And so that's non-trivial, right? That's a lot of simulation that's being run. It's going to be in the billions and in the trillions in the years to come. And so those are all models that scientists are building for themselves based on their data plus their organization's data to help not run so many experiments that wouldn't lead to good results.

30:35Nick Talken:wow that's awesome um i mean i'm i'm personally so i i just uh confessed to cory right before we got on the call i actually skipped my high school chemistry oh man i got out of it but it's because i did a digital science class of you know learned a lot of really cool tools that helped me now as a adult but i did i did skip chemistry but i've learned a lot about chemistry since then because i used to write for a company that's uh in the material sciences trying to invent new uh battery technology. And so battery tech, battery materials is one of the biggest things that I'm focused on because, uh, energy density and finding the right materials that are, you know, easy to source, not scarce, um, you know, not just, you don't become reliant on any one country for them.

31:18Nick Talken:And you can also, you know, pack so much more power in a tiny, uh, form factor is, is like, that to me feels like one of the biggest unlocks that if we can make a lot of progress there, we can exponentially increase progress elsewhere, you know, because it just increases the amount that we can, you know, the amount of power that we can store. If anything, are you doing in the battery space and materials, like energy materials, I guess, let's say?

31:44Albert Invent:Yeah, I mean, some of this stuff isn't public, but one of the great public examples that I can definitely talk about is there's a company called Comores, which is based in the East Coast, and they have an amazing battery lab out there. They're doing some incredible science around battery. That's all now being run through Albert. And one of the great things about the battery chemistry process is it is a pretty data intense process, right? And you think about cycle testing of a new pouch cell or a coin cell or whatever it may be. You're collecting a tremendous amount of data. And so a paper notebook actually doesn't work there, right?

32:13Albert Invent:And that's, you need some tool to use instead. And so they're having a tremendous amount of success, fantastic company. And, you know, we are really proud to be supporting, you know, them. And then, of course, the larger sustainability and kind of electrification efforts that are happening beyond that.

32:29Nick Talken:Like chemistry and material science is a massive industry, but not one the average person thinks about every day. Can you kind of help us understand the scale here a little bit? Like what types of problems are being solved faster and what does that mean for products consumers use every day?

32:48Albert Invent:Yeah, it is funny that people don't think about it. And even somebody like myself who like lives in it, I, there's like a billion dollar revenue company that I stumble across every week that I've never heard of before. And it's like, that's what it's like working in AI too. Yes. A billion of revenue, not, not billion of, of market. Yeah.

33:04Nick Talken:That's not what it's like. On market cap. Yeah.

33:08Albert Invent:And so it's, it's the cool thing about chemistry is the foundation of the physical world. So if you guys just look around where you are right now, I see a guitar in the background, the number of material science projects that went into making that from the material, the metal. that's of the string to the plastic of the guitar to the coating on top of it to I'm sure there's actually some very special materials that are some sort of acoustic dampening or you know acoustic

33:30Nick Talken:properties yeah you know you've got the nut all of the plastics on the back all of that chemicals in the knobs you would have everything the wiring the wiring itself the clothes on your on that

33:42Albert Invent:you're wearing these are fibers right these are spun fibers from some sort of synthetic cotton or maybe polymer or material. So everything in the physical world is chemistry. And that means it's one of the oldest industries as well, right? It's one of the things that humans have been doing for the longest. And so I think, you know, the best way to think about it is anytime you go to a store and you look at everything on the shelf, right, that's chemistry. Maybe not the two by fours, right, that were purely coming from a piece of wood, but everything else is probably not just a simple, you know, single component.

34:10Albert Invent:And so that's super exciting because then you're helping to, you know, We like to think of ourselves as helping to invent the physical world faster, or our customers are using our technology to do that. And so, yeah, it's not like the world is slowing down, right? We all want better products. We want cheaper products. We want more sustainable products. And that pressure from the consumers trickles to the people like the Apples and the Teslas who are making those products. But they immediately then turn around to their supply chain and say, go solve this for me. And that's where we operate. We operate deep into that supply chain there.

34:42Nick Talken:yeah well that's what that's what i was going to bring up a second ago was that like for let's look at apple for example their limiting factor is actually battery battery life on uh their their materials so like they wanted to do uh this is publicly leaked and everything they wanted to uh air glasses like three years ago um or last year released them but they were limited by the the actual like power to power them by the chemistry yeah i'm sure it was a limiter yeah Yeah. So that's where I focus on, you know, battery life and energy in particular is because that seems like that's a limiting factor for so much technology.

35:15Nick Talken:I think it's a limiting factor for almost everything.

35:18Albert Invent:Right. I mean, like Elon wants to go to Mars. Great. Right. That's that's a super cool, inspiring mission. Right. Multiplanetary. That is not a software problem. We very much know how to launch and put a rocket and get it there. It is a pure materials problem for the most part. How do you make an ablative material that can withstand the, you know, coming in through either the Martian atmosphere or returning back into the U.S. atmosphere? How do you have the properties of steel that can withstand, you know, the temperatures and pressures of space plus, you know, on the planet Earth? Like that's what that's there's a huge amount of innovation happening right over there, right?

35:50Albert Invent:Just around chemistry and materials to go solve that problem. We have to solve these problems faster. We can't take 10, 20, 30 years to solve these problems if we want to get done what I think all of us want to in our lifetimes.

36:01Nick Talken:Well, so your point on that, is it a data problem at this point? Is it a compute problem? Like what is the limiting factor actually to solve a lot of this stuff?

36:10Albert Invent:I think it is a data problem for the most part. People can't leverage their knowledge and their data. And then once you start to solve that problem, then it becomes a like a laws of physics problem of how do you like kind of like I was saying before, you know, collect the right data, the right next experiment as quickly as possible. And there's where high throughput laboratory automated testing comes in. There's all sorts of technologies that people are inventing there to help to solve the next set of data we want to capture. But if we're not capturing today's data very well, you know, there's nothing to inform us of what we want to do next.

36:42Nick Talken:Well, I have one last full question for you here. If Albert works exactly as you hope, what becomes possible in the physical world that isn't possible today? What products or materials might we see in, you know, another decade that maybe seem impossible now?

37:03Albert Invent:I'm going to answer that question by giving a slightly different answer. I think that's fair.

37:08Nick Talken:I did just ask you to predict the future. So, yeah.

37:12Albert Invent:What I would love to see in the future at whatever point is possible is that you can invent with a laptop. You can invent the physical world with a laptop. Today, you can do that in the digital world very well. Before, that wasn't possible. 20 years ago, you couldn't just take out your laptop, log into AWS and make some new amazing product. You'd have a server and you'd probably work for a company that had access to a big server. I would love in the future where regardless of where you are in the world, if you have a good idea of how to invent something physical, you should just be able to do that with a keystroke and a click.

37:45Albert Invent:And that is an inspiring world to live in because then you've taken what may be millions of physical world innovators today and you've made it so that anybody out of the billions of us can be. And then what products those people invent, I won't dare to guess, but it will be really exciting.

38:01Nick Talken:Well, you know, imagine how many great ideas float around the world right now that are in the heads of people who have absolutely no idea where to start or what to do with them. Exactly. Exactly. You know, this brings a lot of that to the forefront, potentially.

38:17Albert Invent:Yeah. Yeah. And it's a world that is worth wanting, right? And I think with all the other stuff happening in today's world, you want to be excited about the future. So let's try to make an exciting future that we all believe in.

38:29Nick Talken:Molecule started as a 3D printing company, right, back in the day. What are your thoughts on 3D printing today? We talked kind of about Cloud Labs, but do you think 3D printing is going to play a role in the laptop developer where you can design the experiment and run the models on your laptop and then print it in your house to test it out? What are your thoughts?

38:53Albert Invent:Yeah, I think maybe not print it in your house. I think that was a little bit of a fad, especially for like industrial type applications. But yeah, I mean, 3D printing is an amazing technology to again, how do you take an idea and use something that's a digital application of chemistry? Just got to find the right use case, right? Making like red solo cups with 3D printing is probably not a good use case, but making a dental device that's personalized to your mouth and your use case, incredibly good use case. Making a first prototype of a new idea. I don't think that I would doubt that there's really any prototypes anymore in the world of anything that's being made that 3D printing isn't touching today.

39:30Albert Invent:And as any technology gets more investment, the costs go down, the volumes can start scaling and you start to play that, you know, economics game there. So 3D printing has a very near and dear place in my heart and hopefully a big place in the future of the physical world as well.

39:45Nick Talken:Cool. Thank you. Well, Nick, thanks so much for joining us today on The Neuron. Where can people go to learn more about Albert Invent and some of the amazing work you all are up to over there?

39:55Albert Invent:Check out our website, albertinvent.com. We've got a bunch of great resources on there. And we're also hiring like absolutely crazy right now. We've got a lot of really interesting roles for people who care about this type of stuff. and so come help us invent the physical world. It's an exciting time.

40:10Nick Talken:I agree. Well, to everyone watching, thanks so much to you for joining us today as well. We really appreciate you. If you enjoyed today's episode, please like, subscribe, and do all of the things that help make us keep being able to bring you these videos and these amazing guests. Also, make sure you take a moment to pop by the Neuron.ai and sign up for the Daily Neuron newsletter and join more than 600 ,000 people reading it every morning today. But until next time, farewell humans.