🔬 The Self-Driving Lab — Joseph Krause, Radical AI

22:23Joseph Krause:And then you have the private companies that are forming self-driving labs and that are looking at the automation of scientific equipment. That has really started to kind of push this wave to, oh, now we don't really debate that A-labs or self-driving labs are a part of the future anymore. It's in which part are we going to play in that? And that's a better helpful conversation to have now because we can get access faster. Self-driving labs in biology has been notoriously difficult. You can automate certain parts of them, but you inevitably have people who are just walking around moving trays from one section to another.

22:57And it doesn't actually end up speeding things up oftentimes. It can sometimes even slow things down. Full in-end automation for non-research activities or for manufacturing, we're really good at. But when the process changes, how do you deal with that? And, you know, have you figured out some way of automating the type of problems you're solving?

23:17Joseph Krause:You know, the self-driving lab, first, I think it's important to talk about what a self-driving lab is, because this goes in and impacts your answer. There's a difference between an automated lab and a self-driving lab, right? An automated lab does experiments for you, automated, without humans, and that high throughput. And that can be very effective. A self-driving lab runs research campaigns for you. And there's a big difference. And the way I like to describe it is, you know, one of them is like hands-free driving where, yeah, I don't have to touch the steering wheel. It'll keep me in the lane.

23:47Joseph Krause:It'll keep my speed set. But when a left-hand turn is coming up, I have to pay attention. I have to put my turn signal on. I have to turn the car, and I have to know to make a left. Now compare that to a Waymo, which I love bringing up because every time I'm here, I go out of my way. I just drive around the block sometimes to live in the future. You don't need to make a left-hand turn. Actually, you don't even need to know to make a left. You don't care what route it takes you to get there. you get in the car, you can close your eyes if you want, you can scroll X, you can work on a research paper, and then you end up at your destination without knowing how you got there.

24:20Joseph Krause:That is the difference between an automated lab, which you are controlling and just using automation to do throughput, and self-driving lab, where it is actually doing this entire process for you. So in the self-driving lab, there are things that a human scientist does that are actually very hard. Sample manipulation is a perfect example. When we synthesize these alloys, we get these little pucks that come out. They're called buttons of the industry. And because you're blasting them at 3 ,000, 4 ,000 degrees, they get stuck to the tray. How do you get them out? And you can't, you got to be careful because you don't want to like mess with the microstructure or chip off part of it.

24:54Joseph Krause:Now they're strong enough that you're not going to really do that, but we had to design custom actuators that go on our robotic arms to be able to manipulate them. And that's not, or that does not really have anything to do with like the discovery of this new high entropy alloy. That's just required if you want to run autonomous alloy science. And so that's one answer is there are these challenges that humans either don't face or if we do, they're very intuitive, right? The button's stuck. I take a little chisel. I smack it. I flip it over and I move on. I don't even think twice about doing that.

25:24Joseph Krause:Not so much. Two, we talked a little bit about is the software. And it's not just about controlling the tools, but it's running the lab, right? How do I track my samples? How do I know what samples should go in a tool or should not go in a tool? is there a quality check where if i look at a sample after it comes out of synthesis i actually want to kill that experiment i don't need to waste time going through xrd and scm and the other tools in the lab i want to just stop that sample state save it and throw it away how does it know how to do that and this is where you start to bring in you know all these different vectors from vision different sensors in the lab sensors on the tooling themselves um to kind of build this, what we call it, operating system that runs the self-driving lab.

26:05Joseph Krause:And then the third part is automation. And automation includes what I like to say the connection of the lab. So I have one tool that's automated. I have another tool that's automated. You have this operating system that's running them individually. The robots are how you connect that. The same way a human scientist would come in, look at the results, take the sample out and go to the next one. Our robots do that today. And so those are the three parts that we really see kind of make up this self-driving lab. And And I'd say each of them has their own difficulties. We can walk through them. Some being, like I mentioned, the tool provider.

26:36Joseph Krause:Some being no actuators. Some being like, it's just really hard to load and unload XRD. You have to put it in a hard sample now and it's weird and it's awkward geometry and you need a custom gripper and just what it is. But all of that kind of forms into what a self-driving lab becomes. We're very good at that for alloys today because the tools in our lab are built for alloys. Some tools share XRD, XRF, SEM, even tensile testing, although mostly used in the structural metal space, can be used elsewhere. But I would say like our oxidation chamber, that's very suited for the specific customer application we're going after.

27:11Joseph Krause:I would say our synthesis mechanism is directly for alloys. I mean, we custom build a tool with a third party to do alloy synthesis and high throughput. That's built to do alloys. That's not built to do ceramics or polymers or any other material system today. Is the goal to expand to polymers and ceramics and everything? Or is it we're going to do alloys and basically get all the way end-to-end manufacturing on alloys and then expand? Yeah. Or never expand? It's both, but on the right timeline. So the first one is vertical integration. And this is very important. You know, when we started the company, and I'm not afraid to admit, we're like, we're just going to do seven different labs.

27:52Joseph Krause:seven different material systems across the board. You're going to capture all this data. It's going to be amazing. And then we started talking to customers. It was a matter of time. Yeah, exactly. Exactly. And I'll come back to doing that over time. But started talking to customers and they're like, how are you going to do this? Have you thought about this test? What about when you go to scale? We need to go to 300 pounds. And we were like, oh, no, we hadn't thought about that per se. We were like more worried about going to polymers and ceramics and everything else. And so why is that important?

28:19Joseph Krause:Well, because we are a materials company. All right. And you see the company talk about this a lot. We really believe in inventing new materials that change the future of the world. We think that is the opportunity with AI and autonomy. I mean, there are so many industries that we all care about that are blocked because of a lack of novel material advancement. Automotive and aerospace, manufacturing, defense, climate, energy, semiconductors, electronics. What's your favorite example of that? Like what's a, what's some problem that could be unlocked by amazing material? Aerospace and semiconductors immediately.

28:49Well, like, but what specifically?

28:51Joseph Krause:All right. In the back end of line integration for semiconductors, there are particular materials that we've been using for a long time called interconnects. The entire industry is doing R &D here. They are a cause of not having great efficiency and very expensive energy bills. On the back end of that, a new material would potentially completely remove that problem. That's a perfect example. Is there like a theoretical efficiency that you could achieve? And where are we now compared to that? We have ideas on materials that would be able to solve that problem, but we'll release more on that in the next coming months.

29:24Joseph Krause:We have a specific program we're working on that's directly around that problem, but it's a really exciting one. And there are estimates from the industry on moving past the current material system, what new materials could bring, but there are other challenges. Are we talking about 2x more efficient, 5x, 10x, or 1.1x, which is oftentimes quite huge? Yeah, yeah. I think you could, in the near future, with some of the systems that have been recommended today, you would see like a 2 to 5x, generally, especially when you think about integration. In these materials, you need barrier layers, and there's all these interface things that you have to be able to understand.

29:59Joseph Krause:I think past that, you could start to see it push over 10x. I don't know to what level, but there are cool, exciting materials that we'll share more about in the future. What's the validation timescale for this? In which way? The lab to start working on these materials or a material in a new chip in the iPhone? So you have a material you just created that you think is going to revolutionize the world. How long do you think it's going to take for that thing to get into an iPhone or a NVIDIA GPU? That's still long. That's still pretty long. Yeah. We're early in semiconductors. And actually what's long about that is that when you start from ground zero, you have to build everything from scratch.

30:41Joseph Krause:And so even the way that we do material testing for that industry today, and I would say they're one of the industries that's actually far ahead of everyone else because they invest so much in R &D and materials really make or break some of their performance. Even there, you know, that integration timeline is very slow. And number two, no one can get enough chips. And so everything is delayed in that industry, which is important. And I even saw today or this week, TSMC telling ASML they're going to hold off on some of those new tools until they get through their 2029 production runner. It was something story like that.

31:13Joseph Krause:Just because they're go, go, go. That's what I believe. Yeah. So I'll say I didn't find it after and send it to you guys. But I was like, man, this industry is really getting pushed to their limit. I would say something on the alloy side, like aerospace, we feel good opportunity, three to five year timeline. It's already short. Yeah, correct. I think it'll be an application, not like manned flight. Like, I don't think it'll be a jet turbine because of the constraints there with humans. I think like defense and space systems, though, definitely doable in that timeline. There have been examples in the past, people that have done that in that timeline.

31:44Joseph Krause:And we feel very confident in our ability to try to execute on that. I want to get back to the validation question, because I feel like this is the crux of automation, right? Is it every AI engineer who uses cloud code or something has the experience of one-shotting something? And then when you look at it, you're like, what is this garbage, right? And so if you're talking about what is essentially active learning, where you are hypothesizing, manufacturing, testing, and then forming hypotheses on that and doing that over and over again, your mistakes will obviously compound as you do that. And so how are you thinking about this?

32:25Joseph Krause:Yeah, we call this the negative results, these mistakes. And we do have a version of this loop built already today. So it doesn't include manufacturing data. Like I mentioned, we don't have manufacturability in the lab today, but it does include synthesis, characterization, and those early property tests that I described to you guys. And what this system does is kind of have this AI scientist that is really good at designing these campaigns I talked to you about. So it can make up these campaigns. It comes up with the number of materials it's confident it wants to go make and test. and it'll launch that campaign.

32:53Joseph Krause:It'll send it to the lab. It'll start running autonomously. And then it will go through the whole characterization suite and we'll get all the data. That data is all pulled out autonomously. Some of it is analyzed with machine learning models like computer vision. Some of it, again, has a human in the loop, analyzing it as well. And it'll get put in our database where that AI scientist will look back to when it designs the next campaign on the follow-up of that. So, you know, it's this active learning loop that is campaign by campaign basis. So it is not every experiment. Honestly, we don't need it to be that fast.

33:26Joseph Krause:We actually want to take a few shots and get enough data back to change our hypothesis. But it is very rapid. I would say, you know, we probably could run probably seven to 10 different campaigns running right now inside the lab across different systems. And, you know, you're updating those daily or at least every other day with the results that you're seeing from the lab when it comes out. And what does a human do in that part? Because, you know, I find, okay, so doing, you know, transcriptomic analysis and whatever, that Claude does some of my work, and then I end up, you know, sort of course correcting a lot.

34:01Is that kind of the gist of what is going on in your lab as well?

34:04Joseph Krause:In some parts, yes, though some parts are more complex, to be honest. So synthesis is a really good example. We still have PhDs in metallurgy running our synthesis mechanism. That tool is not yet fully automated. It should be automated by the summer. That's the custom tool I was telling you guys about that we're building with that vendor. And it's not just opening and closing that's automated. So the synthesis mechanism itself requires automation. So if you've ever seen how you cast these alloys, I mean, pretty much you take a plasma torch and you blast them and you melt, you take these raw precursors and you melt them down into a liquid and then you cast it and it solidifies into the shape that you cast it into.

34:43Joseph Krause:So there's a lot of intuition in that. Like a scientist stares at it and looks at that's not melted yet. Let me hit that corner there. So we have models built that can actually start to learn how to do that at the equal performance that a scientist can, a human scientist can. So we're getting up there. So that's not fully automated yet. Characterization is fully automated. We just have scientists annotating images after or results after to train the scientist on. All of our characterization tools can be loaded, unloaded, and controlled with our backend operating system to do characterization. Property testing, two of the three property testings are fully automated.

35:19Joseph Krause:So micro indentation and oxidation are automated. Tencel is almost automated, should be automated in the future. So that's where humans are, and that's where humans aren't. Now, after the process, for generation, all of our materials are generated by our AI scientists today. Occasionally, a human scientist will try to compete. And I love telling this story. They hate when I tell this story. And they'll throw in a composition, and then the AI scientist will say, get that out of here. That's not strong enough. Or we'll see how do we do, how do we think about something new. So you're like red teaming.

35:56Joseph Krause:Yes, that's a good way to describe it. I don't know if they would call it that. I think they would call it losing their job, but they're not actually. They're actually super important to the process. And I think what's cool is sometimes the scientists will recognize a new learning. Oh, interesting that you threw that element in there. That's cool. The other part of that is going places where human scientists won't go. And we have this beautiful chart that I can show you that shows in the high entropy alloy space, all of the different elements that in publication, so in literature, what we can access, where all the places scientists have gone.

36:30Joseph Krause:And then we have a second overlay on that chart of where our AI scientist has gone. And it's moved into elemental families or alloy families no one has ever published on before. And the question is, like, why? Like, why did it think to do that? And so we ask our scientists, like, why did you never go there? Why did you never use that element or that element? And its answer is like, I just didn't think it would be, I didn't think it would work with the other elements that are in that mixture. I think it would cast. I thought it would evaporate when we tried to make it. And I guess it didn't, we were able to synthesize it.

37:04Joseph Krause:I didn't think it would work in the microstructure or would cause grains to be not what I was looking for and would not get the mechanical properties I thought. So I just never considered it, but it actually works in that formation. And so there's this really interesting feedback where, you know, now the scientist is getting good at exploring places that I'd say humans have a biased naturally against, even though it might be unknowing bias. And that's the huge power of an AI scientist. But it's part of this just that you have higher throughput and that you are letting your AI scientist do its own thing.

37:34I wonder what happened if you took those same scientists and say, all right, no constraints, just go crazy. You can do whatever you want to. So, you know, if you have an AI scientist, it may not have pre-conceived notions. I'm actually honestly kind of surprised that it's not just sort of reiterating what is known. But I wonder how much of it is that you just turned up basically the temperature in your sampler.

38:02Joseph Krause:Yeah, that's an important metric. Processing is really important. So, you know, to be clear, there is times when it like goes to what it knows, especially when it pulls in literature. It's like, oh, this is where it is. And actually literature is a great teacher. Like if things work, it's actually a good place to ground on why they work and try to understand why they work. That's a big problem for the materials field that we can talk about. But it also has this, you know, good ability to, because it is high throughput, not be afraid to test. You know, when I was in my PhD, I probably did 50 experiments a year.

38:32Joseph Krause:I don't know, rough estimate, you know, something around like that. So every experiment's kind of important, right? And not to mention like the mental loads, like two weeks of time to like fabricate this thing and synthesize it and then go test it. We don't think, the scientist doesn't think like that. The AI scientist, excuse me, it's like, I'm making eight of them today, 20 of them today. And once that tool is done, I'm making 100 per day. I don't really care about taking a shot on goal and learning from that shot. So it's like a mindset shift there. How much does one experiment cost-ish? So it depends on what elements you use.

39:04Joseph Krause:So some elements, platinum, palladium, are much more expensive than aluminum, titanium. Anywhere from like 60 bucks up to 300 bucks. Okay. And what's your throughput? All element dependent usually. What's your throughput? So today, it can be anywhere from 8 to 20. That depends on elements as well. Refractories, particularly if we're doing refractories, they are much harder to cast. And so we go down to that 8 number. If you're doing things like titanium, aluminum, your standard alloys, Ti-64, those are much easier to cast. They melt immediately or quickly. You could do a higher throughput to 20.

39:36We should be at 100 per day, regardless of system, by like the June, July timeframe, rough estimate, give or take. This is across the entire lab and not like per workflow? Yes, that's correct.

39:49Joseph Krause:That's across the entire lab. Okay. Right. At 8 to 20, you could conceivably have humans sort of inspect many or most of these, or is that a... I don't know. You could. So one thing I wanted to touch on, you just reminded me on that answer is AI doesn't operate in the same dimension that humans do. Let me explain what I mean. When I was a scientist, you go through a very serial-based process. I make a new hypothesis. Actually, backtrack. I read a bunch of papers. I make a new hypothesis. I might run some computational workflows, DFT or MDL net. I go synthesize it in a lab. Then I move to my characterization.

40:22Joseph Krause:I study my characterization for two weeks. I get a new idea from an image or something I saw. I circle back. I do that whole process again. That's what a human does. And it's very serial in that if I take a hundred SCM images, I don't memorize all 100. I'd love to think I could. My advisor would have loved if I could, but I couldn't. And so I pull like one thing out of that or a couple things out of that that I want to learn. Now switch over to the AI scientist and that same process. Now it's parallel. Now I can read 100 ,000 publications and then directly compare them to 100 ,000 SM images at the same time in real time.

41:01Joseph Krause:And I can study, I can learn, I can memorize all of the things I'm seeing in those 100 ,000 SM images and draw direct conclusions back to my papers, back to my hypotheses, or back to my mechanical property testing rate where I'm seeing what actually comes out. I can't do that as a human scientist. And so this parallel nature allows it to operate in a way that just human scientists don't have the ability to do. Okay, but you're still talking like order tens or hundreds of materials that you're producing per week, month. Yeah, the overall scale is not that large compared to even like a lot of biological methods you have ways of scaling up to you know millions or if you're doing uh let's say in next generation sequencing phase assays you can billions you know whatever so you know this is much more reminiscent of like ligand-based modeling where you're you're really looking at a small number of examples and you're trying to pull out like local patterns for you know small molecules you can you have real predictive power this is like these are useful techniques.

42:04But the almost universal rule from experience from ATX is oftentimes by the time those become useful, the actual scientists can just go out and do it. Like they could have designed it by, you know, they could have found the molecule they were looking for without using the AI model by the time the AI model gets there. Yeah. Sorry. So this is like a very specific kind of regime, but it's one that has been well established. So I'm kind of wondering, since it seems like the time scales and this sort of data, it seems very reminiscent. It is sort of surprising that this is actually that much more effective.

42:37Joseph Krause:Yeah, two things there. So number one, throughput is a big, important number. So to our knowledge and what is publicly released, so if there's someone that has done it behind closed doors I don't know about, please, we'd love to talk to them. The largest alloys program was the Mach program. It was run by DARPA NGE Aerospace. They did 500 alloys in about 12 months. They did a bunch of kind of AI and simulations on the front end of that, and then they synthesized 500 new alloys in that whole year. So that's kind of the benchmark, I would say, for how many alloys someone can do in a year. Again, we're trying to do 505 business days.

43:12Joseph Krause:We've done 1 ,200 in three months. So kind of an order of magnitude step up there that we're moving to. The second piece of this is, I think what's really challenging in the alloy space specifically, and I think it's probably specific to alloys, though I do think it will carry over to some other industries, is that there are so many variables that go into like determining your end product and then your end properties from that product. And that makes it actually harder to go do discovery on because there is endless amount of potential combinations. I mean, there are like 10 to the 40 different potential alloys that you could go out and synthesize.

43:50Joseph Krause:So how do you do that? Even if you could do high throughput to your point, it's still not that much high throughput, right? We think it would take human 7 million years to go make all of them. So what do you do, even if you're only doing 30 ,000 a year, right? Well, the screening mechanisms here are very helpful, as we all know, that's where AI is great. But I think the other point is actually because the data is missing from the industry, we don't have experimental data. We do see results from 100, 200, 300 experiments quite aggressively. We see 300 new alloys that we've never seen before from the experimental results of 1 ,200 alloys that we've run today.

44:29Joseph Krause:And you probably think each alloy probably has anywhere from 50 to 150 different data points, depending on how many images you take, how many specters you run, et cetera. That's a fairly small data set. Very small. Very small. And it's funny, when I talk to the ML side, they're like, how are you going to get to millions of millions of data points. And I'm like, I just don't think you need to. We have not seen that you need to to do a discovery yet today. We have a bunch of new discoveries, many that are going through, you know, patent protection and that we're talking to potential customers about.

45:00Joseph Krause:We just haven't needed millions of data points. And, you know, this brings up, I always get in arguments about compute. I got an argument at GTC about this. Like we don't, we're not compute constrained in the materials industry. Yeah, you're making stuff. Yes, we're experiment constrained. I mean, this is even what I do, which is computational. It's oftentimes dominated by data movement, right? It's not like I can, I see these people and I'm jealous of them that they have like 14 cloud sessions going and they have all these different experiments going and I couldn't do that just because I can't move the data around that enough.

45:37Joseph Krause:Yeah. That's almost a good kind of comp to our world of it's not a model problem. It's not a language problem. It's not, we don't have the same problems. There's an experiment problem. It's really, how can you run enough experiments to start to change the output of an AI scientist and capture data you need to discover something new? So for us, it's really about, that is our bottleneck. That is the throughput. That's why we're so bullish on self-driving labs. That's why when I start the combo, what do you guys work on? It's all about the self-driving lab, the autonomy, the experimental data. I mean, we're trying to build, you know, the protein databank for materials.

46:09Joseph Krause:and it's much more complicated than just crystallography structures or whatever else was in there. There's all these different properties you talked about today. It has to be inside that data set to make it relevant. So it's hard. It's hard to do. So that reminds me of Heather Kulik's episode where she said that there is no alpha fold for materials. So first of all, do you agree? I do. I think you can have alpha fold moments for specific areas of materials like microscopy. Perfect example. Reading, you know, using a segmentation model on SEM images, our team does that today. Like, that's a cool, whether you call it like alpha fold moment or not, I don't, but there is a real world where models make a huge impact on being able to do that.

46:51Joseph Krause:What I don't think you can do is go from like, I have this new hypothesis to, oh my gosh, I have a new material. It's scaled. It's done. It's in products in your iPhone. You can't do that today. I would agree with that statement. Okay. But even then, the alpha fold solved a scientific problem, which is how do you take a protein sequence and figure out what the three-minute structure of that protein is. And I want to put in so many caveats so that none of my structural biologists correct me. But anyway. Luckily, I'm not a structural biologist for everyone watching, so I get a free pass. But the thing that seems useful here is that you put in a chemical formula and some sort of processing, and what you get is essentially what you call the microstructure, which is something that you can get part of the information out of x-ray diffraction, but not all of.

47:39So that problem sounds much harder in a lot of ways than the biological problem. Okay. Yeah. Can you maybe explain a bit more about that?

47:48Joseph Krause:Yeah. And it's even harder than what you just described, meaning there are probably things you don't know you should test for yet, or that you might see when you go to scale that you did not know that you should have predicted or been paying attention to. That's really hard to put a data set around. And so kind of what I like to tell people that they do ask about this and, you know, can you build the data bank for materials? Like, well, I mean, again, if you want to do SEM images, scanning electron microscopy images and look at the, you know, use a segmentation, well, yes, you can build a really large data set of SEM images that are very good at finding dendrites or cracks or defects in a material.

48:26Joseph Krause:and the model will be very, very good at using that to predict, you know, and relate that to mechanical property because you're looking for what crack propagation does to strength. Okay. Tracked. But that's not the same thing as, okay, can you, can you make it, can you atomize it? Can you make it with the powder? Can you use that in manufacturing? Can you cast it? Way different thing related. Obviously the microstructure relates to that problem, but just because you understand the microstructure, just because you see and can predict crack propagation does not mean you're necessarily going to perfectly nail manufacturing.

48:55Joseph Krause:So man, there are like just so many things that we see stack up and some things that we, we learn a lot of new things. I think we know everything and then we go somewhere and we learn new things along the way. So I do think it's multifaceted for sure. And each inorganic material has different constraints, right? I talked about that supply chain. That's very relevant for the defense applications are a perfect example. Supply chain is not one of the things we worry about in consumer electronics per say. You know, like TIE64 is understood. I mean, it's available. Like, yeah, that people care about where it comes from, but that's not the same as the critical minerals focus that you see the U.S.

49:32Joseph Krause:have today on where are we getting these minerals that we do not control the vast majority of. Different problem there. So different inputs that are going to put in to get an output. I feel like that's why materials are so hard. It's just all of this other data that comes after just discovery. But I always tell people, the second you design a new material, that's a milestone. The second you synthesize it, milestone. The second you characterize it, milestone. That is not a new discovery. We count a new discovery when you pick up your phone and there's a new material sitting inside of it. That I think is a fair claim on new discovery and a scale material.

50:07So as you get past, so there's fallout in every one of those steps. So there's every milestone. And presumably in manufacturing, there's separate steps where there's fallout as well. So that as you get closer and closer to the consumer or the application, then you have less and less data, right? So how do you, how fundamentally, how do you get over that? Because I think in pharma right now, people are starting to think about there are sort of rules of thumb, I would say, that can be used to do reverse translation back from the clinic to the discovery process. You know, like, how do you do that in material?

50:48Joseph Krause:You know, it's funny. I love telling the story. one of my advisors at the company, he was at 3M for 35 years. And we were asking him about manufacturing. Like, hey, when you guys go to manufacture, like, what are you paying attention to? And this is earlier. This is like three months into the company. He's like, who are you guys got a lot to learn? What do you mean on material scientist? It's like different worlds. So interestingly, one of the challenges, he's like, you know, the hardest part about the data you're asking for or inquiring about, that is a 35-year trajectory person at the company that knows exactly where to turn the knob on whatever manufacturing tool you're talking about.

51:26Joseph Krause:And so what you're asking for is his or her ability to know when to turn the knob right to that spot at this specific moment. How do you capture that? How do I give you that? Even if you assign a formula to it, is it the same every time? And again, this gets back to intuition, which we've talked a lot about today, just in the manufacturing sense. And this is the hard part. I don't have an answer for you on manufacturing it because we haven't done it. But I do have a lot of answers on the discovery side where we've had to look where is intuition important. I talked about the casting of alloys, that torch earlier.

52:01Joseph Krause:That's one of them. Reading SCM images. That's one of them. Looking at XRD spectra and identifying phases and how strong are the peaks. Now that's arbitrary. That's really strong. That's kind of strong. That's not really strong. That's terrible. What do any of those mean? I mean, I can like guess what they mean, but if you look at an XRD, you might not get it perfectly to what, you know, you or you or I think about that. So this intuition aspect is so important. This is why we still have humans in the loop because you want to capture that. Now, when you go to manufacturing, we think we'll have to do the same thing.

52:33Joseph Krause:And we think the opportunity is you can actually rebuild those processes fully automated. And so you can actually put all of the sensors and all of the capture mechanisms, for lack of a better phrase, in place so you can kind of bring all of that back. That's a hard problem to solve. And to be clear, we have not solved that problem yet. We are certainly still at the discovery and the testing side of that. But that's where we want to get to. How do we get there quickly? Partners. We do talk to a lot of companies in our field who make materials at scale in the alloy space who are thinking about this.

53:03Joseph Krause:And they look at it from a different lens. You know, they're not all hype on AI for science. And actually, I'd say a lot of them are kind of bearish. They're like, you don't know what we know. And we've been doing it for a long time. And that's okay. I think that's healthy. What they do know and what they do bring to the table is actually we do have that intuition. We will tell you when you show us a family of elements what we think is going to work or not. And we might be wrong. We can tell you why we think that's going to happen. And we can tell you why that relates to aspects of a business that are important, like supply chain.

53:35Joseph Krause:like cost, like performance under certain environments that don't exist in others, extreme environments, for example, perfect temperature pressure. Those are really important. That's really important information that you want to bring back. That's how we get there in the near term and until we can do it ourself, is you partner with people who want to bring in this discovery, this turbocharged engine, you know, to their process. So, okay. Right now you're still refining that process in the lab. Absolutely. What are some war stories from the lab? Give me your best site. That's a good question. I love that question.

54:09Joseph Krause:Okay, so we bought the first tools in the lab. I can get in so much trouble for saying it.

54:17Joseph Krause:Fleeting the fifth. So some of the tools don't let us interface with the software. We now pay for that software, by the way, and we love that tool vendor. So we were very strategic about how we got access to that. and the engineering team, software engineering team was smart about how he could do that. So that was a whole two-week sprint that we had to figure out how he could probably try to programmatically control this tool. So what's the juice, man? Come on. You can look into the things that are running those tools and you can find out how you can control what you want to control. Fair enough.

54:51Joseph Krause:So that's one. My comms team is going to be so mad. No, no, no. I'm kidding. I'm kidding. I'm kidding. So I think, you know, one of the other war stories that we saw early was how interdisciplinary the team needs to be. So we knew it was going to be interdisciplinary going in. I think each field we kind of assigned has splintered into even more fields. So like, you know, materials at large, that's when we knew you're going to have computational and experimental. Okay. But mechanical engineering, you know, we have real mechanical engineers that build tools, design tools and put them together. They have mechatronics engineers that design all our own custom mechatronics to make those tools run autonomously.

55:34Joseph Krause:Obviously, in the field of MechE, but they really have those - Completely different job zones. Exactly. That's right. Software. Certainly, your standard full stack and like building the operating system, but then certainly more on what we call like applied ML or kind of like I come from that software background and I'm applying the systems that we are building, like pulling out images from SCM into the AI scientists. And that was interesting. robotics, things like path planning and perception, areas we probably didn't think we would need as much as we need today, just because we kind of thought, well, we'll use what's open source and off the shelf today.

56:10Joseph Krause:And then we started to realize that what the scientists were doing were very intuition-based, and that's like the perfect place where perception or CV can be really effective. I do this with the torch. So, man, all these different fields have splintered, and I think we had to build the planet as they fly it. So the startup mantra is where we had to continually add people. Ironically, that has now built a huge moat. You know, in inorganic science, it is not easy to build self-driving labs. And man, if you sent me back two years ago, I'd be like, that is a tough path to walk through. I told you, man.

56:44Joseph Krause:That's a tough path to walk through. And now, of course, it's a big moat for us where we're like, it's not about a robot in front of a tool. Go ahead, put a robotic arm in front of a tool and then watch what happens. Everything else I just talked about will come the second you do that. Now we feel so much farther ahead from the industry on really running self-driving labs for inorganic material science. So that war story, you know, it's funny, we laugh about it, but now we feel as actually a huge win and big edge for us. Is there something special about this moment, which enabled the self-driving lab versus, you know, five years ago, 10 years ago, you've been doing this for a while.

57:17Joseph Krause:So why now? A couple of things. One, AI for science is important, right? Like if I take force fields, machine learned, interatomic potentials, they're what, like two or three years old, whatever the exact timeline that they're old is. I mean, that's interesting. You can actually start to really do some parts of your process faster. And although they're still in the computational sense and the simulation sense with things like DFT, they're still very important to that funnel, to sharpening that funnel and moving faster at the top of the funnel. Two, robotics are just better. First of all, they're cheaper.

57:47Joseph Krause:Second of all, you can do more in actuation, custom grippers, different systems that even we can custom build or we can get. And then three, the buy-in from the tool vendors, like I talked about earlier. Again, I think two years ago, we even saw a difference than we see today where there is a lot more optionality. And I'll give you a perfect example. Some of the tool vendors now have software teams, or if they hadn't before, they weren't focused on this problem. They now actually provide support on, here's how you can work with the interface, right? That's a big change actually for the industry.

58:15Joseph Krause:So we've started to see it just become easier to build self-driving labs from an infrastructure and a hardware perspective. I think most important has been the biggest change. I think some of the other things has just been also like the excitement. I mean, everywhere I go, AI for Science is a talked about area. I was here this week speaking at Unlock. Kudos to Michelle and the measure team. Just unbelievable energy in the room from so many different builders across so many different companies and fields talking about AI for Science. And I think even, like I mentioned, at the national level, I mean, one of the things that we did early on was spent a lot of time in DC, both on the Hill, at the Office of Science Technology Policy, at the Department of Energy, Department of War, you know, letting them know, hey, if you want to be competitive in science, you guys really need to pay attention here.

58:59Joseph Krause:AI for science is a serious field. Self-driving labs are a serious field. There are other people who have already built these systems. We really think it is national infrastructure that should be built out. And there's been a big buy-in on that at the federal level, at the state level as well. So I think you have so many tailwinds that are just like pushing this industry forward, plus the excitement, plus the venture dollars coming in that start to solidify some of that. And I think soon we'll start to see some results. Like, I think we're still waiting on a big result that we see from someone.

59:29Joseph Krause:Hopefully we're one of the first ones there. I think that'll be a cherry on top to the last tip over where the customers who are, you know, coming in with restraint or caution, really see this, we can't believe you did that. We've been working on this problem for X amount of years. We've never had an output like that in that period of time. I'm convinced. I'm a believer. Let's talk about how to work together. And I think you see, look at robotics. I think you're seeing that moment happen already. Like it feels like we're on the upswing of that for robotics where, I don't know, two years ago, of course there was interesting work in robotics.

59:59Joseph Krause:If you were a nerd like me and you were like reading about it in your free time. But I still feel like when I talk to founders in that area, they're just now getting over the hump where, you know, supply chain and logistics companies and the big warehouse companies and even big humanoid companies are now like, oh, okay, now there's real foundation models that we want to pay attention to. We want to push from the 99 % to the 99.9999 % in our foundation model technology. I think we're going to have that for science over the next two to three years. I do. Once discoveries start coming out and this field continues to mature even more.

1:00:31Joseph Krause:Remember, We're early in this field. We are a couple years in from an energy, from a community, and from a new technology perspective. So going to the competitive landscape a bit, I mean, we talked a bit about, you know, in the U.S. or in Europe, what people are working on. But China is both, like, running ahead on materials development and also is thinking about a lot of these ideas about end-to-end labs going all the way through manufacturing. And they do have the expertise to do that. So what is your thought about how we say competitive versus China? And what is the most important thing we need to focus on there?

1:01:06Joseph Krause:This is an incredible question. This is actually what I spend a lot of my time on when I'm in D.C. This is really talking about. So China has an unfair advantage that we do not want to replicate but must figure out how to defend against. So in China, they really will go out of their way. And there's incredible work by like NIST and a couple other groups to documenting this to stand up manufacturing innovation hubs where they make a new material and they will, you know, support via capital or infrastructure the scale of said material system or said invention. And they can do that because honestly, in China, whether you're public or private, one entity owns everything.

1:01:43Joseph Krause:And again, that's the part that we should not mimic. We should not copy. In no way am I suggesting that. What I'm saying is because they have that, we need to have a similar focus. We need to figure out how to break the 25-year timeline. Now, when I come in here and I tell both of you, materials are long, right? You're like, yeah, absolutely. That's all we hear about. Everyone talks. It says the same thing. We know the same thing. We need to change that. How do you do that? I think number one is you start to teach the scientist of the future how to run science this way. You know what the most impressive thing from our lab is?

1:02:13Joseph Krause:I love everything we've talked about today. What is so impressive is we can have one PhD in metallurgy or alloys run 10 campaigns at a time. When I was in a PhD, we had 10 scientists focused on one campaign, one research problem at a time. That's an order of magnitude jump in productivity from one scientist. Now imagine every scientist in the United States, every scientist in North America, in the world, doing 10 times the research output. That's fundamental. I mean, that just changes the trajectory of discovery. But China can do that too, right? Yeah, they can. They can. So I think the second piece is investment.

1:02:47Joseph Krause:And this is where I was going to, you know, I think we're getting it in the private sector, which is great. I think you will continue to see the government invest in this area to try to start bridging these gaps and building up this workforce. You see the Genesis mission as one area where there's a ton of, you know, hundreds of millions of dollars of investment there. I know that groups internal to the national labs are building self-driving labs. My co-founder, Herd Cedar, has one at Berkeley. Argonne has one. I know that Ames is looking at self-driving labs. Livermore is looking at self-driving labs.

1:03:15Joseph Krause:Our mayor already has one. Oak Ridge has a manufacturing demonstration facility, which is almost fully autonomous or semi-autonomous in nature. So these labs are now starting to invest in the infrastructure to start to speed that gap up, to start to show you can shorten that gap. That's important. The third one is, I think, maybe where we have to be different, public-private partnership. And this is what we talk a lot about. This is the perfect opportunity for a private enterprise to work with public research to create the greatest scientific tool, as the DOE likes to say, in the world. Why? Because we have all the HPC that we need, high-performance compute.

1:03:52Joseph Krause:We have all the researchers that we need. We have some of the best scientists in the world at the national labs and the infrastructure from a material tooling or a science tooling perspective. And then lastly, you actually have the data. You actually have more experimental data in all of those national labs than anywhere in the world. Or we think anywhere in the world from all the science that we've run. So if you can couple all three of those things together and you can bring in private enterprise, you can help you make sense of that, help you close that system, help you tie the loop together.

1:04:22Joseph Krause:Now I think the entire national infrastructure runs in this way. The research infrastructure, whether that's corporate R &D or, again, like SBIR, STTR, R &D, runs this way. And private enterprise runs this way. Now you've changed the fabric of all of R &D in the U.S. Now you're at a place where you can compete with China, not by owning everything and doing unforced labor and the unethical practices that they might employ, but rather changing the mentality and the approach to how we do R &D. That's how I think we can compete. That's the only way we can compete. I think if we want to move forward, if we do not do that, then they will continue to win because they will outpace us on cost and they will outpace us on people.

1:05:01Joseph Krause:And so if you try to play that game, it feels like, you know, we're going to lose that game. It feels like, but if you play the game of changing the system and building a better workforce and a better system to do R &D than they have, then we can beat them with withdrawal output. We often ask our guests a question that you've kind of answered now, but I want to ask it anyway and see if you have any more, anything you want to add, which is if you could remove a bottleneck from the industry, what would that be? I don't think this is removable. So that's why it's not a good answer. But the hardest part about AI for science is that our feedback loops are long, right?

1:05:38Joseph Krause:I was talking - That's fundamental. Yeah, exactly. It's fundamental. That's why I don't know if you can remove it. Maybe there's ways to get it faster, but I'll give a perfect example, you think about math, like AI and math, right? You can run a lot of experiments in hours that will take us weeks or years to run in science. How do you get around that problem? That's a really hard problem to solve. And I think one answer is large scale automated systems. So a perfect example, if you build a facility with thousand XRDs or SEMs, well, you can certainly build that model that I mentioned can do, you know, image analysis better than anyone else in the world.

1:06:16Joseph Krause:So I think there are paths there to kind of leapfrog the challenge of doing fast experimentation, but it's fundamental. So it's a bad answer to the question. If something that's not fundamental, I would have the tool providers restart their stack. Their tools are built for humans. They should build them for agents and robots. I feel like this is already happening in software. I think you, right, CLI, MCP, like you've seen this already happen. If you could do that at the infrastructure level for tooling, I think it would supercharge this industry. Because now you don't want to train someone on running an XRD or an SEM.

1:06:51Joseph Krause:You want to train someone how to run the system that can do that. And that scales so much more effectively. Now you don't need to get a PhD to analyze your allies in SEM. Now you just need to focus on how I can run the system to do that exact analysis for me. That'd be transformational, but would be quite expensive. So. Okay. Do you have any calls to action for AI for scientists or let's say AI engineers? Yeah, they can bring techniques that scientists are not aware of. On a perfect example of that, I am not a machine learning scientist by training at all. I'm a material scientist by training.

1:07:25Joseph Krause:I did my graduate work in material science. My first job out of my grad school was material investing in material science. Now I run a material science company. I'm a material scientist at heart. That's what I do. One of my other co-founders is a material scientist. He's an academic professor in material science. But we have learned so much from the MLEs and the AI research scientists on our team because they're not material scientists. And so they show up to a problem and they don't get stuck on dendritic formation and grain boundary. And like this, right? They're just like, why don't you just segmentation model for that?

1:07:58Joseph Krause:It's like, I don't know what that is. Or like, that's not the first thought I have. I look at an SEM, but they do. Yeah. So one thing that they can do is they can actually like supercharge the industry with their own skill set. You know, one thing I don't like about the industry, I see so many people trying to be the other thing. Like I meet ML engineers that are like, I want to be a material scientist. And I'm like, why? We need ML engineers that work at Radical. Like you should be an ML engineer that helps us do science. And then I, this one I see way more. Material scientists try to be an MOE.

1:08:29Joseph Krause:Like I did a PhD in materials, did a master's in materials. I got to get in the AI side because that's where the field's going. No, you just have to know how to use those tools to make you better at your job, right? I don't care who can figure out the problem from SEM. I just want to be able to figure it out. So there's so much cross-disciplinary work that I would highly encourage ML engineers to, one, pay attention to AI for science. I think that's already happening, actually. I don't think they need to hear that again, especially on this podcast. I was a huge supporter. But two, like, lean into your expertise.

1:08:58Joseph Krause:Bring a first principle perspective to the way that we do science. We have been doing science the same way for hundreds of years. or 50s of years, or however old the tool is that we're running on. We're doing it for that long. You can come to that perspective and just totally change the way something works. The field has already done that in the past, and it will continue to do that in the future. And I can tell you 100 % guaranteed that we've done that at Radical AI today. So specialization. Exactly. Bring the specialization and lean into your expertise. Don't shy away from it. Don't try to become a material scientist.

1:09:26Joseph Krause:Be an MLE that works in material science. Awesome. So what does your AI stack look like? at a high level, kind of the AI scientist is really a multi-agentic approach. There are multiple agents that sit within what the AI scientist is. And, you know, we really have this orchestrator agent at the top that actually comes up with new hypotheses. It has a specific way to actually test those hypotheses that that is internal, that allows us to kind of test if they're going to be a good hypothesis and before we send it to the lab. But also going into that scientist are a bunch of other models as well, right?

1:09:56Joseph Krause:We are taking in data sets like industry standard data sets. You know, we pay for CalFAD and we actually pull that data in so that we can use it the same way. I would use it if I were a human scientist. That's really important. We have a literature review agent that we've custom built. That benchmark is also public on our website that actually can go and extract figures and information from scientific literature that's relevant to the hypothesis that we're making. So that's in that stack. We have custom models built, you know, one of them called Matrix, which is on our website as well. And I would encourage all the ML engineers out there, go check this out.

1:10:25Joseph Krause:The model and the benchmark are available on Hugging Face. You can find a blog post on our website about this. Matrix is incredible because Matrix is really a VLM that, you know, we have fine-tuned on Quinn that can actually go into images from the lab, experimental data, and extract scientific knowledge from it. And so the obvious benefit that we saw in the model, which you can guess, is it gets really good at reading the experimental data, which is, that makes sense. The one that we maybe didn't see coming was by understanding that data, it gets better at being a scientist. This is really cool, right?

1:10:59Joseph Krause:And so for the ML engineers out there, for the AI scientists, that is how you start to, we talk a lot about this intuition, the scientific intuition you get a PhD on. That's how you start to capture that. Now we have actually seen this and you can go read the publication. It's on archive where the public data set that we used actually is showing improvements like five to 16%, I believe, on general scientific reasoning. Is it adding math to your reasoning? Yeah, actually, I think math is the one area we call it that doesn't work. The theory is the same, right, where you add math and then you end up in other domains.

1:11:31Joseph Krause:Yes, and we do in the paper move outside into the biospace, I believe, and see that same improvement. You can find this all in the preprint that's out in the archive. So what's cool about this? What's so cool is that as you start to build these systems that can do science like a human scientist does, you start to compound the knowledge in the way we talked about earlier. Or I can be looking at all of these different things as I'm making a hypothesis. And although us human scientists would like to think we can pull in CALFAD, pull in literature and extract the right information from literature, not just read a paper, but pull the right stuff out that's relevant to this hypothesis.

1:12:07Joseph Krause:Look at all my past experiments. All of the database of our experiments are feeding into that AI scientist. So when we make a new campaign, it is looking at the past results to make that campaign. And we have a really cool demo that we show customers where when you look at a hypothesis generated, it'll actually tell you what experiments it's pulling into, what it's using to learn from about why it made that new hypothesis. So that's really cool. And then again, into these models like Matrix or Matrix PT, where you actually can start to pull out intuition. And then that intuition actually helps you become a better scientist at large.

1:12:39Joseph Krause:This is a really important concept. This multi-agentic approach is, I think, what an AI scientist really means. I don't think it's ever going to be one scientist. Maybe something will happen in the future. If you're an MLE, maybe that's a good problem to tackle. They filled that and we would love to be a customer of yours. But if not, I think you're going to have these specialized models, these specialized agents that are really good at one thing. And together, collectively, they make a scientist that's better than Joseph. That's better than the scientist that we have today. That's kind of what our stack looks like at a high level on the hypothesis generation and new material side.

1:13:09And then just quick follow up. So I love that you're open sourcing a lot of your work. Why are you doing that? Not that I want to discourage it in the least.

1:13:19Joseph Krause:This is a really important question. Number one, there's three reasons. Number one, I talked about community in this episode. We need the community to move to doing science this way. Open source work is some of the best ways to do that, as we've seen over history. So that's number one. Number two, learning. We actually get way more feedback from open sourcing things than we could possibly work on ourself. You guys are probably aware of TorchSim, which was this package that we open source. We don't need to go into that today. We can, the feedback from the community, the ideas from the community, we've actually spun towards some out into its own organization, nonprofit that can actually continue to run with the community.

1:13:55Joseph Krause:And, you know, we call Ignite a materials revolution, a simulation revolution, which we're excited about. So that's a good example. And so this idea that you can build better technology with the group is number two. Number three, we actually don't think models are remote. we actually think in five years, most models will be open source. Yeah, there's probably a proprietary or model or two the same way there's a proprietary model or two today that I can run, whether it's Claude or ChatGPT or Grok or whatever your favorite AI is. However, we think in science, models aren't the most experiments are.

1:14:32Joseph Krause:And so we actually think the more great models we can share like Matrix, which is out there. The data set's not, right? That data is the model that we built and put in the preprint is built on public data. Of course, we have our own proprietary data stacked on top of it. That's running Matrix internally. And the model can go out there. And I tell people all the time, what happens if someone else comes out with a better foundation model, better MLIP or better diffusion model? I'm like, that would be amazing. It would supercharge our scientists. We'll drop it right into our stack. That's not, we don't want to sell models.

1:15:04Joseph Krause:We don't sell models. We think the entire community will continue to have ideas that we cannot have alone. That's why we open source, because we don't think that's the edge. We think the edge is in the experimental side. And yeah, that's specific to radical. And obviously, I'm talking about what radical believes in the thesis there. But that is a big part of why we do it. If the whole community can push the whole field forward, we benefit from that. And they benefit from that. That's a win-win for materials at large. That's a win for AI for science. And it's a win because our stack now is a better model that we didn't have to produce, which is great.

1:15:34Joseph Krause:So whether it's us, we do have custom models built internally or someone else report that model in or use that or even pay for proprietary model, which we do on the LLM side, obviously. We don't build custom LLMs. Of course we use ChatGPT or Claude. All of that just goes into making a better scientist. And that's why we open source for the community to get better ideas and to really understand that we think experiments or really push that we think experiments are remote, not the model itself. Well, yeah, thanks for chatting. Yes, Joseph Cross, thank you so much. Thanks for having me, guys. Awesome to be here.

1:16:04I'm glad you enjoyed the show so much. I hope that we can spread the good vibes.

1:16:10Joseph Krause:You guys are. And I think we just talked about a great closing topic, which is how important this industry is. The impact that the world will feel from AI for science is enormous. People that can start at the ground root and actually push that forward like yourself are imperative. So thank you for everything you do. Super happy to be here and looking forward to coming back when the lab is fully autonomous. We'll run an episode in the lab. Yeah, I was just gonna say that. Yes. We should definitely do that. We have to come back to New York. Yeah. No problem. Pick a different time in the winter, though.

1:16:38Joseph Krause:We had a tough winter there. Okay. We'll do something. We'll do something. Perfect. Thank you guys for having me. Thank you very much.