0:00Ramses Alcaide says the technology was stuck in the lab since the eighties, and Neurable's AI boosts brain data performance enough for headphones, earbuds and AR glasses. He says it is noninvasive: no surgery, removable anytime.
2:34Ramses Alcaide demos headphones with sensors showing his focus as a live bar, plus a browser plug-in he coded in a few hours that speeds a podcast up to 1.72x when he focuses and slows it when distracted.
5:54Ramses Alcaide says the main uses are tracking focus and detecting when your brain needs a break, plus brain health metrics like cognitive strain, mental readiness and brain age. A biofeedback mode changes the audio when you get distracted.
7:56Ramses Alcaide says Neurable released a system with HP at CES, and a Tom's Guide reporter using its Prime feature cut 100 milliseconds off his gaming performance. He says Neurable provides tools rather than building every solution.
10:31Ramses Alcaide says a family member needing prosthetics inspired him at eight, leading to a neuroscience PhD at the University of Michigan. Seeing Alzheimer's and Parkinson's diagnosed ten years in, Neurable spent about ten years in R&D, backed partly by the US Army.
12:15Ramses Alcaide says Neurable has no SDK per se but offers a research kit that gives access to the system's data, which he calls effectively an SDK. He points people to Instagram, LinkedIn and, for students, Discord.
13:38Ramses Alcaide says a cognitive snapshot after ice baths showed all the men gained anxiety resilience while all the women saw a reduction, showing wellness solutions may not work equally across individuals.
15:03Jordan Metzner says cameras must analyze 15 to 25 frames per second in any environment, quickly and cheaply, with limited on-device chips and cloud budgets. Ramses Alcaide says Neurable faces similar trade-offs processing brain data on the edge.
18:36Ramses Alcaide calls it an overfit issue: the model assumes anyone with a mustache is an adult. He says brain data can track brain age, and some companies turn two minutes of brain data into a key that can't be replicated.
Brain-Computer Interface Headphones: Neurable's Focus Demo: the key questions from this episode, answered with quotes and timestamps.
Ramses Alcaide [0:00]: This technology has been stuck in the lab since the eighties, and it's now because of our Neurable AI system that essentially boosts the performance of brain data that we're able to bring it to everyday devices like headphones, earbuds, AR glasses, etcetera, and still get the performance that can deliver for customers. Built This Week, breaking it down. Built This Week, we show you how. A fresh idea, a clever tweak, you locked in shoe. Built This Week.
Sam Nadler [0:27]: Hey, everyone, and welcome to Built This Week, the podcast where we share what we're building, how we're building it, and what it means for the world of AI and startups. I'm Sam Nadler, co founder here at Ryz Labs, and each and every week, I'm joined by my friend, business partner, and cohost, Jordan Metzner. How are doing today, Jordan?
Jordan Metzner [0:47]: Hey, Sam. Happy to be back. Another exciting week in the world of AI. Lots of crazy fundraising from the major labs, and looking forward to today's special guest as well.
Sam Nadler [0:56]: Yeah. Before I introduce our special guests who I'm really excited to talk with, please don't forget to like and subscribe. We have new episodes every Friday. We've just crossed the 25,000 subscriber mark on YouTube and growing every week. So today we're really excited to chat with Ramses from Neurable. Ramses, do you mind giving us a brief intro of who you are and what you do? And then we'll jump in to the little demo we have.
Ramses Alcaide [1:23]: Yeah, for sure. So first of all, it's great to be here today and to speak to both of you. Really what we work on is something called a brain computer interface, which is just a fancy way of saying a wearable device that helps you better understand your brain and control different devices. So these headphones that I'm wearing actually have sensors on the inside that record my brain activity. These are typically used in laboratories to track things like epilepsy or sleep disorders, etc. But you can use them in so many incredible ways, from tracking different disease states to the health to even, for example, helping you focus, or this really fun demo that I put together that actually helps me learn at the speed of my own thought, which is going to be a really fun time.
Sam Nadler [2:08]: Amazing. And my understanding is your first product is non invasive, correct? There's other kind of players in this space that are invasive and this is a non invasive approach.
Ramses Alcaide [2:20]: Correct, exactly. So no surgery, and you can take it off anytime you want.
Sam Nadler [2:24]: Amazing. Well, how about, if you don't mind, you show us what you built and how you could theoretically apply this technology to an everyday use case?
Ramses Alcaide [2:33]: Yeah, for sure. And just to share a little bit of background too on what we do, we make it so that these devices can have brain computer interfaces, but then the trick is how do you take this complex brain signal and actually turn in something useful for people. Right? And so these headphones can actually track my focus in real time. And I'm just gonna show you here this, my screen real quick. Yeah. This is gonna be fun. You should be able to see a window here. This is actually a podcast. And do you guys see these kind of, like, blue bar that's scrolling right here? That's actually my focus in real time. So when I start to focus on this podcast,
Sam Nadler [3:13]: Oh, you can see it increasing.
Ramses Alcaide [3:16]: Exactly. Exactly. So you saw it increasing right here. And then now that I'm gonna get distracted, it's gonna start to drop off. Right? Yeah. Now what's really cool is like, yeah, sure. One thing is being able to track your focus, but what if you could use it to actually help you learn? Right? So this is just a quick browser plug in, and I can turn on this feature called mind. And what's gonna happen is that and this happens to me all the time, I'll be like working, listening to a podcast, maybe doing the laundry while this happens, and sometimes I'll get distracted and then I just realized I missed like a key part of the podcast. Right? Well, what if, because I listen to podcasts at like 2x speed, what if it could regulate the speed based off of how concentrated I was on the content? So that's what we're gonna do. Right? I'm gonna turn on mind. And then at first, what I'm gonna do is I'm gonna start focusing on this podcast, You'll and see that this line will go up, and then eventually, I'm gonna get distracted, and you'll see it go down. You'll see that my speed went up to 1.72. Right?
Jordan Metzner [4:20]: Wow. Yeah.
Ramses Alcaide [4:22]: And now I'm getting distracted, and you'll see that it's slowing down. And then I'll focus again.
Sam Nadler [4:32]: That's amazing. This is a dream come true for Jordan who listens to about Podcast at 2.5x.
Ramses Alcaide [4:39]: So you can see that that joke dropped my focus dramatically. You see that?
Jordan Metzner [4:43]: Yeah. Oh, so cool. Like Yeah. It keeps you off task. Amazing. And this is just to be clear, this is just from the headset you're wearing on your ears right now. Right?
Ramses Alcaide [4:55]: Exactly. Exactly. And, this headset is available in the market. There's an app and everything that you can use that tracks your brain health, tracks your focus, and you can even use it to remind you when you're going out of focus, too. It'll change the sound that you're listening to remind you to get back to task. But you can imagine how being able to leverage the brain, you can use it across so many different tasks. Like this thing. I literally whipped it up in, a few hours by coding it. Like now I have this automatic podcast information delivery system.
Jordan Metzner [5:27]: Yeah, amazing. Yeah, maybe you could have it change the video if you get, if your interest wanes too low or yeah, if the videos were shorts, maybe you would just switch the short, as your interest dies or something.
Ramses Alcaide [5:39]: So many things that you can do. Like the brain is the most powerful organism in our body. Right? And it has the most breadth of things that it can do out of any other organ. So the really, the possibilities are limitless. Right? This is just one fun demo to show it off.
Sam Nadler [5:54]: Let's jump into the business as a whole. Then and I know, we just demoed this one use case, but walk us through, like, I've heard that there's a few other use cases. Gaming could be one. I'm sure there could be some medical use cases. Walk us through kind of, I know you've been at this for also many, many years, so it would be great to be here a little bit about where the product is today and where it evolved as well.
Ramses Alcaide [6:17]: So the main use case for these products are two key things. One is tracking focus and attention, and the other one is breaks. Right? So I'll show you guys something really cool here if I can just share my screen real quick. So this is actually somebody reading a book for an hour and a half, and you'll see that their focus is relatively high in this green zone. Right? And here's the crazy thing. When you feel tired, that's actually your body that's tired. Your brain has been tired sometimes for hours beforehand, and we can detect when that brain is getting tired, which is this dip right here. If you don't take a break, you're slowly burning out. But if you take this break, it actually releases something called the Dina sign, and it's like getting coffee for free without the caffeine. Right? You essentially get this boost in performance. Right? But it gets even cooler. If this is detecting when you need a break, we can also detect when you're getting distracted. Like how many times have you read a book and you realize at the bottom of the page you didn't mind wandering the whole time? That's like me every time. Right? Yep.
Ramses Alcaide [7:14]: But we can actually detect when you're getting distracted, this yellow zone, and change the audio, and we've been able to keep people in this, like, medium to high focus consistently. And it's just in the app. It's this little button called biofeedback right here that you just turn on, and now it's giving you live feedback about your focus. And all this is just available essentially in the consumer application. The second use case is with brain health, so it tracks things like how much cognitive strain are you under, what is your mental readiness for today, and even the age of your brain. And you can see like, hey, maybe my brain is aging at a faster rate. Maybe I should go get an MRI or get checked out by a doctor. Those are the two main use cases right now on the consumer product.
Jordan Metzner [7:55]: And what about with sports? This sounds like kind of a sports opportunity as well. Just thinking about concentration.
Ramses Alcaide [8:00]: Yeah, I mean, so there's there's just so many use cases for the brain, right? I mean, Sam mentioned, for example, gaming. You're mentioning sports. Well, in gaming, we have this new system that we released with HP at CES. Right? And if you just Google search CES, like Neurable, you'll see that essentially it's like the system that helps you overclock your brain. So what if you could cut fifty to one hundred milliseconds just while you're gaming? Right? We have this biofeedback system that's gonna be released with those devices to help you improve your gameplay. In sports, same thing. Right? Imagine doing a small priming exercise that then helps you essentially, get faster in your actual, your gameplay or be more ready for the work that you do.
Sam Nadler [8:47]: Yeah. I was thinking almost like potentially surgeon use cases, I was thinking, and maybe this is like a, an ER doctor who's got a twelve hour shift and they're operating on people. It's high stress environments. And, I could imagine towards the end of the shift, if they can help maintain a sharper focus, they probably would have better health outcomes. Maybe that's a stretch, but it sounds like there's just millions of different use cases.
Ramses Alcaide [9:16]: For sure. And that's the key thing about what we're building, which is our goal isn't to build every solution. It is to essentially provide the tools for people who know the surgical room really well to leverage brain computer interfaces and their own use cases, individuals in gaming that that know that area really well to create new capabilities, etcetera. But the key thing is that this technology has been stuck in the lab since the eighties, and it's now because of our Neurable AI system that essentially boosts the performance of brain data that we're able to bring it to everyday devices like headphones, earbuds, AR glasses, etcetera, and still get the performance that can deliver for customers. I wanted to share with you guys something that I think was really, really cool regarding kind of this system. So this was actually from a post of one of the reporters that came and saw the system. It's it's a Tom's Guide post. And he says and he used this system called Prime that helps you accelerate your brain. And he's like, a 30 gamer who fell off a long time ago in first person shooters found his swagger again. Essentially, he was able to cut a whole 100 milliseconds off of his gaming performance.
Ramses Alcaide [10:25]: Like, imagine you could do that just by using a brain computer interface. Like, it's so cool, the things that are possible.
Jordan Metzner [10:31]: That's incredible. Can you give us a little history of how you got into this, and how you even found this field and opportunity, and study of all of this, how you guys got your product to where it's at today?
Ramses Alcaide [10:43]: Yeah, I mean, it's been a lifelong journey. I got passionate about brain computer interfaces when I was about eight. Right? I had a family member get into a tragic accident, unfortunately, where he ended up needing prosthetics. And so I wanted to build prosthetics that could be controlled by the brain. And then that made me focus my life toward electrical engineering. I got a PhD in neuroscience, and that's really where the first version of this Neurable technology got built in grad school at the University of Michigan. But what's really key there is I also saw something that that completely just rocked my world. Right? And in a bad way, which is like and you both might know this just through the breadth of audiences they've spoken to, but the standard of care for knowing they have, like, Alzheimer's and Parkinson's is is, like, ten years into the disease. Like, that's crazy. Right? And so what if we could bring this incredible technology that's in the lab to at scale devices like headphones and earbuds? We could do neuroscience earlier, we can identify problems sooner, we could take action. Right?
Ramses Alcaide [11:43]: And so that became the mission of the company. And our goal was not to be the first company to release headphones with brain sensors or earbuds with brain sensors. It was to make sure that the performance was high enough that it would actually deliver on the promise of brain computer interfaces. So we spent about ten years in research and development, building out the technology backed by, great investors, the US Army, and working across numerous partnerships. And now fast forward all that time later, we started working with consumer brands to bring this technology to everyday devices.
Jordan Metzner [12:15]: Amazing. Amazing. Okay, cool. And I think before we kind of move on to some other stories, how can users find you? How can users find the product? Where can they find it? Is there an SDK API? What are they what are people building with it? Just tell us a little bit more to kind of get how to get people and a product in their hand, maybe.
Ramses Alcaide [12:32]: Yeah, for sure. I would highly recommend that individuals come join us essentially at our Instagram. We have two. One is neurable underscore. The second one is mine. It's just my name, Ramses Alcaide. And the reason I recommend that is is especially mine. I think mine is, like, a lot more fun. Don't tell them that. But the reason for that is like I have these crazy experiments that I do. Like I'll drive a race car and I'll record my brain activity. I'll walk on fire and I'll record my brain activity. And so I got all these crazy things that I've done. I'll get into an ice bath, and I'll see how does it affect men versus women. Right? So there's just all these really fun experiments that you can see, like how your brain reacts. So once again, Instagram, LinkedIn, feel free to add us there. And if you're a student, highly recommend that you join our Discord. We have a ton of students there. They share their projects.
Ramses Alcaide [13:23]: They tell us about ideas that they're using to build with our existing system. We don't have an SDK per se, but we have something called a research kit that enables people to get the data from the system and build different devices on top of it. It's effectively an SDK, but with a fancier name.
Sam Nadler [13:38]: Okay. Just Cool quick question from one of some of your experiments, the race car driving, walking on fire, ice bath, which were surprising? Did your brain shut off in the ice bath? Or is there anything that would be as fun that was unexpected?
Ramses Alcaide [13:56]: Yeah. I mean, what I think was a really interesting thing is we were at breakfast, and we had, like, an ice bath lined up earlier that day. And this girl comes up to us, and she's like, hey. I heard some rumor that women and men, react differently to ice baths and that maybe women may not get the full benefit of what an ice bath as a male would. And in my head, was like, I don't know if I fully believe that, but I have the tools to test it. Right? So we ran some women and we ran some men and we did something called a cognitive snapshot, which you can do actually on your phone. It's in the app. And she wasn't wrong. Like, we saw this key variable called anxiety resilience, which is how well you can handle stress. Like, all the men had an increase in anxiety resilience, which means and that's what you want from an ice bath. You want to be able to handle stress better. So you became more resilient to stress. But all the women got a reduction in it. So we actually saw that, this thing that ended up being a breakfast rumor actually turned out to be more true, and it shows you how wellness solutions may not work equally across individuals.
Ramses Alcaide [15:00]: It really is a customized thing.
Sam Nadler [15:03]: They're more of a sauna cohort. Right, guys, let's jump into the news. We wanted something a little fun. This isn't, too serious of a news day. We're sharing this first one. Security cameras are failing spectacularly at common sense. AI descriptions, I think, are calling brake lights fires and dogs bears. But, Jordan, just because you have so much experience with building these systems and hardware, I just want to hear what you think is going on.
Jordan Metzner [15:35]: Oh, man. This is a I mean, this is a RingTag camera, but, why is this a hard problem? So security cameras live at the edge, right? So they're like on your doorpost, they're on, they're in your house, right? Then they have to connect, probably to your Wi Fi, right? So they're not really to hardwired, right? And then they have, physical sensors on them. So like infrared sensors and other types of sensors on them, maybe radar. And then they also have the camera, right? And then they have to have either a local model, a model on the device, right? Or a cloud based model that can then process these images as they're coming in at like 15 frames per second or 20 frames per second, 25, depending on the camera style, either locally or on the cloud, and be able to analyze these pictures, accurately in all different types of environments. And, in the case of here, like this very dark, low inhibited environment. So like, you don't always know what you're looking at because like the user themselves could put the camera in any direction upside down in any type of environment. And so you have kind of this, non heterogeneous, dataset and you're trying to build a model that like works for all these different environments. It has to work very fast.
Jordan Metzner [16:38]: And the other thing has to be cheap, right? Because like if you put like a very heavy model, on the cloud, then like customers aren't willing to pay like hundreds of dollars a month per camera, let's say to analyze like all of these photos. And so you're stuck in this position where you want to analyze things both at a, on device level, at a cloud level, do both of them to like try to provide some real time solution. Right. When you see the animal, you want to get notified. Right. So they got to send you a push notification. Right. And all these things have to happen very, very quickly. And you don't have a lot of dollars like of dollars to spend both on the device side. Right. You can't put a really expensive, Nvidia, crazy chip on it because nobody's going to buy a $10,000 camera. Right. And then on the cloud side, you can't put like a very heavy chip on it because then no one's going to pay a monthly subscription for a really high rate. So you're stuck in this place of like consumer electronics where you need to put the right type of technology, you need the right type of response time, but you're highly limited on, the type of, hardware, software and type of inference you're able to put on every, like, per instance that's happening.
Sam Nadler [17:37]: Oh, sounds like a miserable problem. Ramses, did you get a chance to read it and any high level thoughts? You're in the hardware space, so maybe that something resonates.
Ramses Alcaide [17:47]: What I would just say is what's crazy is that these are the problems that people see in different ways across different devices. Right now, we process brain data on the edge with these headphones. And so it's like we're trying to balance costs, we're trying to balance compute capabilities, sending to the cloud, all these things. And at the end of the day, it's just so hard. Like, don't think people appreciate, like, how hard it is to even do the simplest things. Like, you look at it and you're like, Why does that think it's a bear? It's clearly a raccoon. You know? And it's like, but one, your brain is just such an incredible, amazing machine that can classify these things that easily that you take it for granted. But, I mean, somebody's probably spent their entire life classifying this raccoon and getting it wrong. You know? It's like it's that hard of a problem.
Sam Nadler [18:35]: Great. And just to wrap up here, guys, just for fun, we thought this was hilarious. Kids are bypassing age verification checks with a fake mustache. Leave it to kids to get past some of those filters. I heard, I think it was today, Facebook announced that they're analyzing bone structure and facial height to understand if the user is a minor, but we thought this was a fun article to end the day.
Ramses Alcaide [19:01]: Yeah, I think it's kind of crazy to think about that's how simple these machine learning models are to a certain degree, that just putting on a fake mustache is enough.
Jordan Metzner [19:10]: Yeah, it reminds me of kind of hot dog not hot dog, right? So the model can just say adult, not adult, right? And then you put the mustache on immediately, it's adult, right?
Ramses Alcaide [19:19]: It's an overfit issue, right? It's like what kid has a mustache? So as long as there's a mustache, the model's like, Oh man, clearly this must be an adult, right? Like no matter how their face looks like, which is kind of crazy to think about.
Jordan Metzner [19:31]: Yeah, I remember there used to be video games to check your age. They would ask you like trivia like kind of that would age you properly, you know? Maybe we'll have to go back to that, but then ChatGPT just solves it again. So you know, I don't know. There's you know, that's why we need a better device to understand, true identity. Tell us more about how your device can tell true age.
Ramses Alcaide [19:53]: Actually, that's a really interesting perspective, which is, so we've captured thousands of people worth of data at this point, and some of it with work with the Department of Defense and tracking the age of people's brain and how much damage, has happened or, the case of a soldier in the field. And so, yeah, I guess that's one way of at least verification. There's also a few companies out there that are doing individual verification. It's really hard to duplicate a person's individual brain signature, and so I've seen a few companies focused on how do we collect two minutes worth of data and then turn that into a key that can't be replicated? That's another way of doing it.
Jordan Metzner [20:32]: Super cool. All right. Well, was really fun episode. Was really great to chat with you. Awesome to learn about your product and obviously just the early days of kind of like, being able to get this feedback. Obviously, people have things like Apple Watches and Oura Rings and Whoop bracelets and things like that, but I think your headset just shows that we're starting to creep into a new area of self analysis that really will allow us to empower us to do cool new things.
Sam Nadler [20:57]: Absolutely. Thanks for joining. I'm a little scared when I eventually get one of your headphones, how distracted I am throughout my typical workday. Maybe I don't I want to
Ramses Alcaide [21:08]: Tell you, Week over week, you'll get better at it. That's and that's why You're getting them. So there you go.
Sam Nadler [21:12]: Thanks for joining.
Ramses Alcaide [21:15]: Honored to be here. Bye, everyone.
