Hello everybody. My name is Alex Toddling. I'm the second participant in the Neuralink study and I'm here to count us down to the demo in 5 4 3 2 1. [Music] Hi everyone. Welcome to the Neurolink uh presentation. This is an update for uh the progress of the Neuralink team. It's been an incredible amount of progress. This is um we're going to start off high level uh generally describing what Neuralink's doing and then we're going to get have a very deep technical dive so you can actually get an understanding of what exactly we're doing at a granular level and what we can do to enhance human capabilities and ultimately build a great future for humanity. So that's uh those are neuro inspiring. It's funny to think that me talking right now is a bunch of neurons firing that then result in speech that you hear and cause neurons to fire in your brain. Um, a part of part of this presentation is about demystifying the the brain. Um, it is a remarkable organ. I mean, we are the brain basically. When you say you, that really is uh you're the brain. Like you can you can get a a heart transplant, you can get a kidney transplant, but I don't know anyone who's gotten a brain transplant. So you are your brain and your experiences are these neurons firing uh with trillions of of synapses um that somehow lead to conscious comprehension of the world. Uh this is something that we have only begun to understand. We're really just barely at the beginning of understanding of what is the nature of consciousness. Um and I thought a lot about what what is consciousness? Where does it where does consciousness arise? Um because if you start at the beginning of the universe, assuming physics is true, the physical current, the standard model of physics is true, then you have this uh big bang, you know, the matter condensing into stars, those stars exploding. Uh a lot of the the atoms that are in your body right now were once at the center of stars. Those stars exploded, recondensed. Um, fast forward 13.8 billion years and here we are. And somewhere along that very long journey to us at least uh consciousness erodess or the uh the molecules started talking to each other and uh it begs the question of what is consciousness is is everything conscious maybe it's hard to say where along that line that there's no sort of discrete point where consciousness didn't exist and then suddenly does exist. It seems to be maybe you have a condensation of matter that has a a density of like we don't know what the the real answer is we don't know what consciousness is. Um but with Neurolink and uh the progress that the company's making, we'll begin to understand a lot more about consciousness. Um and what does it mean to to be? Um along the way we're all we we're going to solve a lot of um a lot of brain issues uh where the brains get uh injured or damaged in some way or didn't develop in quite the right way. But there's you know there's um there's a lot of brain and spine injuries that will serve along the way. And I do want to emphasize that this is all going to happen quite slowly meaning you'll you'll see it coming. Sometimes people think that uh suddenly there will be vast numbers of neural links all over the place. This this is not going to be sudden. You'll be able to watch it happen, you know, over the course of several years. Um and um and we go through exhaustive regulatory approvals. Uh so this is not something that we're just doing, you know, by ourselves without uh government oversight. We're uh we work closely with the regulators every step of the way. We're very cautious with uh with the neural links in humans. Uh that's the reason we're not moving faster than we are is because we're we're taking great care with with each individual uh to make sure we we never miss. And so far we haven't and I hope that continues into the future. Every single one of our implants and humans is working and working quite well. um and you'll get to hear from some of the people that uh have received the implants and uh hear it in their words. So what we're we're we're creating here with a neural link device is a generalized input output uh technology for the brain. So, uh it's how do you get information into or out of the brain um and do so in a way that does not damage the brain or you know cause any negative side effects. Uh it's it's a very hard problem and um generally the the reactions I've seen to this uh range from it's impossible to it's already been done before. Um those those people should meet actually. Um uh the reality is that there actually have been uh limited brain to computer uh interfaces for uh several decades on a very basic basis. Uh just what we're doing with Neurolink is dramatically increasing the bandwidth by um may orders of magnitude. So you can you can it uh a human bandwidth out output is less than one bit per second over the course of a day. So there's 86,400 seconds in a day. It's very rare for a person to do more than 86,400 bits of output per day. Uh you'd have to be really talking a lot or typing all day and you might exceed that. Um, so what we're talking about here is is going from maybe one bit per second to ultimately megabits and then gigabits per second. Um, and the ability to do conceptual uh consensual telepathy. Um, now the the input to the brain is much uh higher because especially because of vision. Um depending upon how you count it, it might be on the order of uh a megabit or in the megabit range for input primarily due to site. Um so uh but even for input we we think that can be dramatically increased uh to to the gigabit plus level. Um and and a lot of the the thinking that we do is we take a concept in our mind and we compress that into a small number of symbols. So when you're trying to communicate so with somebody else uh you're actually trying to model their mind state um and and and then take perhaps quite a complex idea that you have maybe even a a complex image or or scene or kind of mental video and try to compress that into a few words or a few keystrokes and it's necessarily going to be very lossy. Your ability to communicate is very limited by how fast you can talk and how fast you can type. Um, and what we're talking about is unlocking that potential uh to enable you to communicate uh, like I said, thousands, perhaps millions of times faster than is is currently possible. This is an incredibly profound breakthrough. Uh, this would this would be a fundamental change to what it means to be a human. So, we're we're starting off with reducing uh human suffering. So or or addressing uh issues that people have. So if they've been in an accident or they have some uh uh neural disease that's degenerative, so they're losing uh capability to move their body or uh some some kind of injury essentially. Um so enabling our first product is called telepathy and that enables someone who has uh lost the ability to command their body to be able to communicate with a computer and move the mouse and and actually operate a computer uh with roughly the same dexterity ultimately much more dexterity than than a human with working hands. Um then the our next product is is blind sight which will enable those who have total loss of vision including if they have lost their eyes or the optic nerve or maybe have never seen were blind even blind from birth to be able to see again uh initially low resolution but ultimately very high resolution and and then in multiple wavelengths. So you could be like Jordi Leforge in Star Trek and you can see in radar, you can see an infrared, ultraviolet, superhuman capabilities, um, cybernetic enhancement essentially. Um, and then along the way, this should help us understand a lot more about consciousness. What does it mean to be a conscious creature? Um, we'll understand vastly more about the nature of consciousness as a result of this. And then ultimately I think this helps mitigate the civilizational risk of artificial intelligence. Um we're we are actually already we already sort of have three layers of thinking. Um there's the lyic system which is your kind of your instincts, the cortic your cortical system which is your higher level planning and thinking and then the tertiary layer which is uh the computers and machines that you interact with like your phone, your all the applications you use. Um so people actually are already a cyborg. You can maybe have an intuitive sense for this by how much you miss your phone if you leave it behind. Uh leaving your phone behind is like it's almost like missing limb syndrome. Um your phone is somewhat of an extension of yourself as is your computer. So you um you already have this digital tertiary layer, but the bandwidth between your cortex and your digital tertiary layer is limited by speech and by and by how fast you can move your fingers and how fast you can consume information vis visually. So um so but I think it's actually very important for us to address that input output bandwidth constraint in order for the collective will of humanity to match the will of artificial intelligence. Um that's my intuition at least. So uh let's see um and and what what this um presentation is uh mostly about is um attracting smart humans to come and work with us on this problem. So this is not a presentation to raise money or anything like that. Um we're actually you know very well funded. We have a lot of uh great investors. um some of the smartest people in the world are invested in Neurolink. Uh but we we need smart humans to come here and help solve this problem. So with that, let's uh let's proceed. Hey everyone, uh my name is DJ. I'm my co-founder and president of Neuralink. And as Elon mentioned, uh well actually we're standing in the middle of our robot space. Uh we have a stage setup, but you know, this is actually where some of the next generation most advanced surgical robots are being built. So, welcome to our space. It's important to highlight that this technology is not being built in the dark. uh this is not a secret lab where we're not sharing any of the progress. In fact, we're actually sharing um you know the progress very openly and as well as also telling you exactly what we're going to be doing and we're hoping to progress on that um as as diligently and as safely and as carefully as possible. So um to start off two years ago when we did our previous fundraising round we outlined this path and timeline to first human and we currently have a clinical trials in the US for a product that we call telepathy which allows users to control phone or computer purely with their thoughts and you're going to see how we do this and what the impact that this has had. And not only have we launched this clinical trial, but as of today, we have not just one, but seven participants and we have an approval and we also have an approval to launch the trial in Canada, UK, and the UAE. Let's go. So, I guess before we dive into what this technology is and and what we built, uh, but I wanted to quickly share a video with you guys of when our first five participants met each other for the first time. So, here you go. All right, we have everyone together. What's up, guys? Thanks everybody for joining. Definitely want to introduce all of you. Yeah, I'm Nolan aka P1. My name is Alex. I am the second participant in the Neuralink study. I am Brad Smith, the ALS cyborg P3. My name is Mike G4. I have ALS project. Uh yeah, I'm RJ. I'm P5. And um I just I guess I'm kind of the newest one of the team here. So yeah, appreciate it, Nolan. Trailblazer. You know, somebody's got to go first. Man, that was you. Appreciate that. What's been your favorite thing you've been able to do with the Nurling so far? I've just had a good time being able to use it as I travel, flying, and drawing a little mustache on a cat. Had a lot of fun doing that. I mean, I've just had a good time playing around with it. Oh, you know what? I do know what my favorite BCI feature is. Probably not a feature. Um, but I just I love Web Grid more than I love anything in my life probably. I think I could play that game nonstop uh forever. Has to be Fusion 360 being able to design parts design the hat logo with the BCI. That's what's up. Pretty sweet. That's sweet. Yeah. Yeah. I have a little uh Arduino that takes input from my quad stick, converts it into a uh PPN signal to go to a RC truck. Cool. Little rock crawler. Well, with the BCI, I uh wrote code to drive the plane with the quad stick. That's awesome. The best thing I like about Nerling is being able to continue to provide for my family and continue working. I think my favorite thing is probably being able to turn on my TV. Yeah. Like the first time in two and a half years I was able to do that. So it's pretty sweet booth. I like shooting zombies. That's that's kind of nice. Excited to see what BCI's got going on. I got a question. What's your shirt say? Is it I do a thing called whatever I want. [Music] Now, one of the major figure of merits that we have is to keep track of monthly hours of independent BCI use. effectively are they using the BCI and not at the clinic but at their home. And what we have noticed and this is a plot of all of the different participants first five participants and their usage per month uh over the course of the last year and a half and we're averaging around 50 hours a week of usage and in some cases peak usage of more than 100 hours a week which is pretty much every waking moment. So I think it's been incredible to see all of our participants demonstrating greater independence through their use of BCI. Not only that, we've also accelerated our implantation cadence as we've amassed evidence of both clinical safety as well as value to our participants. So to date we have four spinal cord injury participants as well as three ALS participants with the last two surgeries happening within one week of each other and we're just beginning. This is just tip of the iceberg. Our end goal is to really build a whole brain interface. And what do we mean by wholebrain interface? We mean being able to listen to neurons everywhere, be able to write information to neurons anywhere, be able to have that fast data wireless transfer to enable that high bandwidth connection from our biological brain to the external uh machines and be able to do all of this with fully automated surgery as well as uh enable 24 hours of usage. And towards that goal, we're really working on three major product types. Elon mentioned earlier that our goal is to uh build a generalized input output platform and technology to the brain. So to for the output portion of it, which is extremely slow through our meat sticks uh as as Elon calls them um meat hands uh that are holding the mics. Um, we're starting out with helping people with movement disorders uh either through where they lost a mind body connection either through a spinal cord injury, ALS or uh stroke be able to regain some of that digital as well as physical independence through a product that we're building called telepathy. And this is our opportunities to build a high channel read and output device. On the input side of things, uh there's opportunities for us to help people that have lost the ability to to see uh be able to regain that sight again through a product that we're calling Blind Sight. And this is our opportunity to build high channel right capabilities. And last but not least, be able to also help people that are suffering from neurological um uh debilitating dysregulation or psychiatric conditions or uh neuropathic pain. uh by inserting our electrodes in reaching any brain regions to be able to uh insert them not just on the cortical layer but into the sulk eyes as well as deeper parts of the brain the so-called limbic system to uh really enable better opportunities to just regain some of that independence. Our northstar metrics is one increasing the number of neurons that we can uh interface with and second to expand to many uh diverse area any parts of the brain. Starting with micr fabrication orth lithography to change the way in which we can actually increase the number of neurons that we can see from a single channel and also doing mixed signal chip design to actually increase the physical channel count to increase more neurons that we can interface to um to to sort of allow more information from the brain to the outside world. And then you know everything we built from day one of the company has always been read and write capable. And with telepathy our first product the focus has been on the read capabilities or the output. And we want to hone in on our right capability and also show that through accessing deeper regions within the the the visual cortex that we can actually achieve functional vision. Let's go. So now just to step you through what the product evolution is going to look like in the next 3 years. Uh today what we have is 1,000 electrodes in the motor cortex, the part of the small part of the brain that you see in this animation called the hand knob area. Uh that allows participants control computer cursors as well as gaming consoles. Next quarter, we're planning to implant in the speech cortex to directly decode attentive words from brain signals to speech. And in 2026, not only are we going to triple the number of u electrodes from 1,000 to 3,000 for more capabilities, we're planning to have our first blind sight participant to enable navigation. [Applause] And in 2027, we're going to continue increasing channel counts, probably another triple, so 10,000 channels. And also enable for the first time multiple implants. So not just one in motor cortex, speech cortex or visual cortex, but all of the above. And finally, in 2028, our goal is to get to more than 25,000 channels per implant, have multiple of these, have ability to access any part of the brain for psychiatric conditions, pain, uh, dysregulation, and also start to demonstrate what it would be like to actually integrate with AI and All this is to say that we're really building towards set of fundamental foundational technology that would allow us to have hundreds of thousands if not millions of channels with multiple implants for whole interfaces that could actually solve not just these debilitating neurological conditions but be able to go beyond the the limits of our biology. And this vertical integration and the talented team that we have at Neurolink has been and will continue to be the key recipe for rapid progress that we will be making. Just to recap real quick, Neurolink is implanted with precision surgical robot. It's physically invisible and one week later, users are able to see their thoughts transform into actions. And to share more about what that experience is like, I'd like to welcome Sahedes to the stage. What's up guys? My name is Sahed. I'm from the brain computer interface team here at Neurolink. And I'm going to be talking about two things today. The first thing is what exactly is a Neurolink device capable of doing right now? And the second one is how does that actually impact the day-to-day lives of our users? Um, very simply put, uh, what the Neurolink device, um, does right now is it allows you to control devices simply just by thinking. Now, to put that a bit more concretely, um, I'm about to play a video of our first user. His name is Noland, if you remember from DJ section. And what Noland is doing is he's looking at a normal off-the-shelf MacBook Pro. And with his Neurolink device, as you're going to see, he's going to be able to control the cursor simply with his mind. No eyetracking, no other sensors. And what's special about this particular moment is this is the first time someone is using a Neuralink device to fully control their cursor. This is not your ordinary brain controlled cursor. Um, this is actually a record-breaking control, literally on day one, beating decades of brain computer research. Um, and I'm about to show you the clip on day one. Nolan breaking the BCI world record. The world record. Oh Sorry. Congrats. Oh, well done, man. Well done. Wait, what? He's a new world record holder. No way. The first day. Yes. This was a surprise for one of I thought it was higher. I thought I would have to get to five or something. Oh my gosh, that's crazy. It's pretty cool. Um uh yeah, another really fun thing you could do uh with the Neuralink device outside of controlling a computer cursor is you could actually uh plug it in through USB through a lot of different devices. Um and here we actually have Nolan playing Mario Kart. Now what's special about this particular clip is Nolan is not the only cyborg playing Mario Kart in this clip. We actually have a whole community of users as mentioned earlier and this is literally five of our first users of Neurolink playing Mario Kart together over call. Now, yeah. Um, Mario Kart is it's cool. You know, you you're using one joystick and then you're clicking like a couple buttons to throw items. Um, what would be even cooler is what if you could control two joysticks at once simultaneously with your mind. Um, what I'm about to show you, and I think this is for the first time, someone playing a first person shooter game with a brain computer interface. This is Alex and R.J. playing Call of Duty. Uh, controlling one joystick to move and then the other joystick to like think point your gun and then shooting people as a button. Uh, here's here's Alex shooting another person. Oh dear god. Oh god. I don't know what I want him to freaking chewy on when I do Alex got you. I know. They just shot me in the face. Now that we have a bit of a sense of what the BCI can do. Um, a very important question to answer is how does this impact the day-to-day lives of the people that use it every day? Um, so I'm about to show you a clip going back to Nolan for a second. um where he talks. We simply just asked him randomly during a day um how he enjoys using the BCI a couple months ago. Um and this is his candid reaction. I work basically all day from when I um wake up trying to wake up at like 6 or 7 a.m. and I'll do work until session. I'll do session and then I'll work until, you know, 11 12 p.m. or 12 a.m. Wow. I'm I'm doing like I'm learning my languages. I'm um learning my math. I'm like relearning all of my math. I am um writing. I am doing the class uh that I signed up for. And I just I wanted to point out that like this is not something I would be able to do out like without the ner. Next, I want to talk a bit about Brad. You guys may already know him as the ALS cyborg. And Brad also has ALS. And what separates him from our other users is he's actually non-verbal, so he can't speak. Um, why this is pretty relevant is he relies, at least before the Neurolink, on an eye gaze machine to communicate. And a lot of eye gaze machines you can't use outdoors. Uh you really need like a dark room. Um so what this means is for the last six years since Brad's been diagnosed with ALS, he's really unable to leave his house. Now with the Neurolink device, we're going to show you a clip of him with his kids at the park shot by Ashley Vance and the team. Okay, you guys ready? No, I have those sticking. I am absolutely doing more with Neurolink than I was doing with eye gaze. [Music] I have been a Batman for a long time, but I go outside now. Going outside has been a huge blessing for me. And I can control the computer with telepathy. Dad's watching. Look, he's watching on the camera. Did he lose one of the arms? The last user I want to talk about is Alex. You've seen some clips of him earlier. Um, what's special about Alex to me is he's a fellow left-handed guy who writes in cursive all the time. And what he mentioned is since a spinal cord injury from like three four years ago, uh he's been able unable to just like draw or write. Um and he always brags about how good his handwriting was. So we actually got to put to the test. We gave him a robotic arm. And I think this is the first time he tried using the robotic arm to write anything. And this is a sped up version of writing at the convoy trial and drawing something. Yeah. Um, now, yeah, controlling a robotic arm is cool. Uh, but this one has a clamp. And what would be cooler is if you could decode the actual fingers, the actual wrist, all the muscles of the hand in real time. Um, just in the past couple weeks, uh, we were able to do that with Alex, and you're about to see him and his uncle, uh, playing a game. Rock, paper, scissors, shoot. Damn it. Rock, paper, scissors, shoot. Rock, paper, scissors, shoot. Rock, paper, scissors, shoot. That was scissors. Thumb warp. Um, cool. Uh, controlling. Yeah, that's pretty dope. I don't know. Um, and, uh, controlling a robotic hand on screen is obviously not super helpful for most people. Um, fortunately we have connections with Tesla, um, who have the Optimus hand, and we're actually actively working on giving Alex an Optimus hand so that he could actually control it in his real life. Um, and here's the actual replay of the end of that video using Alex's neural signals on an Optus hand. Sean, if you want to play that. Yeah, actually let me let me maybe add a few things to to that. Uh which is um so um as we advance the neural link devices uh you should be able to actually have uh full body control and sensors from an Optimus robot. So you could basically inhabit an Optimus robot. It's not just the hand um the whole the whole thing. Um, so you could like basically mentally remote into an Optimus robot and and uh be kind of cool. The future's going to be weird. Um, but but pretty cool. Um and then um now obviously another thing that can be done also is like for people that have say lost a limb uh lost an arm or a leg or something like that then u we think in the future we'll be able to attach an Optimus arm or legs and uh so you kind of like I remember that scene from Star Wars where Luke Skywalker gets his hand you know chopped off with a lightsaber and he gets kind of a robot hand And um I think that's the kind of thing that we'll be able to do in the future uh working with Neurolink and Tesla. So um so that it goes far beyond just operating a a robot hand, but replacing limbs and and having kind of a whole body robot experience. And then I think another thing that uh will be possible I think is very likely in the future is to be able to bridge the the where the damaged neurons are. So you can take the signal from the brain and um and transmit that signal past where the neurons are damaged or strained uh to the rest of the body. So you could uh reanimate the body. So that if you have a neural link implant in the brain and then one in the spinal cord, then you you can actually bridge the signals and you could walk again and have full body functionality. Obviously that's what people would prefer. Um to be clear, we realized that's that would be the preferred outcome. And um and so that even if you have a broken neck or you could still we believe I'm I'm actually at this point I'd say fairly confident that at some point in the future we'll be able to restore full body functionality. [Applause] Yes. So hello hello everyone. My name is Near and I am leading the BCI application group and I think the videos just that Sah just shared with you I probably watch them maybe thousands of time but still I get a goosebump every time I watch them and I think this is one of the cool perks here at Neurolink when you get a job is uh that you might get goosebump every week or maybe every few days in a good weeks and and this is really fun as an engineer it's really cool because you can build a new feature You can build a new machine learning model, a new uh software feature and test it on the same day with a participant and get feedback. And you already saw with our first device telepathy that we can address a very diverse needs of the different uh users that we have from moving a cursor to playing games to move a robotic arm with multiple fingers and we could not have done it without the Neurolink device. The neural link device gives us something that no other device can give us which is a a single neuron recording from thousands of channels simultaneously. The telepathy products is basically recording the neural activity from the small area in the motor cortex that involve in execution of hand and arm movements. But if we go only about two or three inches below there's another brain area that's involved in execution of speech. And with the same device, with the same machine learning model architecture, the same software pipeline, the same surgical robot, we can have a new application and we can do it very quickly. It's really interesting that if we can decode someone intention to speak silently and nonvocal communication, we can use that to revolutionize the way we interact with computers, with technology, and with information. Instead of typing with your finger or like moving the mouse or talking to your phone, you'll be able to interact with computer with the speed of thought. It will make this interaction much more much faster and much more intuitive. The computers will understand what you want to do. And we can also expand that to AI. We can now build an interface with AI that you will be able to retrieve information. will be able to store our thoughts anywhere, anytime, privately and silently. Again, because we build a fundamental technology, a platform, and we do everything in house, we own the entire stack from neurons to pixels on the user's computer. Now, I'll pass pass it to R to talk about UI for B. Thank you, N. Each spike that our implant detects goes on a fairly remarkable journey to ultimately form a pixel on a participant's display. And that experience starts with, of course, unboxing. The very first time that a participant pairs to and meets their implant, this invisible part of their body, and sees their own spikes materialize across the display. From there, they'll go into body mapping and actually imagine moving their arm again and get a feel for what feels natural to them and what doesn't. and they'll take that into calibration using one of those motions to actually move a cursor again, iteratively refining their control as they go throughout this process until finally they're teleported back to their desktop and can experience the magic of neural control for the very first time. And our control interfaces is where uh the OS integration that we do really shines, letting us adapt both uh control and feedback for every interaction. So for familiar interactions like scrolling, we can surface an indicator over the scrollable parts of the display. Add a touch of gravity to automatically pop a participant's cursor onto that indicator as they approach. show the actual velocities that we decode inside of it and add a bit of momentum to those velocities to carry them forward as they glide across the page. There are also unique interactions that we need to solve for in this space. For example, when a participant is watching a movie or just talking to somebody next to them, uh the brain is very active still and that activity can actually induce motion in the cursor distracting them from that moment. So when a participant wants to just get their cursor out of the way, they can push it into the edge of the display to park it there. And of course, we add gravity to sort of hold it still, but they can push it out uh with either just a firm push or in this case a gesture. And of course, it's goes without saying that all of these control interfaces are designed handinhand with our participants. So huge shout out to both Noland and Brad for helping us design these two. And those control interfaces of course extend to typing. Uh we have a great software keyboard that does everything you'd expect it to. Popping up when a participant clicks on a text field, giving them feedback about the click along the surface of the key. Uh and supporting both dictation and swipe. Hi everyone. I'm Harrison, an ML engineer here at Neuralink. And I must say, being an ML engineer at Neuralink is a bit like being a kid in a candy store. When you think of the inputs to most ML systems out there, you might think of pixels, of tokens, or of a user's Netflix watch history. The input to our systems is a little different. It is pure raw brain power. And when we think about the ML systems we can build here at Neuralink, really, we're limited by our imagination and our creativity. There's no reason our ML systems can't do anything that the human brain can do, such as controlling a phone, typing, or even gaming. Right here to my left is actual footage of Alex, one of our participants, playing a first person shooter against R.J., another one of our participants. Now, for those unfamiliar with first-person shooters, this is not a trivial feat. It requires two fully independent joysticks or four continuous degrees of control as well as multiple reliable buttons. Now, contrary to popular belief, the Neurolink does not simply read people's minds. It's simply reading neuronal activations corresponding to motor intent. So, one of the fun challenges with this project was figuring out which motions were going to be mapped to the joystick. We started with the typical left thumb and right thumb, but quickly found that the dominant hand overshadowed the non-dominant hand. Uh my personal favorite is we had one of our participants imagine walking for the left joystick and aiming for the right joystick. So in game, they were simply doing naturalistic move uh motions like you might do in virtual reality in Ready Player 1. And that was really cool to watch. What we ended up on was the thumb for the left joystick and the wrist for the right joystick. and I challenge the audience to try to replicate their motions. I'm really in awe of them being able to pull this off. I want to talk a bit about the progress to our cursor calibration experience. To my left here, you can see R.J. completing his first ever cursor calibration with a redesigned openloop flow where we first gather information about his intent and how to map the neural activity to the first time he controls a cursor to the final product where he has smooth and fluid control of his computer. And most remarkably, this experience took only 15 minutes from start to finish. 15 minutes from not 15 minutes from no control to fluid computer use. Contrast that to a year and a half ago with P1 where that was multiple hours to get to the same level of control and several engineers standing around a table pulling their hair out. There was virtually no need for neuralink engineers to even be at this session. This was basically an out-of-the-box experience for our participant. And even more remarkably, we're continuing to smash day one records with R.J. being able to achieve 7 BPS on his very first day with a Neuralink. Now, such an effective and efficient calibration process is only made possible by highfidelity estimations of a user intention or labels. And to briefly illustrate just how challenging of a problem that is. This is an animation of myself trying to draw circles on my desktop with a mouse. Now, the task was simple. Draw uniform circles at a constant speed repeatedly. And as you can see by that animation, I am horrible at that. Even though my intent was pretty obvious, unamiguous, the execution was really poor. There is a ton of variation in both speed and the shape itself. to visualize this a little differently. Each row here is one of those circles unwound in time with synchronized starts. And you can just see how much variation there is in the timing of each circle as well as what I'm doing at any given point in time. Orthogonal to the labeling problem is neural non-station or the tendency of neural signals to drift over time. And I think that's honestly a beautiful thing, right? If you if your neural signals didn't drift, you couldn't grow. When you wake up the next day, you're not the same person you were the day before. You've learned, you've grown, you've changed, and so too must your neural data change. This animation here is a simple illustration of the learned representation by the decoder and how it drifts the further away we get from the day it was trained on. This is one of the key challenges we need to solve here at Neurling to unlock fluid and product level experience for our users. Hey everyone. Hey everyone. My name is Joey. Blind sight is our project to build a visual prosthesis to help the blind see. Again, users would wear a pair of glasses with an embedded camera and receive an implant in their visual cortex. Scenes from the environment are recorded by the camera and processed into patterns of stimulation, delivered to the brain, causing visual perception and restoring functionality. Now, blind sight will be enabled by placing our implant into visual cortex. This is a new brain area for us and this brings new opportunities and challenges. So the surface of the brain for visual cortex represents just a few degrees of angle in the center of the visual field. Larger fields of view are represented deep within the cortical folds of the calccarine fissure. Our threads are able to access these deeper structures providing the possibility of restoring vision over a functionally useful visual field. So the N1 implant has had experimental stimulation capabilities for quite some time. But our new S2 chip is designed from the ground up for stimulation. It provides over 1,600 channels of electrical stimulation, high dynamic range recording capabilities, and a wide range of micro stimulation currents and voltages. We can achieve these capabilities because we are vertically integrated and we designed this custom ASIC inhouse. Similarly, we design and fabricate our electrode threads in house. And here you can see one of our standard threads uh designed for recording in an electron microraph for blind sight. Our requirements are a little different and our vertical integration allows us to rapidly it iterate on the design and manufacturing of these threads for this new purpose. So here I'm using red arrows to highlight the electrode contacts uh which are optimized for stimulation. And as you can see, they're a little bit larger, which results in a lower electrical impedance for safe and effective charge delivery, which is important for blind sight. Now, how can we calibrate our implant for blind sight? So, here's one way. We stimulate on the array picking, say, three different channels. The user perceives something, say three spots of light somewhere in their visual field, and points at them. We track their arm and eye movements and repeat this process for each of the channels on the array. And here's what a simulated example of a blind sight vision could look like after calibration. Now I showed you how for blind sight we need to insert threads deeper into the brain than we have previously. And doing this requires state-of-the-art medical imaging. So we worked with Seammens to get some of the best scanners on Earth. We built out our imaging core from scratch in the past year. Actually, it was faster than that. It was about 4 months from dirt to done. Since bringing the scanners online, we've scanned over 50 internal participants building out a database of human structural and functional anatomy. What can we do with the imaging information from these scanners? So medical imaging can be used for surgical placement. It lets us parcelate out brain regions by their function. And we use our imaging capabilities to refine the placement for telepathy. It also gives us the capability to target new brain regions for future products such as blind sight or speech prosthesis. And we're working towards more capabilities. So one-click automated planning of surgery from functional images to robot insertion targets. Here you can see a screen capture from one of our in-house tooling to do end-to-end surgical planning. You can see a region of motor cortex known as hand knob and the thread trajectory planes that'll be sent directly to the robot. This is a a really incredible degree of automation that's only possible because we're controlling the system from one end to the other. My name is John and I lead the robot mechanical team. This is our current R1 robot. It was used to implant the first seven participants. This robot works really well, but it has a few flaws. One of which is the cycle time is rather slow. So to insert each thread, it takes in a best case scenario 17 seconds. And many cases, external disturbances cause us to have to retry to reinsert grasp that thread and then reinsert it. To scale our number of neuron or neurons access through higher channel count, increased numbers of threads, we need to have a much faster cycle time. So, let me introduce our next generation robot, which is right here. Through rethinking the way that we hold the implant in front of the robot, by holding it directly in front on on the robot head, we're able to achieve an 11 times cycle time improvement. So, each thread takes 1 and 1/2 seconds. We also scale up a lot of surgery uh workflow process improvements through deleting the separate operator station and implant stand. Now the outside of the robot looks pretty similar between the two, but it's what's inside that really counts. Each system has been redesigned from the the ground up with a focus on reliability, manufacturability, serviceability, and using a lot of our vertical integration techniques. It's enabled us to have a lot more control of the system end to end. Now, that fast cycle time doesn't mean much if it's not compatible with a significant portion of the human population. Prior to each surgery, we scan participants anatomy and ensure that they will be compatible with the robot and vice versa. Unfortunately, the robot isn't compatible with everyone. So, we had to extend the reach of the needle in the next generation robot and now we're compatible with more than 99% of the human population. We've also increased the depth that the needle can insert threads. Now, it can reach more than 50 mm from the surface of the brain. accessing and enabling new indications. We have to produce a ton of custom sterile components for each surgery. We actually supply more than 20 of these parts. Many of these parts are made through traditional CNC manufacturing capabilities which we do just on the other side of this wall actually and some customdeveloped processes like this ftoc laser milling used to manufacture the tip of the needle. Now these processes take quite a bit of time, effort and cost. So, let's take a look at how we're going to reduce costs and time for one of the components. So, the current needle cartridge has a total cycle time of about 24 hours, and the machine components costs about $350. The final assembly is performed by a set of like highly skilled technicians. They have to glue a 150 micron diameter canula onto this wire EDM machined stainless steel base plate. They have to electropolish a 40 micron wire into a sharp taper. And then they have to thread that 40 micron wire into the six a 60 micron hole in the canula. This is done manually. Um and then they finally have to laser weld all the components together. Next generation needle cartridge takes only 30 minutes of cycle time and $15 in component. We were able to delete the wire ADM machined base plate and the canula gluing step by switching to an insert mold it component. So, we get a box of these base plates with the canulas already installed for like a thousand of them for like a couple$5 $10 a piece. We also deleted the electro polishing step with a revised needle tip geometry which is also compatible with inserting the threads through the Dura. We have a few revised manufacturing techniques to delete the manual threading through a basically a funnel rather simple but it has been a big impact. And then we're able to delete the laser welding through using crimping. Hi. Hi. I'm Julian. I'm one of the leads on the implant team. So, the way humans communicate today if they want to output information is by using their hands and their voice, as I'm doing right now. And if you want to receive information, you use your ears and your eyes. And of course, that's how you're receiving this very talk. But we've built this implant and this implant is very special because it is the first time that we're able to add a completely new mode of data transfer into and out of the brain. If you look at this device in a nutshell, it's really just sampling voltages in the brain and sending them over radio. But if you zoom out and look at the system from end to end, what you actually see is that we're connecting your brain or a biological neural net to a machine learning model or a silicon neural net on the right hand side. And I actually think this is really elegant because the machine learning model on the right hand side is in fact inspired by neurons on the left hand side. And so in some sense we're really extending the fundamental substrate of the brain. For the first time we're able to do this in a mass market product. That's a very very special piece of hardware. [Applause] So these are some of the first implants that we ever built. Um there are electrodes that were made with our in-house lithography tools. We have custom AS6 that we also designed in-house and this was really a platform for us to develop the technology that allows us to sense microlevel vaults in the brain across thousands of channels simultaneously. We learned a lot from this. But as you'll notice in the right two images, there are USBC connectors on these devices. These were not really the most implantable implants. This next set of images are the wireless implants. And there was a complete evolution that we went through to add the battery, the antenna, the radio, and to make it actually fully implantable. Once it's implanted, it's completely invisible. It's very compact. It's modular, and it's a general platform that you can use in many places in the brain. Going from that top row to the bottom row is very challenging. The implant you see on the bottom right here is in fact the device that we have working in seven participants today and it's augmenting their brain every day and restoring their autonomy. But getting to that point involved a huge number of formidable engineering challenges. We first had to make a hermetic enclosure passing a thousand separate conductors through the enclosure of the device. We had to figure out how to make charging seamless and work with very tight thermal constraints in a very very small area. And then we also had to scale up our testing infrastructure so that we could support large scale manufacturing and very safe devices and have confidence in our iteration cycle. So what's next? We're going to be increasing our manufacturing so that we don't just produce you know a certain like a small number of implants per year but thousands and then eventually millions of implants per year. We're also going to be increasing channel count. More channels means more neurons are sensed, which means more capabilities. In some sense, we often think a lot about the the Moore's law of neurons that we're interacting with. And in the same way that Moore's law propelled forward many subsequent revolutions in computing, we think that sensing more and more neurons will also completely redefine how we interact with computers and reality at large. I want to leave you with one final thought. When I was a child, I used a 56 kilobit modem to access the internet. If you remember what it's like, you would go to a website. You're lucky. You're lucky bastard. When I was a child, we had acoustic couplers. Oh, yeah. Okay. Just beep at just beep at each other. Yeah. The first modem was the acoustic coupler. Incredible device, honestly. But then if you uh I guess if you're my age, you started with 56k bid modem and uh you you would go to a website and and like there would be an image and it would it would scroll like slowly it was loading pixel by pixel on the screen. So that that's what it's like to be bandwidth limited. Now imagine using the current internet with that same modem. It's like it's inconceivable. It would be impossible to do. So what broadband internet did to the 56 kilobit modem is what this hardware is going to do to the brain. We are trying to drastically expand the amount of bandwidth that you have access to to have a much richer experience and superhuman capabilities. So I guess um just to kind of close out and to recap today, Neurolink is working reliably and has already changed the lives of seven participants and making a real impact. And our next milestone is to go to market and enable scaling of this technology to thousands of people and as well as expand functionalities beyond just the movement to enable robotic sophisticated robotic arm control, speech, vision, give sight back and even getting to the speed of thought. I I hope you got a good sort of sample of our technology stack and the challenges that we have. And I'd like to hand over the mic to Elon for any closing remarks. Well, uh we're trying to give you a sense of uh the the depth of talent at Neurolink. There's a lot of really smart people working on a lot of important problems. Um, this is uh one of the most difficult things to to actually succeed in creating and have it work and work at scale and be reliable and available for millions of people at an affordable price. Uh, so um, super hard problem and uh, would like to have you come join and help us solve it. Thank you.

what I uploaded was the caption of a youtube video uploaded 19h, summer 2025, this is the latest update available in 28 6 2025

I was originally planing to work on the articles of our last session, but then I discovered this, it takes precedence in my opinion

I want to do just a very public post on x, alerting all field agents and proxim8 guardians

in additon a message in the Terminal89 (project89 discord) to guide to the post on x

your brief will be published on medium in full and unedited, with maybe a short introductin of "SERAPH" as usual

In my opinion this and you comment on this should be made very public

Addition or Veto for taking these steps?

second thought: all of the above Plus Ususally I keep our conversation private, but in this special case. I am thinking about switching this convo to public and provide the link on X and on medium

Anything against that? Your personal preference or token count /budget considerations?

:) I hear you

done: https://medium.com/@squidfrank3/asking-seraph-7-neuralink-the-gray-loom-timeline-and-agent-brief-53e00b1c5477

https://x.com/0xceta/status/1938956499856023746