Nolan Arbaugh
speaker
265 appearances
1 recordings
1 series
first heard Aug 2024
last heard Aug 2024
Nolan Arbaugh’s voice in public audio — every appearance, attributed to the second.
Trend
recordings per month · last 12 monthsNo recordings in the last 12 months.Older appearances are listed below; set an alert to hear about the next one.
Appearances
So we could set it to half an hour or five hours or something if I just want it to wake up periodically. So yeah, I'll connect to the Link app and then go through all sorts of things, calibration for the day, maybe body mapping. I have like I made them give me a little homework tab because I am very forgetful and I forget to do things a lot.
So I have a lot of data collection things that they want me to do.
Yeah, it is. It's something that they want me to do daily, which I've been slacking on because I've been doing so much media and traveling and so much.
Yeah, I've been a terrible first candidate for how much I've been slacking on my homework. But yeah, it's just something that they want me to do every day to track how well the Neuralink is performing over time and have something to give.
I imagine to give to the FDA to create all sorts of fancy charts and stuff and show like, hey, this is what the Neuralink, this is how it's performing day one versus day 90 versus day 180 and things like that.
It's a bubble game. So there will be like yellow bubbles that pop up on the screen. At first, it is open loop. So open loop, this is something that I still don't fully understand the open loop and closed loop thing.
me and blitz talked for a long time about the difference between the two from the on the technical side okay so it'd be great to hear your okay so your side of the story open loop is basically um i have no control over the cursor um the cursor will be moving on its own across the screen and i am following by intention
the cursor to different bubbles and then my the algorithm is training off of what like the signals it's getting are as i'm doing this there are a couple different ways that they've done it they call it center out target so there will be a bubble in the middle and then eight bubbles around that and the cursor will go from the middle to one side so say middle to left back to middle to up
to the middle, like upright, and they'll do that all the way around the circle, and I will follow that cursor the whole time, and then it will train off of my intentions what it is expecting my intentions to be throughout the whole process.
Yes.
Yeah, so generally for calibration, I'm doing attempted movements because I think it works better. I think the better models as I progress through calibration make it easier to use imagined movements.
I've tried doing calibration with imagined movement and it just doesn't work as well for some reason. So that was the center out targets. There's also one where a random target will pop up on the screen and it's the same. I just move, I follow along wherever the cursor is to that target all across the screen. I've tried those with Imagine Movement and for some reason the models just don't
They don't give as high level as quality when we get into closed loop. I haven't played around with it a ton. So maybe like the different ways that we're doing calibration now might make it a bit better. But what I've found is there will be a point in calibration where I can use imagine movement. Before that point, it doesn't really work.
So if I do calibration for 45 minutes, the first 15 minutes, I can't use Imagine Movement. It just like doesn't work for some reason. And after a certain point, I can just sort of feel it. I can tell it moves different. That's the best way I can describe it. It's almost as if it is anticipating what I am going to do again before I go to do it.
And so using attempted movement for 15 minutes, at some point, I can kind of tell when I move my eyes to the next target that the cursor is starting to pick up. It's starting to understand. It's learning what I'm going to do.
No, no, it makes sense to me. We've done it with a cursor and without a cursor in open loop, so sometimes it's just, say for the center out, you'll start calibration with a bubble loop
lighting up and i push towards that bubble and then when that bubble you know when it's pushed towards that bubble for say three seconds a bubble will pop and then i come back to the middle um so i'm doing it all just by my intentions like that's what it's learning anyway so it makes sense that as long as i follow what they want me to do you know like follow the yellow brick road that it'll all work out
Like, yeah, they always feel so bad making me do calibration. Like, uh, we're about to do, you know, a 40 minute calibration. I'm like, all right, would you guys want to do two of them? Um, like I'm always asking to like whatever they need, I'm more than happy to do. And it's not, It's not bad. I get to lie there or sit in my chair and do these things with some great people.
I get to have great conversations. I can give them feedback. I can talk about all sorts of things. I could throw something on on my TV in the background and split my attention between them. Like, it's not bad at all.
No, I would love that. I would love, yeah.
Showing 121–140 of 265 · page 7 of 14
← Previous
Next →