WEBVTT

00:00:00.000 --> 00:00:08.320
Real world and then it's gonna go in there and then suddenly it's gonna notice the oh wait a minute, I know when I'm done because you can feel and literally the voltages will slightly change.

00:00:11.840 --> 00:00:15.280
And so these are the subtle little cues that are just so hard to tease in a simulation.

00:00:15.360 --> 00:00:18.720
They're so hard to get from egocentric data and why they want to do more and more of the

00:00:19.040 --> 00:00:19.520
data capture.

00:00:19.840 --> 00:00:22.560
And then of course the other things they can do is they may have like a proxy.

00:00:22.720 --> 00:00:25.040
We're not sure before they have all the alphabetic.

00:00:26.400 --> 00:00:28.320
It seems that they have alphabetic outfits.

00:00:28.880 --> 00:00:35.200
That means that's almost like a string of nine.

00:00:36.640 --> 00:00:37.680
This is not just the hands.

00:00:38.880 --> 00:00:46.800
almost have the whole thing as which is basically how Tesla did full self-driving is that people were not driving the car remotely.

00:00:46.880 --> 00:00:48.400
They were sitting in the seat, right?

00:00:48.960 --> 00:00:50.960
Literally driving the car the way the car is supposed to be driven.

00:00:51.360 --> 00:00:52.160
We'll we'll get to that.

00:00:52.240 --> 00:00:54.000
it's a very good comment that you made.

00:00:54.320 --> 00:00:58.560
Everyone else puts on they get the p humans to put on glasses and they put on gloves.

00:00:59.520 --> 00:01:08.720
And you're saying actually what Tesla you think is they're doing is they're actually putting on exactly what the robot has, like a battery pack in the back, the actual headgear.

00:01:09.440 --> 00:01:18.800
as if they are the robot and that's interesting we'll we'll cover that a little bit more but tell me about what will it take for Optimus 3 the new robot we haven't seen

00:01:19.200 --> 00:01:21.760
To be able to do the things Elan says we would do.

00:01:21.920 --> 00:01:24.560
You put together a deck here, let's let's walk as good as

00:01:26.160 --> 00:01:27.440
so basically there's the three things.

00:01:27.520 --> 00:01:28.560
You have the Swiss wash, the

00:01:28.960 --> 00:01:31.440
hundred miles per hour fastball and chainsaws and motorcycle.

00:01:31.600 --> 00:01:36.160
We're gonna break them down one at a time to get kind of an idea of of what's actually meant.

00:01:36.400 --> 00:01:37.280
So yeah.

00:01:37.520 --> 00:01:38.640
So you know the the first thing

00:01:39.280 --> 00:01:42.320
is you know what would it be like to assemble a Swiss watch?

00:01:42.480 --> 00:01:48.400
You know, it's with one hand, with the head looking down, right, at the at the work, and then suddenly has to catch a hundred mile per hour fast.

00:01:50.720 --> 00:01:53.120
It's not like it's going to drop something to be able to get it.

00:01:53.280 --> 00:01:58.320
You know, thrown from basically an angle, 'cause he he said, you know, thro obliquely I think was the word.

00:01:58.400 --> 00:01:58.720
So

00:01:59.600 --> 00:02:00.800
And everyone's wondering what that means.

00:02:00.960 --> 00:02:03.040
And what I think that means is not straight on.

00:02:03.200 --> 00:02:03.520
Okay?

00:02:03.760 --> 00:02:06.160
It's gonna be coming from the side somehow.

00:02:06.480 --> 00:02:08.640
So and

00:02:08.880 --> 00:02:12.000
And there's actually probably some advantage to doing it that way anyways.

00:02:12.080 --> 00:02:17.600
You know, one of them is like if it misses you know, if it doesn't get the catch, it just goes by, it doesn't like hit it right in the head.

00:02:17.680 --> 00:02:18.640
It's also gonna be a lot easier.

00:02:19.680 --> 00:02:28.640
And then finally, what kind what's required for like the torque requirements and everything else and responsiveness in the actuators to be able to do something like that

00:02:29.120 --> 00:02:32.960
juggling chainsaws on fire on a unicycle and everything else.

00:02:33.200 --> 00:02:37.440
And it seems like individually a lot of these things could be done.

00:02:37.600 --> 00:02:38.640
The question is you can eat

00:02:38.960 --> 00:02:41.200
you put that all into one machine.

00:02:41.520 --> 00:02:43.520
So let's see.

00:02:43.680 --> 00:02:45.920
Let's go ahead and start breaking it down.

00:02:46.880 --> 00:02:47.840
All right, so.

00:02:48.960 --> 00:02:49.920
It has to be a fair fight.

00:02:50.080 --> 00:02:56.960
In other words, the robot's not allowed to use tools that the human doesn't have, but at the same time we're not going to take tools away from the robot that we need as humans.

00:02:59.040 --> 00:03:01.600
a Swiss watch, we are not doing it barehanded.

00:03:01.920 --> 00:03:07.040
we have a lot of things that are helping us, you know, a loop or a magnifying glass, you know, tweezers.

00:03:07.200 --> 00:03:08.640
In many cases there's also something

00:03:08.960 --> 00:03:11.600
to rest your your wrist on to keep you from shaking and everything else.

00:03:11.760 --> 00:03:17.040
So that's fair game just so long as it's not specifically modified to be robot friendly.

00:03:17.200 --> 00:03:18.800
Okay, it has to use the same stuff.

00:03:18.960 --> 00:03:20.720
And if it doesn't need it, fine.

00:03:20.880 --> 00:03:22.320
But I would say it's there.

00:03:22.480 --> 00:03:27.680
the other thing is that when we talk about it's not really blind.

00:03:27.760 --> 00:03:28.560
It does have peripheral

00:03:29.120 --> 00:03:33.440
view but it should not be relying on any external cameras or anything else.

00:03:33.520 --> 00:03:37.920
It literally has to be whatever it sort of has on there and they have it set something else up.

00:03:38.160 --> 00:03:38.320
So

00:03:38.880 --> 00:03:42.240
For instance, this kind of stuff of tracking balls, there's lots of robots who can do it.

00:03:42.320 --> 00:03:46.080
We've already been seeing that there are bots that can play tennis and ping pong and everything else.

00:03:46.320 --> 00:03:48.320
Industrial arms have been doing it for over ten years.

00:03:48.960 --> 00:03:54.640
be able to do that tracking, but usually it meant they mounted other kind of camera systems around there to be able to do the response.

00:03:54.800 --> 00:03:58.640
even some of the tennis playing bots that we've seen, I believe they were not doing

00:04:09.040 --> 00:04:14.400
this idea because there are people who are able to juggle chainsaws and I think maybe even on fire.

00:04:14.560 --> 00:04:16.320
I'm not sure if on a unicycle.

00:04:16.480 --> 00:04:17.920
I know there are jugglers on unicycle.

00:04:18.080 --> 00:04:18.800
I don't know if anyone tried that.

00:04:18.960 --> 00:04:19.600
with a chainsaw.

00:04:19.920 --> 00:04:20.960
But those are props.

00:04:21.040 --> 00:04:23.680
Those are not the chainsaw that's down in your garage.

00:04:24.000 --> 00:04:24.960
They are much lighter.

00:04:25.280 --> 00:04:26.160
They're balanced different.

00:04:26.320 --> 00:04:28.320
The handles are different to be easier to grab.

00:04:28.880 --> 00:04:31.600
They're dulled and everything else, the the blades a little bit shorter.

00:04:31.840 --> 00:04:32.960
You know, a bunch of things like that.

00:04:33.040 --> 00:04:38.160
So it's like, okay, it can use the same ones that humans would be using to do that particular trick.

00:04:38.320 --> 00:04:38.640
But

00:04:38.960 --> 00:04:42.320
it has to use the same unicycle that a human would put.

00:04:42.400 --> 00:04:44.880
So we may see some some bots in unicycles.

00:04:44.960 --> 00:04:48.560
As a matter of fact, I think there already was an example back in the spring

00:04:48.960 --> 00:04:50.720
of a G one on a unicycle.

00:04:50.880 --> 00:04:57.600
What wasn't clear is whether it was actually a pedaled unicycle or whether it was an electric unicycle that was able to do self balancing on its own.

00:04:57.680 --> 00:04:58.400
That's cheating, right?

00:04:58.480 --> 00:04:58.720
I mean

00:04:59.040 --> 00:05:00.960
Using another mechanism to do the balancing.

00:05:01.200 --> 00:05:04.240
And the other thing is like that's a G one that's not human scale.

00:05:04.560 --> 00:05:06.880
So you wanna have something that that's fully human scale.

00:05:09.040 --> 00:05:18.720
things are just going to be a back of the envelope calculation to kind of see is it feasible or not and could we tease out the direction that opt this might be going if they really believe can have.

00:05:18.880 --> 00:05:22.160
So the first thing is you have to make some assumptions.

00:05:22.320 --> 00:05:26.320
So the only thing we know is you mentioned it's a baseball.

00:05:26.560 --> 00:05:27.440
A hundred miles per hour.

00:05:27.520 --> 00:05:28.400
Now when I think of a hundred miles

00:05:28.960 --> 00:05:38.720
an hour baseball think of a pitcher delivering it from a pitching mound which is 60 feet six inches away and of course the World Series is right now and there's a pitcher for the blue for the the brewers that can

00:05:39.040 --> 00:05:40.480
throw like 104 miles per hour.

00:05:40.560 --> 00:05:41.840
So I think that's why that kinda comes up.

00:05:42.000 --> 00:05:44.960
So let's assume you can't throw it from ten feet away.

00:05:45.040 --> 00:05:46.720
It's it's gotta be a reasonable distance.

00:05:46.960 --> 00:05:48.480
So let's assume it's being shot

00:05:49.120 --> 00:05:55.280
out you know some sort of pitching arm or something like that, that's gonna cover that distance in under half a second.

00:05:55.760 --> 00:05:58.400
So that means in less than half a second the robot has to

00:05:59.200 --> 00:06:02.960
acquire it, figure out where it's going, react, and put its hand in the right place.

00:06:03.280 --> 00:06:05.040
So we can kind of break down what's gonna happen.

00:06:05.840 --> 00:06:07.440
Humans are well, yeah.

00:06:07.600 --> 00:06:08.640
Humans can, not all.

00:06:10.480 --> 00:06:14.800
Those have been trained, who have good reflexes, are are able to do that.

00:06:15.040 --> 00:06:16.320
And this is kind of what goes on.

00:06:16.640 --> 00:06:18.640
And again, this puts our world model.

00:06:19.200 --> 00:06:23.920
we are very good at being able to track incoming ballistic things.

00:06:24.080 --> 00:06:28.560
Now we we've we certainly heard in Warzone that they do tracking of of incoming warheads.

00:06:28.800 --> 00:06:37.520
And the reason why you can do that is that they're on a known trajectory, and once you get enough of it, you can figure out where it's going to land and you can try to intercept it, unless they do evasive maneuvers.

00:06:39.120 --> 00:06:41.920
can only do the evasive maneuvers by putting spin on it to make it curve.

00:06:42.000 --> 00:06:48.720
But basically we as human beings have seen enough things fly through the air that with just a few images in our eyes, we can almost predict.

00:06:48.960 --> 00:06:49.680
where it's gonna land.

00:06:49.920 --> 00:06:54.720
That's why we can we can grab, you know, ru know where to run to grab a a catch or something like that.

00:06:54.880 --> 00:06:56.560
So that's what the same thing that's going on.

00:06:56.720 --> 00:06:58.400
You have a a short window

00:06:58.880 --> 00:07:02.320
in which you've got to figure out where the ball's gonna go so you're gonna react.

00:07:02.400 --> 00:07:04.080
And a batter has to do the same thing.

00:07:04.240 --> 00:07:08.720
So a batter has to very quickly kind of guess and decide whether they wanna swing the pitch.

00:07:08.960 --> 00:07:10.720
The same thing with getting your hand out there.

00:07:10.880 --> 00:07:13.920
So there's a little bit of a breakdown here we have of kind of looking what's going on.

00:07:14.080 --> 00:07:18.640
First, you know, looking down isn't the same as being blind, because we we will see something.

00:07:19.040 --> 00:07:27.200
And the only question is whether it's gonna look up, but I think he was saying it's still gonna be looking down almost as if it's bored and it goes and catches the ball Optimus.

00:07:27.280 --> 00:07:28.560
where are the cameras on the Optimus?

00:07:29.120 --> 00:07:30.320
Don't they have extra extra cameras?

00:07:30.560 --> 00:07:31.520
Yeah, they have extra cameras.

00:07:31.600 --> 00:07:31.920
Yes, yes.

00:07:32.080 --> 00:07:34.000
And and they may even be cameras from behind.

00:07:34.160 --> 00:07:36.480
we don't know if there's gonna be risk cameras.

00:07:36.560 --> 00:07:37.600
We we have have no idea.

00:07:39.040 --> 00:07:41.280
someone in the also in in the torso.

00:07:41.600 --> 00:07:43.600
So it's impossible there there are other cameras there.

00:07:43.760 --> 00:07:45.840
Right now I think there's stereo cameras.

00:07:46.000 --> 00:07:47.760
It may be like a chin camera or something like that.

00:07:48.000 --> 00:07:48.640
But we can assume there's

00:07:50.000 --> 00:07:50.160
Yeah.

00:07:50.400 --> 00:07:51.360
It's like it's like the car.

00:07:51.440 --> 00:07:52.080
The car has eight.

00:08:00.960 --> 00:08:08.720
But there's another reason is that it's a lot easier to track a throw coming from the side to figure out where it's going to go to

00:08:09.040 --> 00:08:10.160
to one that's coming right at you.

00:08:10.320 --> 00:08:12.560
If it's coming right at you, you don't have enough information.

00:08:12.720 --> 00:08:15.200
So you do want to actually have a little bit of obliqueness.

00:08:15.520 --> 00:08:17.360
Okay, so which is which is fair.

00:08:17.520 --> 00:08:17.680
Okay.

00:08:17.760 --> 00:08:18.560
If he said oblique

00:08:18.960 --> 00:08:20.960
That means it's like it doesn't have to be straight ahead.

00:08:21.040 --> 00:08:25.200
He's being f very straightforward and saying it's gonna be to the side, so we're giving a little bit.

00:08:25.360 --> 00:08:28.560
So you have really as as you see when

00:08:28.960 --> 00:08:33.520
when you throw that, only about a hundred milliseconds to make a decision on where it's going.

00:08:33.680 --> 00:08:38.480
So you you get enough and how many data points you have in there is gonna depend upon the frame rate of your camera.

00:08:38.880 --> 00:08:39.840
That's kind of very important.

00:08:40.000 --> 00:08:44.080
So you get that, then you have to make a decision to commit where the ball is going to go.

00:08:44.240 --> 00:08:48.560
And at that point you have, you know, about a quarter second or

00:08:49.040 --> 00:08:54.880
something like that to move to wherever the hand is up to where it needs to go with a with a peak velocity of around three meters per second.

00:08:55.040 --> 00:08:58.480
And three meters a second is obviously something that people can do and these robot arms should all

00:08:58.960 --> 00:09:04.720
also be able to something like that that at peak and th there should be enough torque and everything got be able to get over to where it needs to be.

00:09:04.960 --> 00:09:08.560
So so you know this has implied that there's gonna be some some latency in

00:09:16.240 --> 00:09:18.320
Now how far the ball

00:09:18.960 --> 00:09:19.920
moves between frames.

00:09:20.000 --> 00:09:22.880
So most cameras have maybe 30 hertz.

00:09:23.200 --> 00:09:25.280
Okay, so that that's what a lot of them are running at.

00:09:25.360 --> 00:09:28.400
And if you're going at that, that means it's moving well

00:09:29.120 --> 00:09:31.520
over a meter between frames.

00:09:31.760 --> 00:09:32.080
Okay.

00:09:32.720 --> 00:09:36.880
So that that that means at a hundred miles per hour.

00:09:37.120 --> 00:09:38.560
So that means that

00:09:38.960 --> 00:09:44.400
That first look you're gonna get in the first hundred milliseconds you're only gonna see like three frames, which is barely enough to do the fit.

00:09:44.560 --> 00:09:47.840
Now you can do the curve fit because you can assume it's a parabola, okay?

00:09:48.000 --> 00:09:48.480
It's it's not

00:09:48.880 --> 00:09:51.840
Like I'm seeing three data points, I have no idea what curve to fit to that.

00:09:51.920 --> 00:09:54.480
It's like we know what curve to fit to it, so that's kinda sufficient.

00:09:54.640 --> 00:09:58.480
But the more data you have, the better it's gonna be because you've got to worry about blur and a lot of these

00:09:59.040 --> 00:10:08.560
other things so it it could be that that Tesla is already running maybe a little bit higher 36 frames at least in the Tesla cars we don't know

00:10:08.880 --> 00:10:10.320
what the cameras are going to be doing.

00:10:10.480 --> 00:10:16.960
So pretty much to pull this trick off, you would want to have cameras which are greater than 200 hertz.

00:10:17.200 --> 00:10:18.480
And that means you know not

00:10:18.960 --> 00:10:23.040
just that you're capturing images that you now need to have a central processor that can do that.

00:10:23.200 --> 00:10:25.680
I don't know if AI four can do that.

00:10:25.920 --> 00:10:27.520
Maybe AI five can.

00:10:27.760 --> 00:10:28.320
So you you know

00:10:28.960 --> 00:10:31.360
You're getting a lot of data now what are you gonna be able to do with it.

00:10:31.520 --> 00:10:33.920
So you gotta worry about motion blur as well.

00:10:34.160 --> 00:10:38.800
And that, you know, those kind of exposures to see how much smear you have in the ball.

00:10:39.040 --> 00:10:41.680
You know, these are all things you gotta kinda tease out.

00:10:41.840 --> 00:10:44.800
And then if you have stereo depth, that helps as well.

00:10:44.880 --> 00:10:47.840
So if you just have a single camera, it's gonna be very hard to figure out.

00:10:47.920 --> 00:10:48.640
I mean you can do

00:10:49.040 --> 00:10:51.360
stereo through basically time.

00:10:51.520 --> 00:10:54.960
The f the fact that a little bit of time is moved or you move your head back and forth.

00:10:55.040 --> 00:10:58.560
But if you're kind of fixed and things are quick, it's really good to have two cameras there.

00:10:59.040 --> 00:11:03.040
stereo to be able to kind of figure out where that depth is and and get a lot quicker.

00:11:03.200 --> 00:11:08.720
So it's possible to do the tracking with with something a little bit higher and it's probably possible to get the

00:11:08.960 --> 00:11:10.240
hand in that position.

00:11:10.640 --> 00:11:13.760
But the real question is going to be, what about the catch?

00:11:16.640 --> 00:11:18.160
This is where the concern is.

00:11:19.040 --> 00:11:20.400
Miles per hour is pretty darn fast.

00:11:20.560 --> 00:11:24.480
Have you ever tried to catch baseball barehanded?

00:11:26.000 --> 00:11:28.560
I mean you do see people that actually catch the baseball barehanded.

00:11:28.960 --> 00:11:32.320
handed when they they snag a home run, but it's not coming in at 100 miles per hour.

00:11:32.480 --> 00:11:38.640
So it's it may have left the bat at well over it, but because of wind resistance, everything else, when it comes on down there, it's

00:11:38.880 --> 00:11:39.760
It's a little bit slower.

00:11:39.920 --> 00:11:42.800
It could still sting a little bit, but but basically you can't.

00:11:43.040 --> 00:11:48.240
But there's a huge difference between a fifty mile per hour changeup and a hundred

00:11:49.920 --> 00:11:51.520
You know what that difference is?

00:11:53.760 --> 00:11:55.280
It's really the energy.

00:11:55.520 --> 00:11:58.720
Even though 100 miles an hour is twice as fast as the energy.

00:11:58.960 --> 00:12:02.640
as fifty, it has four times more kinetic energy.

00:12:02.800 --> 00:12:03.200
Mm-hmm.

00:12:03.520 --> 00:12:05.920
Which is why it hurts a lot more when it hits you.

00:12:06.080 --> 00:12:08.000
It doesn't hurt twice as much as a fifty.

00:12:08.080 --> 00:12:08.800
It hurts

00:12:09.120 --> 00:12:10.240
four times more.

00:12:10.400 --> 00:12:15.760
And so there's that energy has to be dissipated and has to be dissipated very rapidly and very quickly.

00:12:15.840 --> 00:12:17.600
And so it's a question of reflex.

00:12:18.000 --> 00:12:18.320
So

00:12:19.440 --> 00:12:22.960
You're talking about assembling a Swiss arm a Swiss watch.

00:12:23.040 --> 00:12:26.480
Is it going to be a one handed assembly or kind of two are down there?

00:12:26.640 --> 00:12:28.400
One's holding tweezers, the other one is keeping

00:12:29.040 --> 00:12:36.000
something steady and suddenly its hand just goes whoop up and catches the ball because there's not time to put on a glove, that's for sure.

00:12:36.160 --> 00:12:38.800
Or it's gonna have to already have some kind of padding.

00:12:39.280 --> 00:12:45.360
because the the hand will shatter attempting to capture that thing for a variety of reasons.

00:12:45.600 --> 00:12:48.400
It doesn't have the compliance to be able to to do.

00:12:48.960 --> 00:12:50.800
that so it could stretch and break the tendons.

00:12:50.880 --> 00:12:56.560
the tendons could stretch so quickly that it could cause damage to the gearbox and the forearms very easily.

00:12:57.440 --> 00:12:58.720
Fingers could potentially still be able to do that.

00:12:59.040 --> 00:13:02.800
snap off the and it it's a question is probably not enough reaction.

00:13:02.880 --> 00:13:08.560
So the way you get around it is that let me go ahead and and get my little prop here is that either the

00:13:08.880 --> 00:13:11.360
The ball is just gonna come in and smack me like that, right?

00:13:11.760 --> 00:13:14.080
And then the hand everything in the hand's gonna come back.

00:13:14.240 --> 00:13:16.480
Well first thing, I have to get my hand up like this, right?

00:13:16.560 --> 00:13:17.440
And I want it to come in.

00:13:17.520 --> 00:13:18.640
Do I want it to hit my fingers?

00:13:18.960 --> 00:13:22.400
I want to hit it right here on the palms because when it hits the palm usually hurts more.

00:13:22.560 --> 00:13:26.080
Usually you want to try to get it there so your fingers will comply a little bit.

00:13:26.240 --> 00:13:27.760
Your fingers are not going to be down like this.

00:13:27.840 --> 00:13:28.480
They've got to be open.

00:13:29.040 --> 00:13:32.240
open because they have to then come for the grasp a little bit later.

00:13:32.400 --> 00:13:35.120
So that means they're gonna be at c almost full extension.

00:13:35.280 --> 00:13:38.640
When it comes in here, these things are already at their hard limit, which means you could go back

00:13:38.960 --> 00:13:39.440
and snap it.

00:13:39.520 --> 00:13:41.040
There's not gonna be anything to absorb it.

00:13:41.200 --> 00:13:48.640
The only way to do it is if it's tracking it well enough that it's smart enough to move the hand maybe back at a very high rate.

00:13:58.960 --> 00:14:03.440
relative velocity is fifty and you capture some of the energy that way and get the absorption.

00:14:03.600 --> 00:14:05.360
The thing is whether it could respond enough.

00:14:05.520 --> 00:14:07.600
So you've got to do that move at the right time.

00:14:07.760 --> 00:14:08.720
If you do it too early

00:14:09.200 --> 00:14:16.640
you know, you may be getting your hand out of the way and you may not be able to react fast enough that as soon as you hit, the damage is done.

00:14:16.720 --> 00:14:18.080
You've got to start moving beforehand.

00:14:18.160 --> 00:14:18.560
So you you

00:14:18.960 --> 00:14:20.880
maybe feeling that before it goes.

00:14:21.040 --> 00:14:25.440
So the real thing is that hand is not going to be able to handle a hundred mile power of passport.

00:14:25.520 --> 00:14:28.560
So so that's like the first place we say, that's incredulous unless

00:14:29.040 --> 00:14:32.000
you come up with some other ways to get around this very, very difficult to do that.

00:14:32.240 --> 00:14:32.560
A glob.

00:14:32.960 --> 00:14:36.640
And the assumption is that after it does it, it goes back to assembling the Swiss Army watching.

00:14:36.880 --> 00:14:38.480
Hopefully it's not with a broken hand.

00:14:42.000 --> 00:14:43.920
Okay, now the juggle.

00:14:44.240 --> 00:14:46.720
This is a different kind of catch that that we're doing on here.

00:14:46.880 --> 00:14:48.560
So if you're juggling and putting

00:14:48.960 --> 00:14:51.600
something up now the first thing is you said juggling.

00:14:52.240 --> 00:14:55.840
So when you say juggle, how many objects are you referring to?

00:14:56.400 --> 00:14:56.880
Three.

00:14:57.120 --> 00:14:58.400
I I think everyone I mean

00:14:58.880 --> 00:15:01.840
In order to juggle something means you've got more items and you have hands.

00:15:02.000 --> 00:15:03.360
So it'd be a minimum of three.

00:15:03.440 --> 00:15:04.960
It's not like, oh, we're just gonna do this.

00:15:05.120 --> 00:15:06.640
This is not juggling, okay?

00:15:06.960 --> 00:15:08.640
So I've gotta get them all up here.

00:15:08.960 --> 00:15:10.400
handed two.

00:15:18.960 --> 00:15:20.320
One catch every second.

00:15:20.480 --> 00:15:24.960
And you've got to throw it up there long enough to give you that one second while you're manipulating the other one to move around.

00:15:25.040 --> 00:15:26.480
That's the whole part of juggling.

00:15:26.640 --> 00:15:28.640
So when you're taking that, it's it's coming up, it's coming.

00:15:28.880 --> 00:15:33.280
coming down, you've got to catch it, you've got to absorb the energy of that and you've got to put that energy back in again.

00:15:33.600 --> 00:15:38.480
So again, we might be looking at more theatrical chainsaws, which might be as low as like

00:15:38.880 --> 00:15:40.000
three kilograms of weight.

00:15:40.080 --> 00:15:43.040
Most chainsaws are maybe around five to seven, something like that.

00:15:43.120 --> 00:15:48.720
so it'd be a lighter one with a lot of things kind of taken out of it to make sure it doesn't hurt anyone.

00:15:49.280 --> 00:15:52.080
So there might be a chain on it, but there won't be any teeth.

00:15:52.240 --> 00:15:54.880
and you need to be able to throw that up.

00:15:54.960 --> 00:15:57.920
It's gonna have a certain launch velocity that you need to be able to do.

00:15:58.960 --> 00:15:59.440
amount of energy.

00:15:59.520 --> 00:16:04.560
So you see we're looking around thirty-five joules there, which is a lot less than the 145 that we're kind of deal with.

00:16:04.640 --> 00:16:08.800
And when we we capture it, we already are kind of know we're gonna catch it and go down.

00:16:09.040 --> 00:16:13.040
to absorb the energy as opposed to having this thing like just smash right on into us.

00:16:13.360 --> 00:16:18.560
So that means we get an idea of what's that going to be like.

00:16:19.120 --> 00:16:24.080
And it's gonna be somewhere around like having a ten or twenty kilograms in your hand.

00:16:24.320 --> 00:16:26.640
And we know that's around the payload capacity.

00:16:26.800 --> 00:16:28.640
So if if that's possible and

00:16:28.960 --> 00:16:34.240
And if we kind of look at what the peak torques are going to be out there for all the motors and everything, it's within the possibility.

00:16:34.400 --> 00:16:38.800
So based on what Tesla has announced before going back to AIDS.

00:16:39.120 --> 00:16:45.680
Day two, where we get an idea of what the the torques are going to be in the various motors, it's within that.

00:16:45.840 --> 00:16:48.320
And I'm assuming those actuators might actually be a little bit stronger.

00:16:48.960 --> 00:16:49.760
think they've made them weaker.

00:16:49.840 --> 00:16:52.080
I assuming they're they're probably even a little bit stronger than theirs.

00:16:52.240 --> 00:16:55.840
So that means it would have the strength to be able to pull this off.

00:16:56.800 --> 00:16:58.560
And it should be able to have the cord

00:16:58.880 --> 00:16:59.360
coordination.

00:16:59.520 --> 00:17:01.840
I mean it it seems to me that this is something you could coordinate.

00:17:01.920 --> 00:17:04.160
Again, I I'm pretty sure we've probably seen some humanoids.

00:17:04.400 --> 00:17:08.720
There there have been robots designed for juggling, you know, so almost everything we're talking about, someone

00:17:09.040 --> 00:17:10.240
has built something like this already.

00:17:10.320 --> 00:17:14.800
Someone has already built a simple little bot that has been able to ride a unicycle.

00:17:14.880 --> 00:17:16.000
It just wasn't a humanoid.

00:17:16.320 --> 00:17:18.560
Someone for juggling, someone for doing a catch, all those

00:17:18.960 --> 00:17:19.440
different things.

00:17:19.600 --> 00:17:20.720
Now we're trying to fold them in.

00:17:20.800 --> 00:17:22.560
So we know physically it's possible.

00:17:22.720 --> 00:17:28.480
it's just a question whether a humanoid would have it and whether the specs meet what we expect to be

00:17:28.960 --> 00:17:31.360
in Optimus or what we've seen being Optimus.

00:17:31.600 --> 00:17:33.120
So it's kind of within the range.

00:17:33.280 --> 00:17:38.800
The the biggest trick of course is that when you are juggling these things, assuming you have the other strength,

00:17:38.960 --> 00:17:42.560
You are on a literally a wobbly base, which is a unicycle.

00:17:42.800 --> 00:17:48.320
And balancing that will be a bit tricky, but for these control systems they d they'll just be able to react fast enough.

00:17:48.400 --> 00:17:48.560
So

00:17:48.880 --> 00:17:50.880
Yeah, every I'm pretty sure they get the balance.

00:17:51.200 --> 00:17:53.200
Every limb is that's the beauty.

00:17:53.280 --> 00:17:57.040
That's the they got multiple cameras, but they have every multiple that they can manage.

00:17:57.520 --> 00:17:58.560
Yes, two years ago this was

00:17:58.960 --> 00:18:02.160
was not really possible for a lot of companies because they didn't have whole body control.

00:18:02.560 --> 00:18:08.640
They they really had kind of this locomotion policy and they had the policy up there and while the hands could move around and you know

00:18:08.960 --> 00:18:10.400
the system was correcting for the bounds.

00:18:10.640 --> 00:18:11.920
Now it's gonna be much better.

00:18:12.160 --> 00:18:18.160
It it really is knowing what the hands are doing and the sort of the expectation of what the reaction is about to be and it can prepare us.

00:18:18.320 --> 00:18:18.480
Certainly

00:18:20.400 --> 00:18:28.720
And this is something that's actually fairly easy to simulate in a physics simulator because it's really coming down to rigid body physics and dynamics.

00:18:29.040 --> 00:18:33.280
dynamics and doesn't require super high fidelity that you would for other things.

00:18:33.360 --> 00:18:37.520
So this is something that they could probably nail in their physics simulator and get it trained up.

00:18:39.600 --> 00:18:48.640
So now the the whole thing is about whether they do this live and you know running

00:18:49.040 --> 00:18:50.960
engines with fires and stuff like that.

00:18:51.120 --> 00:18:56.400
maybe something that if you do it live, you're gonna really have to make sure it's kicked off.

00:18:56.960 --> 00:18:58.400
You know, it's like just about

00:18:58.800 --> 00:19:00.240
And anything could go wrong with that.

00:19:00.400 --> 00:19:08.720
But you know, for the most part, everything here seems like it's plausible and could be possible from the standpoint of the unicycle.

00:19:08.800 --> 00:19:18.560
But what we should really look is at what of all these things that we've we've talked about, we haven't got to the the the Swiss clock yet or the Swiss watch, which do you think is probably the most challenging?

00:19:21.440 --> 00:19:22.880
I still think the switch watches.

00:19:23.200 --> 00:19:24.320
The tiny little things.

00:19:24.480 --> 00:19:28.480
I am not I'm not concerned about the unicycle or the juggling or the catching.

00:19:28.880 --> 00:19:31.200
I think those are all possible Yeah, yeah.

00:19:31.280 --> 00:19:33.040
And again it goes back to John Carmack.

00:19:33.120 --> 00:19:33.520
He nailed it.

00:19:33.600 --> 00:19:37.040
He just said like it's it's these fine little fiddly things that are very, very difficult.

00:19:37.200 --> 00:19:38.880
So the bot could go out and

00:19:38.960 --> 00:19:45.360
bring a jack-o' lantern into you for you to do the repairs, but you know, the you know, getting that is is the real challenge.

00:19:45.440 --> 00:19:48.320
So so the the point is that the bot is able to kind

00:20:06.960 --> 00:20:07.920
And the dexterity is a very good thing.

00:20:08.960 --> 00:20:15.040
Bots, yeah, they can show you they're walking and running, but that doesn't take a lot of you know, AI chip power that they don't have.

00:20:15.280 --> 00:20:15.680
Memory.

00:20:15.840 --> 00:20:16.000
Yep.

00:20:16.160 --> 00:20:16.400
All that.

00:20:16.640 --> 00:20:16.880
Yep.

00:20:17.840 --> 00:20:18.560
And now when

00:20:19.040 --> 00:20:20.800
So again, this is a Swiss watch.

00:20:20.880 --> 00:20:22.080
This is not a Swiss clock.

00:20:22.240 --> 00:20:22.800
It's a watch.

00:20:23.200 --> 00:20:27.360
So we can assume that is things that are you know, would go on your wrist, which means it's very small.

00:20:28.880 --> 00:20:34.080
to be made up of these small movements with lots of little gears and you know very, very, very, very small parts.

00:20:34.320 --> 00:20:38.720
And again, this is not something that any ordinary person can do.

00:20:39.120 --> 00:20:40.960
assembling a s a Swiss watch.

00:20:41.040 --> 00:20:44.080
It takes a lot a lot of training and it just needs the right tools.

00:20:44.160 --> 00:20:48.640
So that's the difference between a jeweler and you and me is that they own the right tools.

00:20:48.880 --> 00:20:50.480
And they know how to use those tools.

00:20:50.720 --> 00:20:58.000
and the thing is we as humans do not have anywhere near that kind of accuracy that's demanded to put these things together.

00:20:59.200 --> 00:21:03.680
We use a lot of props and tricks and tools to give us the precision for that.

00:21:03.920 --> 00:21:05.680
And a lot of it is patience.

00:21:05.840 --> 00:21:08.800
The other is like magnifying glasses and special little tools.

00:21:09.280 --> 00:21:18.560
So we're able to correct for the fact that we are very sloppy meat bags that go around with absolutely no precision because we are looking at what's going on

00:21:18.880 --> 00:21:21.840
and we'll make little adjustments and movements until we get it right and it falls in.

00:21:22.000 --> 00:21:24.480
So in some ways it's difficult and challenging.

00:21:24.720 --> 00:21:26.800
The other time it's just a processing power thing.

00:21:26.960 --> 00:21:28.480
I I I think that's more of

00:21:29.040 --> 00:21:33.760
a mind over matter kind of issue as opposed to that you need to have something that's super accurate.

00:21:33.920 --> 00:21:38.160
So again, we've seen these robots that have been able to thread a needle and everyone's impressed.

00:21:38.240 --> 00:21:38.640
Oh look at the

00:21:39.840 --> 00:21:42.960
That's not a big deal because they were already given the needle, they're already given the thread.

00:21:43.120 --> 00:21:46.480
The real challenge is picking those two items up before you go ahead and do that.

00:21:46.720 --> 00:21:48.480
But even then, if you if if there's

00:21:48.800 --> 00:21:51.520
They're going, you know, threading the needle like that, that's impressive.

00:21:51.680 --> 00:21:57.200
But they're going like what we would until you make the adjustment and you see it's right and you move on in.

00:21:57.440 --> 00:21:58.720
Same thing with the Swiss watch.

00:21:59.120 --> 00:22:03.760
is that when you're dropping that little gear in there, you're not just getting it right the first time.

00:22:03.840 --> 00:22:08.480
You're kind of getting it over very, very close and you keep making these micro adjustments until eventually it goes in.

00:22:08.960 --> 00:22:09.920
Because you're using supports.

00:22:10.080 --> 00:22:11.280
You're making sure there's something there.

00:22:11.520 --> 00:22:15.520
If I was just like holding this up in my hand, I would probably have difficulty doing that.

00:22:15.680 --> 00:22:18.480
But so long as I have like a nice fixture to put it on and everything.

00:22:19.120 --> 00:22:24.480
else and let's say the the bots allowed to cheat just the same way that we're allowed to cheat.

00:22:24.560 --> 00:22:24.880
Okay.

00:22:25.040 --> 00:22:26.640
Just can't do anything extra than that.

00:22:26.720 --> 00:22:28.240
So that will be a challenge.

00:22:28.960 --> 00:22:36.240
but I can believe that it it could multitask and like do this grab the ball at the same time.

00:22:36.400 --> 00:22:38.720
That's it so the question is.

00:22:39.120 --> 00:22:40.560
Who's gonna do that first?

00:22:40.880 --> 00:22:48.560
I I have a feeling a couple of these, some Chinese robot companies will probably do it before Elon gets a chance to show it up.

00:22:48.880 --> 00:22:55.760
Which is what I I told him it's like don't don't tell them what you're gonna do because within two weeks one of 'em is gonna do part of your demo.

00:22:56.080 --> 00:22:56.960
I'm not worried about that.

00:22:57.280 --> 00:22:58.640
I mean the whole point is it's a

00:22:59.040 --> 00:23:00.480
demo versus a real thing.

00:23:00.960 --> 00:23:02.080
Can it really do it?

00:23:02.400 --> 00:23:05.520
Okay, so what is your yeah, your your kind of thing here?

00:23:05.680 --> 00:23:08.480
You're basically saying yeah, you can do these

00:23:09.040 --> 00:23:10.240
things, you've got it.

00:23:10.400 --> 00:23:12.000
Seems like it's possible, right?

00:23:12.080 --> 00:23:13.280
Based on the implied specs.

00:23:14.320 --> 00:23:18.320
It's it's possible assuming those are the specs that Optimus is going to have.

00:23:18.480 --> 00:23:18.640
So

00:23:19.040 --> 00:23:28.160
if if Elon really believes and I you know, if it's not something that he just kind of pulled out of his hat to say, All right, this is what I want to do but he had been discussing it and

00:23:28.960 --> 00:23:33.200
thinking about that that that's kind of the capability and they all agree that it it has the has that.

00:23:33.360 --> 00:23:38.080
It tells us something about the potential specs, you know, of of what Gen three may potentially have.

00:23:39.200 --> 00:23:39.920
Gen four by the way.

00:23:40.000 --> 00:23:41.040
He never did get a date.

00:23:41.200 --> 00:23:43.200
I mean he says, you know, it could be gen four.

00:23:43.280 --> 00:23:44.400
You know, that could be the future.

00:23:44.960 --> 00:23:45.680
So here we go.

00:23:45.840 --> 00:23:47.680
Catch 100 mile per hour with a mit.

00:23:47.920 --> 00:23:48.720
You said it's possible.

00:23:48.960 --> 00:23:50.160
Yes, it's ha could be happening.

00:23:52.960 --> 00:23:54.240
Juggle balls, very possible.

00:23:54.320 --> 00:23:55.040
I've seen we've seen that.

00:23:55.200 --> 00:23:56.720
Juggle props, very possible.

00:23:56.960 --> 00:23:58.480
Not just plausible, possible, very likely.

00:23:59.040 --> 00:23:59.200
likely.

00:23:59.440 --> 00:23:59.680
Right.

00:23:59.920 --> 00:24:01.120
Not on stage.

00:24:01.360 --> 00:24:02.880
watch likely.

00:24:03.040 --> 00:24:04.560
What's unlikely is the full movement.

00:24:04.640 --> 00:24:07.200
So maybe the case in hand, but certainly not the full movement.

00:24:07.360 --> 00:24:08.240
And all at once.

00:24:08.480 --> 00:24:08.720
Yeah.

00:24:08.960 --> 00:24:09.920
not not gonna happen.

00:24:10.400 --> 00:24:11.120
Yeah, yeah, yeah.

00:24:11.280 --> 00:24:18.560
So i again it kinda comes down to this like I'm sure it could do a watch battery pretty easily, just like I could do a watch battery, but th but a lot of the other stuff I would have a hard time.

00:24:19.520 --> 00:24:25.040
Unless, you know, I was really given the right tools, then I I might surprise myself on how far I could get along in it.

00:24:25.120 --> 00:24:28.720
It's just that I could probably take it apart, but then it wouldn't go back together.

00:24:29.040 --> 00:24:29.520
Right.

00:24:29.840 --> 00:24:30.320
Gotcha.

00:24:30.640 --> 00:24:30.960
Okay.

00:24:31.280 --> 00:24:33.200
So that was, you know, very cool.

00:24:33.360 --> 00:24:34.960
So these are metrics though.

00:24:35.040 --> 00:24:38.640
You do think that this is the like it's i he I think it's

00:24:39.120 --> 00:24:44.160
You know what he's doing is he's pushing the goalposts in terms of like, yeah, it's one thing for you to pick and place.

00:24:44.320 --> 00:24:45.520
That's not what we're going for.

00:24:45.680 --> 00:24:48.480
We're going for a human a a humanoid that is super hum

00:24:49.040 --> 00:24:49.280
human.

00:24:49.360 --> 00:24:50.640
It can do these things.

00:24:50.880 --> 00:24:55.520
That would be impressive if it can do things that human that's what Unit tried to show you.

00:24:55.600 --> 00:24:57.040
This thing can lift a car.

00:24:57.200 --> 00:24:58.640
If it's true, it'd be cool.

00:24:59.040 --> 00:25:01.920
Of those those three things, which is the most practical in your mind?

00:25:02.240 --> 00:25:03.040
The switch watch.

00:25:03.200 --> 00:25:08.640
I mean obviously the others are just jokes and fun things, but if you can actually you know it's it's

00:25:08.960 --> 00:25:10.000
When John Carmack said, right?

00:25:10.080 --> 00:25:14.000
It's like, yeah, I don't want you just bring in the thing, I want you to put in the batteries.

00:25:14.160 --> 00:25:15.600
Can you really put in the batteries?

00:25:15.920 --> 00:25:18.560
Because you know how hard it is for us to like you know.

00:25:18.960 --> 00:25:20.800
No, the Costco battery thing.

00:25:22.560 --> 00:25:25.760
How do you how do you you try to cut it, the plastic thing?

00:25:25.840 --> 00:25:26.480
It's hard.

00:25:26.640 --> 00:25:28.640
It's hard or like trying to open the back

00:25:41.440 --> 00:25:43.360
And then you can put the batteries in the right order, right?

00:25:43.440 --> 00:25:44.960
If you get them if you get the positive and negative

00:25:48.800 --> 00:25:51.920
At the end of the day, Elon believes, no no no, this is possible.

00:25:52.000 --> 00:25:54.400
It whatever human can do, the bot can do.

00:25:54.560 --> 00:25:58.640
And that is why he's designing the hands to be very he talked about it's not.

00:25:58.960 --> 00:26:05.120
Not just 22 degrees freedom like everybody else's hands, all the other kind, but no no, he wants skin.

00:26:05.280 --> 00:26:08.720
He wants you know the the the ability to do this he pointed out right

00:26:08.960 --> 00:26:09.280
Right.

00:26:09.760 --> 00:26:17.760
So I just wanted to also show that this these guys are really like th they have the academy.

00:26:17.840 --> 00:26:18.640
So you you do a great

00:26:23.200 --> 00:26:28.640
Yeah, and I think the last thing to remind everyone is that we already saw two years ago Optimist catch

00:26:29.200 --> 00:26:29.680
A tennis ball.

00:26:29.840 --> 00:26:38.480
So we know the jug that it can already but yeah, I think that was where the telephone is those who are involved in the development and maintenance of open source software.

00:26:39.440 --> 00:26:41.200
According to the FBI and U.

00:26:41.360 --> 00:26:41.440
S.

00:26:41.520 --> 00:26:48.160
Justice Department, face dealer hackers use fake or hijack social media accounts.

00:26:49.280 --> 00:26:58.880
to invite potential victims into video calls hosted over imposter versions of Zoom, Microsoft Teams, and Google Meet.

00:27:01.200 --> 00:27:02.000
Shop.

00:27:03.280 --> 00:27:04.720
RPM now.

00:27:05.360 --> 00:27:07.040
You just don't get it, man.

00:27:07.680 --> 00:27:08.560
You say, you know.

00:27:09.440 --> 00:27:11.760
bringing dating partners so stupid.

00:27:12.000 --> 00:27:16.720
I mean maybe if you're like really trying to win, right?

00:27:17.040 --> 00:27:18.160
And then beyond

00:27:19.040 --> 00:27:23.200
that I mean chicken had like Beanks as like his one of his partners or whatever.

00:27:23.440 --> 00:27:25.840
She gets eliminated, he goes on to win the fifty K.

00:27:26.080 --> 00:27:26.960
So it's like

00:27:31.040 --> 00:27:33.040
It ultimately didn't hurt him.

00:27:59.040 --> 00:27:59.840
And that's a slow pitch.

00:27:59.920 --> 00:28:01.280
That was a lava stuff like that.

00:28:01.440 --> 00:28:04.960
So we know all these things are are coming and are possible.

00:28:05.200 --> 00:28:07.200
And again, the Swiss Army are possible.

00:28:17.680 --> 00:28:18.400
If you have twenty

00:28:18.960 --> 00:28:22.400
20,000 optimists and they're playing around.

00:28:22.560 --> 00:28:25.840
That's how you train them to be that much more precise.

00:28:26.000 --> 00:28:28.560
And remember when one bot figures it out, the other bot's

00:28:28.960 --> 00:28:29.520
get it right away.

00:28:29.600 --> 00:28:33.040
So they're all helping to get better, smarter, smarter, smarter.

00:28:33.200 --> 00:28:36.400
this is where they're going to build those 10 to 20,000.

00:28:36.480 --> 00:28:38.640
We know we have the free mod factory in California.

00:28:39.120 --> 00:28:44.640
That's supposed to do a million robots per year, but like you said, not till 2028 or 2029.

00:28:45.200 --> 00:28:48.560
But they'll have 10 or 20,000 coming out of the Fremont factory.

00:28:49.200 --> 00:28:52.240
But this is actually the Giga Texas.

00:28:52.480 --> 00:28:56.400
In near Giga Texas, this is where the op the Optimus factory is.

00:28:56.560 --> 00:28:57.680
It is massive.

00:28:57.840 --> 00:28:58.720
And you can see where it's

00:28:59.040 --> 00:29:06.800
progression is it's already to the point where Joe Techmar believes it will open in about six months where you can actually put things in it.

00:29:06.960 --> 00:29:08.560
So as soon as the

00:29:09.680 --> 00:29:18.640
you know it probably won't start building robots for another year or two but it will be housing the academy that's where the 5000

00:29:19.120 --> 00:29:20.160
robots could go.

00:29:20.400 --> 00:29:23.040
10,000 robots can go and they can start training.

00:29:23.440 --> 00:29:23.680
Yes.

00:29:23.760 --> 00:29:28.720
And and that's probably a reasonable assumption because again, we we've talked about what do you do with 5,000 bots.

00:29:29.040 --> 00:29:31.600
And it requires a l a lot of room and a lot of space.

00:29:31.680 --> 00:29:38.560
So either Tesla is renting a lot of warehouse space around Southern California that we're not aware of, for the bots that they're gonna be producing, or

00:29:38.960 --> 00:29:44.880
you know they're gonna have to build something internally and I don't think they have that much room in in Palo Alto to be able to do it.

00:29:45.200 --> 00:29:48.720
They are being manufactured in Fremont, so I assume they're kind of being housed there.

00:29:49.040 --> 00:29:50.720
or very closely for now.

00:29:51.120 --> 00:29:54.400
At this point, you know, we don't know how many they have.

00:29:54.720 --> 00:29:58.560
I I would say they probably have in the order of a thousand, maybe approaching to

00:29:58.880 --> 00:30:01.520
two thousand this point, based on some of the reports of what's coming out.

00:30:01.760 --> 00:30:08.560
We don't know if if those are full bodies or not, whether they're just the bodies and they they don't have all the hands yet because they were having subtles of hands.

00:30:09.200 --> 00:30:14.080
But based on on the reporting at 250 well, it was several hundred, okay.

00:30:14.240 --> 00:30:18.000
And so I'm assuming that several hundred might mean around two fifty a week.

00:30:18.960 --> 00:30:19.920
early September.

00:30:20.080 --> 00:30:27.760
So they probably are north of a thousand by now, trying to hit five thousand by either the end of the year or the beginning of next year.

00:30:27.920 --> 00:30:28.800
That would be

00:30:29.120 --> 00:30:32.320
just enough to really start the Alpins Academy that they're going up.

00:30:32.480 --> 00:30:37.600
However, it sounds like they're not waiting for them to come around to start doing the data collection.

00:30:37.680 --> 00:30:38.480
And that's something you can do

00:30:39.200 --> 00:30:48.080
well in advance of them being there to start that flywheel so that when you have the optimize to go in and close at Cinderel Gap, they have actually something to work on.

00:30:55.280 --> 00:30:58.640
Yeah you you talked about this so number one we already know that in game

00:30:58.960 --> 00:31:04.960
Giga Germany, Kiga Berlin, those staff were interviewed and they said yes, they're actually being trained.

00:31:05.200 --> 00:31:08.320
They have to put on, you know, stuff in t equipment.

00:31:09.040 --> 00:31:10.640
to show optimists what to do.

00:31:10.720 --> 00:31:12.480
So we know that they're doing it in factories.

00:31:12.640 --> 00:31:16.000
Then a couple shows ago we showed that there's huge hiring.

00:31:16.240 --> 00:31:18.720
Tesla is hiring a lot of people all over the place.

00:31:19.440 --> 00:31:23.200
and in US and you said, you know, I think that that's gonna be the service centers.

00:31:23.360 --> 00:31:28.560
And Lars Morvey was just interviewed by Munro Live and he confirmed that A, that Optimus

00:31:28.880 --> 00:31:37.520
human or robot will be helping to put the chargers into the cyber cabs and the robotaxis to charge them and will help in a service center.

00:31:37.600 --> 00:31:38.320
So you're you're hit

00:31:38.960 --> 00:31:43.600
you would hit that one out of the park that they're you're gonna use the service centers as ways to train the bots.

00:31:44.000 --> 00:31:48.640
Then we know that they they they they're hiring people to put on

00:31:49.040 --> 00:31:49.520
equipment.

00:31:49.680 --> 00:31:55.200
And what you figured out, I just pointed out earlier, is that they're not just putting on glasses and calling it a day.

00:31:55.520 --> 00:31:58.480
No, they're they're like actually being outfitted as if they

00:31:58.960 --> 00:31:59.440
are Optimus.

00:31:59.600 --> 00:32:05.680
They got the backpack battery, they got the thing so that they're almost like a cosplay as an optimist.

00:32:05.840 --> 00:32:08.240
Like every every part of the Optimus is probably around them.

00:32:08.320 --> 00:32:08.640
And then

00:32:09.040 --> 00:32:10.800
there's a leak here from Robert Scoble.

00:32:10.880 --> 00:32:14.080
So Robert Scoble is a well-known tech insider.

00:32:14.400 --> 00:32:18.640
He's been covering as a journalist technology since the beginning

00:32:19.040 --> 00:32:20.240
in Silicon Valley.

00:32:24.160 --> 00:32:24.960
He said this.

00:32:25.200 --> 00:32:26.720
Tesla, this is just yesterday.

00:32:26.800 --> 00:32:28.640
He said Tesla optimist training regime.

00:32:29.120 --> 00:32:30.080
It's a leak.

00:32:30.720 --> 00:32:36.320
Workers and its Palo Alto R and D facility have been holding robot university for many months already.

00:32:36.560 --> 00:32:38.800
Number one, he's saying this is happening already a long time ago

00:32:42.240 --> 00:32:48.560
Workers are wearing twenty four pound suits, this is what you've been saying, with up to forty cameras and grids of three D sensors to keep it.

00:32:48.960 --> 00:32:52.400
capture every detailed video in 3D fields of whatever the worker does.

00:32:52.640 --> 00:32:54.160
There are multiple configurations.

00:32:54.320 --> 00:32:55.920
They are given different tasks to do.

00:32:56.000 --> 00:32:57.520
They don't know what the tasks come from.

00:32:57.760 --> 00:32:58.560
Multiple squads

00:33:08.960 --> 00:33:09.200
cameras.

00:33:09.280 --> 00:33:13.600
This leads to a data flywheel that is orders of magnitude more data than the car captured.

00:33:13.920 --> 00:33:18.640
Separate teams are capturing home data like making a sandwich at home, like in a house

00:33:19.920 --> 00:33:25.280
Like making a sandwich while other teams capture jobs and factory floor like installing HVAC systems in cars.

00:33:25.600 --> 00:33:27.040
Elon isn't playing around.

00:33:27.200 --> 00:33:28.560
I can't tell you how I learned

00:33:31.520 --> 00:33:34.400
So do we trust him because he hears a lot of things?

00:33:38.960 --> 00:33:45.360
The information already kinda reported something like this back in September and they they were talking about some of the Alpha suits and that they were wearing backpacks.

00:33:45.520 --> 00:33:47.600
They didn't have specifics of how much it weighed.

00:33:48.880 --> 00:33:49.600
I heard that.

00:33:49.680 --> 00:33:56.080
I said, Oh, okay, this is deja vu and if you go back four years ago we actually saw everyone an outfit exactly like that.

00:33:56.240 --> 00:33:58.800
So this may not be exactly what they're wearing because this

00:34:01.920 --> 00:34:08.560
But we kind of looked at it and said, wait a minute, they just took the cameras out of the Optimus head and just mounted it onto the Optimus.

00:34:07.640 --> 00:34:16.520
Operator and then they probably took all the compute and everything in the back and stuck that on there and said what we want to do is we wanna capture it as if it's the robot.

00:34:16.760 --> 00:34:17.240
So there's