Latest / In the Loop AI / World Models: What are They, and is Google's Genie 3 AGI?

Transcript

World Models: What are They, and is Google's Genie 3 AGI? · In the Loop AI

0:00
Josh: Google just released something that I think may be more important to creating
0:03
Josh: AGI than ChatGPT was itself.
0:06
Josh: They released an AI that doesn't predict text, it simulates reality.
0:10
Josh: You describe a world and it builds it in front of you in real time,
0:13
Josh: 720p, 24 frames a second, just like a video, except there's something a little bit different.
0:18
Josh: You walk through it, you drive through it, the world responds to you.
0:21
Josh: And it was so good that within one week, Waymo, which is a self-driving car
0:24
Josh: company worth $126 billion, they took that technology and built the most advanced
0:29
Josh: driving simulator ever created.
0:30
Josh: They can now simulate things that the cars have never seen, like tornadoes or
0:34
Josh: elephants in a highway or snowstorms in cities that never get snow.
0:37
Josh: So today we're going to break down what world models actually are,
0:40
Josh: why some of the biggest companies on earth are racing to build them,
0:43
Josh: and why this might be the most important shift in AI since the Transformer.
0:47
Ejaaz: Yeah, Demis Hassabis, the head of Google DeepMind and Google's AI efforts,
0:52
Ejaaz: said something a few weeks ago that I haven't been able to get off my mind,
0:55
Ejaaz: which is world models will be the single most important thing that Google focuses
0:59
Ejaaz: on this year to take us to AGI.
1:02
Ejaaz: And all I could think of was this is just like a video generation model, right?
1:06
Ejaaz: And then as we went down into the weeds for prepping for this episode,
1:09
Ejaaz: I realized that it's so much more.
1:11
Ejaaz: But I think we have some visual examples that we kind of want to show the audience
1:14
Ejaaz: first to kind of demonstrate what we mean.
1:16
Josh: Oh, this one is so cool. So what we're seeing on screen is two versions of the video example.
1:21
Josh: One, a person kind of building a box. It's a child.
1:24
Josh: They build a box, they build a little toy it looks like this walking little
1:26
Josh: piece of cardboard they drop it into genie 3 and it,
1:30
Josh: puts it into your own worlds but in a
1:33
Josh: way that's fully controllable like a video game so imagine you have a
1:36
Josh: favorite stuffed animal or a doll or in the second example a cat
1:39
Josh: that lives in your apartment you can scan in not
1:41
Josh: only your apartment but your cat and then you could walk around
1:44
Josh: your apartment as if you are your cat engaging in
1:47
Josh: this real world's kind of pseudo reality
1:51
Josh: it's it's really bizarre watching this work and this other example
1:54
Josh: that we're seeing now proves that you can actually engage with the
1:57
Josh: world around you so what we're seeing is someone that looks
2:00
Josh: like they're walking through a neighborhood but they walk up to a car and you could actually
2:03
Josh: open up the door and you could look inside the car
2:06
Josh: and the hand kind of reaches out and grabs it and i think what's so amazing
2:09
Josh: about this model is it's it's different than any other model that we've ever
2:13
Josh: seen because it actually has this deep understanding of reality it merges base
2:17
Josh: reality with this virtual reality and i think a way that's like very one it
2:21
Josh: shows how smart it is and how well it understands physics but two,
2:25
Josh: I think there's a lot of downstream implications towards training better AIs
2:28
Josh: on this that Genie 3 is going to use.
2:30
Ejaaz: There are a ton, actually. And I was trying to think about how explicitly to
2:34
Ejaaz: explain the difference between an LLM, which you and I and our listeners know
2:38
Ejaaz: very well, and a world model. And I think it's the following.
2:42
Ejaaz: Think of an LLM like a nerd that has never left the library.
2:47
Ejaaz: He has read every single book. He understands the world in theory,
2:51
Ejaaz: but he's never stepped out of
2:53
Ejaaz: the library. So he's never experienced the world for what it actually is.
2:56
Ejaaz: He understands how grass looks and what it feels like, but he's never touched
3:00
Ejaaz: it, felt it, seen the way it changes form when he brushes his hand through it, right?
3:04
Ejaaz: A world model, on the other hand, is a lived and experienced version of AI.
3:09
Ejaaz: It understands the physics and simulated reality of the world.
3:13
Ejaaz: And it understands how like water flows, how people can jump through the air.
3:17
Ejaaz: And it understands the physical reality of like us humans as we experience it, right?
3:22
Ejaaz: And that's the core difference that we see here. Now, Genie 3,
3:25
Ejaaz: which is Google's flagship world model, can basically do this,
3:29
Ejaaz: but at 24 frames a second at 720p, which is the big breakout that everyone's freaking out about now.
3:35
Ejaaz: Now you can just go from a prompt to a simulated reality that it creates in
3:39
Ejaaz: real time that is physically accurate. And that's so cool.
3:41
Josh: Everyone knows that ChatGPT predicts the next word, but World Models predicts
3:45
Josh: the next frame of reality.
3:47
Josh: They simulate how these environments evolve and how your actions change them
3:51
Josh: and the effects that your physical actions have on this digital world.
3:55
Josh: And what we're seeing here is this really cool graphic that we actually, Ijaz,
3:58
Josh: you had Claude build this up, that describes the difference between
4:01
Josh: the two so if you look at the table it shows a few of
4:04
Josh: the statistics whether it's interactive whether it understands physics whether
4:07
Josh: it's generated what it's generated from and what
4:10
Josh: you'll find is that the world model is unique in every way
4:13
Josh: because it it reacts to the world that
4:16
Josh: it simulates around it in an ai video when you're watching
4:19
Josh: a sora video it's all been predetermined and you could put on your goggles
4:22
Josh: and you could watch it as if it's virtual reality but it's all been predetermined
4:25
Josh: by code and it is fixed with a world
4:28
Josh: model that is all dynamic and it's generated on a
4:31
Josh: frame by frame basis so now anytime you interact
4:34
Josh: with something let's say you put some paint on a wall the paint actually
4:37
Josh: sticks and it stays and the world model remembers it and it understands that
4:41
Josh: the paint drips slowly down the wall because that's how paint works in the real
4:44
Josh: world and i think game engines probably feel threatened by this because it does
4:48
Josh: all the things that game engines did except it's infinite and it's fully customizable
4:51
Josh: like that example with the cat where you can take a photo of your cat in your apartment
4:55
Josh: and it'll scan it in and you could actually walk around your apartment,
4:58
Josh: jump on your couches if you're your cat.
4:59
Josh: That is a unique and novel thing only understood and only possible through world
5:04
Josh: models. And that's what makes them really unique relative to anything else that we have.
5:07
Ejaaz: Yeah, I think like a lot of people seeing these demos that we're showing just
5:11
Ejaaz: kind of think like, okay, this is just a video generation model or it's kind
5:14
Ejaaz: of like a game engine, right? What's the difference between this and GTA 6?
5:17
Ejaaz: And the point is everything that goes into producing this thing.
5:20
Ejaaz: Typically, it's extremely expensive. Like how long has it been since the last
5:24
Ejaaz: GTA came out. It's been like, what, a decade now at this point?
5:27
Ejaaz: And every year they keep on delaying it. And now you have a physical,
5:31
Ejaaz: rather an AI engine based on physical reality that can do this in a matter of minutes.
5:36
Ejaaz: Like right now you can go on, type in a prompt with a Google Ultra subscription
5:39
Ejaaz: and minutes later, you have a 60 second interactive world that you can kind
5:42
Ejaaz: of interact with, move around and kind of manipulate to your liking, which is insane.
5:47
Ejaaz: And then with video models, remember, it's all predetermined, as you said.
5:50
Ejaaz: Now, naturally, right, if you were a gaming company looking at this,
5:53
Ejaaz: having spent five to 10 years building your next AAA game, you're going to be kind of scared.
5:58
Ejaaz: And actually, that's exactly how the stock market reacted.
6:01
Ejaaz: This is ugly. Look at this kind of summary of the top gaming stocks and their
6:05
Ejaaz: reaction to Google releasing Genie 3.
6:08
Ejaaz: Unity, which is the prime time gaming engine, dropped 30% in stock price.
6:14
Ejaaz: Roblox, obviously the number one game amongst Gen Z and older,
6:17
Ejaaz: dropped 13% in stock price, and some of the others dropped between 8% to 10%.
6:22
Ejaaz: Now, this is a market reaction to basically Wall Street not understanding,
6:26
Ejaaz: or rather understanding that these models can now emulate any kind of game in
6:30
Ejaaz: a matter of seconds and how that affects gaming development is really important.
6:34
Ejaaz: I read this wild stat in preparation for this episode, Josh.
6:38
Ejaaz: It was an official report on the state of gaming from the Gaming Developer Conference in 2026.
6:44
Ejaaz: And they said over the last two years, 33% of gaming developers had been laid off
6:50
Ejaaz: most of them in the last 12 months. And that's because of technology like this.
6:55
Josh: Yeah. And as an Halo fanboy for life, I have to highlight a pretty interesting
6:58
Josh: example that relates to this, which is Bungie, the company that made the famous
7:02
Josh: video game Halo that's lived on for 20 years in infamy.
7:04
Josh: They started with a team of 40 people when they released that first game.
7:07
Josh: And then they ballooned to 1300 people in 2023.
7:11
Josh: And the reality is, is that you don't need that much.
7:14
Josh: And there's so much bloat that exists in these companies that,
7:18
Josh: I mean, shortly after they laid off some employees i'm sure they're going to continue to
7:20
Josh: do so but the reality is is that you it doesn't take
7:24
Josh: a huge team to build these things when it's
7:27
Josh: just a matter of putting in the right prompts and iterating through something
7:29
Josh: like genie which is a world model that can build any of this for you dynamically
7:33
Josh: in real time it's so much more impressive and i think the market reaction to
7:36
Josh: it is warranted like stocks probably should be going down the same way sas companies
7:40
Josh: are while the market figures out and the gaming industry figures out how to
7:43
Josh: re-evaluate this new tool set that that exists yeah.
7:46
Ejaaz: I saw a really funny meme online where um someone said uh we got gta 6 before
7:52
Ejaaz: we got gta 6 because someone had like recreated what gta 6 would probably look
7:58
Ejaaz: like in arguably a better quality
8:00
Ejaaz: or same quality as some of the demos for the actual case looks like
8:03
Josh: Yeah it's pretty impressive but.
8:05
Ejaaz: The truth of the matter is like they world models aren't just a one-off like
8:10
Ejaaz: novelty They're going to be popping up everywhere.
8:13
Ejaaz: And right now we've got kind of like six or seven kind of main startups and
8:17
Ejaaz: big companies that are building them.
8:18
Ejaaz: The likes of Google DeepMind with Genie, Runway, NVIDIA is working on their
8:22
Ejaaz: own for robotics, specifically Roblox just announced their new world model.
8:26
Ejaaz: Tesla's been using world models to train autonomous driving models for Tesla vehicles,
8:32
Ejaaz: World Labs, and much more, which now makes me want to talk about some of the
8:35
Ejaaz: other important use cases because this isn't just a story about gaming engines, right, Josh?
8:41
Ejaaz: There are, or even like Hollywood effects. There's so much more that you can
8:45
Ejaaz: do with this that I kind of want to touch upon.
8:48
Ejaaz: The first use case that I'm super excited about and the video that we're showing
8:52
Ejaaz: on the screen right now is not really related to this, but it kind of is.
8:58
Ejaaz: Is robotics. Now, robotics is eventually where AI enters into the physical world.
9:04
Ejaaz: Right now, all we're talking to is a chatbot.
9:07
Ejaaz: But in order to kind of like make that jump from the virtual software into the
9:12
Ejaaz: real world where robots are going to do helpful and useful things for us,
9:16
Ejaaz: that is going to take some kind of a bridging model.
9:19
Ejaaz: And that is the world model. So why is it important?
9:22
Ejaaz: Well, robots are actually incredibly hard to train.
9:26
Ejaaz: Why? Because an LLM doesn't work with a robot. You can't describe to it what it needs to do.
9:31
Ejaaz: You need to show it the world and help it understand the world.
9:36
Ejaaz: And so there are two ways to do that right now.
9:38
Ejaaz: One, you can stick a robot in a room and tell it to fold the laundry,
9:41
Ejaaz: and it can try a million times and fail a million times and then learn iteratively and slowly over that.
9:46
Ejaaz: Or two, the more scalable way is you can generate a simulated world,
9:50
Ejaaz: which is physically accurate to a room with clothes that need to be folded and
9:55
Ejaaz: then just run it through a billion simulations at lightning speed.
10:00
Ejaaz: And Google is actually doing this. So it created Genie 3 and then it has an
10:04
Ejaaz: agent or a model called SEMA, S-I-M-A, look it up.
10:08
Ejaaz: And it's a robotics model where they can basically just place into this simulated
10:13
Ejaaz: environment and get it to run a million different scenarios.
10:17
Ejaaz: And it's really meta. And it's kind of like the moment that kind of made the
10:20
Ejaaz: point for me that Demis was getting at, which is, this is the massive step in
10:25
Ejaaz: AGI, which was preventing robots from kind of like making that leap. And we finally have it.
10:31
Josh: Yeah. And it's funny because I look at this and I can't help but think about meta.
10:35
Josh: And how they shifted their name to Meta in anticipation of building a metaverse.
10:39
Josh: And this to me feels like the closest thing we've ever seen to a metaverse.
10:42
Josh: Now imagine this video we're seeing on screen where someone's walking around
10:44
Josh: the woods with the GPS was collaborative.
10:47
Josh: Imagine two people could share the same reality and it could be generated in
10:50
Josh: real time. You could share the same spaces.
10:52
Josh: I think this very much feels like that first step towards a metaverse.
10:55
Josh: And then if you could put a human in there to navigate and move around,
10:59
Josh: then surely AIs can watch how they move.
11:01
Josh: They could learn from them. It creates this great training ground for like you
11:04
Josh: said robotics it creates training grounds for anything another is
11:07
Josh: like medical surgeries or driving like
11:10
Josh: we're going to talk about soon with waymo and how you can train cars to do this
11:13
Josh: and i think it's just this unbelievable progress in
11:16
Josh: understanding that feels like the missing piece towards embodied ai
11:19
Josh: and to your point it's it's not just an llm anymore it's much
11:22
Josh: more than that and these videos like we're looking at a blockbuster demo right
11:25
Josh: now very nostalgic very nostalgic very
11:29
Josh: lifelike and again this is the worst it's going to be and one thing
11:31
Josh: to note is that this model came out last year what was it last august or september
11:36
Josh: like later in the half of last year and only now are they actually allowing
11:39
Josh: the public to use it but this is currently last year's technology this isn't
11:42
Josh: even what the newest version is going to look like that i'm sure they've been
11:45
Josh: building on their new set of tpus and it's it's going to get so good so quickly yeah.
11:51
Ejaaz: It's it's super impressive um the point that you made around medical surgeries
11:55
Ejaaz: is actually like one that most people probably don't think this will affect but it 100 will
12:01
Ejaaz: It's an incredibly precise set of skills that you need. It takes like how long
12:06
Ejaaz: does the average surgeon train for? Like probably their entire life, right?
12:10
Ejaaz: And a decade's worth of experience. And to have a robot that can kind of like
12:14
Ejaaz: precisely do things and make minimal error, well, it reminds me of autonomous
12:19
Ejaaz: driving, right? Like self-driving.
12:21
Ejaaz: I remember when Tesla announced FSD was kind of like this impossible fee and
12:26
Ejaaz: everyone was like kind of crapping on it. And now it is statistically better
12:29
Ejaaz: than the average human driver, right?
12:32
Ejaaz: So Tesla's proven this. Waymo is now doing it with their own world model.
12:35
Ejaaz: And I'm excited to see what other applications this gets involved in.
12:39
Josh: Yeah, I want to do a quick run through the specs that I wrote down here,
12:41
Josh: just so everyone's aware of the limitations, because I thought this was interesting
12:44
Josh: too. So it can generate these 3D worlds.
12:46
Josh: Currently, it's limited to 720p resolution, which is the standard is 1080p.
12:50
Josh: So it's just under true HD, what a lot of people would kind of refer to as.
12:55
Josh: It's the first world model that allows for real-time interaction. we've
12:58
Josh: spoken about this previous versions had a lot of lags and then
13:01
Josh: this is unique in that you can describe your own world and choose
13:04
Josh: how to explore it so one of the earlier examples you showed is that
13:07
Josh: you can fly through it you can walk through it and it understands the
13:10
Josh: difference in how you navigate through these worlds what it can't do it can't
13:13
Josh: generate anything longer than 60 seconds so after you've generated 60 seconds
13:17
Josh: of gameplay or visuals or whatever it stops it can't quite render legible text
13:22
Josh: inside the game engine yet or the world engine yet so if you want it to type
13:27
Josh: anything, it just can't.
13:29
Josh: And it can't simulate real world locations accurately.
13:32
Josh: So if you wanted to put yourself inside of Times Square, it won't actually get
13:37
Josh: Times Square right just yet, which feels a little disappointing because they do have Google Maps.
13:41
Josh: And I'm assuming it's just a matter of time.
13:44
Josh: And we have this example here actually of an F1 car driving through Times Square, but it's not quite...
13:49
Josh: Accurate it is not exactly how timesquare looks it's
13:52
Josh: a perception of timesquare and i imagine that there
13:55
Josh: will be a world in which like you know how you have the microsoft flight
13:58
Josh: simulators where the planes can drive through like a one-to-one
14:01
Josh: replica of the world using the google maps api i'm sure it's just a matter of
14:04
Josh: time until they converge those two together that'll be really amazing and then
14:08
Josh: there were other things that were in the august 2025 demo this one yeah here's
14:13
Josh: a constraint when a person's walking up to a mirror and they look the other
14:17
Josh: way and the mirror, the reflection.
14:19
Ejaaz: Oh, there's like two of them. Like that, look, she pops out of the mirror now.
14:23
Josh: Oh God, that's a little cursed. Yeah, so there's stuff they need to figure out
14:28
Josh: still. But for the most part, it's a pretty killer model.
14:31
Ejaaz: Yeah, and listen, like this thing will get better.
14:35
Ejaaz: This is version one of this technology and it's already this good.
14:41
Ejaaz: You can imagine what this is going to be like in version three, four, five and beyond.
14:45
Ejaaz: And the iteration cycles between these model releases are getting so much quicker, right?
14:49
Ejaaz: So we're probably going to have a much better model this year.
14:52
Ejaaz: It wouldn't surprise me.
14:53
Ejaaz: That being said, this stuff is also incredibly expensive, more expensive than I was thinking out here.
15:00
Ejaaz: We have a tweet here from Mark where he says, Genie by Google DeepLine runs
15:04
Ejaaz: on four H100 GPUs leaked from an internal presentation.
15:09
Ejaaz: That's per instance. So every 60 seconds of video that you kind of want to generate,
15:15
Ejaaz: It requires, I don't know if it's the total capacity, but a good chunk of four H100 GPUs.
15:20
Ejaaz: Now, the average cost of each of these GPUs is around $25,000 to $35,000.
15:26
Ejaaz: So it's not cheap enough for you. It's costing Google a lot of money to do.
15:30
Ejaaz: But, you know, with all the scaling laws, I assume this cost will go down over
15:34
Ejaaz: time. But one thing is pretty certain at this point.
15:38
Ejaaz: Compute is a never-ending resource that we will need to power the future for
15:42
Ejaaz: any of this. like any world models, chat GPT prompts or whatever you could think of. So,
15:47
Ejaaz: It's a really prescient point where if we now want to train physical embodied
15:52
Ejaaz: AI with robots, and we haven't even got V1 of that yet, we're just going to need a ton more compute.
15:57
Ejaaz: That was the other thing that I thought of. Like, this is just going to be a
15:59
Ejaaz: very expensive game to play, pun intended.
16:01
Josh: Yeah. I mean, in addition to the consumer use cases, like what we're seeing,
16:05
Josh: the commercial use cases are very real. Like you said, the embodied AI is a huge perk.
16:09
Josh: And just last week, Waymo, they announced the Waymo World Model,
16:13
Josh: which is built on top of Genie 3, but it's adapted for
16:16
Josh: something very specific which is generating photorealistic driving
16:20
Josh: simulations and what it means is it's
16:23
Josh: able to create these like lidar point clouds and it could create
16:25
Josh: all the camera outputs and yet like we're seeing on screen and
16:29
Josh: it can actually create a simulated reality
16:32
Josh: that the ai which is training on can't tell the difference between so
16:35
Josh: if you show the ai self-driving model a
16:38
Josh: representation created by genie 3 or by the real
16:41
Josh: world it doesn't know the difference so they've essentially
16:44
Josh: unlocked this this data stream that
16:47
Josh: is capped only by the amount of gpus that they can use to
16:50
Josh: render these scenarios out for the model so what we're seeing here
16:53
Josh: and it's funny is is a weird anomaly there is an elephant in the middle of the
16:57
Josh: road i can't imagine there's many times in which an elephant's in the middle
17:00
Josh: of a road and the model now understands not only what an elephant is but kind
17:05
Josh: of how it works the size of it and that you should not hit it and i think it's
17:09
Josh: an interesting example to show how powerful this can be because a lot of the times,
17:13
Josh: the constraints with this physical embodied AI is going to be that data set.
17:17
Josh: It's going to be giving it examples that allow it to get better when navigating the real world.
17:21
Josh: And now using this world model, at least in the case of full self-driving,
17:24
Josh: Waymo was able to do this at scale in a place that they previously haven't had a whole lot of data.
17:29
Ejaaz: Yeah. So I think if I had to summarize the impact of world models this year
17:33
Ejaaz: in particular, it's going to help us make the jump from
17:37
Ejaaz: digital AI to physical AI. And that's going to come in the form of robots that
17:42
Ejaaz: help with really precise surgeries,
17:45
Ejaaz: robots that help with manual automation in factories, and robots that kind of
17:49
Ejaaz: help drive us from point A to point B with a 0% error rate. Hopefully we eventually
17:54
Ejaaz: get to that rounding error.
17:56
Ejaaz: I think this is the next step to get that kind of AGI level type of experience
18:02
Ejaaz: because AI models just don't do a good job today of interacting with reality.
18:08
Ejaaz: It describes reality really well. It tells me how a glass might fall off my
18:12
Ejaaz: table and crash to the ground, but it can't simulate and emulate that.
18:16
Ejaaz: And as humans, we take in everything through our eyes, ears,
18:19
Ejaaz: and a million other sensory stuff.
18:21
Ejaaz: So if we can get an AI model that can achieve all of those things,
18:24
Ejaaz: we can just take that next magnificent leap to a better AGI-like type experience.
18:29
Ejaaz: And I think world models is that step.
18:31
Josh: Yeah, I agree. I mean, think about what we described today. Google,
18:34
Josh: they built a foundation model that understands how the world works.
18:37
Josh: Now Waymo is using it to train cars.
18:39
Josh: Every single AI company in the world who's building robots needs it for training.
18:42
Josh: Waymo is using it for training their fully autonomous cars. It's like every
18:46
Josh: road leads to world models. And it feels like this is a paradigm shifting thing.
18:50
Josh: It's like, in a way, world models are to AGI what the Transformer was to LLMs.
18:55
Josh: And it's like the Transformer paper in 2017, it made everything in the world of LLMs possible.
19:00
Josh: And now that we have Genie 3, it feels like it unlocks this whole new world
19:03
Josh: of possibilities that were previously not available just in time to help train
19:07
Josh: the robotics that are going to be coming into this world over the course of the next 12 months.
19:11
Josh: So it's a really exciting development. And again, I think it's important to
19:15
Josh: note that this came out in August of last year.
19:17
Josh: They've only just recently allowed the public to start using it and engaging
19:20
Josh: with it. And that's why you're seeing companies like Waymo adopting it.
19:22
Josh: But imagine the progress that they've made since last August till now and how
19:26
Josh: much better this is going to get so quickly. So it's something we'll be paying
19:29
Josh: very close attention to.
19:30
Josh: As we continue to navigate and explore the frontiers of AI and technology and
19:35
Josh: all this crazy stuff that happens every week. That wraps up this episode.
19:39
Josh: Thank you, as always, for listening. We have some exciting news in the fact
19:42
Josh: that on Apple Podcasts, we just crossed the top 100 technology podcast, number 99 and counting.
19:48
Josh: Thank you. A lot of that is in part to people who went and wrote a nice review.
19:52
Josh: We got almost 50 new reviews last week, so thank you for that. That was so generous.
19:56
Josh: If you have not written a review, let us know what you think.
19:59
Josh: That's one of the best ways to improve our chances of climbing the
20:02
Josh: charts second to sharing these episodes with your friends if you enjoyed them
20:06
Josh: if you have a friend who is into full self-driving cars or gaming or anything
20:10
Josh: that possibly could have had ties to today's episode send them the episode see
20:14
Josh: if they like it see if they enjoy it as much as we did recording it thank you
20:18
Josh: always for watching ijaz any final parting notes before we we sign off yeah.
20:22
Ejaaz: If any of you listening to this have a Google Ultra subscription,
20:27
Ejaaz: I really want you to try this model out.
20:30
Ejaaz: I'm curious what your feedback is. Is it as cool as the videos and demos that we're seeing?
20:34
Ejaaz: Josh and I don't have access to this right now, but if any of you do,
20:37
Ejaaz: like, you know, maybe there's a better use case for this that you guys find.
20:41
Ejaaz: Share with us. Let us know in the comments. DM us. We're on every social media
20:44
Ejaaz: platform. And we'll hear from you soon. But until then, we'll see you on the next episode.
20:49
Josh: See you in the next one.
20:50
Ejaaz: Peace.