We tested JSON prompting in Veo 3

0:00In this episode of Denoised, JSON prompting in VO3, useful hack or hype? Hicksfield Steel, a controversial new product with a weird marketing campaign. And AlphaGo, an AI model that can build other AI models. Let's get into it.

0:18Welcome back, Addy. Thank you. It's nice to be back. Where have you been? I've been in a deep Asia for the last two weeks. That's amazing. I was in Tokyo for about a week and then took a small flight over to South Korea. I was there for another week and now I'm back severely jet lagged and just really happy to be podcasting again. Good to be back here. Yeah. Well, I'm glad you seem awake enough. Yeah, I'm going to share some photos. I saw a Kodak store, like a full on like branded Kodak sandals, Kodak t-shirt. Obviously the film you can buy there. It was so much in demand that I saw another one being built out.

0:55Oh, another Kodak store. Another Kodak store being built out in Tokyo. so and i have just like more of the licensing play from uh like that stuff i saw at ces where it's just like codec everything it's exactly that and i i got myself this this is from my childhood i think yours too i do remember that yeah i never thought when we use this for real that one day we would buy it as a prop that would be nostalgic for it and it's gonna be on the podcast set here wait it takes this one holds 39 photos is that a lot yeah used to be 24 right there was a 24 or 36 exposure this is 39 exposure dude they stepped up the game they gotta step it up compare to compete with the with the flash card i don't know where i'm going to process it if i ever do use i think there's some mail-in services that still okay exit but also i mean well here in la like at least like there should be yeah it's just it's just really nice to see uh kodak making a comeback you know like we talked about jurassic world recently and then sinners and yeah it's awesome yeah film film's not dead film is very much not dead all right so while you're gone this started boiling up like a week ago, but it's still it's still trending.

1:56JSON prompting has become a hot topic in the Twitter sphere of via especially with VO3 prompting. But now I've been seeing JSON prompting bleed into just AI prompting in general. But we'll kind of focus on VO3 because that was where a lot of the attention was given. I would say this started I don't know if it started but came on my radar with Dave Clark, who posted out a new short film that looks really good. And he did it all with VO3. And then he was saying that he changed his prompting format to JSON. And so JSON is a format language. Yeah, it's ASCII language. So it's our alphabets and numerics.

2:29So anybody can read it in English, but it's it wraps up into like a text file, if you will. Yeah. And it's like a structure and it just basically gives a lot of structure to the prompt. And you have sort of fields for let me look at this sample one. Yeah. It's somewhere between like code and human language. Yeah. It's human readable, but it's got some of the coding formats. but I'm going to pull up an example here. So like in this one example, it has a description of your prompt shop, but then it also has a field for style, a field for camera, for lighting environments. And so the thought behind this was by having such structure to the prompt in JSON format, it would, you'd get better outputs.

3:07And then also if you're doing multiple shots and you're trying to have consistent characters, consistent scene, consistent environment, you keep these factors the same. So you can reprompt the shop, but you have other elements that stay the same. Yeah, it becomes more modular and easier to scale up. Like as you have a structure, you know, all you do is if you're going to change from a wide shot to a medium shot, you go into the camera section, change the lens, something like that. Similarly, yeah, or just, yeah, change your prompt, but like at least your lens data is the same. Sure. Lighting data is the same.

3:33I was thinking it also leads to if you're messing around with like cloud code or something, you could build a little interface with like drop downs to kind of spit out like in a nice interface, kind of write up your prompt, and then it spits out a JSON. format with the consistent elements. Yeah, I would even go a step further and use a VLM, a visual language model. So ChatGPT one has built in where you can input a frame of something you're trying to create, right? It could be a hand sketch. It could be something out of Unreal Engine and then have it give you a JSON file with the prompt that would be required to generate it.

4:08Yeah, and that was a test I did where I started just having Gemini or ChatGPT give me the prompt, tell it the prompt of the shot I wanted, but give it back to me in a JSON format. In Dave Clark's original post, he sort of also worked on some other things, which he didn't quite get into details yet. And I'm curious about this, because this also might play into just how JSON is a speedier way to build out a short film. But he said he wrote an agentic workflow to automate JSON formatting based on the entire script. So it sounded like he gave the entire script to Gemini and then got like, not just a single shot in JSON, but like the entire sequence.

4:43Yeah, sure. So he sort of posed a little bit about that, but I'm kind of curious about how that further develops when he does post or explain more of his workflow. So, but JSON prompting in general. So the argument is it gives you structure and you get better outputs. But then other people were saying, this is a bunch of hype. Jason's not a AI peeps. JSON prompting is just influencer hype. Highly structured prompts are way better than all the extra info that I keep seeing in people's JSON prompts. So he's basically saying just a nice, good text prompt is funny. I don't agree with this guy's language and just like, you know, this is not the right way to approach it, but I do understand the sentiment here.

5:21And this goes back to what I've been saying for a lot of episodes is like movie making is done on a shot by shot basis. And if you try to automate it with a giant JSON file, you're still working in a shot by shot basis, but that entire shot is now inserted into a giant sequence JSON, right? So why do that when you could be as granular as at shot level and I think you'll you'll find that as you go higher and higher up the quality ladder in movie making the more and more granular you have to be so go from shot by shot to now tens of frames or maybe a single frame and so on and I don't see json formatting and json prompting beneficial for those high-end films having said that like those 10 second 30 second add spots, sure.

6:08Go use it all day long. Yeah. I mean, I'm thinking, well, first off, it's like, look, try this out for yourself. If this helps you structure your prompts better and you find that you're like getting better outputs. Cool. Have fun with that. JSON, I think is, I don't find it super easy to read. I think you like, especially reading it on a social media platform, like you really need to copy this and put it into an actual markup language editor, like a Sublime or something that's free where it'll like format it nicely for you. And you can see the hierarchy of the levels. I mean, I think overall, just text prompting in general is annoying and kind of dumb.

6:40Yeah, it's not the way. Shifting away from that. Absolutely. That's not the way we're going to go forward. Text prompting, even if it's like 500 characters or in this case, 10 ,000 characters, whatever, is not going to be the way of the future. Like we're going to have a better interface into AI generation. Yeah, something more visual, something more tangible. Absolutely. Yeah. Moving things around with mouse and keyboard or timeline or something like that. And there's been tons of attempts at that. And I think it'll only get better. Also, the formatting of JSON is not going to save you or give you any better results because all you're doing is essentially adding whitespace and parentheses and labels and tag names.

7:20Yeah. And there are some arguments to are saying like, basically, you're adding much extra stuff that is going to use more tokens, it's going to cost you more and not necessarily add more. Then there's some other debate or some other suggestions put up, like Chris put out that YAML is another formatting language, which I wasn't really familiar with, but uses less tokens is another way to format your prompts. But sure, you know, could put the info in there. And at the day, it still comes down to natural language, right? Like these clip encoders that these video generation image generations use is trained on natural language.

7:50It's not trained on JSON scripts. So whatever JSON file you insert is going to get decoded. Or the argument was like, yes, people are like, oh, that they were trained with JSON. But it was like, yeah, they're trained on JSON formatting, but they were trained to understand human language, natural language, not JSON. Like when I say photorealistic, that has a very specific meaning to you and me. And that's what the clip encoder is going to try to generate when I put photorealistic, that word in my text prompt. Yeah. So I want to test this. Oh, nice. So I did a couple of tests and basically I used Gemini and I just had a very basic shot of like a person at a diner.

8:27And we started a close up of a coffee cup and then we like tilt up and rack focus to a detective guy who looking out the window. Nice. And I just kind of gave it that basic prompt. And then I said, give this, you know, build out the shot in a JSON format. And I gave it like one of Dave Clark's JSON prompts as a structure base so that it would just change it and modify it and give me the output. And then I had to rewrite that JSON prompt as just a regular text prompt. so then i ran them both twice okay and so then i ran them in vo3 fast started on the cup tilt it up rack focus tilts guy looks out also it's just crazy how how realistic this looks like the steam out of the coffee shot itself is crazy yeah fine right i mean it did what i did what i asked for also gave it some specific time markers like zero to two seconds we push it on the cup two seconds to flower seconds we pan up or tilt up yeah that has a little handheld handheld feel to it the other one came out really dolly like and then this one is the paragraph format

9:30completely different shot it hit the point i mean i i still think it's a matter of i mean it still did what i asked this one's weird because he sits in so this one didn't quite nail the specifics and it's inversed mirrored. Yeah, I didn't really give it screen direction. I will say, well, the shot I had in my mind, the JSON one hit what I had in my mind. Spot on. But having said that, the second one you showed with a little bit of a handheld, I prefer that one. Yeah, these are the same prompts. I just had to do two outputs. Right, but again, it's like a random draw. Yeah, these are just different seeds.

10:02For sure. And then let's see, I did another one where I wanted to have like a reverse shot of the guy. None of them understood what I had in my mind, but I didn't specify screen direction as well in my initial prompt.

10:16can i get you some more coffee the only thing i wanted to say was gonna get you some more coffee and then it had some chippers in the beginning so crazy how good that looks like if you look at the gate on the waitress and the the coffee fluid slushing around yeah oh my god can i get you some more coffee yeah i would do some audio massaging on that dialogue yeah and the in my description i wanted the i was thinking more that it would be from it from the right side of him but this would be just more be like i need to i would just need to finesse my prompting for sure um and then this is the paragraph version of the same shot milk pot can i get you some more coffee didn't pour yeah yeah i mean apples and oranges super similar yeah and then this was the one you sent me.

11:04I just ran the prompt as is. And let me give a shout out. Yeah, shout out to Saeed Ali Kazim for sending us this JSON. And this is what he generated. I'm more amazed that it's able to do the copyright logos and stuff. So this is the JSON, the prompt, the original one he posted, different seed from whatever he demoed. But thing popping out of the box, and then I gave Gemini the same exact JSON prompt, and I said rewrite this into a paragraph format.

11:31it's pretty much yeah the two wheels fly up and never return and then two new wheels appear it did that too here like see these wheels go out that entire yeah yeah we need to work on that but yeah so it's more or less the same pretty much the same yeah and then there was another one that i'm more amazed that it could do the superman and not give you a copyright issue error correct yeah that's this was one that i found online that they posted yeah and then i just had to rewrite it and it does pretty much the same thing also like when it comes to that copyright stuff i wonder you know again i'm not a liar obviously and i'm not a lawyer but there is a certain gray area where you can be doing this and either it's under parody law or under fan fiction um so like yeah i mean i think i can't go into the outputs and how you use this like there are uh there's leeway to that i just had issues with vo3 where i had a name of something it like flagged it and said we can't generate this it didn't tell me why i assumed it was because i had a name of something that had some copyright protection but it seems not the case because this prompt said superman and spit out superman like um one of the channels that i watch on youtube i think it's called star wars um it's like a fan based star wars thing that's fully ai generated okay and like a stormtrooper some vlog stuff it's nicer than that um i'll pull it up uh and it's basically taking bits of star wars that was never included in the original six or seven films okay like moments where like luke luke meets uh general grievous for the first time you know something like that okay and it'll use ai to generate it and that stuff is up on youtube it's making a lot of money you know it's taking a lot of views and uh they're not taking it down there is no copyright infringement there i'd be curious if there was like similar to if you upload a video with a song and depending on the label they have choices of if they either want to just block the thing entirely or if they want to claim monetization so like leave the video up but they take the money got it yeah money what you make so i'm curious i'd be curious if yeah and it's like it's mark hamill right there's no mistake about it like they used his likeness and everything probably without his permission yeah but it's still up there yeah yeah yeah uh that's a separate wild west of stuff but yeah i'm just i'm more surprised that vo3 was putting these outputs out but yeah i mean i think with the json stuff you know i think look try it out if it helps you yeah make if you get better stuff if it helps you organize your shots or just you think better that way sure cool go for it um if you like tech stuff long paragraphs better yeah cool whatever works yeah it's like uh look i like my coffee um as an americano you like your coffee as drip but end of the day we're getting caffeinated it's like come on guys get caffeinated yeah yeah whatever works for you and also i think it's just more something to be aware of and it's like yeah you can try it in your toolkit and maybe this works for you also like you know maybe if you just had a little bullet point list with all of the like same exact things of and it's just listed out yeah you know shot frame lighting you might get the same exact quality output anyways exactly i think the the thing that they're uh missing the argument on is still consistency like jason is not going to save you from that like from shot to shot to shot no no i mean maybe it'll help you get a little bit closer and stuff but no it's not um and since we last spoke vo3 now does have first frame Yes.

14:55Yeah, which is the person who commented like, 0-3 had first frame for a while. Yeah, we recorded that before that. Because literally the day after, I think it launched, and then I was like, you know, man. Yeah, good luck. If you have an AI podcast, good luck trying to stay up to date. Yeah, good luck trying to create evergreen content for two weeks from now because it's all outdated. But because they added first frame, there was another thing posted. And I think this is just also interesting on a bigger level where even the companies putting these models out are still figuring out cool ways to use the model that they did not even intend or know about.

15:23So Google posted a hack tip that they realized where basically if you with VO3, if you I think VO2 works too, but VO3, if you take your first frame and then you mark up what you want to happen, like with text or text boxes on the image, and then you give it that image and then you say, follow the instructions on the image or something to that effect. Right. It will start with the first frame with that marked up image, but then dissolve out the text and then make whatever you want that you describe happen, happen. That's so cool. So you lose like a few seconds in the beginning because it's going to be unusable, but you have far greater control over what you're trying to do.

15:59And that's how, like, if you've ever worked any feature or TV show, like, you know, that's how directors give notes. That's why we have Frame.io markup. Yeah. Yeah, exactly. Yeah. It's like, oh, I just want to literally draw on the frame and markup. Yeah. And I didn't have Frame.io. I mean, Frame.io too, but there are like tons of other companies too, where they solely exist to... SyncSketch is out there. Yeah. F-Track. F-Track. PF. No. F-Track and then ShotGrid. there's a bunch of revision yeah with very specific tools to mark up every single part of the frame yeah so this was people have been posting different hacks and stuff of you could do text boxes someone even realized you could upload an image like they uploaded a picture of an image on like next to a tv screen and then it put the image on the tv screen like with static and stuff wow so that you could not only just do text inputs but image inputs as well dude so i love it crazy use case but it's like just an example too of like everyone's messing around with this stuff and there's no there's no like rule book my brain instantly goes to how difficult that task was pre-ai and now with ai yeah yeah right but yeah between that and also olive which we'll talk about at the end of the week but um runways olive and the demos i've been seeing from that and what it can do with existing video is christobal you did it again you son of a gun addy's open invite to cristobal yes uh still holds especially now i'm a big fan of alif we're gonna do we're gonna do a super cut so yeah um some cool prompting stuff yeah prompting debates all right higgs field steel higgs field steel so there have been you know debates and you know it's like kind of fine lines right now going on with ai and copyright protection and ethical uses is Higgsfield's put out a product that's literally called Higgsfield's deal.

17:47And their demos are, well, the pitch is basically, I mean, honestly, it sounds kind of similar to like a lot of other products out there, where it's like, you can give a couple of source images or, and kind of create something similar to it or combine elements. A lot of other products have protections in place. If you're using copyrighted characters, I believe it's called indemnification is the legal term. So like, as long as you're using that product under the correct license and in the correct way, then the company that makes the product will essentially cut a got your back okay yeah higgs field steel's demo is using like where is it some of the demo like uh dualipa and i'm trying to think of what other so the daniel craig daniel craig as a nightwalker oh yeah daniel craig is a nightwalker from game of thrones so basically just using all sorts of uh real people not knowing about the awareness and the ip protected scenes and stuff it's not good it's not good at all a bit icky but that was weirder was a lot of the top ai creators on x started posting promoting steel which i know i believe they're all like paid like higgs field ambassador so like i mean you know a lot of the ai creators are ambassadors to the companies but they're all sort of putting out the same messaging so like yeah this was the this was the daniel craig ice walker one joker yeah it's all right but i mean the messaging was just weird you know it's hollywood's in trouble then just new hicksfield steel ai tool can now steal camera angle composition color lighting dude that one's obviously like the the hollywood's in trouble thing is is getting old always like kind of funny but it is evolving it's not it's not in trouble it's in a transitionary period right now well it'll be fine adding nuance doesn't work well on the internet oh yeah here that's one from tech hawa who's a big creator and has a lot of good stuff but then And the message, you know, forget about copyright, just grab it.

19:34It's like, you probably shouldn't forget about copyright. It's kind of important. Yeah, I'm trying to look up, like, my first media thought was like, Higgsfield's probably a Chinese company, so they don't have to abide by American laws. That's true and probably true. So I looked it up and it's not. So former Snapchat executive. That's right. I forget. We talked about this in a while ago. Yeah. And I guess he has funding from, according to Google, funding from Kazakhstan. Okay. so uh it could i mean it's still a american i mean i think they're just gonna ready fire aim and then see what happens but yeah and then then this other one this other promotion posted out uh a few days ago was the same exact messaging from this one from tech hall again mid journey stole from artists constantly now you can take it back use higgs field steel to get what you want from mid journey and it's a video and then literally the same exact messaging from alex uh petrasku they stole first now it's time to steal better take directly from mid-journey with higgs field steel same video similar messaging it feels like there's fox news um the the sinclair broadcast remember that clip when it was like all of the local tv stations were reading the same exact script yeah it feels like that in the ai space totally yeah and this is not in my opinion this is not the right move uh not a great look especially when like there's all this other literal legislation about like what ai companies can train on and do and and might and maybe in the The influencer space and the consumer space, sure.

20:57I think it could be a cool meme or cool trope to get some eyeballs on your product. But as you move up into the enterprise space with professional studios, big companies, they're not going to want to do anything to do with stealing. No, no, absolutely not. No, I don't think Higgsfield's in that position. Yeah. I mean, just call it style reference. Call it something else. Yeah, like every other company that has something similar. I mean, yeah, I guess if you want to make a name and splash for yourself and stand out. from that. I don't know if it's best long-term play. Yeah, totally. But it's good to sort of get a good calibration on where AI is right now.

21:32Like on one end of it where, you know, we have company like Adobe that's being super sensitive about stealing because they've made some mistakes in the past. And the other end of the spectrum, you have Higgsfield who doesn't give a F, right, about any of this. So, you know, obviously we're somewhere in the middle where we understand that AI has intrinsic value in bettering our content creation, our lives. At the same time, there's some real ethical issues it's up against. And we got to figure that stuff out quickly. Yeah. The whole thing felt icky. Icky. Icky's right. I felt icky in Tokyo. It was 95 % humidity.

22:08Different kind of icky. All right. The last story of this paper, AlphaGo. Yeah. So interesting paper. Now, I got to say, forewarning to our viewers, prepare to be scared. Okay. So we talked about Ilya Setsiver before and artificial super intelligence. We know that companies like OpenAI, XAI, and pretty much anybody is working at artificial general intelligence. So AGI, for the lack of a better term, is where a model or a combination of models matches human intelligence. Like it's as smart as you or me or whatever. and then ASI, artificial super intelligence is as smart as several humans or a thousand humans so it's like infinitely smarter and it has the ability to get smarter over time so how is this actually going to happen?

23:01this is a glimpse into the future my friends so this is giving me some Skynet vibes I gotta say and I don't know how I'm feeling icky about this a little bit but at the same time it's really cool that research is going on So AlphaGo is a research paper and we have the general understanding is AI architecture is incredibly difficult and that's why AI researchers get paid hundreds of millions of dollars, right? Like to build a new model. To build a model, there is, just like in software or in hardware, you have to put together a bunch of little blocks in a way that is novel, that's new, and it'll do new things.

23:38And now up until this point, even though AI has gotten better and better, the only reason it's gotten better and better is because the architecture and the models were developed by humans and it's just gotten a new one out that hasn't existed before. So fundamentally, in order for AI to be super intelligent, you're still limited by humans. Like if a human can't figure out how to make a certain AI model more computationally efficient, better at quality, whatever, then it's just not going to happen. To beat around that problem, they now have an AI model or rather an AI system that can come up with its own AI architecture.

24:17AI building AI. AI building AI. And we've talked about this vaguely before, but this is like really nailed down. It's really granular. So let me go through this at a level that I understand. And to be honest, most of it is beyond me. Anytime Joey's like, hey, dude, can you do the white paper? I'm like, God damn it. You're going to make me sound like an idiot in front of the viewers. I brought the first two. I'm like, ah. Okay. Read the last one for me. Yeah. So if any of our viewers have a better understanding of AlphaGo, please definitely shout out in the comments. To what we understand, it basically breaks down the problem into four agentic behavior.

24:54So it has a researcher, an engineer, an analyst, and a cognition base. We're going to put up the photo right here so you can kind of see it from the paper. And each of these functions are done by a separate AI model. And what it's basically doing is it's figured out a way to systematically produce innovation. So it has a database of about 50 core AI models, architectures. For example, unit architecture is something that image generation uses, but that's just one type of architecture. And then LLMs and ChatGPT will use a transformer model or hybrid transformers, which is a whole different thing.

25:31So it has a library of 50 architectures that it knows is gold. And then it has a variation of those, another 200 or so. And then given enough sort of room to create, it'll come up with a brand new architecture based on that. So once it has the architecture, and I believe the researcher model comes up with that architecture, then an engineer goes in and actually implements it, uses code, uses CUDA, uses NVIDIA GPUs, and builds it out completely. Automated, which is freaky. And then an analyst will come in and test that for performance and test it for how novel and new and cool it is. So it has a quantitative measurement and a qualitative measurement.

26:13And based on that, you can either say this new architecture is amazing. Let's use it. And here it is. Here's how it's built. Or go back to the drawing board, do another one and do the whole process over it. Yeah. Okay. Yeah, that's wow. So four sort of groups of agents, the cognition base, thinking of this stuff, the researcher looking into it. The cognition base, think of it as a giant database. Yeah. Because I also see it has like a diagram pointing to a chat, like an extractor from Hugging Face. Yeah. Yeah. So remember those 50 or so models, those models probably all live in Hugging Face. Yeah.

26:48And it's pulling key features out of that. Yeah. Right. And then the researcher has, I think the researcher is where all of the magic sauce is because it can figure out completely new architecture. Like put models together in a way that's never existed before. And this is where humans come in, right? Like we have our creativity. We can think of things that has never existed before. And the researcher is mimicking that. Yeah. Yeah. And I see that regenerate kind of loops. So it just seems like also could like probably loop this stuff thousands of times way faster than like any human could. Any human could.

27:19Yeah. So this is one sliver of the path to ASI, artificial superintelligence, is like once AI is sufficiently capable of building one new type of architecture, it could then go ahead and exponentially make more and more and more of those and try to figure out things better, faster, cheaper, running on less GPU, running far more, you know, in higher quality. Yeah, is this how you do a deep seek slash ASI? Yeah. Deep seek kind of thing. On a second note, I saw something really interesting. Jensen Wang, CEO of NVIDIA, was on an interview, and I'm fascinated by Jensen, right? Because I think we all are in the AI world.

27:55His vision is like, I don't know, two miles out from where we are today. Where we are today, he's already thought of it two years back. He's like, yeah, you idiots, you're just figuring this out now. So he said something like, all you need is 150 people to change the world. So he goes on to say, you know, OpenAI is about 150 people. I think DeepMind is about 150 people, like Anthropoc, same, about that size. And if you give 150 people a few billion dollars and let them do their thing, we're going to change the world. And that's going to happen very soon. It's happening now. Yeah. And you combine that with new technology like this, like you're really accelerating where technology can take us in the next few years.

28:39Yeah. Probably not a coincidence. Isn't that Dunbar's number? I think it was called Dunbar's number. 150 was like the number of human connections that like someone could sort of maintain. Right. Consistently. On, yeah, like on a, yeah, one to one level before it just was like either too much or. Yeah. Yeah. And that's one of the main reasons why like big CEOs of big companies have direct reports that are less than that number. like Mark Zuckerberg, I think famously said, he doesn't talk to anybody else at Meta except for like 30 to 50 people. Yeah. That reports to him. Yeah. Cause he's just, you can't, you can't, yeah.

29:13Your brain can't comprehend it. Yeah. You can't do it. I mean, NVIDIA did say that they have like a pretty flat hierarchy, right? Doesn't Jensen, all of the VPs and everything, one report, just go to him directly. All the billionaires that report to the super billionaire. Yes. Is that how it works? No, no. So on that same interview, jensen was like uh yeah i the executive team at nvidia are all billionaires i don't know if it was flexing but he was like yeah and we've done well for ourselves yeah well i mean i'd be sure you do the math i mean what they passed four trillion yeah so like right they've all got stock options like yeah the math maths makes sense yep all right cool yeah that's kind of crazy paper and um i'm curious to see what comes out of it again and and the pace at which this happens is first the paper drops yeah and then an ai company will build a r &d version of this and then if there's enough revenue and there's enough business case then they'll build a product around it and then we have it right so this is the progression of things so research paper look out for those first and i think i mean in this case all the research companies which are most ai companies they're essentially research companies will be all over this yeah yeah for sure yeah yeah So yeah, we'll see what comes out.

30:25All right. Wrap it up. Yeah. I want to give a quick shout out to some of our listeners out there. So one of our super viewers, David Vognild, if I'm pronouncing it right, thank you for your support.