Google's Nano Banana 2 vs. Nano Banana Pro: Which One Wins?

8:52Joey:I think this part, I think it's in the model. I think the model itself has just more world training up to some certain point. I think that's in the model itself because also this isn't a parameter that you can turn on or off. This is, you give the model a prompt, it has a real world understanding. So I think it's just all the data that it's trained on, it just knows it.

9:14Addy:I mean, this is so solid for like, if you're writing a news article about Randy's Donuts and you forgot to take a photo of the place, you just generate it and add it to your news article. Sort of.

9:24Joey:I mean, it doesn't feel like that's open to the camera. That's not journalism at that point. Yeah, that's a slippery slope. People are doing it. I'm just saying, hey, I'm not a journalism major. I do not doubt that. Other one was the 4th Street Bridge. This was Nano Banana, which looks like LA.

9:44Addy:It's too clean. It's too clean. Yeah.

9:47Joey:But the 4th Street Bridge has the new ridges, the arches. My friend, let me school you on LA stuff. Is that incorrect? You are so incorrect.

9:55Addy:So the last one could have been either 4th or 3rd Street. Yes, they both look like that. But this one is 6th Street. And it is completely incorrect. those arches are actually slightly uh tapered and angled like this if you're looking at my arms not straight up perpendicular yeah so it got it not this one either oh i schooled joey out of la

10:14Joey:yes all right i thought i thought i just took its word for it no this is not right the prompt was the fourth street bridge in downtown los angeles a golden hour show the specific art deco concrete

10:25Addy:arches of the bridge spanning the la river uh you confused the model if you had said six street bridge with contemporary arches it probably would have nailed because the fourth street bridges uh yeah it's it's like 100 years old it's old but this one is brand new they just finished

10:40Joey:it like two years ago right i thought that was this one okay yeah it doesn't look like that all right okay so it all got it it's user error my friend don't blame the model but now let me go to um i'll talk about the current the the web search stuff so prompt was create a photorealistic editorial news photograph depicting the biggest news story in the United States today, February 27th, 2026. Nanobanata Pro had this, which is also a bit weird. It's just it's kind of generic, like protesting in front of the White House for vote and democracy, which is topics that have been relevant in the last year or so.

11:17Joey:But I wouldn't say like this could be used for any day of the week. Yeah, I would say it's just a bit too today. Yeah. Nanobanata doesn't have that option. So Nanobanata just made up something else. also kind of similar topical stuff over the past year or two. Nano Banana 2.

11:32Addy:Oh, wow. I mean, that's literally happening now, I think, or just happened.

11:35Joey:Yeah, it is. Bill Clinton in a congressional hearing with text in the background saying, House Committee on Oversight and Accountability hearing into the Jeffrey Epstein files.

11:47Addy:Okay, you've answered my question on how well-connected the Nano Banana model is to the Internet.

11:53Joey:Very well-connected. Yes. So this is pretty wild. This has probably been the best or most impressive use case to close everything else out of the water that I've seen.

12:02Addy:Dude, there are so many interesting things that can come out of this. If you have an image model that is fully aware of the latest and new cycle, you can automate YouTube content, for one.

12:14Joey:Yeah, I mean, you can do that. Out of the image, that's cool, too. I mean, yeah, you can still do that now. I mean, getting out of an image is pretty cool. because you could have done something where you have like a have an llm source the web and then create a text prompt yeah you can do it manually but yeah i'm not creative enough to like think of

12:32Addy:novel use cases but this is really powerful i appreciate that yeah one shot out of this from

12:38Joey:one text prompt with the web search turned on uh it's pretty crazy yeah and there's no bill clinton in your prompt it just kind of figured it out so that was yeah that was the best the best use case Yeah, overall, these were just kind of detail style outputs. More of a comparison, like this was a macro shot from Nada Banana, the original one. Here's Nada Banana 2. So a lot more detailed. On par, this was Nada Banana Pro.

13:00Addy:Oh, Patek, wow. I don't think Pateks have a circular shape. Yeah, I'm kind of getting into watches. I can't afford a Patek. Those are like$50 ,000. But yeah, this is pretty impressive that it got the font right for the most part. and i think the watch dial itself but um i don't think it has exposed gears like that i don't know i don't know if that center thing is real or like accurate i mean it says it here too uh let's see

13:26Joey:what i got fisherman portrait not this guy again this was not a minute one this is pro this is two i prefer pro you yeah pro looks a bit more realistic realistic but this has that tone map look yeah it looks like that kind of yeah that expanded hdr look but still way better than

13:46Addy:nanobanana 1 yes i agree so nanobanana pro is i think still by far quality wise the one to beat but nanobanana 2 is more agile connected to the internet and is able to do like a few has a few tricks up the sleeve that pro does not have yeah and i think for a lot of stuff i would probably

14:07Joey:now try Nanamanad 2 because it's like if you could do it and it's faster and cheaper then what do I need to spin up Pro for if 2 can already handle it?

14:16Addy:I think that's what Google wants you to do too is because it probably uses less GPU so it's cheaper for them on the inference side that's my guess.

14:24Joey:Yeah, I mean I think the official product name is Gemini Image. Flash. 3 Flash. Light or Flash, yeah. Let me see, text rendering this was original Nanamanad, this

14:35Addy:is two and this is pro yeah pro is closer much closer it has the the the chalk yeah like hand prints from the chalk but the two light bulbs are totally ruining it i'm sure you can remove that

14:46Joey:um but yeah okay and then what was this uh you did another test where you took an actual image

14:50Addy:i have a whole backstory and i'm gonna tie it to my theory all right so um turns out i have a rat problem in my backyard like my my neighbors behind my house they um it's a dirty backyard let's say So they're probably coming over to my backyard.

15:06Joey:So I go to Home Depot. I pick up this rat poison. You need to watch like Ratatouille and have like an appreciation for the rats.

15:14Addy:I love Ratatouille. Don't like the rats. I love Remy. I saw a lot of examples of Google's latest product, which is called Pomelli or Photoshoot. That is really dialed in for user-generated content for marketing and commercials. So instead of feeding it a really polished image of a product, you just take an iPhone photo of your product and then you could generate campaigns with it, a bunch of things with it. So this is an iPhone generated photo that I had in my phone. I ran it through Google Nano Banana 2, the new one. And if you go to the next image, my prompt was make a commercial for Decon Rat Poison where two rats are vacationing and they're drinking margaritas and they have this as a snack.

15:57and then the bottom it says rats like the taste so that's a little fun cute way look kind of

16:03Addy:ratatouille-esque like make the rats look cute and it did a decent job just based on yeah from my initial photo if you zoom in the the text is all correct it even put those little bricks onto a bowl like a snack bowl oh i guess some of my other generations did but yeah it's it's right

16:20Joey:there i mean yeah but the bricks are displayed it's got the little the light the line that goes there this is off center but that's probably yeah and it has a tile top instead of a wood top

16:31Addy:and then i i prompt more of my prompt went into that bottom text if you go yeah rats are spot on

16:37Joey:okay no i was looking at the rats because the rats look good and even like their little rat fingers are grabbed gripping the martini yeah the uh martini whatever that is uh margarita margarita glasses that stuff looks great yeah so the rats like the taste i want i said my prompt was

16:52Addy:bold font with a gradient and slight transparency so i kind of like 90 nailed it but the fact that i don't have to do a second pass in photoshop to add that text that's a huge plus so my theory is that the google pom pompelli photoshoot product is using nano banana 2 under the hood which is really meant for user-generated content specifically iphone or phone generated imagery as product reference. That's my theory.

17:22Joey:That sounds like a good theory. I mean, it makes sense that, yeah, maybe they had Nada Banana 2 under the hood when they rolled out the Pompeli product. I'll go to the product page in a second. And yeah, I mean, maybe they rolled that out. They rolled that out last week so maybe it was like a stress test and refined some stuff and then roll out Nada Banana 2 as the full product.

17:37Addy:So if I were to kind of segment markets if I was in Google and I was looking at go-to market, then I would say the Nada Banana Pro product is still geared for our world for film, television, and high-end usage with high pixel count versus Nano Banana 2, which is better for high volume of content with imagery that may not come in perfect.

18:01Joey:Yeah. And at the cost that is priced at per image, that also makes more sense for e-com where you're like, I need to do a bunch of product shots or variety or different markets and stuff. And so I need to like, I just want to make a lot of images. And so if it's more cost aware and cheaper, then that is a more appealing model. Yeah.

18:18Addy:And Nano Banana 1, I think, is just so far behind now compared to these two models. I think they're eventually going to sunset that very soon to free up GPUs. Yeah.

18:27Joey:Yeah, there's really no sense to... I mean, sure, it's slightly cheaper now, or like half the price of Nano Banana 2, but for the quality upgrade you're getting from Nano Banana 2, it's, I think, well worth it. I would say, yeah, I mean, also, the only issue here, too, is just like the... As we zoom into the text, it starts falling apart. But you're doing this in the Gemini app, correct? so you got the Gemini output or did you use this somewhere else? I think I used FreePick.

18:50Addy:But yeah, I mean, I wouldn't expect a different result.

18:52Joey:Were you doing 1K or were you doing 4K? 2K. Okay. So also 2K can go up to 4K. So maybe if you did 4K, I'm curious how it would do. Like the refillable word, it looks like refuckily. Yeah.

19:06Addy:Yeah, garbled it a little bit. But like the shape of the package is spot on, man.

19:12Joey:Oh, I know. And this top part, it got nailed in the dead mouth.

19:16Addy:Yeah, I mean, my photo is not the best, but it kind of recovered detail from it.

19:20Joey:Your photo is like a weird angle with like glare. You tore the top off.

19:24Addy:I was ready to kill those rats, you know?

19:26Joey:Like crap. Yeah, this is a crazy demo. I mean, look, we're thinking of this image from like a year ago. You're like, here's a crappy iPhone photo of my product. Make me a, you know, a good ad. And you got this, you'd be like, your head would explode. Okay, exactly.

19:42Addy:And two years ago from today or three years ago, the only way to make this would have been either in CG, you build a pool and put the rats on a patio chair and da-da-da-da, or you have a 2D artist come in and composite the entire thing. And now we can do it in seconds.

19:58Joey:Yeah, it's crazy. Let me switch back to share. I'll share that. So yeah, here's the Pompeli. Pompeli, yeah. I think it's just called photo shoots now.

20:06Addy:I'm not sure.

20:06Joey:Google's naming convention, man. You guys got to figure this out.

20:09Addy:But yeah, this is the product I'm talking about. It's basically like single image to full campaign automation, where it'll generate PDP, product detail photography, as well as product in situ, in situations. And I think it's able to then generate it in multiple formats. So 916, 169 aspect, whatever ratio. So I think it's going up right against Adobe's product called Gent Studio. So it's like two giant tech companies trying to figure out marketing automation.

20:41Joey:That plus there are like a million startups that are also trying to do this. And I remember seeing all the posts like Google just destroyed a bunch of startups.

20:48Addy:And this is really like now that I'm in the marketing world now and I'm trying to understand how they are operating like this. This is putting a lot of fear into a lot of people's hearts. It's like, oh, do we do we need to exist as an agency anymore if somebody can just do this on their own?

21:04Joey:If the brand themselves can make thousands of assets with every variation of market and stuff that they would need in one go.

21:12Addy:Yeah, I think to counter that, my response would be, of course, you still need an agency because it's not just about generating in quantity or generating multiple variations. It's about curation of assets. It's about an overall creative arch and having targeted creative per region. And a lot of that expertise only exists in an agency.

21:32Joey:yeah i mean it's just maybe i think you still need an agency it's just the agency will probably

21:37Addy:be a lot smaller than it was in the past yeah and more specialized all right anything else

21:42Joey:that's it for now i'm waiting now uh i mean if there's a nano banana nano banana 2 there's got to be a pro pro pro 2 coming out at some point so you seem like a pro guy to me you have a macbook

21:55Addy:pro yes now to banana banana pro you're a pro editor clean pro final cut pro seem like the

22:04Joey:pro guy resolve yeah to resolve this studio resolve not resolve it doesn't do pro all right

22:09Addy:what we got next okay let's talk about ai agents my favorite thing okay so yeah we talked about

22:15Joey:open claw uh a few weeks ago and uh i'm still in my open claw experiments but we talked about how Like, you know, and it was called ClaudeBot. Anthropic's like, please don't call it that. And then he calls it OpenClaw and then he gets hired by OpenAI. Meanwhile, Anthropic has not sat idly by. So they launched three, they've been launching updates like every day this week, but they launched three updates specific that kind of tie into what OpenClaw is doing. One was remote control. So basically, if you spin up ClaudeCode, you know, it runs in terminal and it's very powerful in what it could do, but it was sort of like you're kind of sandboxed into what you were doing on your computer.

22:59Joey:Now they have a remote control feature where you can run Cloud Code on your computer and then log into that session from any other web browser or your phone and continue what you were doing on the computer. So if you're using Cloud Code as not for actual coding, but like as an assistant or giving it access to stuff on your computer, Now that leap that a lot of people liked with OpenClaw, where you could kind of run it on your phone, now you can do that with CloudCode. So that was like one feature that they added that was a... So is it like an iOS app? It's not an app. It's either, I mean, it basically, they already have the Cloud iOS app.

23:36Joey:So now you could run your CloudCode session on your iOS app. But you're basically still controlling the actual session on your computer.

23:43Addy:You're just remotely connecting into it. It's just much better than like WhatsApp.

23:47Joey:up it's uh basically the way open claw works is it's running this thing on terminal on your computer that you're leaving it run all the time and then you're porting in to talk to it either via terminal or whatsapp or discord however there's like a million options of how you can set up to talk to it and a lot of people liked that feature of it where you could talk to your ai your personal ai bot that's running on your computer via a phone so now with cloud code you could do the same exact thing without all of the extra open claw setups if like running an ai agent on your phone was like very appealing to you now uh clawed added a feature where it's like super easy to do and you don't have to do open claw if that was one of the main reasons that attracted

24:29Addy:you to open claw was the phone thing so it's your very own agent that you're running at home

24:35Joey:available to you everywhere you go yes in a much more elegant package than like messaging it kind Yeah, it's still a very specific use case if you were using Cloud Code as an AI agent on your computer. Now you could talk to it. You don't have to be on your computer to talk to it. You could talk to it via your phone or another web browser.

24:56Addy:Right.

24:56Joey:That's one feature. The other features that they launched were memory inside Cloud Code. So now there's better memory features, which was another thing with OpenClaw, whereas you keep using it. It kind of remembers patterns and things that you like. So now that's also built into Cloud Code. So sort of another feature overlap from OpenClaw. And then the last one was schedule tasks. This one's in CoWork, which is separate product from Cloud Code. It runs in the Cloud desktop app, but it's sort of like Cloud Code Lite, where it can still do things on your computer. But now you could schedule things to happen.

25:29Joey:So this is also the main thing that OpenClaw does under the hood that is like very simple, but very powerful, is that you could talk to it via sort of any other device. device. It's just a bunch of like M markdown documents that set up its memory and instructions. But then it can also run crone tasks, which is just basically like a piece of code that runs at a specific time. And the crone thing is like old school and simple, but like actually really useful for AI agents where you could just every morning have it be like, you know, check my inbox or like run an analysis on this or just have these recurring tasks.

26:02Joey:Stock market stuff. Yeah, you can't do in Claude code. You can't set up Crones to like run in Claude code. But now Claude added this feature in their co-work product. And now it's just like another feature grab, like all these little things that were attracting people to open Claude, the tradeoff being you're using this highly experimental product that can like go off the rails, is like one by one being added in Claude, added in Claude, added in Claude. So slowly, but not slowly, this is over a week, quickly, but surely they are adding more and more features that kind of put it on par with some of the benefits people were getting out of OpenClaw.

26:37Joey:And Claw is already a much more refined and developed product. Let's take a step back.

26:44Addy:Correct me if I'm wrong, but from what I'm understanding is now that OpenAI acquihired the OpenClaw guy, and most likely OpenAI is going to re-release OpenClaw as a paid product, but way better, and da-da-da-da-da, Claw is anticipating that competition and now they're retrofitting cloud code to compete with this upcoming thing in the future. Is that right?

27:04Joey:Okay. So yeah, my understanding with them hiring Peter Steinberger, they didn't acquire OpenClaw. OpenClaw is still an open source product. He's still actively developing it. There is like a new update every two days for OpenClaw. So it's still actively developed and pushed. My vibe of that is just like OpenAI wanted to support it, hire him to keep developing it. And it's like if more people are using AI agents and are using open AI models, that's good for open AI. I don't think they acquired that or are going to roll it into like being an open AI only product. I'm sure they're building something separate that has similar features that, you know, would eventually roll out and be more, you know, user friendly for a wider market.

27:46Addy:Yeah. So you think just it's not like a wall garden per se, it's just like a really

27:51Joey:compelling integration i think the open claw thing just sort of on or just awoken people to that like people want some sort of like ai agents that are more integrated in their computer smarter kind of learn from them powerful uh and not piecemealing different little chatbot steps along the way but something that's more holistic and integrated and that the tech is getting there microsoft missed a boat on this big time right because i think yeah copilot was going to

28:20Addy:to roll into windows and it was going to essentially uh take over your computer for whatever that means and the open claw is that right and i think it's linux space it's it's

28:30Joey:open source and all that good stuff yeah you can kind of run it and integrate it into into anything

28:34Addy:you know at your own risk right now yeah it's interesting yeah back to the other uh the initial

28:41Joey:open claw agent thing so the other product launch that ties into that space is uh from perplexity perplexity computer. And so this is basically a virtual machine computer that can kind of connect to all like your email, all of your like web platforms and is, you can spin up sub agents, you know, you can give it a task recurring thing. So it's sort of this like central virtual AI computer that can automate and connect to a lot of stuff. It's only for the Max plan. I haven't really dabbled with it.

29:10Addy:They're all competing for that same market, right? It's the local, kind of local thing that lives on your machine? Well, this is web-based.

29:20Joey:So this feels like it kind of lacks the appeal of OpenClaw because it's not on your system. I don't know if it has a local... My impression was it was like a virtual machine. So I don't think it can connect to your local system. It can just connect to all of your cloud services. So it felt a bit like Manus, maybe like a little bit more powerful Manus that could kind of spin up a virtual machine

29:43Addy:and do automated tasks that MetaBot.

29:47Joey:So yeah, it's still in that same agent space and more powerful space, but I don't think it could do local computer stuff. But yeah, just another product launch into the world of, you know, I think AI agents unlocked a lot of things. Yeah, I mean, look,

30:00Addy:you're way ahead of this stuff than I am. Like you're experimenting with OpenClaw now, obviously. So yeah, you tell me and the viewers where you're at and how this world is evolving. Very curious to hear it.

30:12Joey:So one of the bigger questions with OpenClaw has been terms of service and if you're allowed to connect OpenClaw to any of your subscription plans, if you have like OpenAI Codex or CloudMax or Google's version, which I forgot what it's called. So once I connected it to, I switched from paying for API, which is really expensive from Cloud to, I tied it into my CloudMax plan. So it's using my same monthly subscription. So that's made it much more appealing. It has been debated. There have been different stories of some people saying they got booted off of CloudMax from using it, that it violated terms of service.

30:52Joey:But then some other people at Cloud have posted on X saying that they just don't want people to use CloudMax for business purposes, where you would be using the API. But if you're using it for personal development or just kind of app development or OpenClaw, that fits the use case. So far, fingers crossed, I have not gotten booted. using it that way and not having to worry about like the daily cost of tokens has made it much more appealing and it's been good for um moving and consolidating some stuff that was already set up with uh like zapier automations um it's streamlined that a lot more as far as like writing social media posts a lot of the web articles and newsletter stuff so it's been handling that and I'm still, the next kind of phase is like something that could chop up these videos and turn them into shorts.

31:41Joey:That's been my, that's been my next question.

31:43Addy:Speaking of which, and you're no stranger to Eddie AI, premier guy who I follow on YouTube. She's probably the biggest premier influencer. If that's the thing, she had a big endorsement for Eddie AI. She liked it a lot. So just thought I'd let you know that.

31:57Joey:Yeah, that's good. Yeah. I was literally using it yesterday. They do a lot of updates and it's on better even it gets better every week i did ask him i'm like do you have api connections he's like it wasn't really on our map right now because my thought was like if i could plug this into any ai it could maybe help cut up some of the shorts but i don't think that tool would work i'm looking at some other tools that that might be able to uh help with that but yeah that's my my goal with this is like if there's a ai agent that could kind of monitor social media and knows all of our videos and stuff and can pull clips and post stuff and learn from how they're received and then learn the editing style and improve on what clips it pulls.

32:38Joey:That's my goal project for this of an AI social media agent that can pull from our library of content and stuff. That's an interesting goal. I like that. Still in progress. So far, some stuff's working out well. I have not had all my emails deleted, so that's good too. run unplug it so he did in one of the product updates i think he put in a uh an update that says if you say stop open claw then it will actually stop like oh like a like a hard reset button or a stop like a hard like a hard uh like kill switch like kill switch is still software you need a hardware kill switch to explain this there was someone who posted on x who's also the chief safety officer or one of the top dogs at meta.

33:28Joey:Gave OpenClaw access to her emails and was having it delete emails, which I also think is kind of crazy because I just wouldn't have it archived. But then it forgot the context and just started deleting all of her emails. And the only way she could get it to stop was to unplug her computer. She was running to it, literally. In the threaded replies, it says that OpenClaw compacted the conversation and so forgot what it was doing. And that was why it went off the wall. That's why this stuff's experimental. So, you know, be careful. All right, real quick. Two new model launches that I saw that were kind of interesting.

34:04Joey:One is Quiver AI. So A16Z-backed company that is focusing on generative... Vectors. SGGs. Vector graphics. Generative vectors. Their model is called Arrow 1.0. Okay, that's great. I think it's cool. Yeah, that's great. Because last week you turned me on to Reframe and I was messing around with that. And having AI vectors is nice because you just don't have to worry about resolution. Exactly.

34:29Addy:And then you solve the print issue. So when things go into print, it's all splines and lines at the end of the day. Yeah, I think the technical difficulty here was that image models work in the latent space and come out into pixels in the variational autoencoder. and then it goes to another step where the pixel space stuff is converted into vectors like that's how it's generally done i think they may have solved that problem by going natively out of late space into vector space which is very novel and innovative yeah it looks great yeah yeah and for logos and things like that you don't need like a bonafide nano banana pro level image model like you're generating stuff that's abstract and you know cliparty anyway yeah yeah and a lot of

35:18Joey:times those logos that you spit out of like down to Manhattan are just so over the top and coordinate and crazy yeah there's like it doesn't work that's why ideogram is such a good model like it's dialed in for this kind of stuff yeah and then other model there's a new video model called p video from pruna ai and uh they're i believe one of the only one of the main european labs to ship a uh decent video model and i mean i've looked at some of the samples you know i'd say it's on par with, I don't even know, like a LTX or a wand. But yeah, I mean, the main kind of things from this, the quality is pretty good, but what you get is like pretty fast generation at pretty low cost.

35:58Joey:So 10 second generation speeds for five seconds of 70, 20p video, two cents per second. Hold on, did you say 10 seconds for a five second video?

36:06Addy:That's really impressive. That's their post rate. Yeah, so it's fast, it's fast and cheap.

36:11Joey:And it has a draft mode for video, multimodal. It can do audio outputs and stuff. So overall, you know, it's pretty good. It seems like a pretty solid model. I was trying to look at some of the test clips. They have a lot of animation stuff with speaking characters. So, yeah, you know, I always like to throw this stuff on the radar because depending on what project you're working on, some models might be great.

36:28Addy:Yeah, I call this like the preview window model stuff like this. We absolutely need it. You know, when you're ideating and you want to do it with videos and small animatics and things like that, you don't want to wait five minutes. Ten seconds is perfect. and then just keep rolling the dice and it's cheap and it's going to speed.

36:47Joey:I, you know, that's the big trade off with Automata Pro. And when I'm thinking back to our Laura reference showdown, like Z image quality wasn't on par, but like seeing the speed of stuff coming out, I'm just like, that's actually pretty nice. Like, how can I incorporate some of that into the workflow? Because just being able to like iterate and not have to wait around 30 seconds or a minute is it gets taxing.

37:06Addy:Yeah. And multiple sessions, multiple tabs doesn't really solve the problem because you're still waiting a few minutes per session.

37:12Joey:Yeah, so that's a good point. Speed is good.

37:16Addy:Speed kills, man.

37:19Joey:All right. Good place to wrap it up. Links to everything talked about at denoisedpodcast.com.

37:24Addy:Hey, you remember I talked about the YouTube high points? Well, give us a couple of high points. Actually, I think 750 is the minimum that you can give us. That seems to really help boost our videos on YouTube. So yeah, it's on the app. If you go to the bottom and scroll to the right, you'll see a little party icon. I think that's the hype icon. Give it a go. Thanks for explaining that. I don't know what 750 hype points are. It's a new thing YouTube rolled out. It's like you can like a video or you can hype a video. All right, hype it. Hype it up. Thanks, everyone. Catch you in the next episode.