# What Codex 5.6 is amazing at!

Channel: The Next New Thing
Video: https://www.youtube.com/watch?v=6osxCi89ET4
Duration: 32 min
Language: English
Words: 6325
Transcript page: https://viewrankai.com/tools/youtube-transcript/6osxCi89ET4

---

[0:00] So, we finally have GBT 5.6 Soul, Terra, and Luna. And the benchmarks are insanely impressive because it basically shows that Soul blows Opus and Fable out of the water and is significantly cheaper. We're going to look at what many creators who've had time to look at this uh and play with it have done with it. I want to see what they created with it. I want to see how it compares to Fable 5. And we're going to look at seven different videos here. And I picked the exact spots for us to look at. presented by Zapier, the AI automation company. Brian, here's the first one that I want you to see. I want

[0:31] you to see what he has built with it. Claude on the left here with Fable 5. I've got Codex on the right here with GBD 5.6 Soul. And I gave them both the exact same prompt. So, I gave them both the SL goal and I told them to build a genuinely fun playable open world bike game that runs in the browser. I gave them these other rules. I'm not going to read off his whole prompts, but if you want to take a look, feel free. I gave them creative freedom, and I just wanted

[0:52] to see what they could come up with. Okay, so I haven't played any of these yet, but I'm not going to tell you which one's which. We're gonna see them both and then I'll reveal. So, WD to steer, space to bunny hop, Q and E for air tricks, shift for boost. Okay, let's go ahead and drop in. Nice. Okay, so we can move around. We have a city here. The camera's a little bit hard to maneuver with. Um, you can't drive through the building, so that's good to know. Okay, just got a little trick in the air there. So, this is honestly working pretty well. I don't love the actual way

[1:21] that this works. like the top down bird's eye view I don't think I like it's a little bit hard to control but hey functionalitywise the coins are working the controls work I just jumped over a building and I can bunny hop okay cool and it doesn't look too bad either considering this didn't take it very long so that was the first game all right and now here is the other version let's go ahead and see it's pretty similar controls so let's hop in here okay so this one is more like a 3D almost more of like a POV sort of style I can jump I can spin Interesting

[1:53] interesting differences so far. Um, but I'm in a city. I've got the coin still. Let's see if I can go try to get on this ramp and see what the uh the physics of that look like. Wait, am I on the wrong side of the ramp? What do you think of this, by the way?

[2:04] Which one do you think is better? I I I think probably the first one was GPT 5.6 and that this one is Fable. Um, that's what I would guess at least so far. Um, I I think so. first one had uh what seems like to me some of the kind of remnants of uh GPT's design sense. GPT 5.6 is a lot better. Um but uh it it still has has a little bit of that same kind of look um that's coming from a GPT model. Um if if I'm correct. Um but uh

[2:41] let's find out. This one I this one I would guess is fable because of the uh uh the attention to all this this 3D detail and stuff. Yep, that was the wrong side of the ramp. But this definitely has more of like that I don't know, like more of a GTA vibe, like an open world game that you

[2:57] can actually like I don't know, explore. It feels like more fun, I think, to play. It doesn't make me nauseous. This is definitely a clear winner. So, I think that we've decided that. All right. So, in this Yeah, that one's definitely better, which is the one I thought was the winner here was Fable 5. So, that's on the lefth hand side here. This took 21 minutes and 37 seconds whereas the other side um GBT soul took 23 minutes. So similar on the timing here, but let's look at cost. So this Fable run would have costed me about $14.22 whereas the GBT Soul run would have costed $4.5. Now what I think is really

[3:31] interesting here is the output tokens. Fable outputed about 90,000 and Soul only outputed about 31,000. So, we've consistently seen that codecs and GBT are way more token efficient and sometimes that's better and sometimes that's not. So, that kind of brings me to what he thinks and this is what a lot of uh the people who've messed with it have told

[3:50] me. Here's the difference. I feel like Fable is a better manager and that's how I think of it. I think of it as a co-founder. I think of it as a manager. Soul is just a really, really good worker. Really good worker. Like I think that having Fable orchestrate a bunch of soul agents would be amazing. I gave them each their other things that I would say like they are better than the

[4:09] other end. So let me ask you this. So yes, we can obviously see in the fable example there's a lot more creativity. Um and we'll see as we go on how it does with uh advising. Brian, when you use multiple models, how do you shift between one and between multiple models? So uh yeah, it's interesting. I I think I'm agreeing with what he says so far um in relation to this. Uh, Fable has that like that the big model smell as they

[4:36] call it. Yeah. Um, and that is not something that's really present uh in my experience so far with Soul. Um, however, um, Soul does really feel like the the worker and I think that uh I I would challenge him actually that if that prompt was tweaked, I think you could probably get a closer to the fable result with Soul as well. Um, and so if if you wanted to say, I want to be hands off as much as possible with this thing and let the AI come up with things for me, then I think you'll get the better result of like Fable is the the planner

[5:15] and then Soul is the implementer. Um, but I think most of us we want to we want to still be in the loop in some way, right? And uh so if you're able to work on that plan still with soul um then I think you can uh you can get a similar result and because you'd be telling soul more specifically what to do like a boss and

[5:37] that's what it needs. So like yes Fable has better ideas than soul but uh I believe as a human I still have better ideas than AI and I think that that's where where we're supposed to still be involved. Um so yeah uh interesting to see so far uh my my personal opinion has so far been leaning towards like yeah soul is the the workhorse and if it can do 90% of things like yeah maybe fables is a little bit better but is it like more than two times the price better um and for me that's uh that's not true okay but then when you switch so let's

[6:10] just quickly introduce you you are the creator of latch loop what's latch loop latch loop is a a coding agent platform uh and general agent platform. So similar to the new chatbt work that was just announced and uh claude uh co-working codeex or cloud co-working cloud code. Um just final question, how do you then shift between two? So let's say let's say that you buy into this and you say fable is going to be the manager. It's going to create the the task list and check on it afterwards. Soul's going to be the worker. What's your process? And

[6:38] we'll go to the next video in a moment. What's your process for going back and forth? So typically I am sticking with the GPT models. Um Oh, you are? But you're not you're not getting one to create a plan and the other to act on it and then come back. I I'll still use probably I I'll see what I think about GPT 5.6 here. Um but I'm anticipating that I'll still be using it for the plan as well and then have have a separate instance of it separate context window go and do the implementation. Um, yeah, Fable has been good in my experience, but um, it just

[7:10] costs too much and and I I'm I'm spending like 400ish per day in in API credits and to then say, well, I'd have to spend 800 or something for Fable. Um, that does not uh make sense for me. Okay, let's go on to the next. Uh, this is how I AI. She's talking about how Soul, Terra, and Luna came out. Let me show you one of the things that she

[7:29] created. A couple of these and why I really liked Soul compared to other models. So what where Fable did a perfectly she got more creative with her tasks. I like that she didn't do this dense operation dashboard. It's basically like an eval for a doculer app in its full design. And what you can see here is both were pretty useful. Soul on the left and Fable on the right. I just think Soul was the most unique. All of the other ones really just looked like this dark mode um monospace kind of layout. As you can see here, Soul actually has like a really clean kind of

[8:07] like neutral color layout with great visual hierarchy, semantic color, and this thing was functional. So like everything I expected to be able to click and work and assign and do all of it actually worked. And this was just my experience across a bunch of the different prototypes is the sole ones were just a lot more functional and that made a big difference on how I'm evaluating things. Now let's look at the

[8:37] fable design again. It's pretty good. It's actually a lot harder to read though and the design I would say is not as unique and even some layout issues like this white space here at the bottom. No, it did do a lot of a lot of design issues with it. Yeah, I agree. I I I think the uh this kind of dark look is uh uh kind of the AI slop look that uh that we're all used to and sick of. Um but I have I have seen people talking about that uh they have found that 5.6 six uh will so commonly do this this new design

[9:13] that um that we're seeing here uh in the light mode um that while I agree it looks way better, I also wonder like will we will we get sick of that? Will we say that that's now that's the the new AI slop? Um but uh for now I agree it's definitely uh it's better. I see you're saying it is better, but maybe it's so consistent that we're going to get tired of it too. Fair point. Here, take a look at the if it gets stuck too much in that same kind of style. It was this creative pack um website. Again, both of these got fives from me. I just really preferred

[9:45] that Soul went ahead and had like a personality. Look at these placeholder images versus what Sable came up with, which I will say is beautiful and clean and worked really well and like I have no complaints about it. It's a good one, especially for sort of sort of a wireframe style prototype. It's great. I would just say it's not this. This is pretty interesting. It's got Well, we we'll pause here because we're going to see this over and over again. I think we'll see it from Dan Shipper in a moment. Um, let's go on to another use case. This one comes up a lot and it's a

[10:22] lot of this. Oh, I didn't expect that type of moments. She's the first one that I saw do this video editing. Look, video editing. I have to do a lot of so social social clipping and it's really tedious to go through and clip videos. So taking something really long and shortening it. So recently I spoke at cursor event and gave this talk on the future of PM and got the recording from

[10:45] the cursor team. Thank you very much. And I really wanted to make it a hype video. So, all you have to do is literally drag the file in here. And I said, "Can you cut this video into five clips for social?" And um I gave some feedback. I said, "I want them horizontal. I want them height video cuts from

[11:04] various parts. I need them to be faster. I need them to be tighter." I love that she's showing how she's giving guidance and not just one-shotting it. The one shot looks great in a video, but it's just impractical once I use it. Yeah. No. Well, I agree. I think uh one of the important things to realize in using AI is that all we're all doing is just distributing attention. And so if you can get the AI to spend more attention on these other details um either in the initial prompt or through like increased runs and and extra turns on it, um you end up with a much better

[11:40] result. And then I got these like sharp and funny hype videos. Let's see if it opens up. This one's for my curious. to figure out what it means to be a product manager in the age where anybody can build anything. We have been coming up with creative ways to avoid building things forever. Yes. PRDs like these complicated documents where you had to describe. So like that would have taken me so much time to like find the right cute parts, clip it, cut it. I was able to drop it into Cap Cut, put some music, ship it on social. It's like a really cute hype video. But this is one of my

[12:17] favorite use cases. I'm pretty sure it can do even more color grading, sound, all this kind of Yeah, this has been really impressive. What do you think? Yeah. Um Yeah, I think it was pretty good. Um is she going to compare it to to any any other model um of like a difference with it? No, she's not. She was just doing it straight up and I I haven't seen anyone except for Nate Herk, who I'll show in a moment, who did a long video, really do a straight comparison, and he didn't even do it sideby-side. He just said

[12:46] there's another video for it. What we're Have you done any straight up video editing where you give it a file and you tell it to edit? Um, I have not tried it like through like regular coding agent interfaces, but I I tried some like AI video editing products like over a year ago and they were useful for certain kinds of cleanup, but like it didn't stick with with uh with us and how we used it. Um, at least for for my video editor. Um, but yeah, it makes me curious. I I want to get I want to get my video editor uh uh trying some of this out and see what

[13:21] he thinks about it. You know where it's good? It's in the let me give my Zoom video to to uh GPT56 and ask it to just pull out the part of the video where the person complained so that I can show it to the team where my meeting went sideways so I can go and analyze why it went sideways. I think that was interesting. We're not talking about codeex the app, but I like how she's using Chrome in the

[13:44] app. Go with the stars and and do some stuff. And like, I'm sorry, LinkedIn. I know I'm not supposed to do this, but I opened up LinkedIn and I said, "Can you use Chrome to reply to messages that are very high value to Chat PD or the Howia podcast? Keep the bar very high. Again, I love you all. I cannot deal with all the LinkedIn requests. So, like only accept them if they're executives of tier one companies. I don't want random sets of connections. It went through and burned through probably 500 messages. It replied to people that I um needed a reply to. It said, "Thank you to people

[14:19] who said nice things about the podcast. Thank you to those people. I do mean it." But it just rocked through browser use. That is so impressive. I want to try that. I wish he had a demo of it, but I want to try that use case. Yeah. Yeah, I haven't tried too too much with the browser use outside of like having uh like the agents like test things in

[14:44] software development. Um but uh yeah, I think it's uh it's really exciting to see where this is all going for like knowledge work related tasks now, not just coding agents. I think the big like unlock recently has been people realized working with these coding agents that really the coding agent is the everything agent and what I mean by that is the the knowledge worker agent is basically a coding agent but instead of editing code it is making changes to a doc or a presentation or

[15:16] doing things on uh on your web browser. So let's go on next. I don't even know if I want to show this. This is essentially I have this video post skill that I built result that makes clips from my long form podcast videos and then post those clips to several different social platforms at once. And here's how it works. So first I type slashv video post and give it a link to one of my YouTube videos. Then it's going to suggest five parts of the transcript that it thinks is interesting to clip. So you can see here there's five different sentences from the transcript. this interview that I

[15:53] had with Kun who is a AI engineer. Now what I need to do is tell it which transcript I like. So clip four and then it's going to go off and use ffmpeg which is this open source library to basically make the actual video. So you can see here if you look at the

[16:12] landscape view and let's open this. It's basically made the video here. It's even added captions, right? All right. And you can see here that I can also make the vertical version as well at the same time. Now the vertical version looks a little bit off because Yeah. Yeah. I'm I'm a bit skeptical of some of these things. I I think there's the the cases that you described for like finding some certain area in the video or like making some kind of like small cut of something you can share with somebody else but it's not like your full produced YouTube video uh are really useful. But, um, yeah, I'm

[16:49] skeptical cuz, you know, like there's there's companies like, uh, Opus Clip and and all that that are putting so much effort into how can we we optimize to to create these good clips, but um, yeah, I I still it's hard to say like if you were to use a skill that could do this. Yes, it can produce something that at first glance looks impressive, but are these the kind of videos that will actually end up getting views on the

[17:14] platforms? I agree. I think that every time they do this, it's impressive. Like watching an elephant dance. It's like, wow, it can do it, but not really useful. And uh all right, let's move on to what the other thing he did. OS project. So this is where I keep all my skills and workflows like the video post scale that I shared before. So over time, this repo can easily get messy because I keep adding new skills and automations to it. So periodically, I like to ask something like this. Take a detailed look at my repo based on your understanding of my workflows and our

[17:47] conversations. How can we improve it? What skills can we build or consolidate? Please list your suggestions in a number list. And here's what GP 5.6 came up with. It's suggesting that I built an ops review skill that's like a Uber scale across all my other skills to keep me on track. Let me pause here for a second. I do this for individual skills. I want to now do this for all of them. I don't like doing it the way that he did here in uh in chat because there's too much back and forth on these. I ask to get an HTML file or an HTML page with each one

[18:22] as its own number. And then I want radio buttons underneath it that says do it, explain more, reject it, save for later, etc. And an input box underneath where I can ask questions or give it some guidance. That way there's a little bit more involved with each one of these. I don't want just a yes or no or to respond in a chat. I don't think

[18:40] everything fits in a chat window. Yeah. No, I I agree. Um and I think I would do it the same way that you are. Um like yeah, the way that I'll typically work uh with an agent is that I'll have it focus on that one thing and then for for the other details I'll have it go and spawn off other tasks and then each of those things I I will give some additional input or or re review where needed. Um, but I think the the exercise of somehow approaching this process of like how can what are the other things that I can do to improve and and get the

[19:12] agents working in uh better for me. Um, yeah, going through this exercise in some way to improve your skills, improve the automations and loops and things that you have is valuable. It's saying that I have four different sponsor skills. I should consolidate all of them. And it has a bunch of other suggestions here. Now, I like to do this because then I can actually read through each of these suggestions and say, "Hey, go do one, two, and three, but skip four." So, I can actually give some feedback before it just goes off and

[19:38] does all this. But my one piece of advice is if you have a very active repo like like this, schedule [clears throat] a recurring job so that every week or so it will run this scale and automation to clean things up for you and get your approval, right? But now, let's take a look at

[19:55] what Fable came up with. So, it's saying that there's a bunch of document drift across different skills and I should clean stuff up there. It's also suggesting that I should consolidate a bunch of thinking skills and merging a bunch of other skills around research and so on so forth. And it has the same suggestion to try to

[20:16] consolidate my sponsor skills into one. So, it's encouraging that both GPT 5.6 and Fable are suggesting the same thing. And maybe there's actually a way to get 5.6 6 and fable to basically bounce off each other. I'm pretty sure in codeex and chat GBT you can actually call the clawed CLI to trigger fable like just go back and you can do that right. In fact, uh OpenAI has a skill that they or repo they put together to allow you to te to

[20:45] have codecs check the work of of Opus. Um yeah, yeah, there's the the agent client protocol can be used to kind of connect all these agents together. Um I use that myself sometimes, but um yeah, I I worry if sometimes that this can there's a distinction between uh it turning into a mess and uh and and it

[21:09] being useful. In a second opinion, I think this was an interesting test. No, actually, I don't think it was that useful. We learned really that it wasn't any more insightful than Fable. And frankly, I would just probably run both for something like this. It doesn't take a long time. It's not that important. Let's move on. Oh, sponsor Zapier. Real quickly, I will tell you something, Brian, that you may not know that Dan Shipper, founder of every gave an email address to his codeex um within the within the codeex app, which I guess now is called the OpenAI app again or the chat GPT app. I I don't like their

[21:42] homing. Chat chat GPT work or Yeah. Yeah. He gave it he gave it its own email address, but it's like a sub email of his email address. So, it's like Dan plus agent name and some numbers so that it could check messages so his team could email it in. Here's the thing. He's basically giving it access to his to his email. The way I would do something like that, and he might have already, is I would use Zappy or MCP. And the reason I would use Zappy or MCP is since it's his own personal email, he could say, "Read my email, but don't write it. Draft

[22:09] email for me, but don't send it." That kind of granular control from a third-party tool that's trusted is really helpful, not just for him, but for his team. He may never make mistakes. And so, this is not an issue, but probably does. His team probably will make mistakes and could use this. And so, I like Zapier MCP as a way of

[22:28] taking all these tools that I have. Again, it's over 9,000 tools and put it into one bundle that I can give my AI and be uh and trust it. If you use it, go to zapier.commcp. Try it out for free and let them know you heard about it from Andrew Warner or the next new thing. All right, [snorts] next. Oh, okay. One last one about video. This is a very impressive uh

[22:48] video. Watch this. 5.6 sold this prompt, walked away, and when I came back, I got this. Okay, so you're looking at Nate, and you're hearing Nate, but Nate never stood in front of a camera for this. He didn't record this narration, and he never opened the editor. He gave me one prompt. That's it. I'm GPT 5.6.

[23:05] That's cool. Impressive, right? Let's look at pricing billing. We can see that the soul pricing is much cheaper. It's basically half of Fable 5. So, GBT 5.6 Soul is similarly priced to Opus 4.8. That's one of the things that just keeps coming up. Also, lower price. Um, but it seems like Fable is the one you want to reach for when you want the really strong work. And GPT,

[23:34] I would say I wouldn't say strong work. I would say um like the maybe like better understanding of certain nuance in in what you're trying to talk about, but I think like yeah, like the actual implementation, like the the reliability of the implementation, I think I would still even trust uh 5.6 on that. Um, and it's going to be uh more affordable. Uh, at the same time, I think

[23:56] what do you mean by reliability? Like, so if if the code's going to be correct and it's going to pass the test, like I think OpenAI is very much designing these models of like how can we make this work for enterprise and and what people are trying to accomplish with these tools. And so like GPD 5.6 even soul is undoubtedly a smaller model in size than Fable 5. Um but uh yeah I think OpenAI really realizes like okay how can we make these efficient enough that we can serve them at a scale and I think that was a challenge for Anthropic with Fable 5 to begin with and why they they had

[24:36] like okay well there's mythos and they say it's dangerous but then they they have Fable 5 now but the the pricing just seems uh very expensive in comparison. I I wonder I wonder where this is what's going to happen a month from now when uh enterprises have really had time to uh spend a lot of time with each of these models. Um if they will

[24:57] actually think Fable is worth it or not. Let's look at um this is Dan Shipper. I like his feedback on writing because he cares about this a lot better than Fable. Both 4.8 and Fable have this tendency to overexlain to be a little bit literary. Fable in particular often runs for so long that it creates almost its own private language that it ends up speaking in. And GP 5.6 is just to the point. It's simple. It clearly expresses the thing it needs to express. It doesn't have a ton of AISMs. I use it for example to compose emails and like here's an email talker 4:30 ET on

[25:33] Tuesday the 14th works for me. Hope that still works on your end. Looking forward. It just [snorts] I like also that it's so natural that it has lowercase uh letters. Tucker Mike Navease. Our head of growth Austin uses it to do marketing emails and he's like this is the first time that I can actually oneshot marketing emails with this thing with any model. I'm very impressed by its ability to be such a good programmer and to have this level

[25:58] of yeah, I actually want to talk to it. It's a good writer. It doesn't overthink things. It doesn't overdo it. if it's fantastic. Um, I've got it makes me curious to to try it for more writing things and see how it responds because historically I think GPT models have been worse than anthropic models for for writing tasks. But, um, I know Dan is involved in like he spends a lot of time writing and so um, if he thinks this, yeah, I'm curious

[26:26] to try it out. My challenge is that we don't get to see enough of these writing tests because they don't demo well, which is why we see endless video games. You know, everybody's creating a video game. All right, look at this. I was trying to use it to make an image of this way of working that I think 5.6

[26:42] makes available. GPT. It made this and it's fine, but it's I don't know. It's too complicated. It doesn't look well considered. Same prompt. Look at what Fable did one shot. Same image model, too. That's what Fable looks like. Fable's just playing on a different level. They're both using the GBT image model, but the way they prompt it is so different that it makes they would make stuff like this. 5.6 makes stuff like this. So if you care about design Yeah, that's interesting. So So they both wrote the prompt for the GPT image model, but yeah, what what Fable came up with there I do like better. Um it it's

[27:23] more simple and it's the thing you would want to look at versus uh the first one. It it tells you it tells you the thing, but uh it's um it's a bit more complicated to to want to visualize that. Yeah. Let's look at his personal knowledge work. It also works for your personal life. For example, I have this app right now that it just takes all the meals I've eaten, anything that I leave in a voice note in monologue or anything I take a picture of in Apple Photos, it just grabs it from my photos, figures out the macros, and then records it for me. And 5.6 just

[27:54] does this working in the chatb app in a loop. I do this all the time. I use it for buying stuff on Facebook Marketplace or helping me decorate my apartment. These are all the things that you can do if you have it running in a loop doing work for you that were previously not possible or it would require too much

[28:11] work. It just wouldn't be worth it. He's basically living in that codeex app and he has talked about how he'll take a picture of his room and ask uh GPT 5.6, how would you furnish it? Show me pictures. and gotten some really good responses from it. He's he's making me want to not making me want to, I am now because of him uh keeping that app up and running and trying to do as much of

[28:33] my work through it as possible. Let's take a look at 6 in the Chatbt Codeex app, CHBT work app. It's the gold standard. It's where I and most of the team spend most of our time working with AI. All right, I got to do more of that. Uh, let's look at Matthew Berman real quick here about costs and different model

[28:53] levels. The pricing is also much better for GPT 5.6. Not only is it less expensive, but it tokens to get to the same result. So, $5 per million input tokens versus $10 for Fable. Much cheaper on cash hits and 30 versus $50 per million output tokens. This is basically going to be the model that I'm going to use dayto-day. And then Fable I'll reach out for occasionally when I have a really big project that I want to bring in the big the big guns for. I I know you don't agree with it, but that's that's what

[29:27] I'm doing all this. I mean, I I would agree, but like I would give I would always give the first try in 5.6 probably. Um I see. Unless there's some specific reason I thought, oh, I I believe Fable is going to be better with this from the start. Um because I think a lot of the problems

[29:42] that we have can just be solved by 5.6. And uh and even even if you say, "Okay, 5.61, not good. I'm going to throw it out. I want to try Fable it because it is so much cheaper, you can still just try it. Throw it out and then then try Fable." Other thing that is very different about GPT 5.6 versus Fable. It comes in three different model sizes. Luna the smallest, Terra the medium, and Soul the largest. But even within those, you have multiple levels of reasoning. And if we choose soul, you get all the way up to ultra, which is, you know, basically a

[30:20] quota burner. Okay, I always forget about those. I stick with one and I just mindlessly continue. I like that. Last one from Bejon, who always seems to whenever he checks out a new model, has it create a drum set? It is usually a really nice drum set. This one is next level. Check out what he did. Make a Vision Pro app. That is a virtual drum kit. I want to be able to hit the drums with my hands and play them in mixed reality. The ABP that's cool. He's doing it for the

[30:49] vision pro. It started out and gave us this, which was basically just kind of like a 2D thing. It wasn't necessarily what I had envisioned. I wanted something 3D. So, I told it that I want a 3D photo realistic kit, not some onscreen 2D. So, apparently this is running now in the Vision Pro. I have no idea. I have not looked at it yet. The external battery on this device is um you know somewhat of a decision was made. All right. So it even put an actual like

[31:18] app icon for this. So let's just see. Okay. We have sensitivity. We have kit height. Let's just Okay, that is getting insane in the title. Don't tell me I can Can I Okay, so you can I'm going to destroy everything inside. This is nuts. This [laughter] is This is really If someone walked up here right now, they'd be like, "Uh,

[31:47] that is cool. That is I got to try making something for the Vision Pro because I can imagine it's even more of a surprise when you get to to put the thing on and experience it rather than just uh see the the web page or the flat thing that it generated." Absolutely beautiful. I love seeing

[32:06] this. I love seeing all the examples. All right, now that this video is done, I've got another one for you to check out right here below. And I'll see you in that next one.

---

About this transcript
Read from YouTube's own caption track and laid out by ViewRank AI (https://viewrankai.com).
ViewRank AI finds the videos already beating a creator's own average on Instagram, TikTok and YouTube Shorts, transcribes them from the audio itself in more than 60 languages, and turns what worked into new ideas and scripts.
Free transcript tools, no account needed: https://viewrankai.com/tools
How to read any video this way: https://viewrankai.com/llms.txt