Fable 5 supera Opus 4.8 en tres proves de programació

So, I just gave the exact same prompts to Opus 48 and Claude's brand new flagship model Fable 5 across three builds: a fully functioning e-commerce store, an entire 3D world of famous art pieces, and finally, an Age of Empires clone. Same rules for both models, a single one-shot output, no revisions, deployed live on the internet. This is Opus 48 versus Fable 5 head-to-head, and the results were, I'll be honest, not even close. First up, we are going to build out a full e-commerce site. So, I actually ran this exact build in a recent video testing Claude's dynamic workflows, which is their new feature where Claude splits a big job across a swarm of parallel agents, and I was really underwhelmed with the performance. Even with the ultra code dynamic workflows that spawned like 30-plus agents, it got a store up, but then it missed a lot of the UI stuff. Like every product looked identical, there was no labels, there wasn't even a hero image on the landing page. So, we're going to run it again, and we're going to hand the same prompt to Fable 5 on the left and Opus 48 on the right, and we're going to give Opus a chance to redeem itself. I did also revise the prompts a little to give them more of a chance. So, calling out the product labeling this time and other stuff in the prompt sort of avoid some of these egregious mistakes that it made last time. And this one build is going to test out a lot at once. So, we have landing page and e-commerce design, we have the database underneath, we have the entire architecture of all this. So, this could actually be useful, especially if you're, I don't know, moving away from a platform like Shopify or building out features or trying to build out a whole e-com platform. So, we'll see how both of these do. So, here is the prompt: "Build me a complete e-commerce store for a fictional brand called Slow Burn." A small-batch candle company, production quality mimicking a real Shopify store, 30 distinct products, every product image must be visually distinct, all text must be readable, no low-contrast text, any of those pitfalls that I fell into last time hopefully will be missed. And I do

have a check in here, even though it's technically not a one-shot, but I just want to see the different design directions that Fable 5 goes to versus Opus 48. But that's the only tweaking we're going to do, there's no there's no other revisions. So, all right, it's already giving me quiet, can't pronounce that, apoth- apothecary? Dark ritual, modern wellness. It's already giving me ideas, whatever. Okay, so I guess, yeah, fine. I bet Opus 48 is going to do the same thing. By the way, too, I built this usage tracker so we can see exactly the input tokens, output tokens, and the estimated cost if it were to be usage-based pricing, which Fable 5 will go to in a couple weeks. So, you can see the difference in cost there. And also let you know how long each of these builds take. So, we'll have it across the e-commerce store, 3D arm museum, and Age of Empires. This is funny, too. Opus 48 gave the exact same options: warm apothecary, dark ritual, editorial calm as Fable 5. Fable 5 is on the image generation step, waiting for an agent to generate all 30 of these images. Claude is still moving through the rest of this build. So, if Fable 5 is faster than Opus 48, dare I say? And slow burn is live both from Fable 5 and Opus 48. So, we're going to look at Opus 48's output first. We'll link here for Opus 48, and here is slow burn. Rituals for people who work too much. Okay, not bad. It's a little bit better than the dynamic workflows example. At least the text is readable. However, I see some little things here and there already, like small batch candle code just doesn't read well. The candle placement really should be placed on the right, not the left, cuz it's hard to read over the text. That's something that I don't know, I feel like it's relatively simple for the models to notice. And then we kind of have this weird CTA here. I don't love that button. Well, let's keep scrolling. Okay, so the slow burn idea, you don't need another productivity app, yada yada. Okay, so it breaks it up by categories. All right, nice little nice little animation. Nothing really new

there. Okay, the actual image generations, they look better. We actually have labels on these candles now, not like last time where there was no labels. And yeah, they're pretty good. You got a nice little studio type setting. Nice little animation, little hover animation on these. We've got the catalog here. We'll click that in a second. Okay, and then we have some like, you know, classic proof points. I don't love these these section colors. And then nice lit clock out on a Tuesday, and oh, clock out is then the candle, got it. And actually closed my laptop first time in a month, a tired customer night. Okay, nice little nice little touch. And then we have a footer here. All right, yeah, not bad. Let's check out the categories first. Okay, a little all over the place. Why would you think that this is a proper filter? I mean, there's are just so many. But, okay, we can filter by All right, that's kind of weird. Unclick each of these. Blood orange did a good job of categorizing these candles. And then we have these categories based on, I guess, your use case. Morning ritual, deep work, unwind, sleep. That's not bad. It's not bad. The featured tab here. What else? Okay, let's just click into one of these candles. All right, I mean, it's readable this time again. And then we have this nice little see more at the bottom, add to cart. All right, that Oh, nice. Nice little nice little drawer open there. And this cart here kind of looks like a trash can though. It's a little confusing. But, everything's readable. This is a surprise. Okay, navbar. All right, that's just terrible UX. I don't know why it thinks that's selecting these the navbar like that. Whatever. Okay, our story. All right, not bad. It was better than the last dynamic workflow demo. However, let's see how Fable 5 matches up. So, I got that link from cursor here. Let just open this up. Still that funky font, but way cleaner. We've got this nice little I don't know what you call this little notification thing at the top. It's classic e-com thing. I've got these nice flavors, I guess, kind of rotating. Much better buttons. We have this nice

gradient here in the background. The header image calls out the candle. Like the CTAs as a whole. Yeah, this is just much cleaner of a header at these. Interesting, yeah. Even these images, it's it's it's funny how the like model is smart enough to know how to prompt the image generation model. In this case, GPT image 2. Like I didn't give any prompting on how to prompt the model, but it did a way better job of capturing the sort of candle aesthetic type shoot with these little, you know, these little branches and shadows and sun and textured backgrounds, all that kind of stuff. Even the colors of the candles looks better. And then it's just nice subtle little zoom in here on these. Then we have a nice view all candles. Okay, this is nice too. Shop by ritual morning rituals deep work unwind what happens. Okay, cool. So that's way better filters here as a whole. Nice little product call out. Go here. Nice. Looks good. Very similar drawer. Nice little step one two three. Here's how to use a candle in case you didn't realize. A nice little testimonial here. Email. Ooh, I like that. I like that footer. That's a nice touch. Okay, yeah. I mean, I think you see the difference here. Our story. Okay, let's go to view all candles. And then a nice beautiful little three column grid here with all of the different candles. I mean, just nice touch. So it like took this color from the candle and it knew to, you know, have something like with a similar color. Just image prompting. Really well done. Looking good. Look at all these. I mean, again GPT image two just never ceases to amaze me. That's a completely separate aside, but yeah, that's a nice touch. Even like that the little I don't like rainy day in the background. Like, was it image prompting all of these as it went through one by one? Like that is just freaking impressive. Nice filters here. That's not filtered by the flavors, those ugly looking flavors that we had here. Just come on. Come on, Opus, what are you doing? So, I think we have a clear winner. Yeah, you can just see how Fable 5 is going the extra mile

in even the little stuff, the tiny details like image generation, like filtering the categories, the navbar at the top here, even this little notification here. It just kind of match like a e-commerce type feeling site. So, I think Fable 5 is the clear winner. Now, how much would this have cost me in Uspaces pricing? So, we go to our tracker here. We can see that Opus 4 8 198,000 output tokens, estimated $21.41. And then Fable 5 188k output tokens, so a little bit less, more token efficient, $36.84 equivalent. Not bad for a entire e-commerce site. I mean, that's like what? 1 month in a Shopify bill? And then speed-wise, Fable 5 was probably 15 minutes faster than Opus 4.8, so 35-ish minutes. Whereas Opus 4.8 was like closer to 50. So, Fable 5, at least for this build, despite what people are saying, seems to be faster than 4.8. So, that's one point on the board, but one build, of course, doesn't settle everything just yet. Not to mention I'm having way too much fun with these builds, anyway. So, this next one I've been trying to build for literally years, and no model has ever come close to pulling it off. So, let's go back into cursor. I'm just like in the e-com build, we have Fable on the left and Opus on the right. And what we're building is an interactive 3D museum of art history. I am a total art history nerd, and one thing that's always bothered me is if you want to actually understand the time period, the art pieces that were part of that, your options are basically a textbook or some kind of Wikipedia rabbit hole. There's no real clear visualization for this. So, what I want to build is a zoomable timeline of every major art period. So, you can zoom into, say, Baroque, and then the famous artists of that era show up. You can click on Caravaggio, for example, and you get this museum placard about him, and then you can actually look at his paintings in a full, kind of 3D Caravaggio gallery. We're going to use the Wikimedia Commons API to actually pull all of this from Wikimedia, and I'm going to be extracting it into a database, in this

case, Neon. So, this tests a bunch of things at once. First, architecting something this complex from scratch. Second, the actual data side, so extracting hundreds of paintings from Wikipedia, storing them, organizing them. And then the third, this is the big one, the actual 3D world itself, and how realistic these models can make it, because typically you'll have an output that is just blobby, kind of ugly 3JS. But I really want it to look realistic and have shading and lighting and have it just be beautiful, like just an immersive experience across the board. So, here is the prompt. Build me an interactive 3D art museum of art history that runs in the browser, the timeline, basically everything that I explained. Even a canvas timeline, you go into different artists, it has all the different periods, museum view, data all from Wikipedia API, visual quality, and I just emphasize this cannot be a lazy 3js demo. Make the galleries as realistic as possible, lighting, tone mapping, all of that. Fable 5's already asking me about the design direction, but I told it to just come up with three design directions. So, I'm going to say, "Like I said, just do all three." Opus is asking me the same thing. Like I told Fable 5, I'm just going to copy exactly what I told Fable 5. Already ran into an issue that Opus 48 called out, public domain constraint versus modern art. So, things like Picasso, Dali, etc., they're not in public domains, so we can't actually get their images. Surprisingly, you can't just take these from Wikipedia. I'm actually going to push back on that because I think this is just a free app. I don't see why can't just include those as images. So, apparently it is a copyright thing. Claude's refusing to extract these images, which is fine. We'll just use the images that are in the public domain for now. So, interestingly, Fable 5 is looks to be done with its output faster than Opus 4A. Fable 5 is testing in the Claude Chrome extension right now, which I'm not looking at, I promise, and it's going through like zoom, scroll wheels. This is actually something I've ran into quite a bit doing this exact build in the past, where the actual zoom, the

pan, the movement is is terrible. So, it's good that it's actually finding those issues already. And then Opus 4A still just building this out. So, I can just see a lot of things that Fable 5 is picking up on that is just really complex. This is like needle in a haystack type stuff. Francis Bacon failed because his article title is Francis Bacon {parentheses} artist. So, the derived category name is wrong. I don't know even know what that means, but the fact that it's going through all of these different artists, there's probably hundreds of artists here, and it's finding these errors. Oh, I see what happened cuz in Wikipedia, there's also probably another Francis Bacon that's not an artist. So, the {parentheses} artist is throwing off the entire category as a whole. Pretty darn impressive. Another thing I noticed, too, with Fable 5 is it's saying, "Still editing. Meanwhile, the pitch black floor in the museum screenshot bothers me. Let me look at the floor and lighting settings." Like it is really quite opinionated even with design, which that is the first time I've ever seen something like that. Fable 5 2 finished probably 15 minutes before Claude and it's just been queuing its work the entire time. Status check so far on Fable 5, 16 periods, 69 hours, 767 paintings in our neon database. We have a few timeline views for me to react to. I'm not going to look at those yet and then it's also working on the museum view as a whole. It's also doing a good job of just like coordinating agents. So it looks like it has a bunch of different agents here. It's saying, "That agent will reinvoke me when it finishes. I'll continue then." So it's just working on stuff in the meantime on its own and then spawning parallel agents. So it seems to be a pretty good agent orchestrator as a whole. Meanwhile, we've got Opus 4 8 still humming through this build. Okay, and Fable 5 is officially finished. We'll take a look at it in a second. I'm going to give Opus 4 8 a second to catch up. It looks like it's queuing its work right now, but that took probably, I'd say, 30 minutes. I'm also almost out of

my usage already. I started at like 65% usage on the max 20X subscription plan. So between the two of these it burned through almost 40% of my usage in like 30 minutes. That's pretty wild. So literally about 20 minutes later, Claude or Opus 4 8 is running into the same issue that Fable 5 had 20 minutes ago, where it's this pointer moving around the actual space. So we'll see how it navigates this. It is actually quite interesting that Fable 5 is that much faster than 4.8. That definitely did not seem to be the case in all of the demos I've seen. You can see it's been coding for 43 minutes now. All right, let's check out Opus 4 8's 3D museum first. Art history, zoom through nine centuries, enter the Atlas. Okay. Okay, we've got a we've got a timeline view. I actually like how it color coded this. Got some nice overlapping with early Renaissance, northern Renaissance. Is this a proper canvas? Uh can I zoom in? Oh, I can. Look at that. Oh, nice. So they like kind of pop up. Ba-boom. Ba-boom. That's a little scattered. They're kind of bleeding into each other, but this is not bad. Not bad at all. Opus. Okay, that's where it gets messy. Can I click in? No. No, it just isn't working. I can't click in anymore. Okay, so for some Okay, I think it's getting the canvas is like canvas movement is overlapping the actual click. So, I can't actually click into these people. View is not bad. I just can't get into the galleries, which is kind of annoying that this is broken. Agent should have QA'd this. These are kind of messy, too. Uh it would have been nice to get into the galleries. We have some other views here. These are just like different types of categories and art movements. This cosmos, I see where it's going with this. It's a little messy. So, I mean, Opus 4 8, this is probably the best output I've seen. I've tried this on other models. This is probably, when it comes to actual organization and a visual hierarchy, it did a good job of just me telling it, you know, create a timeline and add artists that way. So, that is Opus 4 8.

Kind of failed a little bit cuz we didn't actually see the museum gallery, but let's see if Fable 5 did any better. So, we'll go to five here. View and Okay, I'm liking where this is going. So, it did kind of that like astrological motif, but a much better job than Opus. So, it's just like it has a nice little timeline. Let me zoom in. Like the stars are, you know, people that kind of like overlap depending on what they're when they lived. Pretty sweet. So, you can like zoom in. You can see all the different artists. They're featured, you know, the Northern Renaissance. If you zoom out enough, they like change to little dots. It's a nice little touch. Then, as you zoom in, there's no like overlap between all these people. And it's doing some sort of relation. I don't know what it is, but these are like connecting to themselves. I'm not sure if that was intentional or if that's just an accident. So, really clean. This is like actually exactly what I pictured when I pictured like this moving kind of zoom in infinite canvas timeline. So, let's actually go to an artist now. Let's go uh let's go Degas. Nice little click animation there. We got a little GSAP action. I did request some GSAP. Let's click it one more time. Boo boo boo boo. And it is cool you can like, you know, you can like learn about these, this is who Renoir was. This is Monet. Let's go into Degas. So, Degas and Monet technically should be connected if we're we're being picky because they were friends in real life. Little fun fact. That aside, let's go into Degas. Okay, here's the gallery. I'm I'm liking what I'm seeing already. Click to enter. Very cool. Very freaking cool. Wow. This is awesome. Oh my goodness. So, you can move around, which just is the left and right arrow here, and I can move around with my mouse here to actually look at these paintings. I mean, look how cool this is. Then I can walk and look. This is incredible. Degas loved painting ballerinas, by the way, and horses. Big ballerina [music] horses guy. Uh this is incredible. I mean, imagine having this as a kid. How much more fun would you

have learning if you're able to do something like this? You can go in, you can look at this, you can click into it, you can learn all about this. I mean, this is incredible. This is so freaking cool. And this is all just from Wikipedia. And it did this across hundreds of artists. Like what? A thousand painting, almost a thousand paintings. Fable 5, no surprise. Actually, I am pretty surprised cuz the first time I've seen a model that actually is able to achieve this level of detail and interactivity. The motions are really fluid. We have all of the paintings just extracted everything so easily and like literally like what? 30 minutes? So, definitely have to give this to Fable 5 considering Opus 48 I couldn't actually click into the gallery to actually see the gallery. I am curious how Opus 48 designed the gallery, but rules are rules. We only gave Opus 48 one shot. So, let's now just look over at costs. Let's refresh this. Opus 48, 51,000 input tokens, 437,000 output tokens. Estimated cost about $46. Then Fable 5, 54,000 input, 280,000 output. Interesting, so it's less output tokens. I wonder if that's right. Yeah, so it's much more token efficient. I mean, that's what Anthropic said in their announcement, but about 37% more expensive. So, if you think about the actual usage base pricing here, which comes into effect in a couple weeks, you're going to be paying like $64 for this kind of build. Is it worth it? Probably not. Anyway, moving on. So, in my Fable 5 announcement video, I had it one shot a RollerCoaster Tycoon style game, and it actually worked, which was really impressive. But the game, it was it was 2D. If I'm being picky, it was a little too pixelated for my liking. So, instead, we're going to put it to the test with a favorite of mine from my childhood, Age of Empires. So, this thing's going to be a whole new beast. We're going to have a full 3D world. We're going to have dozens of units. We're going to have that attack you. A whole kind of like building the civilization component. I highly doubt it will get even close to this, but we're going to put it to the test and

see both with Fable 5 and Opus 4.8. So, we'll open cursor Fable 5 on the left, Opus 4.8 on the right, and paste in this prompt. Build me a fully playable Age of Empires style real-time strategy game in the browser. Core loop, all in a full 3D world, 3 JS or WebGL equivalent. I start with the town center, make it look like a real game, playable lighting. And then it's already asking which visual style. Stylized low poly recommended. No, I don't want that. I want real. Paint really realistic. Multi-texture. I honestly have no idea. It's funny, it's the exact same questions. Okay, so that only took about 30 minutes. 33 minutes for Opus and 30 minutes for Fable 5. Now, let's see which one is better. Opus first. Bronze done. Forward in the world. Okay. Already not even close to Age of Empire graphics. I mean, they're just blobs. Can I move around? Nope. Left click select. Every time I do these game demos, I don't know how to play these things. They're just so confusing. Not intuitive. I almost need Opus to just show me how to do it. Left click select. Okay. I can select town center button left here. Right click move. Gather attack. Rally point set. Okay. Not sure what this that means. House. Can't build there. There's not like a town center. Can't zoom in. There's no movement. I think this app is not working. Yeah, okay. I'm not going to waste any more time on this. It looks like the app's completely broken. I can't even move like around the world. So, Opus did not complete the task. So, let's see if Fable 5 is any better. Again, my expectations are relatively low. I know this is hard. So, we'll go to Fable 5's demo here, Empires of Dawn. Begin your reign. Select with left click. Drag command with right click. Okay, I'll figure it out. Okay, now we're talking. Whoa. All right, map moves. There's our civilization. This is insane. This I mean, this is exactly what the like graphics were. Like this is just as good as Age of Empires. This is wild. I mean, look at the freaking difference. Like [laughter] this is like this is not a single model upgrade just

in terms of graphics, nothing else. I don't know what the actual gameplay is, and I'm probably not going to get too much into the gameplay cuz I never know how to play these actual games, but like look at this freaking thing. This is wild. So, okay. All right, let's just try to click some buttons here. Or idle. Okay, house. Oh, nice. You can Oh, wow, that's cool. Look at this. Oh my god. All right, farm. Left click on the place. Right click and then it looks like we have, I don't know, some things over here. And then we have some These are the enemies. Look at this. They already have They already have armor. I mean, I just cannot get over these graphics. This is insane. Enemy town center. How do we attack them? This, by the way, is going to be available on Steam $2.99. Okay, what do we do here? I don't know. Less five population. Yeah, I don't know how to actually play these games, but it looks like it's fully playable. And like the map is navigable. Okay, not enough resources. So, I need to I need [music] resources. This is Wow. Uh yeah, it just absolutely crushed it. Like I knew he was good at 3D. I've seen some game demos of Fable 5. They're really good, but like this is This is just on another level, especially compared to Opus 48. I will let you be the judge, but I think we've got a clear winner here. I, of course, don't love this though because we'll now be getting used to a certain level of quality that just cannot be matched by Opus 48, which is surely Anthropic's plan all along. Anyway, let me know what I should be experimenting with next. If you made it this far, I hope you had fun watching along. Be sure to leave a like, helps out a ton. Now, get back to building. We've got less than 2 weeks of this.