I Had Fable 5.1 and 5 Build Me the Same App

0:00 So, I decided Fable 5.1 and Fable 5 build me the exact same app, and it wasn't even close. Not only did these apps look and feel very different, but one cost me 1,200 bucks and one cost me

0:09 500 bucks. One works for a day and a half, one works for just half a day. So, today I'm going to be breaking all of this down for you guys. So, let's not waste any time and just get straight

0:16 into the video. All right. So, I thought that I would start with the prompt that I gave these two agents. Now, this was a big slash gold prompt. Please don't roast my prompting, but I gave them both

0:24 the exact same prompt. The only difference is that this one said you are Fable 5.1 and you work inside of this folder, whereas the other one said you are Fable 5 and you work inside of this

0:32 folder. That's the only difference. Everything else, word for word, the exact same. And I'm going to show you guys how interesting it is because they interpreted it so differently. But,

0:38 here's something that I think is key. I didn't have Fable 5.1 build the entire app and Fable 5 build the entire app. I wanted them to basically delegate everything. I said, "You own strategy,

0:48 planning, delegation, sequencing, quality standards, and final acceptance. Do not personally perform engineering, research, debugging, testing, or visual design production. Preserve your context

0:58 by delegating execution through dynamic workflows. Primarily use Opus workers for architecture, product, and design direction, difficult problem solving, and independent reviews. Primarily use

1:08 Sonnet workers for implementation, research, testing, debugging, and iteration. Give workers clear ownership, prevent conflicting edits, and replace or redirect workers when results are

1:15 weak. Worker failure is still your responsibility." So, I'm not going to read this entire prompt, but this is kind of the gist of it. I gave it bullets on the required product, and I

1:23 gave it the definition of done, and I told it to not stop at a plausible implementation, but continue orchestrating until you have objective evidence that the complete product works

1:31 and is presentation ready. So, essentially what these agents are building is they are building OpsFlow, which is a local-first visual automation studio for designing and simulating

1:40 incident response workflows. So, it's not a workflow automation platform like N to N. It is just meant to visually show and kind of like rehearse. It's for the person who owns what happens when

1:50 production breaks. So, in layman's terms, it lets you draw your emergency plan as a flowchart, and And you can actually visually watch how that plays out. So, now that that boring stuff is

1:58 out of the way, let's take a look at the actual apps that they built. Okay, so here is the first one. I'm not going to tell you who made this one yet. I want you guys to try to form your own

2:06 opinions, and then I'll reveal that after we look at both of them. But, this is what we're looking at. This is the UI. The first thing I'm thinking about is is this overwhelming? I I'm just

2:14 starting to look at this. I've never ran either of these, but I'm just taking a look now, and let's see what we've got. So, we've got triggers on the left-hand side. We have trigger, condition,

2:22 action, approval, resolution. We can drag them into the canvas here, and we can hopefully start to connect them into things. Okay, that looks seems like it works good. We can connect the trigger

2:33 into this section over here. Okay. So, so far the UI is responsive, and I can use this. Let's see, can I close this? Okay. There we go. So, this is kind of

2:43 node-based workflow, but it is vertical rather than horizontal. So, what I'm going to do is see if I can delete that connection, delete this connection, delete that. Okay. So, let's go ahead

2:51 and run this. So, I'm just going to click run right here. We can visually see the stuff happening. That's pretty cool. We're seeing the stuff being processed.

2:59 And now, what do we get at the end? We have a completed run, and we're basically able to see what happened. Can I move this up? So, I'm I'm not able to expand this. I think

3:08 that what you should be able to do is grab here and drag this up so you could look at this full screen, because this is a little bit hard to actually look at right here. So, there was three that got

3:17 skipped in this branch, and there was seven that got executed. The resolution was mitigated by a rollback. Okay, run has been completed. Okay, awesome. So, that's kind of how this one flowed. This

3:26 seems to work just what just fine. We cannot zoom in on that. If we want to zoom in on this thing, oops. Sorry, guys. We have to go like this, but then we can navigate from there. Okay, so far

3:37 so good. Let's go into the other version now. So, this is what the other one looks like. This is the UI. If you think it's better, if you think it's worse, I personally think that this UI

3:45 is a little bit better, because I don't know if you guys have realized this sort of card where you've got like the rounded crop color. That is just that that screams AI generated to me. Now,

3:56 I'm not saying this looks like AI slop, but it that screams AI generated. Whereas over here, this doesn't look as bad. Like I think that this looks a little bit more

4:04 clean. Let's see if I can drag something in. Okay, and I like how it did me a little zoom right there. Let's see how I Oh, that's a resolution block. So, that's not going to let us connect

4:11 anything. Let's do another, I guess, condition since that's what we did in the other one. We can grab the trigger, route it to there, or can we not?

4:20 Okay, uh connection refused. API error spike detected. Already has an ongoing connection. Okay, so one trigger only lets you connect to one thing in this version, as you can see. So, that's

4:29 interesting to note. We'll connect that back in there. I can drag this and connect to there. I can drag this and connect to there. And that gives us a false branch. Okay. Cool. So, that works

4:39 as expected. Let me delete these. We can zoom in down there, and I can move this around. So, everything over here as well seems pretty responsive. Can we move this up? Aha, so in this one you can

4:51 expand this a little bit. You can also make this part Oh, you can kind of zoom that in. And we can also close this tab if we want to. Okay, cool. So, let's go ahead and give this version a quick run.

5:00 I see the run in the top right. I also notice that we can go on light mode here. So, sorry if I just blinded anybody, but let's go ahead and do a run.

5:07 So, we see visual processing here as well. We can see this node is waiting. It's waiting for approval here. So, approve production rollback needs sign-off from this email waiting for

5:16 decision. I'm going to go ahead and approve real quick and see what happens. It goes down the path. Okay, cool. I'm going to run that again and see what

5:23 happens if I decline that. I'm going to reject. Okay, it just goes ahead and stops. But now, if you guys notice, it it's keeps going down the true path. So, I'm trying to look how do I actually

5:31 change that? Um oh, I can view the node, by the way, that that aired. But if I go to the payload, I can choose minor degradation and hit run again, and now it goes down the false. Okay, so that's

5:42 cool. That's cool. If I click into a node, by the way, on the right-hand side we can have a label. We have the action type, we have the target, and we have all this information to configure it.

5:51 And similarly on this one, when you click on a node you get all of that information over here to tweak, I guess. Okay. So, I do like the UI of this one better. So, what I want to do real quick

6:00 is paste in different workflows so we can just see how they look, but I wanted to reveal this one is Fable 5, and this one is Fable 5.1. So, we'll get into how much they cost and which one I think is

6:12 the winner overall, but just wanted to tell you guys this is Fable 5, this is Fable 5.1. And what's really interesting to me is that they accept different schema for the way

6:21 that we upload new workflows. So, if I delete this and I want to import a workflow from JSON, this schema, which now works in here, if I try to import that into this

6:31 version, doesn't work. There's nothing on the canvas. So, I don't know why, but they decided to build it in a way that's different. But anyways, I imported this.

6:40 Let's just go ahead and run this real quick to see what this looks like to process a much larger workflow. There's different paths. I'll go ahead and approve this. I do think that this one

6:47 visually it does look good. I like the way that this feels and looks as we go through the automation. Oh wait, I That was waiting on me again. We'll go ahead and approve. So, anyways, that seems to

6:56 all be working as expected. This is an action. Cool. Okay. Now, let's go over to the other version and let me paste in this prompt. Go ahead and get that in there. Import.

7:05 Okay, cool. So, now we have another one. Now, I will say I honestly think that Fable 5 looks better when you're zoomed out because the text doesn't grow. You see here as I

7:15 zoom in and out, it stays consistent, whereas here, this looks I think this looks very cheap for this to be getting larger. I think it looks cheap. I I guess that's a preference thing.

7:25 Some might disagree, but I think it looks cheap to be like that. So, anyways, let us continue going down this branch just to make sure everything looks good. Overall though,

7:34 I just overall like the UI of this one a little bit better. Except for that zoom thing. I don't love that at all. Okay, cool. So, this is done. Now, let's talk about some results

7:43 stuff. So, what I did next is I had Codex open these two up and I didn't tell which was which. That's why in this chart it says port 4382 and port 5321. And I said, "Hey, I gave these two

7:55 agents the same prompt and here's what they built. Test the heck out of them. Tell me what you like about each one better." Overall, you can see the weighted score is that Fable 5.1 got a

8:03 9.1 and Fable 5 got an 8.4. So, it looked at visual design and hierarchy, Fable 5.1 won. First one, ease of use, 5.1 won. Workflow authoring, you can see here,

8:14 dry run experience, Fable 5.1 in workflow authoring as well as validation and safety, which is important but very, very close. And then, Fable 5.1 ultimately, like I said, won by seven

8:26 points or 0.7 points. And after looking at this, testing them, and having Codex review, this is kind of the chart of what they thought was better about each one. Fable 5 had deeper authoring

8:38 controls, clear auto save timestamp, it included useful negative test presets like missing severity, excellent live preview against the current payload. I think that that is very true. Whereas,

8:48 5.1 had stronger information hierarchy and more readable canvas. I do think that that is true as well, except for when you zoom out. Strong run summaries and downloadable run logs, clear visual

8:58 states for succeeded, failed, skipped, and waiting. Rejection currently fails the run instead of falsely claiming mitigation. So, anyways, that is a little bit of differentiation here.

9:07 Let's talk about the cost. Okay. So, I think this is super interesting because 5.1 cost a little over double of what Fable 5 cost. And it also took about three times as long, which I honestly

9:20 was not expecting. On top of that, what I think is really, really interesting is look at the breakdown of models here. 5.1 used Opus for about 57% of the work, Sonnet for about 40% of the work, and

9:30 itself was only about 3% of the total work {slash} tokens. Whereas, on on side, Fable 5 used Sonnet for 80% of things, which maybe is why some of the stuff is so much cheaper and was

9:41 quicker, but also a little bit worse in some cases, but I'm not convinced that this one was $600

9:49 worth. And what I mean by that is if I spent what would it be? Like, you know, 700 bucks more on this one to improve it just to get where this one currently

9:59 sits, I think that this one would be better, which is the one that Fable 5 built. And keep in mind with the majority of the workers here being Sonnet. And then 12%

10:08 being Opus and 7% being Fable 5. I thought that was extremely interesting. I was not expecting that. Do you know what I mean? Like, I think it's good to try to find some sort of baseline, and

10:16 the baseline for me would be if I spent the exact same amount of money on each of these models, where would we be? And so if Fable 5.1 only or like if this workflow only spent 519 bucks, we

10:26 probably wouldn't have gotten something this good. You know what I mean? So that is why I am trying to, you know, I'm making that justification there. Look at the tokens, too.

10:34 On the input, Fable 5, I I don't know I don't really don't know if this is real. I don't know if there's any way that Fable 5 only took in 236 tokens. So maybe something's a little bit off

10:44 there, but when you look at the output tokens, this seems to make sense. Now, I think because of a lot of this were, you know, dynamic workflows, sub-workflows, things like that, but, you know, it's

10:53 clear that Fable 5 took much longer and cost about double, a little over double, 700 bucks more than Fable 5. And if we take a quick look at the actual context

11:01 window from these sessions, here's the Fable 5.1 that was running on localhost 5321, as you can see. And if I go in here, it only used 404,000 of this context window. So this ran for,

11:13 like I said, a day and a half, 36 hours, and it only used a little under, you know, 40% of the context window. If I go to Fable 5, you can see this one was running on 4382, and this one used

11:24 260,000, so 26% of the context window. So I just wanted to show you guys what that actually looks like in the desktop app when we look at the actual pricing numbers that I just showed you. This

11:33 honestly leads me to conclude that I think Fable 5 won this challenge. I'm not saying I think Fable 5 is a better model. I've had a lot of success playing with 5.1, and I will be honest, when I'm

11:42 doing a lot of my general knowledge work and I'm driving my day-to-day, I do notice Fable 5.1 being more efficient and just feeling like it understands my intent a little bit better. So, overall

11:52 right now, I like Fable 5.1 a little bit more. But, in this scenario, Fable 5, I think definitely wins. When you look at the cost, the time, the efficiency, and the actual end result, I think that

12:04 these apps at the end of the day are pretty similar. And for 700 bucks, like would you pay 700 bucks more for this? I don't think so. But, anyways, that is what I got for you guys today. That's

12:12 what I found. I really hope you found it insightful. But, if you want to see how I use Fable 5.1 to design websites, specifically things like my AI Automation Society site, which I think

12:21 is just absolutely beautiful, and my personal site, and a lot of different styles of websites that have these really premium animations and just scroll elements, then definitely check

12:30 out this video right here. I hope to see you guys over there. And yeah, thanks for making it to the end of this one. See you guys.