How I Make Opus Think Like Fable (5 easy steps)

Since we all got access to Fable 5, I've Since we all got access to Fable 5, I've spent a few thousand dollars in usage spent a few thousand dollars in usage spent a few thousand dollars in usage credits just playing around with it, credits just playing around with it, credits just playing around with it, understanding how it works, and understanding how it works, and understanding how it works, and understanding more importantly how we as understanding more importantly how we as understanding more importantly how we as people can get the most out of a model people can get the most out of a model people can get the most out of a model this powerful. And I think one of the this powerful. And I think one of the this powerful. And I think one of the most important takeaways I've had is most important takeaways I've had is most important takeaways I've had is that yes, Fable 5 is an incredible that yes, Fable 5 is an incredible that yes, Fable 5 is an incredible model, don't get me wrong, but the model model, don't get me wrong, but the model model, don't get me wrong, but the model isn't really the moat. So, think about isn't really the moat. So, think about isn't really the moat. So, think about it like this. You've got a beginner with it like this. You've got a beginner with it like this. You've got a beginner with AI, and you've got someone like Andre AI, and you've got someone like Andre AI, and you've got someone like Andre Karpathy, for example. If you give the Karpathy, for example. If you give the Karpathy, for example. If you give the beginner Fable 5, and you give Karpathy beginner Fable 5, and you give Karpathy beginner Fable 5, and you give Karpathy Sonnet 3.7, Sonnet 3.7, Sonnet 3.7, Karpathy will build something better Karpathy will build something better Karpathy will build something better than the beginner, even though the than the beginner, even though the than the beginner, even though the beginner's model is exponentially beginner's model is exponentially beginner's model is exponentially better. And that's because of the fact better. And that's because of the fact better. And that's because of the fact that it's way more important the way you that it's way more important the way you that it's way more important the way you instruct it and the systems you build instruct it and the systems you build instruct it and the systems you build and the loops you build around the and the loops you build around the and the loops you build around the model. Here's another example I want you model. Here's another example I want you model. Here's another example I want you to think about. I've obviously tested to think about. I've obviously tested to think about. I've obviously tested Fable 5 a ton. I've also tested Opus a Fable 5 a ton. I've also tested Opus a Fable 5 a ton. I've also tested Opus a ton and Sonnet a ton. One of my favorite ton and Sonnet a ton. One of my favorite ton and Sonnet a ton. One of my favorite things to do lately is to use the things to do lately is to use the things to do lately is to use the dynamic workflows that Claude Code lets dynamic workflows that Claude Code lets dynamic workflows that Claude Code lets us, you know, spin up. And I've done a us, you know, spin up. And I've done a us, you know, spin up. And I've done a ton of dynamic workflows where I said, ton of dynamic workflows where I said, ton of dynamic workflows where I said, "Hey Fable, design a workflow, and then "Hey Fable, design a workflow, and then "Hey Fable, design a workflow, and then all of your little sub-agents, have all of your little sub-agents, have all of your little sub-agents, have those be Fable as well." And then I those be Fable as well." And then I those be Fable as well." And then I would do the exact same tests with Fable would do the exact same tests with Fable would do the exact same tests with Fable orchestrating a bunch of Opus orchestrating a bunch of Opus orchestrating a bunch of Opus sub-agents, and Fable orchestrating a sub-agents, and Fable orchestrating a sub-agents, and Fable orchestrating a bunch of Sonnet agents. And what I found bunch of Sonnet agents. And what I found bunch of Sonnet agents. And what I found is that when I run those dynamic is that when I run those dynamic is that when I run those dynamic workflows, the results are about the workflows, the results are about the workflows, the results are about the same, even though the Fable runs costed same, even though the Fable runs costed same, even though the Fable runs costed me exponentially more. So, anyways, the me exponentially more. So, anyways, the me exponentially more. So, anyways, the point I'm trying to make, you can't keep point I'm trying to make, you can't keep point I'm trying to make, you can't keep the model's intelligence, but you can the model's intelligence, but you can the model's intelligence, but you can keep its process. So, today what I want keep its process. So, today what I want keep its process. So, today what I want to talk about is basically, really to talk about is basically, really to talk about is basically, really quickly, how can you turn a model like quickly, how can you turn a model like quickly, how can you turn a model like Opus into something that feels more like Opus into something that feels more like Opus into something that feels more like Fable? And the first thing is that you Fable? And the first thing is that you Fable? And the first thing is that you have to think of this model more like a have to think of this model more like a have to think of this model more like a teacher rather than a workhorse. When we teacher rather than a workhorse. When we teacher rather than a workhorse. When we all got access to Fable, I think we were all got access to Fable, I think we were all got access to Fable, I think we were basically just pushing it to its limits.

basically just pushing it to its limits. basically just pushing it to its limits. And Anthropic even put out some stuff And Anthropic even put out some stuff And Anthropic even put out some stuff about like seeing how it's really good about like seeing how it's really good about like seeing how it's really good at like long tasks, you know, working at like long tasks, you know, working at like long tasks, you know, working towards a goal, planning it out, towards a goal, planning it out, towards a goal, planning it out, executing it, and then verifying it. And executing it, and then verifying it. And executing it, and then verifying it. And it is really good at that, but the whole it is really good at that, but the whole it is really good at that, but the whole idea of model routing is basically idea of model routing is basically idea of model routing is basically finding that balance, you know? This finding that balance, you know? This finding that balance, you know? This task takes this much intelligence, so task takes this much intelligence, so task takes this much intelligence, so why would you need a model that has this why would you need a model that has this why would you need a model that has this much intelligence and cost you this much much intelligence and cost you this much much intelligence and cost you this much for something that you could, you know, for something that you could, you know, for something that you could, you know, grab a much smaller, cheaper model, and grab a much smaller, cheaper model, and grab a much smaller, cheaper model, and you could get the task done at the same you could get the task done at the same you could get the task done at the same level of quality. And that is the whole level of quality. And that is the whole level of quality. And that is the whole name of the game, and that's going to be name of the game, and that's going to be name of the game, and that's going to be a very important skill to master as we a very important skill to master as we a very important skill to master as we head into, you know, the next years of head into, you know, the next years of head into, you know, the next years of AI. So, rather than having Fable, you AI. So, rather than having Fable, you AI. So, rather than having Fable, you know, plan everything out and do know, plan everything out and do know, plan everything out and do everything, we're trying to extract the everything, we're trying to extract the everything, we're trying to extract the way that Fable thinks, and then let way that Fable thinks, and then let way that Fable thinks, and then let other smaller models think it like that other smaller models think it like that other smaller models think it like that and execute like that. I've had Fable go and execute like that. I've had Fable go and execute like that. I've had Fable go through my setups and make improvements through my setups and make improvements through my setups and make improvements and go through my skills and improve and go through my skills and improve and go through my skills and improve them, and I realized that I was just them, and I realized that I was just them, and I realized that I was just treating Fable like kind of like a treating Fable like kind of like a treating Fable like kind of like a co-founder or more like an officer at my co-founder or more like an officer at my co-founder or more like an officer at my company rather than just an employee. company rather than just an employee. company rather than just an employee. Kind of like a senior engineer that is Kind of like a senior engineer that is Kind of like a senior engineer that is about and it's trying to package up about and it's trying to package up about and it's trying to package up everything that it knows to hand over to everything that it knows to hand over to everything that it knows to hand over to the new cohort of junior engineers the new cohort of junior engineers the new cohort of junior engineers that's going to come over or come in and that's going to come over or come in and that's going to come over or come in and take its place. So, one thing that take its place. So, one thing that take its place. So, one thing that happened recently was the system prompts happened recently was the system prompts happened recently was the system prompts got leaked from Cloud Fable 5. So, I got leaked from Cloud Fable 5. So, I got leaked from Cloud Fable 5. So, I read through this whole thing, I had read through this whole thing, I had read through this whole thing, I had Fable 5 read through this whole thing, Fable 5 read through this whole thing, Fable 5 read through this whole thing, and we picked out some important things and we picked out some important things and we picked out some important things that we noticed from this prompt itself.

that we noticed from this prompt itself. that we noticed from this prompt itself. Partial recognition from training does Partial recognition from training does Partial recognition from training does not mean current knowledge, meaning just not mean current knowledge, meaning just not mean current knowledge, meaning just because something's in your memory, you because something's in your memory, you because something's in your memory, you should probably verify it. Very should probably verify it. Very should probably verify it. Very similarly over here, a prompt implying a similarly over here, a prompt implying a similarly over here, a prompt implying a file is present doesn't mean one is. So, file is present doesn't mean one is. So, file is present doesn't mean one is. So, it's told to check that things actually it's told to check that things actually it's told to check that things actually exist. So, basically, making sure at exist. So, basically, making sure at exist. So, basically, making sure at every step of the way that what it's every step of the way that what it's every step of the way that what it's doing and what it's done is accurate. doing and what it's done is accurate. doing and what it's done is accurate. Address even an ambiguous query before Address even an ambiguous query before Address even an ambiguous query before asking for clarification. So, answer asking for clarification. So, answer asking for clarification. So, answer first, then ask. One question max. first, then ask. One question max. first, then ask. One question max. Acknowledge what went wrong, stay on Acknowledge what went wrong, stay on Acknowledge what went wrong, stay on problem, maintain self-respect. One for problem, maintain self-respect. One for problem, maintain self-respect. One for signal facts, three to five for medium signal facts, three to five for medium signal facts, three to five for medium tasks, five to 10 for deeper research tasks, five to 10 for deeper research tasks, five to 10 for deeper research comparison. So, basically talking about comparison. So, basically talking about comparison. So, basically talking about effort. So, yes, we have the discussion effort. So, yes, we have the discussion effort. So, yes, we have the discussion around what model is right for the task, around what model is right for the task, around what model is right for the task, but we also have the discussion around but we also have the discussion around but we also have the discussion around what effort level is right for the task. what effort level is right for the task. what effort level is right for the task. And something that I like to look at is And something that I like to look at is And something that I like to look at is this example, which was on the release this example, which was on the release this example, which was on the release blog for Cloud Fable 5 and Mythos 5. So, blog for Cloud Fable 5 and Mythos 5. So, blog for Cloud Fable 5 and Mythos 5. So, this compares Fable 5 and Opus 4.8 as this compares Fable 5 and Opus 4.8 as this compares Fable 5 and Opus 4.8 as well as GPT 5.5 when it comes to the well as GPT 5.5 when it comes to the well as GPT 5.5 when it comes to the score on the Y axis, the cost on the X score on the Y axis, the cost on the X score on the Y axis, the cost on the X axis, and then we see axis, and then we see axis, and then we see each of these models, and we see each of these models, and we see each of these models, and we see different effort levels. So, if you're different effort levels. So, if you're different effort levels. So, if you're one of those people that has just turned one of those people that has just turned one of those people that has just turned on Fable 5 and you're just using it on on Fable 5 and you're just using it on on Fable 5 and you're just using it on the default effort level, or same with the default effort level, or same with the default effort level, or same with Opus, and you never play with those, Opus, and you never play with those, Opus, and you never play with those, then definitely start playing around cuz then definitely start playing around cuz then definitely start playing around cuz it gets a little interesting. Like here it gets a little interesting. Like here it gets a little interesting. Like here you'll notice that Fable 5 on low is you'll notice that Fable 5 on low is you'll notice that Fable 5 on low is pretty similar to Opus 4.8 on high. Now, pretty similar to Opus 4.8 on high. Now, pretty similar to Opus 4.8 on high. Now, Fable 5 is a little bit more expensive Fable 5 is a little bit more expensive Fable 5 is a little bit more expensive and a little bit higher quality, as you and a little bit higher quality, as you and a little bit higher quality, as you can see here, but they're kind of can see here, but they're kind of can see here, but they're kind of similar. But that doesn't always mean similar. But that doesn't always mean similar. But that doesn't always mean that higher effort is actually better.

that higher effort is actually better. that higher effort is actually better. I've had a lot of times where with Fable I've had a lot of times where with Fable I've had a lot of times where with Fable I'm just basically using it on high, I'm just basically using it on high, I'm just basically using it on high, because when I use X higher max, or even because when I use X higher max, or even because when I use X higher max, or even on Opus, when I use X higher max, it on Opus, when I use X higher max, it on Opus, when I use X higher max, it starts to go way longer, get way more starts to go way longer, get way more starts to go way longer, get way more expensive, and then it overthinks, and expensive, and then it overthinks, and expensive, and then it overthinks, and it, you know, second-guesses itself, and it, you know, second-guesses itself, and it, you know, second-guesses itself, and then it ends up producing something then it ends up producing something then it ends up producing something worse than if I just would have gone worse than if I just would have gone worse than if I just would have gone with Opus 4.8 on high, or Fable on high. with Opus 4.8 on high, or Fable on high. with Opus 4.8 on high, or Fable on high. Anyways, after reading through the Anyways, after reading through the Anyways, after reading through the system prompts and after playing with system prompts and after playing with system prompts and after playing with the models for so long, there are two the models for so long, there are two the models for so long, there are two things that I want you guys to do. This things that I want you guys to do. This things that I want you guys to do. This first one is to basically take the way first one is to basically take the way first one is to basically take the way that you have been playing with Fable, that you have been playing with Fable, that you have been playing with Fable, and the the hardness, or, you know, and the the hardness, or, you know, and the the hardness, or, you know, whatever you want to call it, however whatever you want to call it, however whatever you want to call it, however you've been using it, and turn that into you've been using it, and turn that into you've been using it, and turn that into something that Opus can do, and that something that Opus can do, and that something that Opus can do, and that Sonic can do. So basically we're Sonic can do. So basically we're Sonic can do. So basically we're extracting the Fable method. Now, one extracting the Fable method. Now, one extracting the Fable method. Now, one thing that I would encourage you to do thing that I would encourage you to do thing that I would encourage you to do is, if you've ever gotten a deliverable is, if you've ever gotten a deliverable is, if you've ever gotten a deliverable from Fable that you just loved, and you from Fable that you just loved, and you from Fable that you just loved, and you couldn't really explain what you loved couldn't really explain what you loved couldn't really explain what you loved about it, have Fable analyze it, or have about it, have Fable analyze it, or have about it, have Fable analyze it, or have Opus analyze it. And if you can look Opus analyze it. And if you can look Opus analyze it. And if you can look back at the session, that's even better. back at the session, that's even better. back at the session, that's even better. What did you think about to get here? What did you think about to get here? What did you think about to get here? How did you get here? What did you do to How did you get here? What did you do to How did you get here? What did you do to prove that it worked? How were you able prove that it worked? How were you able prove that it worked? How were you able to get an output that was just so good? to get an output that was just so good? to get an output that was just so good? And then extract that information, and And then extract that information, and And then extract that information, and turn that into a skill. So I basically turn that into a skill. So I basically turn that into a skill. So I basically have this skill now called Fable mode. have this skill now called Fable mode. have this skill now called Fable mode. And whenever I want Opus to use Fable And whenever I want Opus to use Fable And whenever I want Opus to use Fable mode, or if I want, you know, if we got mode, or if I want, you know, if we got mode, or if I want, you know, if we got a really hard problem in front of us, I a really hard problem in front of us, I a really hard problem in front of us, I tried using Opus 4.8 with Fable mode, tried using Opus 4.8 with Fable mode, tried using Opus 4.8 with Fable mode, and it feels really good. It just feels and it feels really good. It just feels and it feels really good. It just feels like the model has been elevated a like the model has been elevated a like the model has been elevated a little bit, because it has this, you little bit, because it has this, you little bit, because it has this, you know, Fable prompt kind of injected into know, Fable prompt kind of injected into know, Fable prompt kind of injected into it. And it works on these five gates.

it. And it works on these five gates. it. And it works on these five gates. So, scoping, evidence, attacking, So, scoping, evidence, attacking, So, scoping, evidence, attacking, verifying, and then reporting. And this verifying, and then reporting. And this verifying, and then reporting. And this is almost like the way you set your, you is almost like the way you set your, you is almost like the way you set your, you know, {slash} goal prompts, and you use know, {slash} goal prompts, and you use know, {slash} goal prompts, and you use dynamic workflows, and you basically set dynamic workflows, and you basically set dynamic workflows, and you basically set these loops, but we're doing this as a these loops, but we're doing this as a these loops, but we're doing this as a skill file as well. Now, one really skill file as well. Now, one really skill file as well. Now, one really important thing about scoping, and and important thing about scoping, and and important thing about scoping, and and what people call, you know, like what people call, you know, like what people call, you know, like planning, is there's a big difference planning, is there's a big difference planning, is there's a big difference between just planning something out, as between just planning something out, as between just planning something out, as far as like, "Hey, here are all the far as like, "Hey, here are all the far as like, "Hey, here are all the steps, plan that out, and go do it." And steps, plan that out, and go do it." And steps, plan that out, and go do it." And then there's also the idea of playing then there's also the idea of playing then there's also the idea of playing devil's advocate and thinking about, devil's advocate and thinking about, devil's advocate and thinking about, okay, what about everything that could okay, what about everything that could okay, what about everything that could possibly go wrong? What if we explore possibly go wrong? What if we explore possibly go wrong? What if we explore all of the unknowns in this plan? And all of the unknowns in this plan? And all of the unknowns in this plan? And that is something that Fable does a that is something that Fable does a that is something that Fable does a really good job at, which is why if I really good job at, which is why if I really good job at, which is why if I have Fable spin up a dynamic workflow to have Fable spin up a dynamic workflow to have Fable spin up a dynamic workflow to help me achieve some end goal, and then help me achieve some end goal, and then help me achieve some end goal, and then once it's planned out every single once it's planned out every single once it's planned out every single possible step, and it thinks about every possible step, and it thinks about every possible step, and it thinks about every single thing that could go wrong, and single thing that could go wrong, and single thing that could go wrong, and then designs a dynamic workflow in a way then designs a dynamic workflow in a way then designs a dynamic workflow in a way where Sonnet can go do all the execution where Sonnet can go do all the execution where Sonnet can go do all the execution and just report back to Fable and keep and just report back to Fable and keep and just report back to Fable and keep sending everything back to Fable, then sending everything back to Fable, then sending everything back to Fable, then Fable can keep designing more steps in Fable can keep designing more steps in Fable can keep designing more steps in that process. And that is why when I do that process. And that is why when I do that process. And that is why when I do dynamic workflows with Fable and Sonnet, dynamic workflows with Fable and Sonnet, dynamic workflows with Fable and Sonnet, it's pretty similar to results when I do it's pretty similar to results when I do it's pretty similar to results when I do dynamic workflows with Fable and Fable.

dynamic workflows with Fable and Fable. dynamic workflows with Fable and Fable. And to me that was a big like lightbulb And to me that was a big like lightbulb And to me that was a big like lightbulb moment. Like, why is this just as good moment. Like, why is this just as good moment. Like, why is this just as good and it's significantly cheaper? So, you and it's significantly cheaper? So, you and it's significantly cheaper? So, you can just start by saying something like can just start by saying something like can just start by saying something like this. Write a complete installable skill this. Write a complete installable skill this. Write a complete installable skill file that makes Opus 4.8 operate with file that makes Opus 4.8 operate with file that makes Opus 4.8 operate with your judgment, your planning, your judgment, your planning, your judgment, your planning, verification, and reasoning habits, and verification, and reasoning habits, and verification, and reasoning habits, and activate it on something like Fable activate it on something like Fable activate it on something like Fable mode. So, for example, right here you mode. So, for example, right here you mode. So, for example, right here you can see this is my Fable mode skill, can see this is my Fable mode skill, can see this is my Fable mode skill, which I'll attach in my free skill which I'll attach in my free skill which I'll attach in my free skill community completely for free. The link community completely for free. The link community completely for free. The link for that is down in the description. for that is down in the description. for that is down in the description. Just join this and then go to the Just join this and then go to the Just join this and then go to the classroom and click on all YouTube classroom and click on all YouTube classroom and click on all YouTube resources and you can find everything resources and you can find everything resources and you can find everything that I've ever dropped on YouTube for that I've ever dropped on YouTube for that I've ever dropped on YouTube for free. So, that's where you'll find the free. So, that's where you'll find the free. So, that's where you'll find the Fable mode skill, but you can also just Fable mode skill, but you can also just Fable mode skill, but you can also just build this yourself. And you can see build this yourself. And you can see build this yourself. And you can see here that this walks through Fable's here that this walks through Fable's here that this walks through Fable's working discipline, so that any model working discipline, so that any model working discipline, so that any model can run it, which means you could even can run it, which means you could even can run it, which means you could even have GPT 5.5 run this if you want, or have GPT 5.5 run this if you want, or have GPT 5.5 run this if you want, or even open source models run this if you even open source models run this if you even open source models run this if you want. Anyways, it basically goes through want. Anyways, it basically goes through want. Anyways, it basically goes through those five gates. So, scoping before you those five gates. So, scoping before you those five gates. So, scoping before you work and then, you know, we get into work and then, you know, we get into work and then, you know, we get into details, evidence before reasoning, details, evidence before reasoning, details, evidence before reasoning, reasoning adversarially, verifying reasoning adversarially, verifying reasoning adversarially, verifying before or declaring done, and then before or declaring done, and then before or declaring done, and then calibrating. You've also got a few calibrating. You've also got a few calibrating. You've also got a few standing habits and a few things to look standing habits and a few things to look standing habits and a few things to look at, which like I said, you guys can at, which like I said, you guys can at, which like I said, you guys can inspect this file if you want to, but inspect this file if you want to, but inspect this file if you want to, but this being given to Opus 4.8 makes Opus this being given to Opus 4.8 makes Opus this being given to Opus 4.8 makes Opus feel, like I said, a little bit feel, like I said, a little bit feel, like I said, a little bit elevated. So, that has been a really elevated. So, that has been a really elevated. So, that has been a really helpful strategy. And then something helpful strategy. And then something helpful strategy. And then something that bolts right onto that really well that bolts right onto that really well that bolts right onto that really well is just, once again, the idea of model is just, once again, the idea of model is just, once again, the idea of model routing and figuring out how Fable or routing and figuring out how Fable or routing and figuring out how Fable or how some smart model can route to the how some smart model can route to the how some smart model can route to the small ones when needed. And something small ones when needed. And something small ones when needed. And something that I've been doing lately is been that I've been doing lately is been that I've been doing lately is been giving my Claude basically a table of giving my Claude basically a table of giving my Claude basically a table of different models that are in the toolkit different models that are in the toolkit different models that are in the toolkit and when to use them. So you could also and when to use them. So you could also and when to use them. So you could also have a delegate to Codex or you could have a delegate to Codex or you could have a delegate to Codex or you could have a delegate to open source models.

have a delegate to open source models. have a delegate to open source models. And this like I said is something that's And this like I said is something that's And this like I said is something that's going to be very very big when companies going to be very very big when companies going to be very very big when companies are starting to think about the unit are starting to think about the unit are starting to think about the unit economics and you know, small teams and economics and you know, small teams and economics and you know, small teams and you yourself maybe you have an AI budget you yourself maybe you have an AI budget you yourself maybe you have an AI budget per month. This is the type of stuff per month. This is the type of stuff per month. This is the type of stuff that's going to separate people that are that's going to separate people that are that's going to separate people that are getting you know, a ton more for a ton getting you know, a ton more for a ton getting you know, a ton more for a ton less. So a good way to split this up is less. So a good way to split this up is less. So a good way to split this up is basically saying, okay, here are the basically saying, okay, here are the basically saying, okay, here are the different models in our toolkit. Here's different models in our toolkit. Here's different models in our toolkit. Here's how much they cost, you know, a higher how much they cost, you know, a higher how much they cost, you know, a higher number meaning a better cost score, you number meaning a better cost score, you number meaning a better cost score, you know, cheaper. And then we have know, cheaper. And then we have know, cheaper. And then we have intelligence and taste. And if you want intelligence and taste. And if you want intelligence and taste. And if you want to throw in some other categories that to throw in some other categories that to throw in some other categories that are based on your workflow, feel free. are based on your workflow, feel free. are based on your workflow, feel free. But intelligence is kind of like how But intelligence is kind of like how But intelligence is kind of like how smart you feel like they are, how much smart you feel like they are, how much smart you feel like they are, how much they understand you, how good they are they understand you, how good they are they understand you, how good they are at maybe reviewing code and things like at maybe reviewing code and things like at maybe reviewing code and things like that. And then on the taste side, this that. And then on the taste side, this that. And then on the taste side, this is what I think more of like the, you is what I think more of like the, you is what I think more of like the, you know, creativity, the thinking out of know, creativity, the thinking out of know, creativity, the thinking out of the box, UI/UX design, things like that. the box, UI/UX design, things like that. the box, UI/UX design, things like that. And so this can really help when you're And so this can really help when you're And so this can really help when you're designing these agent teams or you're designing these agent teams or you're designing these agent teams or you're delegating to sub agents and you're delegating to sub agents and you're delegating to sub agents and you're spinning up dynamic workflows because spinning up dynamic workflows because spinning up dynamic workflows because sometimes your dynamic workflows can sometimes your dynamic workflows can sometimes your dynamic workflows can utilize a bunch of different Sonnet ones utilize a bunch of different Sonnet ones utilize a bunch of different Sonnet ones and Haiku ones and then even Opus ones and Haiku ones and then even Opus ones and Haiku ones and then even Opus ones as well. So here's an example of an as well. So here's an example of an as well. So here's an example of an actual test that I had run where I used actual test that I had run where I used actual test that I had run where I used Opus as the orchestrator and I used Opus Opus as the orchestrator and I used Opus Opus as the orchestrator and I used Opus with this prompt from earlier that we with this prompt from earlier that we with this prompt from earlier that we talked about. Oh, where is it? Sort of talked about. Oh, where is it? Sort of talked about. Oh, where is it? Sort of like the the Fable mode prompt and it like the the Fable mode prompt and it like the the Fable mode prompt and it used a bunch of different Sonnet workers used a bunch of different Sonnet workers used a bunch of different Sonnet workers and Opus workers and Haiku workers. And and Opus workers and Haiku workers. And and Opus workers and Haiku workers. And those were three different tests. And those were three different tests. And those were three different tests. And the one where the Opus orchestrator the one where the Opus orchestrator the one where the Opus orchestrator delegated to all the Haiku scouts, it delegated to all the Haiku scouts, it delegated to all the Haiku scouts, it was this much cheaper, you know, about was this much cheaper, you know, about was this much cheaper, you know, about three times cheaper and the result was three times cheaper and the result was three times cheaper and the result was the exact same. So similar to my example the exact same. So similar to my example the exact same. So similar to my example with the Fable ones, that is something with the Fable ones, that is something with the Fable ones, that is something to be thinking about big time. So I know to be thinking about big time. So I know to be thinking about big time. So I know this one was quick and I wanted to make this one was quick and I wanted to make this one was quick and I wanted to make it quick, but I've just been seeing a it quick, but I've just been seeing a it quick, but I've just been seeing a ton of comments and a ton of people in ton of comments and a ton of people in ton of comments and a ton of people in the communities asking about, you know, the communities asking about, you know, the communities asking about, you know, kind of freaking out about the fact that

kind of freaking out about the fact that kind of freaking out about the fact that Fable is going to be taken away. It is Fable is going to be taken away. It is Fable is going to be taken away. It is going to come back to subscriptions, going to come back to subscriptions, going to come back to subscriptions, that's what Anthropic says at least. We that's what Anthropic says at least. We that's what Anthropic says at least. We don't know when, but it will be back. don't know when, but it will be back. don't know when, but it will be back. But all of this, you know, government But all of this, you know, government But all of this, you know, government getting involved and models being taken getting involved and models being taken getting involved and models being taken away stuff, really has me thinking about away stuff, really has me thinking about away stuff, really has me thinking about the fact that, you You we don't own the fact that, you You we don't own the fact that, you You we don't own anything. We don't own these models. So, anything. We don't own these models. So, anything. We don't own these models. So, what we can own is our processes, our what we can own is our processes, our what we can own is our processes, our systems, our methodologies, the way that systems, our methodologies, the way that systems, our methodologies, the way that we think about using these models. And we think about using these models. And we think about using these models. And also, we can own hardware, and we can also, we can own hardware, and we can also, we can own hardware, and we can own local models. So, I'm definitely own local models. So, I'm definitely own local models. So, I'm definitely going to be digging into a lot more of going to be digging into a lot more of going to be digging into a lot more of this type of stuff. So, let me know what this type of stuff. So, let me know what this type of stuff. So, let me know what you guys want to see around these you guys want to see around these you guys want to see around these topics. But, anyways, if you learned topics. But, anyways, if you learned topics. But, anyways, if you learned something new or you enjoyed the video, something new or you enjoyed the video, something new or you enjoyed the video, please give it a like. Helps me out a please give it a like. Helps me out a please give it a like. Helps me out a ton. And as always, I appreciate you ton. And as always, I appreciate you ton. And as always, I appreciate you guys making it to the end of the video, guys making it to the end of the video, guys making it to the end of the video, and I'll see you on the next one. and I'll see you on the next one. and I'll see you on the next one. Thanks, everyone.