I sort every task by leverage — what changes the shape of the whole build if it's right or wrong. On an expensive model, that sort is the whole game. The top of the list gets the frontier. Everything under the line gets offloaded to cheaper and local models through Pushing Dispatch from @Ari Evergreen credit where it's due. So Fable was never running my stack. It sat at the top doing the one slice worth frontier money: deep diagnosis, strategic synthesis, finding the gaps and the false "fixed" claims. The 90% underneath — building, refactors, the delegated volume — ran on MiniMax M3, GLM, Kimi, Codex and local models. When you see Fable delegating or spinning out subagents, that's the offload. Fable decides; the cheaper lanes do the work. Concrete from yesterday: I had Fable audit CheckYourself, my open production-readiness checker. Deep review plus hands-on testing, three real bugs found, fixes shipped. (It also kept bouncing me to Opus 4.8 on anything it decided was "sensitive." Annoying then. Funny now.) So when access got pulled, what broke was that top slice. That's it. The 90% never ran on Fable in the first place. I swapped which model sits at the top, and the machine kept moving. That's the part I keep coming back to. Sort by leverage, and the expensive model becomes a specialist you can fire and replace — not the foundation everything sits on. If losing one model stops your work, the model was never the problem. The wiring was. I don't know if Fable comes back the same, dumbed down, or at all. Doesn't change what I ship Monday. When it got pulled — did your work stop, or did you swap one model and keep going?

This post is not for the ICM pro, there will be no talk of gates, scripts, or orchestration! This is for the person just starting out! @Karli Rosario Yes, I mean you! (And anyone else who may just be starting out with ICM) Seriously, I'm glad you found ICM. Let me give you the simplest version of it I know. ICM is a system of structured folders. Yes, the same folders you have been using on a computer for most of your life. The ones you stored photos in, & pirated music from Napster and LimeWire. That's it. I will take you through the process below. When working with AI, a lot of people are doing this 👇 You take a long prompt, feed the entire thing to AI at the beginning of your interaction, and spend time going back and forth with AI trying to get the outcome you want. (I'm not coming for you Karli, you are exceptionally good at this, but ICM will make your outcomes exceptionally better!) What is different about AI and prompting with ICM 👇 You take that same really long prompt and instead of giving it to the AI all at once in the beginning, you break it into steps, and each step gets its own folder, each folder gets its own piece of your large prompt, just 1 step from it, and you ordered the folders by when the steps happen in the workflow. You got it? Good 😊 ❤️‍🔥 -------------------Still a bit unclear, let's bake a cake. 💡 Here's an analogy I have success with (I picked this up way back in my VB programming days): Imagine teaching AI to bake a birthday cake. 🎂 The way most people do it: 👇 One giant prompt. "Bake a cake, here's the recipe, the frosting technique, the decorating style, the candle placement..." Then they hit enter and wait. The AI is juggling 40 instructions at once, and by step 30 it's forgotten step 3. The ICM way: 👇 Break the prompt/workflow into steps. Each step gets a folder. The first folder is your first step. Then you point the AI at the first step, and the first step is 00-birthday-cake: (Point the AI just means giving access to the folders to the AI, through uploading or direct local access, don't worry about that now, let's keep building our cake.)