Fable made me start using Codex. Well, actually Claude, Codex, Kimi and MiniMax M3 together. Not because Fable is weak. Because it is the first model strong enough to run the others properly. The shift: stop asking which model is best. Start matrixing every model to the task it performs best at. - Claude (Fable): the seat. Orchestration, judgement, context. - Codex: the coding powerhouse. - Kimi: long-video understanding. - MiniMax M3: the looping build system. For the first time the multi-model workflow is truly effortless. Local models included. It all just works. The model at the top is not doing the work. It is routing it. All of it, loops included, lands in an ARI-OS update. The intelligence is the routing, not any single model. Read the deep-dive: https://aris-space.com/documents/workflows/fable-made-me-start-using-codex [[EDIT]] I wanted to just clarify what I said of in this post by saying that the infrastructure I've built with Fable and the way that it can solve problems when you give it a tight brief and the thoroughness of the model allowed me to create a seamless system. But ultimately, every step of this has been tiered with the model we had. //A<3

We're not experts in every field and sometimes you just don't know what you don't know. I've been working on a project for a business idea and based on a lot of hate I've seen in social media directed towards vibe coders I've taken note of things I might miss in my development. However, by following ICM I've noticed how easy it has been for me to develop my app and then pause and ask claude to help me design what I call a new persona to work on a very specific task. Latest example of this was me telling claude that I am worried someone might find vulnerabilities or back doors in my app and exploit those to get access to my API or supabase or whatever. By describing my concerns and what type of solution I was looking for Claude came up with a Claude.md and Context.md files for a pentest persona. Put those in a folder in my project and now whenever I want to do any type of test like that I just ask for it to do it!. I've done this and now I have, business owners, software auditors, legal advisors, pentester, VC Investors, Branding specialists and some others in my workflow. It just comes to show how incredibly flexible and repeatable this methodology is.

This one reframes what prompting actually is. Vote below, then fill in the blank in the comments: Before this, I thought prompting was ___. Now I think it is ___.

This one breaks down orchestration. Vote below, then pick one AI tool you actually use and tell us in the comments: can you identify which part is the model and which part is the routing layer around it?

You just saw what happens between one line of Python and the hardware. Vote below, then tell us in the comments: what is one thing you assumed about how code works that this video shifted?