I recently finished a rewrite of a coding process. My Video game project, (the main thing I have been using as AI learning project) I have put on hold for now because I needed it. So here I am. With the Learning/Creative itch not being satisfied. It is definitely not being fulfilled at my job. I feel like taking on something ICM related and nothing is coming to me. Writer's block. So hear is the call. 🙃WHAT IS YOUR CRAZY IDEA?☣️ Throw out a crazy idea! Keep to one or two sentences. Let's inspire each other.

Ornith-1.0: the open-source coding LLM that matches Claude Opus 4.7 — and runs on your laptop. This open-weights agentic-coding model hits 77.5 on Terminal-Bench and 82.4 on SWE-bench Verified, beating Claude Opus on both, then ships a 9B size you can `ollama run` locally. MIT licensed, four sizes, and it taught itself the harness.

Last night I dispatched 235 agents to review a codebase. The model wasn't Claude. The harness was though. Claude Code ran the whole thing. The model underneath was a budget one. Here is the thing nobody tells you about dynamic workflows. They are not a model feature. They are a harness feature. ————————————————————————————————— Claude Code has a mode called UltraCode, and UltraCode runs the dynamic workflows for you. Turn it on and it fans out tens or hundreds of agents by default, runs them in parallel, verifies each finding adversarially, then synthesises the survivors. That whole dance is orchestration Claude Code performs. The model just fills the seats. Which is also a cost bomb. Automatic fan-out to hundreds of agents on a premium model is a serious bill arriving by default. So I started renting the conductor and swapping the orchestra. The conductor is Claude Code, the harness: UltraCode, dynamic workflows, dispatch, the fan-out and verify loop. That stays fixed. The orchestra is the model underneath, and the model is swappable. Claude is one player you could seat. GLM and MiniMax are others. Point the same harness at a cheaper provider, GLM or MiniMax, and you keep the orchestration while the token bill collapses. Same UltraCode, same automatic dynamic workflows, a fraction of the bill. You utilise the same UltraCode, you just stop paying premium rates to run it. ————————————————————————————————— Now the catch, because there is one. You do not get all the benefits. A cheaper model reasons worse per agent. One GLM agent is not one Opus agent. What you are buying is the right to run fifty of them for the price of one, and to let structure do the work the raw model cannot. That is the trade. Depth per agent goes down. Breadth goes way up. And the workflow shape, fan-out then adversarial verify then synthesise, claws most of the quality back, because three cheap sceptics catch what one of them misses. ————————————————————————————————— The numbers from one run:

We just broke 40k Members, in less then 4 months... To say I am honored and blown away is an understatement. I feel like yesterday @Matthew Creamer quit his job to sleep on my floor and bust out 15 hour days to build out content, structure and anything else I thought you all would need to make this community worth it. But at the end of the day there is only one thing for me to say. THANKYOU None of this, and I mean NONE of this would be remotely worth it if it wasn't for you all. To list and tag everyone that have contributed so much valuable not just to this community but to me would be nearly impossible. Thank you to every single one of you. Thank you for commenting and helping out on posts Thank you for sharing the wins you have gotten both at home and professionally. Thank you for believing in me and what I am building septically those of you who have been around since the beginning (you know who you are). I cannot tell you how happy my heart is to get in front of you all and teach, talk, ask questions and even learn a lot myself. It is a dream come true to become someone that people can learn from; to share my thoughts and have those very thoughts change the way people live their lives and do their work. It's only the beginning too, I can't wait to see what the rest of the year has in store, and I promise to keep building, working and recording for you all. From the very very very bottom of my heart.....Thankyou! Thankyou to every single one of you reading this and for being part of such an amazing community.

A while back I shared Plumbline -- a spec-driven workflow of AI-agent skills that build code in a trackable, accountable way, coordinating entirely through files instead of calling each other. The pitch was "trust, but verify": make the filesystem the contract, so you can actually inspect the contract. It just hit v1.0, and getting there taught me something I didn't see coming. Quick re-intro for anyone new, then what changed -- including the part where my own framework embarrassed me (on purpose). THE 30-SECOND REINTRO To build a house well you follow the plans, double-check the work, and keep everything plumb. Your spec is the plumbline. Plumbline splits a build into single-responsibility skills that never call each other -- they hand off through files: scaffold --> architect --> foreman --> builder --> inspector (once) (spec) (blueprint) (code) (proof) Each stage reads the last one's file and writes its own. The spec is one file and stays the source of truth end to end. The inspector runs with fresh eyes and proves the software against the spec -- "done" means shown, not asserted. THE NEW PROBLEM I WALKED INTO A skill is read COLD. A fresh agent -- or a different model entirely -- loads one skill with zero memory of the conversation it was written in. So every shared convention that lives only "in the author's head" is a silent failure waiting to happen. One skill writes a status line one way, another reads it slightly differently, nothing errors -- the run just quietly goes wrong. I had skills silently agreeing on dozens of little things -- how a spec tags a finished criterion, the exact words the inspector stamps, file-naming patterns -- and that agreement existed nowhere except in my head and a handful of separate files that were free to drift apart. THE FIX: A CONTRACT THE SKILLS GET CHECKED AGAINST So v1.0 adds a TERMS file -- a single, canonical definition of every token, status line, and convention the skills share. Every skill reads it first and stops if it can't. The shared ground is explicit instead of assumed.