Thank you very much for all of your support and love towards me! :) I really appreciate it, What would you like to see me post next?

I’ve managed to convince one of my closest friends @David Chalk to come join us and learn stuff. I’m saying he’s player 2, because I was totally here first, but in real life where we’re pretty similar he keeps reminding me he is the original… Some of you may remember him as my friend who gives me “frank facts”. 🤣 I have promised to help build an ICM system to help him with some things and encouraged him to get some information directly from the source… because he’s totally going to want this built in a way that works for him. So, short version, please be kind to him and help me say hi. I am willing to open predictions on how long it takes for him to come up with good sim racing use cases for ICM while hanging out with this community… I don’t think it will take very long. Also… are we actually some kind of AI cult? Asking for a friend.

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: