Hand a cheap model a task and it re-reads everything, or confabulates the one ID that actually mattered. So I pack it instead. A Context Pack is one file: exact needles (ids, paths, values) kept verbatim, the bulk gisted, sized to half the model's window. Workers read what matters and re-fetch the rest. A manager routes each task to the cheapest Claude tier that can do it, on your subscription, never metered. Small jobs go direct. Big ones fan out under a cheap large-context model that reassembles the result. I shipped this repo by pointing the tool at itself. It said "12 ok". I believed it only after diffing every file, because a workflow once told me "ok" for work it never ran. Verify the behaviour, not the tally. Repo, MIT, built with Claude: github.com/PUSHINGSQUARES/Build Deep-dive + a fidget to try: aris-space.com/documents/dispatch/context-pack-dispatch //A<3

Everyone says you can't build and ship a real app live on stream. Too fragile. Too many things break on camera. So that's exactly what I'm doing. For two days. And Fable is the clock on it. Fable, Claude's newest model, goes metered on the 7th. This marathon runs two days straight, right until the moment the meter flips on. It starts with Fable free and ends with the meter starts running. A proper send-off, live, as it happens. Here's the twist that makes it worth watching. The app eats the stream. I'm building Mist, an iOS photo app. Fable is the hands. I direct. And the one signature effect we ship gets tested, live, on a screenshot of the stream you're watching right then. The app develops photos of its own creation. Building and developing, same word. That is the whole show. The finish line is real. A green "Ready to Test" checkmark in TestFlight, landing on air. Not a staged demo. One hero effect, shipped for real. This isn't magic and I won't pretend it is. Live build streams faceplant because they put the fragile stuff on camera. Device gremlins, provisioning, signing. So I flipped it. The rule is simple. Pre-flight the boring, stream the real. Every tedious piece is proven before we go live, so only the creative build, the part worth watching, happens on air. If it still breaks, you watch me fix it live. That's the deal. And you're in it. Drop a photo in the Discord and it becomes test data, live. The community's photos are what teach the effect to see. Bring the ugliest, weirdest photo you own. The thing I actually believe, and the reason I'm doing this in public. Shipping live isn't a coding problem, it's a staging problem. The model can do the work. The craft is designing the run so only the survivable parts face the camera. Constraint is the skill. Two days. One effect. One real ship. A send-off marathon that runs right through Fable going metered, building something that photographs its own birth. Twitch: twitch.tv/ari_evergreen

I'm on a hunt for resources. I'm at the point of building my website out. I know the scaffold of what has to be there for regulation in my industry and really already have that made (Data brokering). I'll have my SOC-2 Type 1 complete in the next 2 weeks and estimate is 3 months for Type II. I need help getting a good resource for working out my branding.md and design.md for assets and the website, as well as social media elements for GTM in the next month. Though I'm deep in the coding and engineering aspect, I haven't done much in any visual design with AI. For example immediately applied all @Jake Van Clief's stuff to my database structure, not any of his suggested blueprints. Ideas where to start? @Ari Evergreen

Most of what I ship gets shown finished. The wrong turns never make the cut. Right now they do. I am streaming the build live, and the stream is the part I usually edit out. Call it building in the open. The retries, the moments Claude and I disagree, the method as it actually runs instead of the polished write-up afterwards. The system around the AI is the intelligence. Watching it run live is the only honest documentation of how that actually works. If you have ever wanted to see the orchestration happen in real time instead of reading the recap, now is the window. https://www.twitch.tv/ari_evergreen What is the one thing you would want to watch get built, live? //A<3

This week I published zero posts. By the old unit, that's a dead week. By the real unit, it was the biggest week I've ever had. This post is the doctrine that explains the contradiction, because the contradiction is the doctrine. +———————————————————+ The mistake The world counts output in ships. Posts published. Launches. The thing that crossed a gate and showed its face. That is the wrong unit. Measure by ships and every quiet week looks dead. Every week spent wiring the engine looks like nothing. The graph is flat, you feel flat, you doubt the project. Ships are a gate, not the work. The work happens before the gate, in the rooms nobody watches. +———————————————————+ The reframe Stop counting posts. Start counting squares pushed. A square is the smallest unit of forward motion. A commit. A background job that started and did a thing. A capability unlocked. A wall moved one row over. Output is not the publish. Output is the squares that moved since yesterday. Swap the question. Not *what did I ship this week*: *how many squares did the engine push forward while I wasn't looking.* One question makes you miserable. The other makes you build. +———————————————————+ The call Stop measuring yourself in posts shipped. Here's where it bites. Everyone sees the posts. Everyone treats the posts as the proof. And yes, the publishing gate opens. Later. When the engine is ready to feed it, the gate opens and the posts come fast, because everything behind them is already built. The gate is not the work. The gate is the last five percent. The other ninety-five is the engine growing, the fleet learning, the squares moving, the model teaching itself a skill it could not do Monday and can do Friday. Measure that. Measure the commits, honestly, with chore commits called out and failed runs counted as starts, not wins. Measure capabilities unlocked. Walls moved. Routing getting denser. Conductor getting cheaper. Fleet getting louder. The engine is the output. The posts are a release valve on the engine.