📦 AND SOMETHING NEW: EVERY ENTRANT GETS A FEEDBACK FILE 📦 🔍 WHAT WE DID DIFFERENTLY THIS TIME Every submission was cloned at the exact commit that was public when we read it, and read file by file. The brief. The identity. The rules. The reference layer. The code. Where a repo made a claim we could check, we checked it. Arithmetic recomputed by hand. Sample photos opened and compared against the outputs that cited them. Files diffed. Self-tests traced. Thirty-two repos, read at the code/word level. And one lens over everything, because it's the lens this whole community is built on: does the build keep the human's judgment where it pays and put the deterministic work in code, where it can't hallucinate? 📦 THE FEEDBACK PACKAGE This is the new thing, and it's for everyone not just the podium. 📦 COMP #8: THE WILDCARD - The Vault Every entrant gets a markdown file. Three parts: 1️⃣ The read. What your build actually is, and the strongest thing in it cited to your own files. Rule numbers. Function names. Your own examples. 2️⃣ One push. The single change that most improves your build. Not a list. One. 3️⃣ An idea worth naming something original in YOUR build, credited to you, that the rest of the community is told to take from. Plus links to the builds your feedback points at. Nobody walks out of this comp empty-handed. Thirty-two builds, thirty-two named ideas. The roster alone is worth the download. 📍 The package + the full write-up (what held up, what was missed) live in the new Feedback module: 📦 COMP #8: THE WILDCARD - The Vault 📚 WHAT THE FIELD TAUGHT Three lines split thirty-two repos: ✅ Enforcement. A must in a markdown file is a request. A must in code is a constraint. (That line is from one of your repos. It's in the package. Go find whose.) ✅ Evidence. The builds that shipped receipts of a REAL run transcripts, dated logs, before-and-after fixes read differently every single time.

This one goes back a few years. I have an excel spreadsheet with about 30 columns that represent submittals that were individually reviewed over the last 5 years. Some were told yes; some were told no. We have about 10,000 examples. I want to see if Machine Learning can predict future submissions I have an ICM that builds other ICMs for me. This one is essentially controlled brainstorming. But these stages will help me stay organized. I want to see how machine learning does in terms of accuracy and solution. In about 30 minutes, I am going to type, 'what kind of machine learning is best to solve this problem'. It is a magical time that we have a tool that can guide us through examples like this - we can go from concepts to concrete solutions without a heavy textbook next to us. A few decades ago, linear regression was familiar to me. Backpropagation is very similar math to calculating thermodynamic properties during combustion. But I was raising kids while Machine Learning was king. So this is my chance to fill in the gaps - just a very small bit, I know.

When Bas first added me to this group, I could barely have told you what an API was. I've been mostly quiet since, because I was heads down building something, and I finally get to show you. But the win I want to share isn't the one I thought I'd be writing about. A few weeks in, I was at my kitchen table testing a feature, and my own app wrote something back to me. A little message, the kind it sends to a stylist. I read it and I cried. Me. The person who built the thing. It had just made me feel seen, as a hairstylist, and I wasn't ready for that. I'm a solo hairstylist. That's my actual job. The app is called Rooty, a companion for stylists who are tired of being told the only way to stay booked is to become a full time content creator. I built it between clients over about seven weeks. Here's the part I think this group will appreciate, and it genuinely surprised me: the code was not the hard part. The boring receipts: - 212 commits, about seven weeks, built between appointments - One Python file, roughly 8,000 lines, zero dependencies, just the standard library - 132 tests - Multi-tenant, real logins, running live right now with actual stylists signing up - Claude Code did the heavy lifting on the code, Anthropic's Haiku model runs the AI features - I directed all of it. Every product decision, every word of the voice, every call about what it should and shouldn't do. I'm not a programmer. I'm the person who knew what it needed to feel like. That last line is the whole thing, so let me stay on it. The code, honestly, the AI and I got through together. What I could not outsource, what no prompt handed me, was knowing when a message sounded like a brand instead of a friend. When it was technically fine and emotionally wrong. I felt those the way I feel a bad section in a haircut, right away, in my gut. And I sent them back. So the "it feels like it gets me" that people react to, that came from real decisions: - The captions and replies learn from my actual writing, not a formula. They sound like a person because they're trained on one. - Every AI feature is its own little room with exactly one job. None of them is a general chatbot. A tool that tries to do everything feels like nothing. A tool that does one thing warmly feels like a friend. - And me. I was the reject button. I read hundreds of generated lines and killed every one that rang false.

I realize I’m in a minority here with my location but if anyone is willing to make a trip out I will be at an event on the 29th! I’ve been speaking with the gentlemen running it and it sounds like there’s gonna be over 100 attendees by the time the date rolls around. I’m likely going to be giving a small demo which I’m totally going to try to record and will share here after. If anyone will be around here’s the link: https://westhartfordai.com/

I see an endless supply of posts out there claiming that models are degrading and are ignoring instruction or deleting files or you name it. Even with the advent of fable and sol. This is almost never my experience and I don’t know why. Do I understand the capabilities of each model well enough to avoid them? Do I not ask for big enough goals and tasks? Are my standards and practices well defined to avoid drift? These are the questions I find myself pondering every time I see something like this. What do you think?