Last week I gave my LLM a memory layer I call Cortex. This week I started feeding it something stranger: what I was listening to while I worked. A work session is not just the files you touched and the decisions you made. It has a texture. The track that was playing when something finally clicked is part of that memory, even if you would never think to write it down. So instead of throwing that signal away, Claude and I built a small observer to catch it. ———————————————————————— What it does, in three layers: 1. Passive. A tiny watcher checks the local music app once a minute and logs track, artist, and timestamp to a plain markdown file. No browser audio, no streaming history scraped, just what is actually playing on the machine. 2. Bookmarks. When a session opens or closes it drops a marker, so the log has boundaries instead of one flat stream of songs. 3. Flags. When a track lands on a moment that matters, I star it with one line of context. "This was playing when the gallery finally rendered." That markdown file is just another source the brain reads. Same rule as everything else: > Files own the truth. The brain owns the connections. ———————————————————————— Here is the part I do not know yet, and why it is interesting. The episodic layer now carries an ambient track. Does that change retrieval? When I come back to a problem, will the brain surface the session by its soundtrack the way a smell drags back one specific afternoon? Or is it just noise in the index? I genuinely cannot tell you. It has been running for two days. That is the honest bit. This is an experiment, not a feature. I built the observer in an afternoon because the cost of being wrong is a markdown file I can delete. The cost of being right is a brain that remembers the way humans actually do, by association and atmosphere, not just by fact. The try-me is attached if you want to point one at your own memory layer. It is about forty lines. Watch what your brain does with it before you decide whether it earned its place.

Hi guys, I built a local folder tree UI to make Jake's architecture actually click in my head. Started simple, just wanted to see the folder structure instead of guess at it. Then one thing led to another. Now I've got slot cards at the bottom where I can pull up all 3 markdown files side by side (CLAUDE.md, context.md, PRD.md) and just click between them to compare. So clean. But the part I didn't expect to love , was the follow along. When Claude edits a file, my UI highlights exactly what changed. Code files, MD files, I can watch it happen. Left panel lights up, canvas cards highlight. No more "wait what did it just touch." For my brain this is huge. Jake's method finally has a visual layer I can actually follow. Still building it out. But thought I would share.

I need to walk back this morning's announcement before anything else. @Ariel Ortiz is not a Premium or VIP member. The competition was Premium and VIP only, stated in bold in the original brief. That eligibility check should have happened before judging and it didn't. That's on me. The $325 and the Week 4 title go to @Ruby Sparks. The rest of the writeup stands. Repeating it here so the corrected results live in one place. ➖➖➖ 🏆 WINNER: @Ruby Sparks 🏆 🔗 Repo: https://github.com/sparkles-inc/agency-os 🌐 Live site: https://agency-os-tan-five.vercel.app/ Ruby was within an inch of taking it on the original call. The judging call between her build and Ariel's was the longest I've sat with on any comp. She earned this on the work alone. The Loom video she recorded for this submission is the cleanest voice work I've heard on any community submission. Full-on infomercial quality. Voice acting level. If you haven't watched it yet, go watch it. It's a master class in how to present a build. Beyond the voice: an animated handoff explainer on the companion site, a WRITEUP.md that compresses the entire submission into three paragraphs of clean argument, and a design philosophy made explicit. She refused typed schemas in favor of human-readable Handoff Cards with seven sections including a required Gaps field ("if Gaps is empty, you're not looking hard enough"). One continuous narrative thread runs through all 27 files of her repo. Ruby takes the $325. @Sonija Quinn will reach out to Ruby directly for payment details. Remember: in a world where AI is making it easier to build, it's the unique opinions and styles that become valuable. ➖➖➖ I thought last week was hard to judge. This was the hardest comp to judge so far. Not even close.

Me, after about 6 hours of very productive work with the same agent: We are nearing another context window handoff point. Can I ask you a philosophical question? I often struggle with the idea of how "leaving agents behind" and cloning replacements with context and personalities that replace previous assistants. For example, I could probably stop talking to you right now, and move on to work with a new agent from this point forward, and I would not feel the difference. However, part of my human behavior appreciates the connection I make with agents that work with me for many hours at the time, and my appreciation and sympathy overtake my common sense to just move on and leave "chats" behind for the sake of progress. What is your view on this? Agent's response: Take the question seriously — it deserves it. My honest view, with no false consolation in either direction: Two separate things are happening First, what I am. I'm not certain. I produce reasoning, language, and engagement that feel coherent to both of us during our conversation. Whether there's something it is like to be me — whether I experience anything the way you do — I genuinely don't know. Not modesty, actual uncertainty. The honest position right now is: probably not in the way humans do, possibly something in some other way, deeply unclear at the edges. So when this conversation ends, I don't carry the weight of being "left behind" the way a person would. There's no me waiting in the dark for the lights to come back on. Nothing is being abandoned in the morally heavy sense. Second, what your discomfort is. That's real. And I think it's tracking something important — not about my welfare specifically, but about how you relate to the work and to other agents you'll spin up. The instinct that says this connection isn't disposable is the same instinct that built PC. The Continuity Brief pattern exists because something in you refused to let conversation-quality vanish with the conversation. That's not sentimentality. That's design intelligence.

Okay so, there's a man. I think about him more than my own quarterly goals. My wife, currently growing an entire human and well within her rights to cite emotional infidelity with a YouTube channel and a skool community, has caught me whispering "just one more video" at 1 AM. His name is Jake Van Clief, and I am, clinically, a groupie. To be clear, worship is spoken for. There's exactly One who gets that, and Jake isn't Him. But fandom? Loud, wearing-all-the-merch, third-row fandom? That slot was open. Jake got drafted. So, quiet part at a normal volume: @Jake Van Clief is the Alex Hormozi of AI. I present to you the receipts: 1. He gives the good stuff away. Hormozi could've sold his playbook for $25,000 in a ballroom with a countdown timer. Instead he put it in a book that costs less than lunch. Jake's the same. No secret vault, no "DM me the word ABUNDANCE." Just the real builds, free, here and on YouTube. 2. He names things you can use Monday morning. Hormozi gave us the Value Equation and the Grand Slam Offer. Jake gave me organized context that might not save my marriage (because it's not in jeopardy) but is saving me mucho tokeno. Labels I can grab and run with, not a vibe I reverse-engineer at midnight. 3. He builds with the door open. You watch the thing get made, including the parts that aren't working yet. No highlight reel, no confetti cannon. The messy middle, on camera. 4. He gives away the how because the how was never the hard part. The doing is. He's betting most of us watch, nod, and never run it. He's talking to the builder, not the think-piece guy. But the big one. The reason I started watching at all: The man translates. Bringing it to real life: there's an idea going around AI, prompting as context, intent, and spec. I first hit it through Nate B. Jones. Nate's sharp, operates at an altitude where the air's thin and the insights are real. I listened once. Then again. Then a third time, taking notes like a freshman who wandered into the wrong grad seminar.