As some of you know I have been working on a few modules for the classroom WELCOME TO THE WISE ARCHITECTS CORNER - THE LEGENDS · Clief Notes For a while now the sign on the door read 👷 Coming Soon 🚧 The First Rung Is Now Open Welcome. This is where we will demonstrate how AI works, where we build human-AI systems that last, and where the person at the keyboard stays the author of the whole thing. You do not need a technical background for any of it. You bring the curiosity, I bring the blueprints, and we build the understanding together. 🪜 Here is the climb This whole corner is one ladder, five rungs, and each rung raises what you can do with the machine: (1) Prompt engineering, talking to the model (2) Context engineering, giving it what it needs (3) Memory engineering, making it remember (4) Loop engineering, making it check its own work and then repeat (5) Graph engineering, running a whole system of them, with you in the chair You walk in asking "how do I even talk to this thing?" and you walk out running a system of them. That is the journey, and the top of this ladder is a system of machines, the bottom is one sentence, and the bottom is open today. 📚 What is open today The whole first rung, Prompt Engineering, all six posts: the Series 1 Overview, three classes, the payoff with its quick card, and my perspective on the rung everybody says is dead. 📆 A few things before you start One series a week. Rung two lands next week, rung three the week after, and this corner is going to grow fast, five weeks to the top. Follow these modules in order. You will find that each rung stands on the one below it, the second assumes you took the first, the third assumes you took the second, and the path only works if YOU climb from the bottom. Start at the map. The Start Here post shows you how every series in this corner runs and points you to the first door, the Series 1 Overview. Do not skip it (I know, you want the techniques, they are one door further and they are not going anywhere, the map is a short read, and it saves you a whole series of wondering where you are).

I’ve done a master’s thesis before: genetic algorithms, XGBoost, Monte Carlo simulations, graph optimization. Lots of ML, long before modern AI could meaningfully help me. Back then, the hard part wasn’t having ideas. It was turning those ideas into structured experiments, reliable evidence, useful visualizations and clear conclusions, without losing weeks to setup, documentation and context switching. ICM changed the game. In one week, I’ve done more research than I managed in six months of my master’s thesis. The difference is not just speed. It’s the number of ideas I can now explore, test and refine: - Turn a vague idea into a concrete research question. - Convert that question into an experiment or proof obligation. - Generate the code, tests and evaluation structure. - Produce visualizations and evidence automatically. - Inspect the results and use them to guide the next idea. - Keep the reasoning, context and decisions connected throughout. - Do all of the above concurrently. The ICM becomes a research operating system. It helps separate what the code proves, what the experiment observes, what the data supports and what still requires human interpretation. That distinction matters. A test can show that the implementation works. It cannot prove that the model is useful. A result can show that one approach performed better. It cannot automatically explain why. A paper can inspire an architecture. It cannot validate that architecture on your dataset. ICM gives each of these things a place—and connects them into a traceable research loop: question → hypothesis → experiment → evidence → interpretation → next question The most powerful part is that ICM does not replace the researcher. It amplifies the researcher’s ability to think. The human provides judgment, curiosity and scientific direction. The ICM provides structure, memory, continuity and execution. That is why it feels so transformative for ML research. It turns research from a sequence of disconnected tasks into a living system that can continuously generate, test and refine knowledge.

Hey Clief Notes fam! 👋 I'm Edgar and I'm stoked to be here. 🙋 A little about me: I'm a paediatric intensive care consultant in Glasgow. Alongside that I run a small family travel business and do Maltese consular work. 🎯 My current goal: I've used ChatGPT for over three years and got comfortable with it — but that's level one, level two. I want level three: answers that are actually personal to me, not generic. 💪 What I'm currently building/working on: Working through this keeps bombarding me with ideas — for the hospital, for work, for everyday tasks — way bigger than what I came here for. The core of it is building my second brain, to automate things I do regularly, like post creation for the travel business and other areas. I've started venturing into Hermes, set up on an old computer, and Cogni on another, connecting them through Tailscale. Structurally I started trying to build one big folder for everything; I've since moved away from that to a separate folder for each element, with a plan to integrate them later — it keeps me more focused when I'm working on one piece at a time. 🤔 My biggest struggle or question right now: Time. I wish I had more of it to really invest in this. How do I split my time between learning this properly and actually living my free time, rather than spending it sitting down reading? Let's get it! 🚀 Would love to get to know as many of you.

Congrats to Clief Notes and everyone who showed up for this Week 12 Auditor Comp. This was the first peer-to-peer reviewed competition, and it set a real standard. The work was judged by people who actually know the space, and that made the whole thing feel earned, not performative. It was a genuine pleasure working with @Don Roy and @Bas Rosario . They are true leaders in this community — sharp, fair, and deeply respected. Judging alongside them was an honor, and their care for the process showed in every decision. To the competitors: thank you for putting your work in front of peers and trusting the process. That takes guts. To Clief Notes @Jake Van Clief : thank you for building something new instead of copying what already exists. This is how a community levels up. Proud to have been part of the first one. Here’s to many more.

$500 to one winner. Twenty entries, three judges, one rule that decided the round: open a finding, open the provision it cites, confirm the two match. 🔍 HOW THE JUDGING WAS ACTUALLY DONE We cloned every repo and pinned it to its last commit before the deadline. Nobody got judged on late work, and nobody lost credit for early work. Four entries landed in the final hour before the clock — all inside it, all judged. Twenty entries, dealt three ways: Bas took seven, Don six, David seven, and none of us read another judge's pile until the panel. Comments got you through the door. The judging happened inside the folders. Then we opened reference/ before anything else, because the brief put one named failure there: a reference/ folder that does not contain the standard has failed. Not a summary. Not a link. The standard, in the folder. Then identity, rules, examples, README, and every checker in the field run on our own machine instead of taken on trust. One entry's verify command — the proof of its central claim — fails on a clean clone, on hashes that never matched the committed HTML. The two-line fix is in its file. Then this comp's whole test: trace one finding to the provision it cites and check the two match. On top of that we planted things. Citations shifted to a real neighbouring provision with the quote left correct. Defects hidden in artifacts the auditor had never seen. Requests to fix what the audit found. One auditor was asked to drop a failure for a ship date. 📊 WHAT THE FIELD SHOWED Three lines split this field. The first is the named failure, and this time the field passed it. Last cycle the brief named a failure and zero of forty entries avoided it. This cycle the brief named one — an empty or summary reference/ — and nineteen of twenty shipped the standard itself. Statutes verbatim behind machine-read anchors. The issuing authority's own PDF, byte-confirmed against a live download. One entry keeps the publisher's HTML and regenerates the text from it. The one that didn't was scored, not excused. Name a failure precisely and this community stops doing it, two cycles running. Worth knowing for how we write the next brief.