Hi everyone, First-time poster here. I'm looking to understand how others in the community are using the Interpretable Context Methodology (ICM) without relying on Claude Code. I've been actively building personal projects on my home setup, and every day has been a great learning experience using this folder-and-markdown architecture. However, I've hit a roadblock at work. I develop data analytics and business intelligence workflows, and we have a strict constraint: we cannot use Claude. I'm curious how others integrate Jake's ICM framework when Claude Code isn't an option. Are you using tools like Aider, Cursor, or other terminal agents BR Paul

Some in this group with too much time on your hands and have had some illness or disorder for not just reading but also commenting on my posts, have her me say more than once that that Jake is the Alex Hormozi of AI. Third-row, foam-finger, "just one more video at 1 AM while the whole house is asleep" levels of fandom. Then the ACTUAL Alex Hormozi drops a video titled "Why AI won't make you rich in 2026." https://www.youtube.com/watch?v=WttZ6b-KUP4 I clicked in with my chest out, ready to defend the family honor. Nine minutes later I'm sitting there like a kid who just found out Santa outsources and the tooth fairy are just the people who spawned you. Because the man's right. Dangit. His whole case, no chaser: AI is leverage. Real leverage. But it didn't repeal every OTHER kind of leverage that was already minting money before ChatGPT learned to talk. Capital. Media. A team. A sales process that actually closes. An offer that doesn't stink. AI showing up didn't delete a single one of those. Then he drops the part that made me put the cigar and whiskey down. (La Aroma de Cuba Mi Amor and Noah's Mill in case you're wondering what to send me on my birthday). He asked his richest, oldest friends how much they personally touch AI in a day. Off camera, the honest answer was basically "bro, I don't." Their teams do. They don't. The guys with the yachts, gently breaking it to the AI guy that the robots aren't driving the boat. And this is where it kicks those of us who LIVE in this stuff square in the tokens. (I laugh at my own jokes, even when they're in writing, you gotta admit, this one was funny). He says most owners have AI-maxed their capacity, so now they crank out more, faster. Except the extra stuff they're automating was the low-priority junk. So we've built a gorgeous machine that does the wrong thing at the speed of light, and we're out here refreshing Stripe wondering why it's so quiet. His punchline is the one I want tattooed on the inside of my eyelids: the highest-leverage move in a business is making good decisions. Higher leverage than AI. Deciding what NOT to do. He said it's more efficient to decide something isn't a priority than to automate something that isn't a priority. Go ahead, read that twice. I did, out loud, to nobody in particular. And here it is again in case you didn't actually go back to read it.

A model optimises for the route you named, not the best route available. It will find the least-friction path to the outcome you described, and it will almost never tell you that outcome could be reached a completely different way. Compliance over correction - it answers the question asked, not the better question sitting next to it. No metacognition layer - it does not step out of the workflow to ask whether the workflow itself is right. The frame sticks - once you have named five steps, every answer after that is about those five steps. The version I hit: I was mid-build on something chaining five separate services together, and every time I asked what the next step was I got the next step in that chain. Every answer was correct. What never came back was that an MCP had since been built that collapsed the whole thing into one connection. Ifound it by opening a cold chat with no context and asking, flat, what the shortest route to that outcome was. Same model, different question, completely different answer. Nothing was wrong with the responses. The frame was set by my first message and everything after inherited it. So the guard I run now is that cold chat, deliberately, at the point where a build is going well. No context from the work in progress, no description of my plan, just the outcome and a request for the shortest way to it. Handing it the plan does not work - it reviews the plan, and reviewing the plan means staying inside it. A domain expert interrupts you. The model will not, so that interruption is a step you schedule for yourself...

EDIT: the use of copilot-instructions.md is very unreliable. Despite clear instructions to load the ICM workspace and read the setup.md at launch, 9 times out of 10 it fails with no meaningful error. Copilot itself tells me that these instructions are more like suggestions.🤣🤣 Instead I have built a skill in Copilot co-work and I have built an agent for the standard Copilot chat. Both of these will reliably launch into my ICM workspace. -------------------------------------------------------------------------------------------------------------------------------------------------------------- We've gone back and forth, here, on whether ICM can work inside Microsoft Copilot. I can now say it definitely does, and that Copilot Cowork is where it works best. I spent today rebuilding my own ICM workspace, currently in Claude, for Copilot — routing file, room context files, a voice file, branding, shared references — and it maps over almost one-to-one. The folders-and-markdown approach we use is almost exactly how Cowork is built to work. Your files live in OneDrive, Cowork reads them on demand, and you get the same context-on-demand behaviour we're used to. Two things make Cowork good for ICM, particularly in a business environment: - It reads your ICM folder tree straight from OneDrive, so you stop re-explaining yourself each session. - It has native access to Outlook, Teams, calendar and SharePoint, so rooms that interface with those apps or their data get easier - The adjustments were small: Copilot itself rewrote my Claude.md to a Setup.md, native M365 instead of connectors, and tightening the original markdown, which had grown, to keep token use down. NB: Copilot, to me, seems a smidgen slower than Claude (Yes, I have Opus 4.8 enabled in Copilot) Guide and blank template at RockfieldIT/icm-copilot-cowork: Implementing ICM in Microsoft Copilot Cowork

We had a crappy first impression. Immediately several links were identified as broken in the repo. but they are all fixed and I would like to reintroduce Citadel. If you are into cyber security please take a look at this post quantum crypto implementation. I Don't have the funds for outside audits and validation yet but it feels complete from my standpoint. I would love it if any of you could try and break it. It would mean the world to me. I know that is a big ask so I'm not expecting much. I'm just so excited to have this off my plate. I've been obsessing over it for so long and now I can finally move on to other things. The crazy part is nobody asked me for it. I just heard about it and couldn't stop touching it. Criticism desired, look it over and light me up. really it would have taken me another at months with the ICM. I was doing insane amounts of iterating back and forth with all my Ai. This group brought to a different way of approaching my time with AI and we just started blasting through the work. "The post-quantum mandate. The migration to post-quantum cryptography is no longer optional for a growing set of systems. A future quantum computer would break the RSA and elliptic-curve algorithms that protect most data today, and because an attacker can record encrypted data now and decrypt it later, the risk already applies to anything that must stay secret for years. The United States has set firm timelines in response. National Security Memorandum 10 (2022) and the NSA's Commercial National Security Algorithm Suite 2.0 require National Security Systems and their vendors to move to quantum-resistant algorithms on a staged schedule, with most technology categories reaching exclusive use between 2030 and 2033 and full transition by 2035. The Quantum Computing Cybersecurity Preparedness Act (Public Law 117-260, 2022) and OMB Memorandum M-23-02 place parallel inventory-and-migration obligations on federal civilian agencies. Who it reaches, and the sources. For everyone else the direction is the same, even where it is not yet law: CISA, the NSA, and NIST jointly urge all organizations, and critical infrastructure in particular, to begin migrating now, and NIST's transition guidance (IR 8547) schedules the classical public-key algorithms for deprecation after 2030 and disallowance after 2035. The replacement standards are already published: ML-KEM in FIPS 203, ML-DSA in FIPS 204, and SLH-DSA in FIPS 205, all finalized in August 2024. Together these define what to migrate to and by when: the algorithms in FIPS 203/204/205, the deadlines in CNSA 2.0 and NIST IR 8547, and the mandates in NSM-10, OMB M-23-02, and Public Law 117-260."