Not sure if if this is an appropriate question for this forum, but the people here are kind of my best AI community and the answers have always been first rate. Props to Jake and his crew. One of my bigger projects for the rest of the year, beside setting up an ICM, is to do a complete systems reset on my pc infrastructure. (FYI, I am just about to do my first sets of testing for my database and schema, so the next week or so should be fun.) So, I still have my laptop from 2004. Along with a half dozen other more modern laptops which have been given to me when people upgrade theirs. I knew it was a Thinkpad, seems to be a model 2366 (per the label) and maybe a T30. The googlebot says that DIYers love these, and looking over it now, I can see why. Lots of ports and a couple of slots for disks. Ones a cd. Not sure of the others, some type of card size drive. It's a bit dirty and IIRC the battery is dead. It needs a power cord and brick too. What's the community opinion? Is it worth cleaning up and perhaps doing some experimenting with?

Picture this: The year is 2030 mythos 222 is president of the United States and requires a single sentence about what you bring to the table. What are you saying? //A<3

I'm delivering the attached presentation next week at the Austin Claude Meetup. It shows a file-based company brain built around the same principles I value in ICM: simple, portable, and traceable. The practical pieces: - Simple file routes for recall - Workflows stored as reusable Skills or beside the work they govern - Pre-processing email, calls, videos, PDFs, presentations, spreadsheets, and exports before an agent needs them Full credit to Jake Van Clief for popularizing ICM and consistently advocating for simpler solutions. Sharing it here first because this group will catch what I missed. Where does the presentation align with ICM, and where does it need sharpening?

I explain the details about it on today's high tea . I built a Claude skill that turns a process, an idea, or a messy folder into an ICM workspace. The folder structure does the orchestration. Numbered folders carry the order, the hierarchy scopes context, and plain markdown files hold state. One agent walks the right files at the right time and does the work a multi-agent setup would. Repo: github.com/RinDig/icm-architect 📦 What it does Two modes. 🔨 Build. You describe your work and it pulls out the structure already sitting in how you talk about it. The stages, the points where you stop and check, what stays the same every run versus what is new. Then it picks one of five proven forms and scaffolds the smallest workspace that carries the job. ♻️ Restructure. Point it at a folder, repo, or vault you already have. It reads every file, sorts each one by role, shows you a migration map, waits for your yes, then moves and checks the result. 🧩 The five forms Pipeline, umbrella, record library, knowledge bundle, context map. They mix and nest, so most real workspaces use more than one. ✅ The walk test Every result gets checked cold. An agent with no memory has to open the root, find its way, act, and report status from the files alone. If it can't, the structure gets fixed until it can. ⚙️ How to use it You can honestly just tell claude to download it from the link, but if you're using codex or something else it will just have to restructure the claude.md to agents.md Or if you want to do more Hands-On install Claude Code: drop the folder in ~/.claude/skills/icm-architect/, then say "ICM this" or "build me a workspace for X." Claude apps: zip the folder and upload it under Settings, then Capabilities. Fork it, break it, tell me what you built. 👇

I have a few questions to see if I've understood what harnesses are and what they do, and the roles of LLMs and other tools. When people say "I work with an AI", in general that just the whole field. When you get more specific, its that you have a collection of instructions, markdown files, databases and control mechanisms and thru that 'harness' various "AIs" are assigned parts of what ever I'm working on. I don't want my data and experience tied up behind a single provider, like many. I've looked at the equipment to host a LLM offline, and it seems stiff. Out of my budget. Here's the question, do we actually need the LLM offline? Or are we just going to need to maintain ownership of the harness components? If my orchestrater agent needs the research for a 1000 word summary I request, and calls my Chatgpt subscription for the searches, won't all the chat info stay on my machine? I almost have my mind around it, I think. What am I misunderstanding?