Someone said to me the other day, “you post all this AI stuff but don’t you know it still struggles to spell?” I’m sure we’ve all seen the videos of people asking how many r’s are in strawberry. Showing how unreliable the models are. But often these videos are misleading. Here’s my thoughts below. 👇

This is the only place I can talk local ai without getting blank stares, so let's actually see what everyone is running. I'll go first. here's the whole stack: HARDWARE ▸ Alita - personal dual-3090 rig at home. 48gb total vram, 128gb ram. kept totally separate from anything work related. MODELS ▸ primary: qwen3.6-35b-a3b on gpu0, served by llama.cpp. mixture-of-experts, ~3b params fire per token. q8 kv cache, 256k context. ▸ router: a ~9b qwen on ollama out front, deciding what's actually worth waking the big model for. ▸ embeddings: qwen3-embedding 0.6b and nomic-embed-text, same ollama instance. AGENT LAYER ▸ hermes, running as Alita here. three daily jobs: morning brief, work email summary, personal email summary. all land in discord. ▸ weekly maintenance runs on a different scheduler with hermes as the watchdog, on purpose. runner dies, watcher yells. watcher dies, the daily jobs go quiet and I notice. two failure domains instead of one. MEMORY ▸ obsidian vault as the source of truth. ▸ hybrid search over it - bm25 plus local embeddings, running in-process. no extra service to babysit. ▸ qdrant for the vector-store work that actually needs one. INTERFACE ▸ the observatory - a front end I built over the vault. not a dashboard. a command center I actually work from: projects as boards, sessions as a timeline, drafts moving through a publishing pipeline, all of it reading and writing the same markdown files. The one piece I would not give up is the vault. the models change every few months. the notes are forever. The thing that taught me the most had nothing to do with hardware. I did kill a pile of containers nothing was consuming - n8n, a web ui, a couple databases - but that was housekeeping. the real one was giving up on folders. I spent a long time sorting notes into the right directory and it was wrong again six months later. Now every note carries its own frontmatter and the folders are just a cache I regenerate from it. Type isn't a folder. Status isn't a folder. The structure lives in the file.

This comes straight from the ICM method (I asked Claude to explain to me), so none of it is my invention. But seeing the five forms written out as plain shapes made the whole system land for me, and I'm actively building with it right now, so I wanted to share it the way it clicked. Every ICM workspace is one of five shapes, or a mix of them: 1. Pipeline. Same steps, run over and over, new deliverable each time. Think of a recurring 30-page client document: data in, checks run, sections drafted, reviewed, published. One folder per step, numbered in order. 2. Umbrella. Several different workflows that share one brand, voice, and reference layer. One shared folder holds the facts (brand guide, company snapshot, templates) and every workflow points at it instead of keeping its own copy. One home per fact. 3. Record library. The unit is not a run, it is a thing that accumulates: a client, a lead, a property, a patient. One folder per record, growing over time. The trap here is tracking status by moving files between folders. A status log inside the record is cleaner. 4. Knowledge bundle. The product IS the organized knowledge. A wiki, a second brain, course notes. The value is that a person or an agent can walk it and find things. 5. Context map. The subject is a whole organization. Teams, processes, where everything lives, and a small routing file at the top that answers "where does X go" in one read. The part that surprised me: they compose. My real setup is a context map at the top, holding an umbrella of shared facts, containing pipelines, publishing into record libraries. That's not breaking the rules. That's the normal case. One warning from experience: don't build folders for work you might do someday. I once built a beautifully organized workspace for future tasks, and it sat empty forever because nothing real ever flowed through it. Start with what "done" looks like (a phrase I picked up from @Ari Evergreen. If you can name the deliverable that comes out the other end, and you're already producing it the painful way, build the structure around that. That workspace gets used on day one, because the work is already there waiting for it.

ICM getting you down = @Don Roy Data = @Mira Bradshaw Video/Images/things I can't even pronounce = @Ari Evergreen Needing the human and knowledge = @Carla Bosteder and @Aaron Kruger Admin = too scared to tag them 😉😉 but you will know when you know. other things = classroom, videos and links there is even a Don's bookshelf and ari's space is out of this world (see what I did there). #checkitout Participate in comps (even if you suck... you learn - this is why you are here) Good housekeeping = search (many members have already been where you are) even better check out the legends it is the 11th commandment (Don will post about it -#nopressure Don) Don't be afraid to post but also don't get stuck on the likes and the climbing. Focus on the learning and you will find your place. Above all else... Embrace the 'dumb' it is the only way you truly make yourself teachable. Good luck, God speed, go into the light, break a leg, or whatever people say...