Quick note about Skool’s bot protection: If your comment is just a few short words, you’re better off hitting the like button instead. What you probably don’t know is that the admins are getting absolutely blasted with anti-bot warnings — and Jake didn’t do me any favors by blowing up my notifications. We’re growing extremely fast (25,855+ and climbing), so we’ve got a massive target on our backs. Short, low-effort comments are triggering the system hard right now.Help us keep this community high-quality: Only comment when you have real value to add — sharp insights, innovative ideas, or meaningful experiences. Likes 👍 are there for quick appreciation. Save the comments for stuff that actually moves the conversation forward. Do your part. Let’s protect the space we’re building together. Thanks, legends. *** @Jake Van Clief has not approved this message, he's swamped ***

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.

Something I learned this morning that I should have known months ago: the Clief Notes agent isn't just decoration on the classroom. It runs on Decster.ai, and it's wired straight into the community. Posts, members, profiles, classroom, and DMs. Premium and VIP members have unlimited access. That includes direct messages. You open your DMs, you message the agent, it answers. No ticket, no queue, no prompt engineering degree required. I tested it with the dumbest possible question: @Clief Notes Agent "Who am I?" Then I gave it one real sentence: I want to build a software factory. It knew exactly who I was: my tier, my background, where I was in the Getting Started track. And from that one sentence about a software factory, it mapped a path through five classes in our curriculum, told me exactly what to build first, and closed with a question instead of a sales pitch. The full transcript, unedited, lives in David's Corner in the classroom. Watch how the answer builds as the prompt sharpens: https://www.skool.com/cliefnotes/classroom/c7f102c7?md=84741b365af44869b0af40a93fe1c238 Three things worth pointing out, and the receipts for all three are in the article. It knew who I was before I told it. Tier, background, where I was in the Getting Started track. It reads the same community data you see. One sentence in, one structured plan out. I didn't engineer a prompt. I said "software factory" and it came back with structure, class links, and a next question. That's the difference between a chatbot and something wired into context. It works for you, not the other way around. Unlimited DM access means you can treat it like a colleague that has already read the whole curriculum. Ask it where to start on your specific project. It should answer with your situation, not generic advice. Honest disclaimer: this is still a work in progress for me. I'm testing what it gets right, where it goes generic, and where it invents things. Garage tinkering, not production gospel. But the DM capability alone is worth knowing about, so I'm flagging it now instead of waiting until it's polished.

My Name is Alexandre and I'm really happy to be here. I saw Jake's videos on YouTube months ago. I thought I understood the files and folders concept and went about building everything by myself for months, I got some results and some interesting projects working on a very low budget, which is a challenge I enjoy very much. My Goals: - To learn more, I've gotten so much clarity from actually following the lessons rather than keep building and guessing. - To find a community to grow together. - To learn by building, to do so in public and sharing. I am currently working on: - I have a writing project that was built in Claude projects, it was way too over engineered and needs simplifying to integrate my workspace ICM. - Focusing on a Yoga practice app I built for myself. My greatest challenges: - So much to learn, so little time.

a16z speedrun is one of the biggest accelerators in the world. We submitted our application a bit back on the recommendation of one of our friends. Our EdubaWare software has been in closed testing for a bit (get ready, next week thousands of you will get access to it and see our changes) We received and Email yesterday saying they want to hear more from us and to send them a video in under three minutes that explains: - Your backgrounds and greatest accomplishments, professional or personal - What makes you exceptional, and why you're the team to win this market - What you're building and what problem it solves - Why this is a big, underserved opportunity - What progress you've made so far  Now fitting all that into one video is challenging, but we did our best. I hope this gives you a view into the other side of my life which is my company Eduba!