Hi guys! I’ve watched the video of setting up the AI OS, and I'm kind of disappointed because I anticipated something WOW. I’m not a newbie in that field and already know many things, so after finishing the video, I still have questions, but they kind of go beyond its scope. I want help from advanced users who have already built it for themselves and use it regularly. If you’re not such a user, please, don’t paste LLM-generated answers just to get likes. Thanks for your understanding. Given: 1. I’m using a Mac Mini with an external SSD as my main drive (my user “igor” lives there).  2. I already have ‘igor/Coding Projects’ folder where I have several projects where we do code with Claude.  3. On top of that, in my main ‘igor’ folder, I have several folders, and some of them are small projects for short-term goals (car search, apartment search, etc.). 4. I’m a perfectionist and prefer to build the architecture upfront :)  Questions: Q1: The main question is - how do I organize my folders in a proper way? In the video, Nate shares “one single folder for everything”. All info (personal, business, everything) is stored in one folder. I can’t afford it, because I feel that’s illogical. I feel that I need to keep my “business projects with git repositories” out of everything else - it's just a cleaner approach for me. Following that, I have no idea how to organize it. I don’t want to copy the needed files from other folders and repos into my “AI OS” folder, and, moreover, keep them up to date across all places. I can share basic info about all other projects, repos, and keep that summary in the “AI OS” folder. But, I feel something wrong with such an approach, but can’t put my finger on it. Also, this could potentially be resolved via per-project memories & claude.mds, but it still needs triggers to be triggered without me guiding the LLM. So, what can you suggest? Q2: Do I need 1 LLM Wiki or many? I’ve heard about Karpathy’s wiki from the beginning, but I didn’t need it as I’m fully down the rabbit hole with my business project. Now, when I read about it, I can’t decide whether to have one big wiki for everything or create a wiki for meaningful projects/folders. On the one hand, I have an idea to add a wiki to each of my coding projects to keep documentation up to date and quickly gather needed info without burning tokens. On the other hand, one huge wiki for every aspect of my life seems better, as I can directly query it and get answers to everything. But ingesting seems horrible (either everything lives in the raw folder or I maintain multiple versions of the docs in both sides - wiki and its original source). I don’t know the right answer, but I anticipate that it is a double-edged sword where there’s no universal solution )

Most people in this space know exactly what to do. They've watched the videos. Read the breakdowns. Understand the frameworks. But their calendar is still empty. The gap isn't knowledge – it's implementation. Nobody is sitting with you, looking at your actual offer, your actual outreach, and telling you straight what's wrong. That's the difference between people who close clients and people who keep consuming content. I've been helping a few people here fix exactly that – and once they had someone walk them through it step by step, things moved fast. Honest question: what's actually stopping you from closing your next client right now – is it your offer, your outreach, or something else? Comment below – I read every reply.

I gave up on building AI OS on Codex because Nate’s instructions work much better in VS code + Claude Code! Finished the Context, Connection, and set up one skill. Time to start setting up the scheduled Agent layer! It’s quite fun to build it up and already start helping my work 😊!

Hi everyone! I've heard of some pretty cool cases when people connected Claude with Higgsfield MCP to build almost everything (from simple graphics to games!). But I suppose it costs enormously since you need to pay per token for Higgsfield AI. Has anyone had real experience with it? Can you share it with me, please? I want to hear real figures (how much was spent, whether it was worth it or not), not marketing ones. Thanks in advance!

Meanwhile, a different question is becoming far more interesting: What happens when the smartest models are open? 🔓 Over the last 12 hours, one story has been getting a lot of attention. GLM-5.2, a newly released open-weight model from z.AI, is earning praise from developers for coding and long-running agent workflows. Early benchmarks and developer feedback suggest it is narrowing the gap with the best proprietary models while giving organizations the freedom to self-host and customize. (Business Insider, 2026). Why does this matter? Open models are changing the business equation: No vendor lock-in. Deploy on your own infrastructure. Fine tune for your business. Reduce long-term inference costs. Keep sensitive data under your control. The conversation is shifting from "Can open models compete?" to "Should this workload even require a closed model?" For many internal business applications, the answer is increasingly no. (Willison, 2026). Business lesson: Don't choose AI based on the biggest brand. Choose the solution that delivers the best balance of cost, control, security, and measurable business outcomes. That's where competitive advantage is built. 🤝 👍 Follow for practical AI insights that help small businesses grow, not just keep up with the hype. References Business Insider. (2026). What is GLM-5.2? Another open-source Chinese AI model has Silicon Valley's attention. https://www.businessinsider.com/what-is-glm-5-2-chinese-ai-coding-model-2026-6 Willison, S. (2026). GLM-5.2 is probably the most powerful text-only open weights LLM. https://simonwillison.net/2026/jun/17/glm-52/