Activity
Mon
Wed
Fri
Sun
Jun
Jul
Aug
Sep
Oct
Nov
Dec
Jan
Feb
Mar
Apr
May
What is this?
Less
More

Memberships

Clief Notes

27.7k members • Free

AI Native Engineers

254 members • $89/month

Oracy Club

487 members • Free

DEA - Sales Onboarding

133 members • Free

Engineers in Business

1.1k members • Free

KubeCraft Career Accelerator

861 members • $4,800/year

Limitless Skool

395 members • Free

Synthesizer: Free Skool Growth

41.7k members • Free

35 contributions to Clief Notes
if ur repo sucks i kinda like it
someone in here rebuilt the same system three times in a month. felt stuck. but that's not stuck. *that's the recipe.* --- most people wont feel this. they copy a template, change the colors, call it shipped. they skipped the part where you hate your own work enough to destroy it. *that hate is the signal.* your taste is ahead of your ability. you're not a tourist. --- you're not stuck because you can't finish. you're stuck because you actually care what it looks like when it's done. that's the whole reason you're going to be good. --- i've rebuilt the same workspace a hundred times. don't mistake your reps for failures. each time i saw something i couldn't unsee. a cleaner way. something that made the last version feel like it lied to me. no one sees the versions that die. but those versions are the only reason the current one works. the rebuild loop is not a detour. it is the path. --- this is the very thing that gives you the eyes to see. and you'll need those here. cause when you're actually building, you can look at someone else's project and see where they've been. the constraints they accepted. the fights they won. *it's right there in the workflow*. that's how you know you're among good people. not because they post wins. because they have a folder full of versions that didn't make it. and you know exactly what that means. --- you're not stuck. you're exactly where you're supposed to be. keep breaking it.
0 likes • 8h
This is written with Claude sonnet. It has okay ideas, but please spend more time making it readable 💀
No sales page could ever describe this
No sales page could describe what actually happens in this community. I have been here since pretty much the beginning, and I upgraded to VIP the moment I saw the folder structure system. Not because it was new to me, (I had been doing something similar already.) But the way Jake explained it, the language he put to something I had been feeling but could not articulate, that was the moment I knew I just needed to see where this thing goes. What has happened since has genuinely blown me away! Not just the value Jake and the team bring, which is real and consistent. But the way the community has come together in a way that no sales page could ever describe and honestly, no one would have predicted. Here is what I know now that I did not know then: Premium is where the concepts stop being concepts. The Foundation stuff is good. It gives you the map. But Premium is where you actually learn to drive. Worked examples, production-grade templates, real-world depth. The difference between knowing how something works and knowing how to make it work for you. VIP is something different entirely. I have been in a lot of communities. A lot. And I have paid a lot of money to be in some of them. We are talking well over ten times the cost of a full year of VIP. And I did not get out of those what I get out of this. Most of them have one of two problems: either the value only exists when the founder is in the room, or the “inner circle” is just a room full of people performing expertise at each other. VIP here is neither of those things. What actually happens is a group of people who are genuinely good at different things, sitting in a room together, looking at what you are building and telling you what they actually see. No gatekeeping. No pretending. Just, “here is what I notice, here is what I would check, here is what worked when I tried something similar. Someone brings a compliance question and the person with the compliance background speaks up. Someone is stuck on positioning and the person who has been through it three times says the thing they actually needed to hear.
No sales page could ever describe this
3 likes • 9h
Based comment. most of the value is in listening and having humility. that's in short supply, but we're holding onto it with everything we got.
🏆 WEEKLY COMP #3: THE SPECIALIST 🏆
💰 $325 CASH PRIZE 💰 That's a full year of Premium. Win this and your membership pays for itself. 📋 THE CHALLENGE You just got hired again. Different client this time. Meet Sarah, a freelance copywriter who's drowning in context-switching. 📎 Download the full client brief attached to this post. Short version: She works with three types of clients (SaaS founders, ecommerce brands, local service businesses) and starts from scratch every project. She doesn't need another tool. She needs a system. Your job is to build her a folder-based AI specialist she can drop into any Claude project. The folder IS the deliverable. 🗂️ THIS WEEK YOU LEARN ICM Up until now, comps have been "build a thing." This week you utilize the methodology taught throughout the community. 🧠 Folders as architecture. That's it. That's the whole concept this week. Your specialist is a folder with five things: - 📄 identity.md (who they are) - 📐 rules.md (how they respond) - 💬 examples.md (what good looks like) - 📚 reference/ (source material) - 📖 README.md (how to use it) Drop the folder into a Claude project. Claude becomes the specialist. Reusable. Shareable. Portable. 🎯 PICK YOUR SPECIALIST Don't pick copywriting. That's Sarah's example. Pick something YOU would actually use. A few sparks to get you thinking: - A salary negotiation coach - A meal planner that knows your dietary restrictions - A code reviewer for your stack - A real estate market analyst for your city - A technical recruiter screener - A grant writer for nonprofits in your space The more specific, the better. "Marketing expert" is not a specialist. "B2B email expert for enterprise SaaS targeting CFOs" is. 💼 WHY THIS ONE LANDS ON YOUR RESUME Real talk. Winning a comp in a Skool community doesn't get you a job by itself. But shipping a working folder-based AI specialist with a clean README and a public repo? That's a portfolio piece.
6 likes • 2d
@Dan Gibson several just go through the material
Self governing businesses?
So if I understand correctly, the Hermes agent is the Claude agent that I’m talking to in VS Code. So….. for business owners… a self governing business is the holy grail of what we’re doing here, right? A self governing company starts at VS Code and gets built brick by brick, and that’s what’s happening right now? That’s what we’re doing? And in like 6-12 months we’ll have amassed enough data and infrastructure to support that? Am I getting it?
1 like • 2d
sure, but your extrapolating a lot. like.... A LOT. this is totally possible, but to do it well, there are several orders of magnitude in complexity missing. You could probably do it in 12 months, if you have the technical know-how. That's assuming we are talking about the same thing with "governance" but I don't have a clue what you are talking about. lol
2 likes • 2d
@Ruby Sparks it depends on whatever you think you need. i have worked through some high level ideas, and talking shop on a architecture with some developers. this type of system, if I am thinking I understand what you want would much more complex. BUT - I'd need to learn your specific use-case.
Any Success with Local LLM Setups?
Hi everyone! With the new CoPilot plan restructuring and limiting AI resources by making it more expensive, I have been wanting to get my feet wet with a free local LLM setup. Has anyone succeeded in creating a free local LLM setup that rivals or gets close to the reasoning and speed of Codex, CoPilot, Claude, etc? Please share you free setups: IDE, model, GPU and ram rig. Would like to hear if there have been successes and what failures you have experienced?
1 like • 2d
If you are worried about token spend, get used to it, it will never be cheaper than it is now. :) Unless you have between $25,000 and $40,000, you can get a GPU that can run at the speed of codex, and that's assuming you have the technical knowhow to do MLOps work. Most people are running LLMs on digitalocean or another vps system, or other tools like that to get privacy If you decide to go local you will need a smaller LLM - it will be slower.
1-10 of 35
Austin Johnson
4
50points to level up
@austin-johnson-7173
Full-Stack Software engineer based out of Arizona.

Active 32m ago
Joined Mar 17, 2026
Greater Phoenix, AZ, USA
Powered by