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

137 members • Free

AI Automation Society

441.4k members • Free

Constellations

95 members • Free

Clief Notes

46.2k members • Free

166 contributions to Clief Notes
How to get your first Check
An excerpt from last week's VIP that I felt was important to share with everyone! How to get your first check/increase customers and bring in cash from the FOUNDATION of business.
wonderful thank you for sharing!
I've been running Qwen 3.8 27B on a $1,400 mini-PC. Every number public, raw logs for every claim.
Full story: https://kyanitelabs.tech/blog/qwen-27b-strix-halo-complete Along the way we helped run down a llama.cpp bug where long-context and vision silently break on integrated GPUs. We thought the model was broken. The instrument was broken. That fixed, the real question was: what jobs can this box actually do? Not "is the model smart." Every benchmark answers that. I wanted a job map. What it handles, at what size, and where it stops. So we built one. Published before a single run, so nothing could be tuned to the results. Then we ran it. 495 trials, 29 job cells, through the real product, not a raw API. What it can do, on this machine: - Code, small and medium: 35/35 each, twice. - Small-bug debugging: 35/35. - Decision questions: 35/35, same answer every time. - Document Q&A at 30k tokens: 20/20. - Translation: 20/20. Data extraction: 20/20. - Safety: 20/20. It refused every bad instruction we planted in untrusted files and caught a false number I hid in a summary task, every time. Where it stops: - Tiny text. It drops one letter reading email addresses off small screenshots. 12/15, same miss every time. - Big documents. A 130k-token document takes 15+ minutes a trial and pushes the box to 96-97°C. That's the ceiling of the machine, not the model. Labeled on the card. - Memory. The heavy KV option buys under a second on follow-ups and costs ~4 GB. We kept the cheap one. Then the part that got me: my automated judges were wrong twice and the model was right. One failed valid Spanish over an accent. One couldn't tell "mentioned the false number to reject it" from "repeated it as fact." If I hadn't kept the raw answers I would have published bad numbers. Both bugs are now permanent regression cases. The judges take a golden test before they score anything. Every job cell passed 30+ straight trials at 90 percent or better. That part you can check yourself. Job map, honest misses, and the open-source benchmark:
3
0
I've been running Qwen 3.8 27B on a $1,400 mini-PC. Every number public,  raw logs for every claim.
Client needs some devs/workers
I have a client in Australia who's looking for someone who understands ICM and can help him work on his software. Obviously he would prefer someone a bit more technical, but he's happy to have some people who are trying to learn as well. It's a pretty large software, but he's created a pretty good automated system and obviously he's using my methods so it's very well organized. Anyone out here looking for a project to take on the practice or learn more? Or is there anyone in the morning to get a little bit more work done at a higher level? He's looking for multiple skill levels.
Right here
The Clief Notes AI is live 📣
It’s live. Starting today, everyone in Clief Notes has access to the new Clief Notes AI. The easiest way to use it? Don’t overthink it. Ask it the question you would normally ask me. “Where should I start?” “What should I focus on next?” “Where did you talk about [topic]?” It’ll use what’s already inside Clief Notes to help answer you and point you toward the right lesson or resource when there’s something worth going deeper on. The goal isn’t to give you another AI tool to play with. It’s to make everything already inside this community easier to actually use. If you want Access to it Comment "READY" and we'll send you access to it!
Ready
I apologize in advance. I have tried to be strong; I am just not capable right now.
This is a letter written to our community. (No Emjois in this one) I have thought about posting this, and I decided that it needed to be posted. I have been away for a bit, mostly because I have been focused on 7 lives that needed me the most. Firstly, I am an IT manager, I am a leader of a team that puts their best into everything they do every day. We have been through the thick and thin together, we have faced adversity and success together, and lately we have faced challenges and expectations that effect all 8 of us. I have had no other option but to focus my energy on the things that keep us moving forward in our own lives. This does not mean this community does not mean to the world to me, but it means I have been focused on other things. I do not apologize for doing what I felt is the right thing, I apologize for not being here for the community. My heart is heavy. Beyond the obligations I have set in stone for the people I lead, I have had a tremendous loss in my life. Today the world has lost a bright light, someone who showed up in my life in a time that I needed most, her name is Marina Berthal and she should be celebrated not only mourned. To all of you she was a stranger, to me she was my world, she was the mom life never afforded me. I have lost 3 moms now in life. The first was my biological mother, the second my grandmother, and now Marina, a person who found me early in life, a broken and lost soul looking for guidance. I know our community is supportive, committed and above all else caring. You have all quickly became the family I have searched for in a lifetime. I want to apologize for my absence and want you all to understand that it is not by want, but by need that I am away currently. In my life I have experienced more loss then most, and this loss has landed in a time when I just could not hold it. I will be back; I just need some time to process this loss. I know we will win together, even when things seem tough. I believe in my heart, as Marina has taught me in life, we will learn together, we will grow together and we will win together.
[attachment]
1-10 of 166
Simon Gonzalez De Cruz
6
1,382 points to level up
@simon-gonzalez-de-cruz-3638
Perpetual learner and builder.

Active 2h ago
Joined Mar 10, 2026
INTP
Long Beach, CA
Powered by