Activity
Mon
Wed
Fri
Sun
Dec
Jan
Feb
Mar
Apr
May
Jun
Jul
Aug
Sep
Oct
Nov
What is this?
Less
More
3X Freedom
1.9k
Free
Clief Notes
56.1k
5.0
Free
194 contributions to Clief Notes
What If I Gave You 50x More AI Usage Capacity?
What would you do with it? Would you become 50x more productive? Or would you just waste 50x more resources? If you’re already wasting your current AI quota on poor planning, repeated prompts, lost context and unfinished projects, why would 50x more suddenly change that? You’re not scaling productivity. You’re scaling inefficiency. Now imagine you had to build a system capable of managing that 50x quota intelligently. Persistent memory. Structured workflows. Task prioritization. Agent orchestration. Verification loops. Resource allocation. And it needs to scale to 100x or 200x without falling apart. Now comes the real twist. What happens when you take everything you’ve learned and apply it to your regular 1x account? Same structure. Same intelligence. Same efficiency. Suddenly, you can accomplish far more with the exact same quota. The real challenge was never how to use 50x more AI. It was learning how to get more out of the 1x you already had. So let me ask you: Do you actually need a bigger AI quota, or do you need a better system to manage it? That's the whole point: learn how to get more out of the 1x you already have. That's how you turn 1x into 50x, not 50x into 1x.
2 likes • 1d
@Pascal Pollack it's still running :0
2 likes • 2h
@Pascal Pollack but I bet it's almost done, don't want to kill it now 😭
SGM, the method behind the archive I work in every day
Hi everyone, In this repository I share part of my work: the method behind the archive I use every day with AI agents. It decides what an assistant is allowed to remember about my work, and who answers for it when what it remembered turns out to be wrong. https://github.com/Valmor-R-Reichel/SGM If you want the why, this page tells how it was built and the criterion behind each step. The scripts and tests were written by AI agents at my request, so the page is about what I decided to measure and what I count as an error. https://github.com/Valmor-R-Reichel/SGM/blob/main/docs/criterion-over-repertoire.md If you like the philosophy behind it, the two essays I shared here are that side of the work. https://www.skool.com/cliefnotes/the-social-cost-of-asking-another-person https://www.skool.com/cliefnotes/when-the-flashlight-looks-like-the-sun The repository moves slower than the archive. I work on it when I can, because each piece has to be translated into only the method, without the people and the data from my job. The README still describes the system as it stood in September, and the changelog lists what changed since. The latest entry is from yesterday. I rewrote the main file my assistant reads in every conversation and counted my corrections before and after. The number did not visibly move, and the first judge almost reported an improvement that was not there. https://github.com/Valmor-R-Reichel/SGM/blob/main/CHANGELOG.md
2 likes • 4d
Thanks for sharing. I will take a closer look. Great work ❤️
Multiplayer AI: one ICM, a whole team
Using ICM alone makes one person fast. Using it as a shared knowledge base makes a whole team fast and consistent. I call it an organized organisation 😂 The hard part isn't the AI, it's conflict management. I enforce four steps in code, not prompts: - Resolve conflicts: Git or a shared drive, depending on the case - Permissions and visibility: who edits instructions vs. who edits data - Handle stale files: give new information dates and context - Full auditability: every request is logged My setup today: 7 people on community-based research. I'm the maintainer (rules). Everyone else is a member (data). They can suggest rules, but I approve them. The AI even flags broken rules to me: "he wants to do this but can't, check it out". Still unsolved: stale files. Expiry dates or events help, but assigning them when a file is created is the hard part. For now, expired files stay put, the AI traces linked files to infer why, and asks me when unsure. Every failure updates the rules. If you're building team ICMs, I'd love to compare notes. Technical or not, message me. 🤝
1 like • 4d
@Clare Martinez Yes, commits are awsome. The AI updates and commits exactly what was changed and why. It's amazing.
1 like • 4d
@Emiliano Narváez Thanks!
VSCode
I will make a bet. Every knowledge worker will soon all be using a VSCode like app. Because otherwise, they will be replaced by one who does. Imagine every worker connected to the company data, controlling an agent that can also act on his desktop. The working app becomes: A. Files displayed in the middle of the screen B. Chat window (either left or right of the screen) C. Folder directory (either left or right of the screen) That's just VSCode. Not saying it will be literally VSCode used, but a similar app for sure. After some discussions with some very smart people, I was convinced that VSCode is the desktop app of the future.
2 likes • 17d
@Stephan Vollmer agreed. However, there will always be a need for desktop workers. That's how to get real work done. And VSCode looks like the ultimate desktop app.
2 likes • 10d
@Theo Boomsma Interesting yeah. And you could just ask the AI for the files, good point. But personally I like seeing the structure of my program and data.
𝗗𝗼𝗲𝘀 𝗮𝗻𝘆𝗼𝗻𝗲 𝗲𝗹𝘀𝗲 𝘀𝘁𝗿𝘂𝗴𝗴𝗹𝗲 𝘁𝗼 𝗮𝗰𝘁𝘂𝗮𝗹𝗹𝘆 𝗿𝗲𝗮𝗱 𝗔𝗜 𝗼𝘂𝘁𝗽𝘂𝘁?
I've noticed something lately — there's this weird barrier when I'm reading AI-generated text. I just don't want to read it. But if it's human-written? No problem. It's not that the AI is giving me bad information. It's more like... the writing style itself creates friction. Too polished, too formal, or just predictable in a way my brain picks up on. I'm curious if anyone else is running into this, especially if you're using AI for client work, internal docs, or anything people actually have to read. And if you've found ways to fix it — whether that's prompt tricks, editing workflows, or just accepting that AI is better for structure than final copy — I'd love to hear it.
1 like • 10d
Never thought of that. I think I do that, because I already know that maybe 50% of it isn't useful. So I just skip 50%. But the logic doesn't make sense, because i will always skip some of the right 50%. This also happens because AI generates more output than I can read. So I do need to skim and skip. Curious how others review AI work. I'm definitely biased and wrong. But had never thought about it like this.
1 like • 10d
For me, it's not about how it's written, I go into the text already biased by knowing AI wrote it
1-10 of 194
Nuno Silva
6
905 points to level up
@nuno-silva-1015
AI Engineer, Researcher

Active 53m ago
Joined Aug 17, 2026
Powered by