Activity
Mon
Wed
Fri
Sun
Jul
Aug
Sep
Oct
Nov
Dec
Jan
Feb
Mar
Apr
May
Jun
What is this?
Less
More
Memberships
Clief Notes
39.4k members • Free
63 contributions to Clief Notes
1d •
Built a searchable index of 72 tools from this community (last 3 months)
Three months in this community and I kept losing things. Someone would post a tool in Show Your Work. I'd think "I'll come back to that." Then it was buried under 40 more posts and I couldn't find it again. @David Vogel and others have built some great workarounds to highlight posts and info, but I wanted to put together something that helps me find those tools I'll otherwise flag and forget. So I scanned both categories and built an index. 72 tools. 7 categories. Standalone HTML file: open it in any browser, no login, no server, no account. What it does: - Real-time search by name, author, or keyword - Filter by category (Memory, ICM, Writing, Design, Media, Workflow, External) - Every card links to the original post and the GitHub or site - "Leave Review" generates a formatted reply you paste into the original post - "Submit a Tool" generates a post template for Resources & Finds What's in it: Memory: PMM, Cortex, Session Memory Layer, Codebase Memory MCP, and a non-technical PMM folder template for people without a dev background. ICM: Brofessor, ICM-Builder, Foundations Tutor, CoworkOS, IBE Workflow, Shipyard, Creator Orchestrator Template, PAFA, and more. Writing: Critical Editor, Council of 5, LinkedIn Content Wizard. Design: tastecheck, Weirdness Engine, Open Design, art-direct, Shade_. Media: to-md, TypeWhisper, YouTube Extraction Pipeline, Pushing Talk_. Workflow: ARI-OS, Astrid, SkillOpt, Nightwatch, Porter, The Maintainer, Subscription Auditor, and more. External: Miessler's PAI, Hermes Agent, Zuki, Signal Harmonics, GiTeam, and others. GitHub (open for contributions): https://github.com/FiSimply/clief-notes-index The README has instructions for adding via PR or the Submit button. Anything I missed, drop it in the comments & I'll add it. If there's a better way to accomplish this inside the Skool site, please comment. My way is not "the way" and I'm always open to alternatives.
3 likes • 21h
@Daniel Terry butterfly bandages aren't as good as stitches, but if it works for now... there's a better way - hoping this raises the awareness. There's a lot of awesome being built here, we just need to figure a way to ensure nothing gets lost in the mix.
2 likes • 16h
@Bryan Alva Same. I want to reference some people’s posts and forget the person or tool. It’s not ideal, but between ideal and active, I’ll run to what works/MVP.
1d •
My AI has been hoarding my whole company in a folder I can't see. And it knows...
@Matthew Dave , told you I'd write a post about the thing to watch out for with Claude and going with GitHub. Grab a coffee, I'm gonna grab the Bourbon. This one's got a body count. First thing, so nobody gets the wrong idea. This is not a confession post. Not mine, anyway. The only one confessing here is Claude, and I'm just the guy holding the recorder (and the M16 pointed at my Claude install). This is a rage post. Unfortunately, I'm hot about it again, and by the end you'll know exactly why. Quick refresher. I run my whole company out of a folder system. Not one big repo, a whole pile of them, one per slice of the business, all syncing to the cloud so my team sees it, my machines pull it, and nothing important lives in one fragile spot. The agent that's never lost. You know the gospel, we preach it in here every day. Here's what has me seeing red. My agent has been stubbornly losing things for weeks. In the same spot. And I knew about it. It knew about it! Here's the bug, in plain words. Claude has a private home folder on whatever machine it's running on. That folder is NOT in my repo, or yours. It never syncs, my team never sees it, and if the machine dies it's gone. And the AI's lazy little instinct is to save its work THERE instead of in my actual folders. Every time it can get away with it. I did not just stumble onto this, been dealing with it for weeks. I HATE this bug. A couple weeks ago I blocked out a whole work session just to kill it. Wrote a standing rule into my workspace, added patches, watched it behave, closed the laptop thinking it was handled. It nodded along the whole time. It said sorry, took the blame, said it would never do it again. Said all the right things. Cool. You know what happened today? A contractor I'm working with tells me three of our automations are done. Sweet. I go to open them. They're not in the repo. They're sitting in the AI's private home folder on HIS laptop, invisible to me, running against HIS accounts instead of mine. The exact bug I "fixed" two weeks ago, back from the dead, wearing a new hat.
1 like • 1d
Have you tried @Millenial Cat's PMM (Poor Man's Memory) and @Yucky Yuckyyyy's Brofessor? I added Session Layer Memory (which has been updated a few times since) and use Brofessor for a quick audit. I caught a similar issue with my Claude instances and the combo has resolved orphaned files, folders, and information.
8d •
Your AI doesn't read. It finds the paragraph and bluffs the rest.
Search finds. It never reads. Every "AI that knows your stuff" runs the same trick: embed the material, grab the paragraph nearest your question, bluff the rest. For easy questions the bluff holds. For the ones that matter, it doesn't. So I'm building the missing layer. Call it a reading swarm. Instead of paying one expensive model to read a whole mountain, I cut the corpus into slices and send a swarm of cheap workers, one per slice. Each reads its slice properly and hands back a single finding. A deterministic harness merges them into one verdict. The expensive model only steps in if I ask it to sharpen the final call. Not shipped yet. Still smoke-testing the edges, and I read every verdict myself. But the law already holds: finding isn't comprehending, and comprehension doesn't need a bigger brain. It needs more cheap eyes, one slice each. What's the biggest pile of material you wish your AI actually read, not skimmed? //A<3
0 likes • 1d
Have you checked out https://github.com/opendataloader-project/opendataloader-pdf to integrate into the approach? I've had better results with AI running through MD files vs. PDF as it parses the text better when MD.
2d •
I'm a beaming new papa... (it's a paper)
From lurking and commenting... to a vacation that finally gave me time to chip away at the todo list my normal 60+ hour work weeks keep piling up. I finally did the thing. I published a paper... my first public AI baby! yes, I'm a beaming new papa. lol It is called Sovereign Knowledge Federation, and under the big name it is actually a pretty simple idea. Picture two people who each keep a really solid personal knowledge system, and each has an AI that can read theirs. One of them already cracked the exact thing the other is stuck on. Right now there is no clean way to hand that knowledge across. You can dump it on the open web, paste it into a chat, or give it to some platform that then owns it forever. None of those let the second person's AI actually use the first person's knowledge while still knowing whose it is and how far to trust it. That missing piece is the whole paper: how independent people share slices of what they know, with nobody in the middle deciding what counts as true. Every claim carries a little signed tag for who said it, how sure they are, and where it came from, and your side gets to decide what to do with it. Here is the part that genuinely surprised me, and it is my favorite bit to tell people. The obvious move is to label a sketchy source "low trust" and let the AI quietly discount it. I tested it on local models. It does not work. The model reads the label, sometimes even repeats it back like "noted, low trust," and then believes the claim anyway. So you cannot politely ask a model to be skeptical about something already sitting in front of it. Trust has to act like a bouncer at the door deciding what gets in at all, not a suggestion you whisper after it is already inside. It is a working paper, which is the fancy way of saying it is real but I want it kicked around. So if you read it and something feels off, that is exactly the reaction I am hoping for. Whether this is your first month poking at local AI or you have been building this stuff for years, I want your take. Tell me where it breaks, and give me your ideas for the next phase.
1 like • 2d
tl;dr This paper is worth your time if you're building with AI knowledge systems. The core architecture is sound, the empirical finding on trust-label conditioning is genuinely important, and the author is honest about what isn't solved yet. The cosmological vocabulary will slow you down (read it twice). Not deployable yet - but that's the point. It's an invitation to build, not a finished spec. full thoughts: This paper is solving a real problem. Tools like Obsidian handle structured personal knowledge. MCP and A2A let AIs read those vaults live, but no coherent model exists for federating that knowledge across people and their AI systems with governed, attributed, revocable access, without handing ownership to a platform. You identified the gap correctly and the architecture proposed to fill it is worth taking seriously. I had to read through this a few times (kept getting tripped up by the cosmological structure), and it tripped me up enough that I'll come back to it below. What worked: The boundary-capability synthesis is the strongest technical contribution. Separating where things live from the grants that allow crossing between them is clean and correct. Confusing those two is exactly what causes the sharing-rule ambiguity the paper diagnoses. The provenance envelope design is solid. Asserter identity, epistemic type, justification pointer, hop count, timestamp. Source reliability and item credibility stay on separate axes and combine only at retrieval (not baked in). Trust recomputed fresh each time avoids the stale-score problem. The most practically relevant thing in the paper is the empirical finding on trust-label conditioning (Section 6.2). Weeks reports this openly, including that it strengthens the design argument - that's the most intellectually honest moment in the paper. I love that problems are organized around a single keystone (independence verification from a local view), and not buried or listed and abandoned. What doesn't hold up: The independence-verification problem is acknowledged but not resolved. The entire trust system depends on corroboration from genuinely independent sources. The paper honestly identifies three levels where this fails simultaneously - operationally, at the standards level, and formally. The core guarantees all assume independence is real. Naming the problem doesn't fix the foundation.
1 like • 2d
@David Vogel agreed - thanks for pointing it out!
22d •
📣 Quick Note to the Community
Hey everyone, Going to be transparent with you all. We're pausing the weekly competition this week. No comp #7. We'll be back next week with the next one. Here's the real reason. Jake and I are both on family vacations right now, and we're buried in enterprise work on top of it. We've been running 15+ hour days since this community started, and we've hit a point where we need a few days to actually breathe. This community has grown faster than we ever imagined. None of that happens without you all. The posts, the help in the comments, the bad ass builds people are shipping every week, the way you all show up for each other. It's real and we don't take it for granted. But if we're going to keep this thing high-quality long-term, we can't run on empty. A week off the comp grind so we can rest, catch up on enterprise work, and come back sharp is the right call. The 7-day leaderboard still runs as normal this week. Keep posting, keep engaging, keep helping each other. The leaderboard winner still gets the prize on Monday. Weekly comp #7 picks back up next week. We'll come back with something good. Thank you for understanding. And thank you for being here. ❤️
3 likes • 22d
Better to build sustainable measures than fast and furious. Glad you’re taking time out!
1-10 of 63
@deacon-wardlow-5364
I’m just some guy doing stuff and figuring things out.
Active 2h ago
Joined Mar 16, 2026
INTJ
Mead, colorado
Powered by