I ran a small newsletter for one of the Skool communities @Deacon Wardlow for just this reason. A group of people there didn't have the time to keep up with the amount of posts. The issue that I ran into was how do you pick the ones that make the list, and which ones don't? That group has 6-7 pages of new posts each week (about 200 posts). Took an hour or more to curate the list because I literally needed to look at each post. About half I could ignore. Things like intros and wins. I had a target of around 20 "hot' posts. I quickly noticed it became a list of what "I" thought was hot. I didn't want to become the gatekeeper to the site so I dropped it. So I want to point out, it's not just like deploying an agent. What you purpose isn't a simple or easy job. Just so anyone stepping up to volunteer understands the work. I actually find the search option passable but I understand and agree with your sentiment.

@Deacon Wardlow yes, I have done quite a few newsletters or weekly highlight posts on other forums. They are great resources for those who don't have all day to hang around the group. With all the new options and features out there now, you'd think places like Skool would have one.

I am also a writer/knowledge worker who uses AI to help me write. Though I don't use it on my fiction, just my non-fiction.

Welcome @Stephen Berg I just joined this week myself. Amazing place, with wonderful resources. I can't participate in these yet either, but like you, I'm going to watch them carefully over the next few months and glean as much off of them as well. I didn't think about looking at the files though, so thanks for the hint.

I can't speak directly to why use 'folders' @Alejandro Morales because I'm just starting to look deeper into them as a system. I've been more focused on Nate Jone's Second Brain and was about to build one, then Karpathy released his "Knowledge Wiki" concept, and then last week, I came on the folder system. Now I'm re-evaluating options. But to answer your question, they are all ways to keep more of the benefits of YOUR interactions with AIs and LLMs under your control and making you money, not some hyperscaler selling you a monthly membership. Once they have locked YOUR data, and your chats, behind a paywall, then how much will you pay to access it? With personal offline memory, you control who uses it and if the membership or token cost goes up with current service, you take your toys and go somewhere else. - It's not just control of your data either. First it's all of the customization and boundaries, the preferred formats of outputs, the style of interactions with the LLM; all of that stuff is what turned you from a normal human output to the 5X human with AI assistant output. And hopefully, from a normal human paycheck to a paycheck 5x as big. What happens when that current company says, "Nah, we'll just keep your salary the same, even though your productivity is now much more". Do you quit? If you do, and you go to a new job interview, how do you show that YOU deserve that 5x paycheck? You do it with examples, with slide decks, with demos of any agent work (within the privacy and trade secrets of the previous business). Your AI memory is your new resume. - And finally, token prices, especially for the latest cutting edge LLMs is going to go up. Hyperscalers are subsidizing the big token users. That's going to end. Before it does, a lot of us are going to go with open LLMs hosted on our own local servers. Having most or all your data offline, means you run the simple stuff locally and only pay for the electricity, then only use the token stuff and higher end LLMs for the things that need it.

@Ari Evergreen that is a great explanation. thanks

@Siv Darmalingum no I don't mean do you use prompts collectively when working with your LLM. I mean specifically the summaries of the ongoing chat, which all of the LLMs will do if you ask it to. Chatgpt calls it a "Master Control Prompt" or MCP. You typically upload it and two other files when you start a chat, or continue on a chat which has become buggy because of length. I have an MCP for the overall project summary. That teaches the new version of the LLM what we are doing. In this case; I'm writing a book and the LLM is helping. Then I have a MCP which defines my preferences, boundaries and limits for the LLM's output. These tell it how I want it to work with me. Things like "No emojis". It also defines what kind of general persona I want it to interact with me with. Then I upload a third MCP on the properties of my "GrimDavid" writer's personal. This second persona allows me to use a voice which outputs to about 75% of ME and my style of writing. I toggle in and out of that voice as needed for generating chapter text. You should have at least the first two for all the subjects you are chatting in. The more specific you make the topic discussion, the tighter the output. You can also do separate MCPs for partial or for side chats. Most LLMs allow you to open a side chat, and tell it to not apply any of the data generated in the side chat, to the main subject in that chat. Tell the LLM the opening and the end point of the MCP in the chat, and the end point. Then you can take that, and open a brand new chat to discuss that subject alone. If you want, I can copy/paste one of the ones I have here, for you to see the formatting. Let me know.

@Siv Darmalingum basically, yes. MCPs are/were ways to move the core information of your chat to a new one, or break parts of it off into new chats. (Big Note: I am like you, still learning most of this. Feel free everyone, to double check anything I write and please correct me if I get it wrong.) Do you know that LLMs compact the earlier parts of your chat when the chat has gone on for a while? I've seen videos which say that, at 60% of your chat memory limit, the LLM starts degrading. That's why the longer your chat is, the more likely hallucinations and errors start to creep in. This was one of the earlier ways to handle that. Here is an older one from one of my chats. It is an odt file (think of it as a MSWord file but for LibreOffice) Should open in any Word compatible software. Much of the content plan has since changed. There are also some errors. The "meat monkey" comment got in there when the LLM started hallucinating. One of the reasons NOT to let the chat go on too long. BTW, it looks like I was mistaken and they are named "Master Context Block" in Chatgpt. You can see where I was still using just one MCB when I made that one. It still has the voice and persona included. Let me know if you have any issues opening this file, and I'll just post the entire thing in a comment. ---- ADDED: Looks like the file is short, so here it is posted: Master Context Block Project: Human-centric Resilience (HcR) Core Thesis: Systems can be resilient while the humans inside them are exhausted, replaceable, and degraded. HcR addresses this gap by shifting the focus from system survival to preserving human agency and dignity under long-term grinding pressure. Key Principles & Definitions: - Definition of HcR: The practice of adapting to long-term pressure in ways that preserve human agency, dignity, and continuity, rather than optimizing people to serve resilient systems. - Embedded Survivalism: Remaining functional and useful inside a deteriorating society rather than withdrawing into total isolation. - The Triad of Survival: - The Target Reader: The "Mantle-Picture" reader—a thoughtful adult (approx. 35–65) with family/community responsibilities who values competence, discretion, and realism over fear-based prepper culture or ideological extremes.