First post here, so be gentle, lol. I'm having a hard time wrapping my perception about what kind of data you can, or should put into yours for your AI memory. I've been messing around with computers and by extension data manipulation, since the 70s. I have a good understanding of how a relationship database runs. But we're not building that kind of ecosystem(?) are we? We can go bigger. Before I dug deeper, I always picture an LLM like Chatgpt, as having this huge massive brain, which held all of the Internet, and when I asked would wave it's virtual hands to say "Here it is". I know that's incorrect. I'm using AI as a research assistant and junior co-writer. I'm doing a non-fiction book what kind of skills you'll need to make money in the next 20 years. I'm doing a ton of digging for trends and possibilities and...all of you have a good idea of what that means, I'm sure. I went into this thinking it would be more like a Wiki compiled form all my research and conclusions but is that what I want? Seems like there so much more than just a glorified book list. I do want to have a folder style system, with the full transcripts, complete articles, or other important documentation that I need. That's doable too. But recently, I wanted to start at least collecting the base data. If I don't start doing that, I'm just digging my hole deeper. So I laid down a basic schema, and then asked GPT to pull me 5-6 highlights that it thought should go into the database. Once I get the workflow built, I pretty sure I'll try to automate it, so as I research, the AI formats and stores any highlighted data I come across. It pulled those six, then another three from our discussions on the first six, and we were in a side chat at the time, the main chat was on markdown files. We got 10 entries from that. So I had nineteen. I haven't done any more, but when I look at what I have, I get this weird vibe that the majority of them aren't on the book subject, but are more of how the LLM views the way I work? That's a poor description of it, I hope it works.

I am pulling records about the same people out of a few different systems into one folder, so an agent can actually work with them. The merging is not the hard part. The hard part is that the same person shows up three times, slightly differently, and every system is convinced it is the right one. Phone written four ways. Name spelled two ways. One system has the newest email, another has the newest address, and the one with the better data is not the same one twice in a row. Right now I pick a winner per field instead of per record, and I keep the losing values in the same file so nothing disappears quietly. It works. But the file keeps getting fatter, and I am not sure fat but traceable is the right trade for something an agent reads on every request. For anyone whose folder is fed by more than one system: do you settle the conflict once on the way in, or keep both versions and let whatever reads the file choose at the time? And what happens on the day one of those systems changes its mind about a person you had already settled?

Hey Clief Notes fam! 👋 I'm Joseph and I'm stoked to be here. 🙋 A little about me: A DevOps Engineer based in Munich. 🎯 My current goal: Improving my understanding of ICM and AI. 💪 What I'm currently building/working on: Various personal projects and consultations 🤔 My biggest struggle or question right now: Am I using ICM properly for my project? Let's get it! 🚀

I was thinking a lot about a post from @Carla Bosteder (Using AI without losing YOUR voice) from a few days ago and I came to a conclusion that I rely too heavily on AI to write for me. Yes, AI has some training on how I think and how I write. Yes, I dictate my thoughts to AI to generate the copy I want to write. But this is not the same. Somehow the soul of the communication is lost. I started noticing this more and more in this community. The tell-tell signs of AI generated text. It makes me stop reading and just feed the post to AI to summarize it for me. I was never a great writer. I managed to get As and Bs on composition papers in college. Some people have a gift and can write well, just like some people have a gift with art or music. For me it was always a process of writing, re-writing, editing. I do not have the time for that now, so what do I do if I want to preserve my soul in my work? I would love to join a community that focuses just on that. How to use AI as a tool when writing and not a text generator. Use the AI more like a secretary back in the age before office computers. Use the AI more like an editor that enhances and clarifies writing, and not like a soulless generator. There have to be methods and strategies from the past we can apply in the AI age. I am not the person to uncover those "ancient" methods, but I sure would like to learn from people that do. In the meantime I will dust off my copy of "The Elements of Style" by Strunk & White as I feel that writing style may be just perfect for the AI Era. P.S. No AI was used to generate this message.

Hi, I'm Gary here, and I'm here to share my AI journey! I'm currently using AI for all kinds of things, but a regular thing I do is generate html slides for presentations. I work as a university tutor and like to put together presentations for my students to help them understand the content we are working on during a given week. AI has been a big help with deciding what to include or not include, what things warrant a deeper explanation or even a demonstration. I'm fairly comfortable with building structured systems, but am very new when it comes to using AI and discovered this community because I want to do things the right way and what Jake is teaching makes sense. It still feels like the wild west out there, but Jakes method just feels solid. A good framework that will serve you six months from now, and six years from now! One thing that caught my attention from this lesson is it's overall simplicity. Files and folders being navigated by a single agent strips away the complexity and shows that this isn't voodoo! I'm excited to learn how to apply this methodology to all of my projects and see how structured approaches to AI can help me not only build better systems, but to do it in a way that stays resilient well into the future!