I'll never post one of these videos on YouTube again.

Being hosted. Super fun. Uh, and I pretty much do SEO and small to medium business size automations, or that's what I'm trying to do. Uh, and I've been just learning so much from you and I've been really like integrating into my own workflow and I'm looking actually to hire people now to help, um, use kind of AI to do all the work that we do for websites, SEO, and yeah, and it's been great. Oh, you're muted, Jacob.

Well, I love that. Thank you so much. Um, when it comes to the hiring thing, uh, we're actually launching it, uh, probably this week. Uh, our ledger, we've been working on it and it's a place where people, uh, like, you know, our competitors, you can actually upload them as kind of portfolios and then you can put yourself out there as freelance to work, uh, full employee to work, and it'll show what your kind of work you've already done, um, kind of with all of that. Uh, so, uh, keep an eye out for that. We're doing, um, two portals and we're going to make it free to everyone who's VIP and, uh, premium. Of course, there's not going to be anything. Y'all are going to have to pay. Uh, you're already paying, so, uh, I don't see a reason to to make you pay more. Um, and so hopefully it'll be a platform where you're either able to get some of the top talent or vice versa, some of that top talent can, you know, find their own ways. And then eventually we're launching the ICM, um, kind of deployment layer. Uh, so basically we've created a kind of dockerized deployment environment. So you can just upload a zip, we deploy it, and then, you know, let's say you do hire someone, instead of them having to install a whole bunch of stuff on a new computer or get it all in, you just log in and you can use that workflow, those files and folders you're building, or you can deploy it to other clients. And of course, we're going to make sure you all have access to that for free. Um, and actually the goal for that one is to have it where you can charge other people, um, to kind of like have access to your workflows. You're licensing a version of yourself, is my idea there, which we've chatted about before, but, um, I'll talk on that later. I don't want to take up too much time. Uh, but Marcelo, I'd love to hear from you next.

Hi. Hi, Jake. Hi, everyone. I'm Marcelo from Brazil. I am, uh, a trained psychotherapist first, but always loved technology and, uh, you know, end of last year started to hear about open claw and agents and I jumped back into, you know, the tech, uh, space. Uh, and it, I just, it just blew my my mind and and I'm, I'm working with that since since then. I'm, I'm creating, uh, products to, uh, event management companies and, uh, small businesses. And, uh, I was just working on a supplier management, uh, dashboard with a chatbot attached to it. Uh, and, uh, I'm using a lot of ICM and, uh, I've created something called the workspace creator. So I created an an ICM style, uh, folder structure that creates workspaces.

So I go through all the things and it it speeds a workspace for me. So it's, it's been fun and and amazing.

Thanks.

That makes me so happy.

No, thank you, Marcel. And that's kind of like the idea behind why I've been pushing this out there is I knew, right? I I saw the structures. I've spent years diving into old papers from the 60s to the 70s and how we were building file trees and why we built them. And the whole goal wasn't to help us control the computer more. It was to allow us to collaborate with information among other people. We want an environment in which we can move ideas, move intent, move contents. That's the entire goal of software is to take our intent, amplify it with a machine, and collaborate and share that with other people, share that value. And I built ICM based on the idea of how do we take that into the next step, the next stage, knowing that AI exists as a platform, as a process. Um, and it's at the core of it, it's organization, right? It's how do we organize thoughts, concepts, movements, value in a way in which these tools and myself or others can access it. And the idea of workspaces, um, I'll chat a little bit about it today, but I'm really glad you're diving into that. In fact, I've been reading a paper. Um, it's from 1962. It's called Augmenting Human Intelligence. Um, and it's from the guy who invented the mouse. So, the mouse that you're using was invented by this guy. Um, and I'm going to be making a YouTube video, so don't worry. You all won't have to to go through and read it. Um, but it is absolutely amazing, right? Uh, it's Oops. Hold on. This is the newer one. That's the That's the Let me see. 1962. Let me grab the actual one from it. Um, there we go. Or sorry, Augmenting Human Intellect, not Intelligence. Um, and, uh, it is just it's by Engelbart and he's done a lot more than just inventing the mouse. He invented a whole bunch of things. Um, but it is just an absolute amazing paper about looking about how do we look at these processes and it's very funny because if you'll notice a lot of the things I talk about, right, about breaking them down into these artifacts, these processes, language is a control space. This idea of needing to train the human to get to the understanding of how to use that control space. It's why I made my community and I didn't read this paper before starting my community. So, I've just been having an absolute blast, uh, going through his work. So, expect a video on that soon. Um, and I think it'll help you a lot with what you're building around your workspace. And I highly urge you actually, while I was at London, this was a common theme I saw people missing is this collaborative effort. They keep automating single people tasks or automating processes rather than creating an environment in which those processes can be collaborated between each other or between yourself. So I'm very excited to have you here Marcelo. So I like that. Thank you. Um, and hopefully I'll teach you some stuff in the cult today alone, let alone everything else. And a lot of other people in here. Again, there's amazingly brilliant people in here. Um, let's see. I think, uh, Joe Quinn, you also raised your hand and said you were new.

Yeah, you can hear me. Yeah.

Yes.

Okay. My name is I'm from Uruguay in South America and I'm a software developer and I own a software dev agency implementation of AI. Uh, and this course was like I have so many issues, problems, how to build stuff that is not going to be built later for the for cloud or for open AI. So this course has been like an opener in a way and so many ideas have been like popping in my mind the last week that yeah, I want to write new stuff. I want to discuss new stuff and yeah, thank you very much for everything.

I'm so glad. No, I I just I kept getting so angry, um, because right, I'm working with large like Fortune 500 clients and I have been for a while and, um, I kept seeing these people like just pitching stuff online and sharing certain aspects. I'm like, uh, we're never going to, it wasn't even a, oh, let me do it out of spite. Part of it was there, but it was, if we can get everyone on the same page of building and creating, we can move past all this BS of like caching features because my whole goal is, right, when how often, raise your hand if I'm incorrect, but how often do you all freak out and look at news articles when, uh, iOS updates or when Excel updates or when Quickbooks updates? You don't really. You're focused on other things. Maybe if you're in compliance, there's a different area. Um, I think I see, Yeah, Tiffany's in here. She She'll probably scour those because there's always data changes there and that's important. But most of the time, you don't really care when a software that you use every day is integral to your life updates because your workflow, your process, your employees already know how it's supposed to work. The updates just make your workflows better. We eventually want to get to the point where, uh, oh, did I did you guys lose me there? I just saw Okay, cool. We eventually want to I saw my screen kind of paused for a second. We want to get to the point where when Claude updates, when OpenAI updates, it's just another update. It's just, oh, cool. That's lovely. I enjoy that. And keep on working the exact same I'm working. If you're not at that point, we haven't fully understood how the technology works. Like when Fable came out, I was just Now it's gone again. We've all lost Fable thanks to the US government. Um, but is I don't know if anyone's familiar with that news article that just came out. Is anyone not familiar with what happened there? For those of you who aren't, um, Claude, Anthropic dropped a model called Fable, uh, which is a smaller or more controlled version of Mythos. You know, it scored a lot higher on a lot of benchmarks. But then the government was like, no, we don't want foreign nationals using it. We think it's a security threat. And unfortunately, Anthropic has foreign nationals inside of their company. So, they decided just to shut it down access to everyone. I think it could still be part of marketing personally, but I also think it's, you know, some political stuff, but we don't have to dive into that right now. Um, but long story short, that dropped. I tested on my workflows. My ICM methodologies just got better, right? That's that's all I care. I was like, "All right, cool. It's better. I still could use less tokens because it works well. The output is the goal, not necessarily another feature." So, yeah, absolutely with you on that, John, super happy to have you here. Um, who else is new? Allan, uh, you you're not new, right? I I think you've been in the the past ones.

Yeah. Yeah. I was going to say you've you've brought up a bit. I just you're I don't know if you've changed your background or something. It looks different. Um, uh, or I haven't chatted much before with you unfortunately. Um, oh boss. Yes, boss and Roy. I think both of you are new. Uh, would you guys, uh, be willing to, uh, introduce yourself to everyone here and then we'll dive into some some of the structure. I just think it's important we all know each other and what we're doing because again, I'm valuable here, but everyone in here, this is a value point. This is a place of potential business, of potential collaboration. We want to know everyone in here is at the higher levels of understanding AI. They're where you are. You don't have to sift through all the social media and be like, "Does this person really understand what I'm working on?" No, it's like, "No, everyone in here should have a pretty solid, uh, idea for it." Um, but yeah. So, boss, would you, uh, would you be willing then to say hello? Uh, if you don't want to share your screen, that's also perfectly fine. Um, but be happy to to hear from you possibly if you're allowed to. I do not have permissions. Let's see. There we go. It should should let you share your screen and audio now hopefully. Allegedly. Oh, and Sandra. Yes. Hello.

Go for it.

Just let me know when you guys can hear me. Can you guys hear me?

Hear me? Yep. Absolutely.

Fantastic. Fantastic. Fantastic. I woke up about, uh, 45 minutes ago, so I'm not going to get on camera. I am a very, very busy person. I'm an IT manager for a very, very large company, 160,000 employees. I have seven direct reports and I I manage seven different buildings. One of those has 2100 people in it. So I work around 60 hours a week. I commute 20 hours a week as well. That stands for 80 hours a week that I am not using AI. Yeah, I know that's crazy. Uh, which means that everything you see me doing is in the in between. Everything I build, every every competition I enter is in the in between time of that 80 hours.

It should tell you what AI is capable of, not what I'm capable of. So, um, yeah, I am I'm really grateful to be in this group. I think that we have a lot of talented people, but I think there's something more than talent here. I think there's real community, people that actually care. That is what it's about and I think that that is what keeps me coming back. So, um, I absolutely love ICM. I think that it's, uh, I'm an autodidact. I love to teach myself things. I love to learn new things. I love to pull things apart and see the structure behind them and see how they're running. And I think that that's at the core of ICM, knowing how things are running at the core.

Once you understand something fully, you can break it down and you can really hammer it out. Iteration also absolutely key. It goes along with the whole thing with like being afraid of failure. If your builds are failing, that's a beautiful thing. It gives you opportunity to find out where they're failing, why they're failing, and to iterate, fix it, and move on from it. It is absolutely crucial that we fail as much as possible to be honest.

100%. 100%.

But yeah, that's

Oh, go ahead.

No, I was just going to say that's just me and I will talk forever, so I will be quiet. I am I am I am I am autistic. So yeah, sometimes you'll have to be like, "Hey boss, be quiet."

Well, and this is an important note. I always remind everyone too if, um, I always let these calls go even after I get off for today. So feel free to kind of chat amongst each other. And then of course the Discord, um, I set up the Discord for us to be a place to just make it easier because school is good, but it's not so great when it comes to, you know, kind of collaborative being able to talk on the fly, things like that. So, make sure, uh, you're in the the kind of high-te VIP side of Discord so you can connect with everyone there. But no, amazing to have you here and I'm so glad, right? The whole ICM methodology was built off this idea of like output and creating and looking at things like if you go into my research paper, one of my core parts is looking at how myself and like 50 other people, well technically was 32, but then I added another 10, um, were editing stuff, editing AI outputs. The rest of the paper was built around the patterns that I saw and then just rereading, um, stuff from the 70s, right? Unix methodology, stuff like that. It's the fundamentals. Once you learn the past, you can really predict the future. Not in a predicting of, hey, this is when events are going to happen, but like this is probably how people are going to work because this is how we've always worked that there's patterns in it all. So, yeah, absolutely. And also, thank you for giving your time on a weekend and that includes everyone else here. Uh, I really try to make these as valuable as possible. Again, for those of you who this is new, I take the transcript. Um, I pretty much create all sorts of different extra artifacts for every single high-te that you can either give to your AI, throw into your knowledge base if you have a second brain. That's I kind of build them for that there. Um, and then it's just nice to be able to review. So, so thank you for that. Thank you for your time because yeah, managing an IT, especially in today's world, is a nightmare. Um, so thank you for your time. Um, okay. Let's do, uh, Sandra, do you want to introduce yourself real quick? Is that okay?

Hello. The mic work?

Yes. Hello. Um, I'm from Austria. Hello to everyone. I didn't know that, um, talking a lot is an autistic trait. So now I know why. So please stop me because I also go once I started. Um, I'm a real estate developer in Austria. I build by basically grounds, develop apartment houses and sell them again. Um, I have three running projects with, uh, 50 apartments and houses. So not a totally big thing, but also not really small. Um, and I have a marketing agency longer than I have that, uh, then I have the real estate, uh, development. Um, in the marketing agency, I was really lucky to got a really professional and good, uh, foundation for for graphic design and for programming. I actually programmed more than I did graphics. Um, so I write HTML and CSS like a letter, I'm I I always say. So that kind of got me into to connecting maybe more with Claude, maybe lowered the barrier maybe a bit to the the anxiety to get in touch with it. And then I was really lucky. I got, uh, I have one tenant in the house which is a full stack programmer and IT guy and he introduced me in February to Claude. So I started programming something an app immediately and, uh, very simple thing, a desktop app and an app for my bookkeeping. My bookkeeping basically is, uh, digital purely since 2018. So I'm really strict. I have a really strict naming convention for my for my files since 2016, something like that. Um, so I I basically have this structure already. So I'm I'm very clear in my structure also. My the the files for the graphic agency were always very structured and always the same in every in every client's folder. Um, so I had that kind of and and then I I I started, uh, immediately when I started working with, I actually programmed, I I got programmed, uh, an app for my bookkeeping already in 2024, I think, or something or 22. But today it's like with Claude, it's done like in a week or so. So it costs, uh, like a hundred thousand euro back then. So, and now it's I just did it all over again, basically. Um, or I'm doing it all over, basically. Um, so I the way I got to know you. So I got to know you right in the moment where I started thinking, wait a minute, I need to make a memory file. I don't want to say things over and over again. I need to put a file into the root where is that's my identity file. I called it maybe different than you did, but basically I did the same and then I got to know you and thought, oh wow, there is somebody doing that actually, way more advanced. So let's get into it. But now I'm a little stuck because, um, I try to implement your method like perfectly and, yeah, that's not happening.

Instead of just going along.

This is a good question then and we'll move on here in a second, but what what is the main issue that you're having? What is like If you were to name like, okay, this was the goal that I was going to have and this is what's not happening, even though I'm trying to use this methodology, what what is, uh, if if you were just to do a high level, um, kind of description?

I'm asking myself exactly that. So I think one part is in a moment, in the moment where I where I saw somebody's doing that professionally or more advanced, I got stuck because I also wanted to do it.

Ah.

Perfect. That's maybe one thing. The second thing is that I'm really busy and that my my day is running. So for instance, um, next step, next very simple step would be that, um, um, that I improve the naming convention also for because my son is actually using it a lot and also my assistant. So it needs to be improved, but I'm I'm just not doing it because I'm working on implementing this ICM. So,

so I have it now in different places and, yeah, and then I I I open Claude and and I do a thousand other things and not what I what I wanted to do. So, I'm I'm stuck kind of in the in the setting up or Yeah.

Well, sorting out again, new or so like I I don't know how to sort it out new. And today I thought then VS code. Yeah, I want to implement VS code. What again is it for? Yeah. Okay. It's do I really need it? And then I'm asking five times, do I really need it? Because one thing is maybe that that I don't want to use any more tools because in the graphic agency, you know, it was like every year another project management system, every year, and yeah, as you say, the updates and everything, so I'm really tired of that.

So I don't want to immediately start to use another tool, so I'm very reluctant whatever comes.

Let me let me say that may help and then give you some questions to ask yourself, right? Because right now there's three main things you want to ask yourself. It's a delegation question, it's a complexity question, and it's an outcome question. And what I mean by that is, right? So my M, right? It's it's a methodology for organizing thoughts for yourself as well as for any sort of AI so that you can start getting an outcome, start getting it to do something well. And one of my favorite ones, this is one of my things I use most of the time because I just love creating, editing, writing, scripting videos. I have some for clients. Again, picture what I'm saying and apply it to what you're doing. Don't worry about my paper. Don't worry about any of the details right now. Think about why you want to implement it. I wanted to be able to use Claude. And again, maybe you want to use it in here, right? Let's let's start even simpler. Let's get rid of that. Let's say I'm doing something for a client, right? And you have maybe you're doing your real estate. You have a whole bunch of name conventions and data, right? You have it. Maybe you have a whole bunch of folders that are, uh, you know, they have everything you need, whatever the explanation is, right? But let's say you don't want to look at that. You're not looking at VS Code. It's just, you know, some folder on your desktop or wherever you're putting them. Maybe it's on Google Drive or something like that, right? We want to reference that, right? Every time I'm using Claude, my goal is to be able to do something with it. And for you, maybe it's like, hey, I am working on property A and I need this information, information B, um, to do task C, right? And what I mean by that is, right, when I say this to an AI, if I was just to put this in right now, Claude would have no idea what's going on. Be like, what are you doing? What are you? I don't know what what's the property? What does any of that mean? But if I'm if Claude is sitting inside of a large kind of workbase and let's say you're just in co-work, right? Um, which I don't know if you've used co-work, you can use that over Oh my gosh. Hello. What's going on there? There we are. Let's say I'm sitting inside of my project here. And let's say that that project has a couple folders about those properties. It has a markdown file that describes, hey, you know, this folder is for property A and here's all of the different information on that property and why I might need them, right? Um, and in that case, when I say, hey, I'm working on property A, Claude immediately ignores everything else in that folder. It ignores all these other files and just goes to the file where property A is. Let me actually try to do this right now in front of you. That might be good. Um, let's do

But you mean you mean because of the because you you tell it in the prompt, not not because it's rooted somewhere else or it's already set up like that.

So do you do you need to tell it if I say I'm working on property A then ignore the rest? Do you need to say that somewhere or is it by default like that?

So you want to say it once, but you would want to say like from a description. So the whole idea is let's say you have that top markdown file, right? Um, and I'm going to do it in here because it's already let's say let's ignore all of this because this is where it is. But let's say I'm sitting there and you have folder for property and again this concept works for everyone else, right? This is the most basic version of ICM. You have prop you have another folder inside of it property, uh, a, oh gosh, I can't spell, um, property and you don't necessarily have to write this. You can have, um, AI kind of structure some of this too. Um, property C. All right. And then you'll have route file or you can call it your Claude.md. Right. I most people call it a Claude MD. But the whole goal of the top markdown file is to basically tell Claude, right off the bat, anytime you open up a fresh version of it, right? If I open it up in here, if I open it up with a different AI, open AI, whatever AI reads it, it's just giving it a description of what's in there. And for your case, right, you might you want to think back to why you're using it. What are you doing? I was assuming you're going to want to be able to look at a property, right? Someone emails you about a property or some sort of issue is there, and you need to be able to pull information from the information you've been already labeling, right? Um, and I want to be able to take that information and write an email or give a report or send a payment or do something for someone, right? And that would be that task. Each of these is a workflow or a description or a process. If you were to describe to Claude a prompt of how to do that, right? So, if I sat here and spent 20 minutes, right, just writing a whole bunch on how to do that, how I would do it, what your naming conventions are, what you actually can do is copy that and instead of having to type that every time, you're putting it into this routing folder or into a subfolder. So, let's say, you know, you know, property, uh, like I would be listing this routing file would list what the folders look like, right? So here I have source materials, pillars, ideas, brand voice, source materials, and everything that's that's underneath it, right? I have pillars, I have, uh, ideas, brand voice, and it's just what's underneath each one. And then inside of those documents, I'm just simply saying, and you don't, again, you don't necessarily have to type or write all these out. You want to describe that folder structure to Claude, and it can write out a solid routing file like this, um, especially if you gave it my paper, and it'll do it well. And then I'm just saying, hey, this folder is for this, right? In your case, you would say, hey, property A, here's all the things in it, tax documents, tenants, right? Um, can you give an example of like one of your labeled conventions or something like that?

Yeah, I just thought of it, but I only know it in German. So, um, like the the specs of the the specs of the how do I say that?

How do you say that?

Yeah, like the what the tiles are, the the flooring and things like that, the materials used.

Okay, perfect. Right. And so, you would want to separate those based on how you would kind of think about it or read it, right? So, it's easy for you to read as much as it is anyone else. And basically this immediately gives Claude, just by reading this, it knows what's in there without h having to waste tokens to read what's in there, right? And when you say, hey, right, if you set that up, I'm working on property A, it immediately will read this and go, oh, well, property A is in this folder and I know that it has these things in it, right? And I go, okay, and I need this information, perhaps it's, I need to know which tiles were used and when they were installed, right? And in order in order to give an email, again, you might have a much more complex task, but this is just to kind of get the idea there. Now, if I was just to send this to Claude or to any AI, it would kind of be kind of crappy and or people would say, "Oh, I can build you a real estate agent, and it's going to have all of your properties in it." Which can be useful. I've seen people build good systems that way, but the amount of effort it takes or to even have someone else describe this, I think is minimal once you once you understand the simplicity behind it, well, it's maybe not that simple, but in that aspect. So, in order to give me an email, when I send this to Claude, even if it's a fresh version, not a random agent, or I send it to OpenAI, and as long as it has this routing folder, it's going to know, oh, okay, well, then I'm gonna go read property A. I'm gonna go pull up I'm gonna ignore tax documents. I'm going to ignore tenants. I'm just going to go to the spec of the property folder. And maybe you describe kind of where each thing is, right? Maybe you have different documents. You're just organizing them based on when you need it. Then where ICM gets kind of more special or more focused is when you add another MD file, right, that then describes all of these. So like maybe you have a naming convention, maybe there's organization of how those materials, maybe where those contractors are. Your goal is to make it so that the AI has to think as little as possible to get to the information it needs. And so this top markdown file can be huge, right? This is a huge one. But you can break it down. You can break down all of this context into smaller ones. So when I go into and I say this is from my side instead of property, I want to make a video instead of, you know, the materials, I have different styles of video production. So when I say, right, let me get rid of all this and I won't even do it in here. I'll do it in this one. When I say I want to make a video for NLP logics. Now, usually that would require an agent, all you know, a whole bunch of prompting things like that. This is a fresh co-work. And again, I could do this with OpenAI, I could do it with Hermes, I could do it with other things. And what it's going to do is immediately Oh, well, I didn't have it actually read the Claude MD, so it's going to take a second to dive in, but that's okay. It'll it'll find it there. Um, it's going to immediately actually read that and go, "Okay, cool. So, my Claude MD is right here. Here's what the folder looks like." Then it's going to look at the actual project. Oh, wait. You have an NLP logix's project. It's immediately becoming the agent, right, that you would have created for each client or each problem. And immediately catching up from one single prompt. It's immediately knows, oh, hey, do you want to make a new video because you've I see you've made five more before this. Do you want to change videos? Do you want to rework an existing video? Right. So, I'm just going to hit brand new. It immediately is then understanding just by reading and navigating the folder what I want, how I talk, what my things are. It's going through and saying, "Oh, okay. You said NLP logics, right? You said you want to make a video." Well, I know if you want to make a video, you go over here, right? Record and cut pipelines. If you want to do a project, then you have projects for different clients and NLP Logix is inside of that. If you want to do something with that video inside of these projects and inside of here I have a description of what I do and how those videos are. So it's very quickly without having to go through and read every single file, read every single thing to assume what I'm doing. It immediately knows, oh, that's what that workspace is for. The the way you organize the information and describe it for yourself becomes what the AI then understands. Now, I've talked a bunch and I'm sharing a bunch. And again, this can all be done. You never have to touch VS Code. Technically, you could just upload my paper into Claude and say, "Hey, I'd like to restructure this folder with my information, um, to have a couple of these markdown files to route everything." And you could build something like that or you could have your IT person do something similar for you. Um, and that's also on top of all of this, which we will talk about here in a second. And I'll shift off of this. I felt this was important to answer. Um, we are building kind of the layer so you could just upload your stuff and it kind of gets organized that way, um, to make it a lot easier and then you don't technically even need another tool, um, where you'll actually have those kind of workspaces, uh, organized through ICM and whatnot. Um, and I'll let this load up and kind of come in. But like you'd be able to come in just upload this folder that I'm showing you here, right? And then it's easily just kind of just there and you can just connect your AI to it. It's all kind of in there and you can just start a chat with it and call it a day. Um, but going back, does this making more sense kind of how I described it there or no? Did I confuse you?

It it's a it's a bit like it acts a bit like, uh, the PHP between front end and back end.

Beautiful.

Does it maybe make more sense if I say I have for instance in my agency I have these files with the specs in it for instance I produce myself in the agency. So I have an agency folder for the for all the graphic stuff with these files in it. The specs for instance or the brochure or things like that. And I have for the real estate for the pure real estate area I have another, uh, another folder, another big folder with projects in it, the same projects in it, just the one or the graphical. So I could say pull pull the the brochure from from that and pull the contract from this folder and things like that. So it acts a bit like because you said you could build of course, um, for a real estate developer, you could build a real estate agent's page or whatever and you have to feed all that content constantly into it and it needs to sync and everything, but that's what the PHP is is doing all the back end and front end. So I keep only my back end.

Essentially. Yes. Pull with and and pull on demand my

content.

Exactly. Exactly. 100%.

My my formalization, my structure is there based on the patterns I'm seeing everyone else doing and what I think is the average of all of them. You don't have to take it as concrete. Hey, it has to be this way. My goal of that paper and my process was describe, hey, based on every single workflow in every single industry, this format seems to be a good methodology in which to implement it. But at the core of it, the reason I formalized all of it is that is I noticed when someone like you, as long as you can route where it is, you know more about your information than anyone else will, even myself. And I also believe that the human should be in the compute layer. I think the argument that, um, agents are replacing people forgets the fact that humans are infinitely abstracting creatures. Uh, not everyone, this is not to say that jobs are not being lost, all of this jazz, but I think we are able to take technology that has collapsed extremely complicated processes and do more complicated processes on top of it. Um, so I, yes, essentially that's what you explained, kind of this idea of PFE, if the backend is farther away and you're just kind of saying, "Hey, it's almost like the AI becomes your runtime."

It's almost like the AI becomes your runtime.

Um, oops, someone, uh, got to hear myself twice though. That's good. Um, but yes, I think that's a really great way. But does that, so that helps you? That kind of gets you in a in a better mind state for that? Obviously, there's still a little bit of extra work that needs to be done there. And that goes into the first question, which is, is your time more valuable spent on something else in your business and you offload this to someone else, or is this valuable enough for you to do yourself that then it will return that value? Because that's a question I I tell a lot of people to ask. Yes, all of us can use AI and can build with AI and should be using it to a certain extent, but should you do you build? Right? You said you have an IT guy. Why? Why would you if you're willing to have

No. Not anymore.

Unfortunately, not anymore.

I would I would need one. I thought I need one, but that's actually not the problem. So, if I would go if I would continue with the app,

But I I actually, um, didn't see so much need anymore to to do things with with apps. What what I have now is is good and helped a lot. If I would continue that, I could continue, I could easily continue that also with a with a code editor. I'm used to working with that. Um, I would probably get somebody. I would still if in the community somebody would like to do that to to get some to get the security audit. So, you know, somebody checking if it's if it's secure and everything that I that I couldn't do, but I but but I totally appreciate the fact that me as the person that needs something to be to to just to get it done. You know, I I know what we need. So, I can easily program that, but a full stack programmer or IT guy probably would have to make the security audits. So, that that's not that's not the problem. It's it's more like, um, it's more like these little things that for instance now, um, the naming convention could be done better.

Okay.

That's it's it's just not to I I don't even know it takes longer to explain it to someone than to do it myself, but there are so many little things that I could do myself that I'm overwhelmed with it.

Well, and and like I said, that I think that ends up becoming a business question, not a technical question, right? Is

like is the time of being overwhelmed stopping you? Because is your goal more money? Is your goal to scale? Are you enjoying learning these processes? Um, and like I'm sure Natalie has some questions because she's chatting about this and this is the important part. Being an expert in AI in your industry does not mean you are the one using it, right? Or you're the one building it. If you're if you've been in construction or you've been in real estate or you've been in some industry that is not software your whole life, it's okay if you want to transition. That's what you want to make your passion, but think about opportunity cost. It might be better to bring someone else on board and direct them your ideas, right? Some of the greatest companies I know were great at delegation and it's okay. Yes, I really

Yeah, sorry. I really tried, but we really don't get people. So if I would get someone doing that, really it would be it would have been lovely if, but he's so he himself is is so busy.

Yeah, somebody wants to do that then.

Sounds like down to a collab as well though. Um, now I do want to shift off this, so thank you. I was answering things. Thank you.

Because I felt like it resonated to the rest of the room before I kind of respond to more stuff. Did anyone learn anything or Ruben, you had mentioned that, um, that was kind of important there? But is there anything that anyone wanted to kind of hit on that you thought was really important about that conversation? We always want to look back at dialogue because there's always hidden things that we we learn during it. Um, does anyone have? Yeah, go for it, Krill. I think one of the actual things that you've taught me in like the courses and the content that I've is also the fact that, um, so you have your way of doing things, whatever it might be, if you're doing video editing, or if you're doing SEO or websites or things like that, on the fly, as you're doing something, you could take a course from another person and then you're like, oh, I like this part. So now every single one of my client processes, I just want to slightly alter it. And with the file structure that you teach, it's so amazing, amazing. But I'm literally just taking every single SEO course that I can and the points that, uh, they will add something new. I just tailor it and I was like, "Oh my god, that's money well spent because now I can just use that and then I just build my workflow and it breaks it down into every single one." So the way that I like edit clients, uh, for example, portfolios or the way that I edit their services, and it makes a huge difference. Like these are like multiples. So I feel like they're working like at a hundred or a thousand times better just because I'm able to take outside information that people have been teaching and really apply in my business almost instantaneously.

Yes. And that's the important part, right? Is I'm trying to create systems where it allows you all to productionize your opinion because Anthropic, OpenAI, they're going to make way better integrations. They're going to make their models stronger. But the things that are fuzzy, the metrics where you think it should be done differently than the industry does, or you know, in your niche it needs to be done this way because of your opinion, how you've been it. That's hard to automate. That's hard to train an AI. I can't create for those of you who might be in machine learning. I can't create a reward function for your opinion that will then be generalized to the rest of the world easily. You can in certain stages, but it's very challenging. And in that challenge, you find value. You find something that lasts past model updates. And that's important. Is every little update you're adding to your files, right? Every little word in here, every little process is you are productionizing your opinion because now your AI is amplifying the way you have put data together, the way you think business should be run. And that's where I again think this is important. It's not that ICM is automating processes. It's that it's organizing processes to be automated so that you can then collaborate with information better at a higher level, a higher abstraction. So yeah, 100% keep focusing on that because then when when a folder becomes super valuable, it it it becomes a great production layer. Uh, and again, that's why I'm trying to create the thing that allows you to deploy that because in my head, imagine you or the six other people in this room could deploy that onto a platform and I'm able to protect and so I'm creating all the security on Azure and we're using, um, C C++ and C# uh, kind of backends to like build our own infrastructure because we don't trust anyone else. Um, and we want to kind of make it so that certain parts of your folders can be editable by a client or a company that licenses your workflow and attaches it to their AI, but other parts of it can't be. And it you get paid for for licensing that workflow out to people. And so we're trying to create the infrastructure that allows that easier to where it's like

You could either hire someone and then also license their ideas out to the rest of the company. Or B, you hire the virtual version of that person or their workflows. Like they say, "Hey Krill, I'll pay you this much a month or I'll pay these tokens to access your folder setup to do that workflow." Um, and I believe that solves an employment problem while also creating a lot of money for people.

Um, so Jay, could I add something real quick?

Yeah, please go for it, Chris.

Um, hello, Chris.

So, um, I'll make this quick because I know you want to move on. We're here.

I'll definitely leaders and organizations, CEOs, whoever, who aren't in front of their computers every day, if you can, and it's legal, wherever you are, get something like Plaude or be taking your thoughts and recording them on your phone, whatever, talking out loud, and have your first agent or one of your first agents in your ICM should be an ingest agent where you take all of those transcripts, drop them into an inbox, and it pulls in your conversations, your thoughts, how you make decisions. Um, you know, all of those different types of things will form how your sort of scaffolding, your folder structure, all of your context will get built out. Um, so I don't know that's you don't have to make like you're saying, you don't have to sort of build this all yourself. You can take raw material, then use the ICM research paper, gives Claude a starting point, and then use your materials to make it tailored specific to you.

Yes. Yes. Yes. Yes. Yes. Yes. Yes. And I I'm just pulling up one thing that I'm doing right now, and I'll I'll I'll throw it up on GitHub here soon when I'm done. I'm I'm testing a distillation process. So, right, you don't want to just simply grab transcripts and things like that. I mean, you do you should right now like if that's what you can do and that's what you can move. But I Ari's worked on an amazing one and hi Ari. I got to see Ari in London which is amazing. She's building it based off of brain structure and doing a whole other level which I'm I'm excited to have her share here soon. Um, but I've been doing a very simple version because I I want to start with a simple one um that kind of is there and it's like taking transcripts, taking the my papers, things that I've written and then I'm trying to essentially go through and be like, okay, what information would I want everyone to know that I wrote and why I wrote those things? What types of things do I want to keep private? Right? But then on top of that, how do I want the signals from all of those things to be broken down to be like actually looked at? I want to be able to ingest that input. I want to be able then to separate it into these process into these units. And then I actually want to extract not just the physical words, but the patterns between those words. Why do I talk a certain way? When did I say it? How did I say it? Then I want to distill it into its processes much like we do with a brain. And this is kind of how we train models, but it's in a much more structured way. And I like to do a lot of versions of this. And in a lot of ways, ICM's kind of already naturally doing that, right? As I'm building this, I'm like, "Oh, I don't like how the AI did that, so I'm going to change um, you know, my the voice constraints here. I'm going to add another one." Right? I don't like performed questions or, "Hey, I don't like, "Hey guys, energy" type stuff, right? I'm adding these in, which is then kind of creating a version of my brain there. In a very simple way, I can then hand this to someone else in my company. my employees, they won't be me, but their work can be influenced by the way I think at a lot higher level and it creates a kind of I don't know speed to production. Again, it's not perfect. It's never perfect. Uh but I think it's something interesting there.

So yeah, thank you Curtis. I I agree 100%. Within, you know, rules obviously there's limitations with depending on the companies, but um yeah, thank you so much for that. I really appreciate that.

Um Oh, yeah. And so I just saw some tax in there. I just put it in there. But for those of you who are not in the Discord, um uh if you go into uh the classroom and you come down to uh the drawing room VIP Discord setup, this specific link will give you VIP role and whatnot. And then you should be um sitting inside the Discord. And this is just a great place to be able to link up with everyone. Um especially if you're not level five yet. And I apologize that we had to shift that, but there was just so much bot and spam stuff. And someone's even botting my Instagram right now um trying to send a bunch of comments on to me and I've seen like six fake accounts from me which whatever that's the price of growing I guess but um definitely hop in here. There's a lot of talks going on a lot of um kind of people diving into what they are and if you want to connect and then of course there's uh talk rooms as well if you want to get into it. So um highly highly recommend uh diving into that if if you are in VIP. Um I think it's extremely extremely useful because again I'm here to answer lots of questions. we're here having these talks doing these kind of masterminds. Um but and I want to give more value than any of the other AI groups out there in these like my goal is to just make these you know almost Harvard level lectures if I can um in in certain ways kind of back and forth but the other value is everyone else in here right Ahri is insanely brilliant like when we sat down in London we got to talk about a whole bunch of like really cool weird stuff uh that she's building for distilling information using like neuroscience for the folders and so such cool stuff but there's a lot of other people in here who are I mean every single person who's introduced themselves today has just been really cool stuff like all of you are doing really cool stuff and that's the other thing I want to remind you of and I say this all the time but if you ever feel like you're behind of course you do you're surrounded by experts if you look at the rest of the world right now most people if you go walk down to a coffee shop most of them have barely touched claude or chatgpt a lot of people I've worked with companies today who none of their employees have even used it right and it's like you have to remember how far you are ahead of get not only are you using it not only have you seen the downsides of it you've discovered a structured way in which to organize it and use them to such a level that it feels like cheating almost but we're surrounded by brilliant people so we're like oh man there's still so much for me to learn it's a process slow down you're you're here so you're not left you're already not behind I can promise you that right now like you you are so far from not behind it's not even funny.

Um, and it all takes time. It's not an overnight process. If it's an overnight process, it's marketing. That's them saying, "Hey, it's that's gonna if they're telling you, you know, this AI thing is going to change your whole game." It is. If you haven't used any AI for the last three years, that would be like if I someone hasn't been using AI for three years and I gave them a cla account, it's a pretty big difference. But it's not like you eventually then need to learn the skills. You need to learn the process, right? Excel is a hugely powerful technology, but guess what? It's still not overnight. I if someone who's been using Excel for a year versus someone who's been using Excel for 20 years is quite literally a different software. Like the guy who's used Excel for 20 years is a monster. Um, and even then, right, in those areas. So, yeah, do not feel like you are behind, please. It is it is it is a learning process. I'm still studying and reading stuff every day. I I I was at London Tech Week sitting down with with PhDs and weirdos and all sorts of fun people and I still felt like and even conversations with Ari, I'm like, damn, I didn't even think of that. That's such a good idea. There's no such thing as behind when you're building your own future. It's the world is hugely complex and infinite. So, yeah, don't stress it. Just motivation thing. Relax, enjoy it. That's what we're here for.

Um, but of course, stay competitive. We got to dive in. And speaking of competitive, um, I know we're coming up on the hour. For those of you who are used to my VIP calls, I always go over, so I apologize if you only slotted in an hour. Don't worry, I'm recording. You're more than welcome to leave. I'm not finished and I love talking like this. So, we're going to be here until I've finished um all of this. So, um yeah, we'll make sure we're getting our time out of it. But again, it's all recorded. So, if you only slotted an hour, that's perfectly fine.

So, what did I hear in London? I got to see all sorts of crazy individuals. I mean, we had the CEO of AMD was there. We had people and researchers from AWS, Nvidia, Microsoft, HubSpot, uh 11 Lab CEO was there. We had the mayor of London. There were some amazing people there that were doing some crazy talks. Uh a lot of it was kind of government capital and silicon focused, but there was a lot of really cool startups from Turkey and the Philippines and just all around the world. And it was really cool. But the reason I I kind of want to chat about it is to these startup and these tech events are a really good place to see where the industry is going, right? This is a really good place to find out what are people looking at and also to see what not to invest in because if you see 27 startups doing the exact same thing, which I did, then you know, oh, okay, I probably shouldn't waste my time there because someone has already solved that problem or is solving it in a good way. I can just pay them later, right? Because when you're running a business, it's not always about being innovative because you built it. It's about knowing who else is being innovative. And when you buy someone else's software, you have to remember if you want to waste the time and build it yourself, not waste the time, but build it yourself. That's good. But sometimes it's like buying a development team because they're handling the software updates. They're arguing about the same questions of AI. And so you want to think about is this software that I'm building is this AI solution that I'm building am I the best person to build this or someone else going to do a better job and I need to focus on some other value acquisition in my company and it is highly dependent on your company where you are but I really want to make that important there also there was a lot of VC and uh private equity investors I sat down with the guy who invested in perplexity and open AAI five years ago or four years ago for both of them um and so he was really one of the investors there's obviously a lot.

Um, and he was really cool. He wanted to to chat a lot more. Kind of a It's so weird once you get into the tech world, there's so many weirdos and stuff there. But I will say out of all the investors I talked to, all of the money that seem to be going, a lot of it is around structure and infrastructure. So I'm seeing a huge amount of effort going into this kind of like, hey, you know, the models are important, but what they're seeing, how they're seeing it, right? of obviously what we're working on in here the kind of top level data is going into physical infrastructure as well as data infrastructure. So like hey, you know, how do I get it so that my data is being seen by the AI better or um hey, we need more chips so that the AI can run locally on my computers. AMD was sharing a new chip that they had um and it was a big service center that you could buy for your home so that you could run uh trillion parameter models at home. Um, and Nvidia obviously dropped their version of it too, which is is really interesting.

Um, also I find that there is uh, and this isn't guaranteed. This is this is kind of a the buyers changing is a weird thing here, but I noticed that there's groups of startups that are not selling to people, they're selling to the agents, right? So, HubSpot, Salesforce, um a couple small startups were creating payment layers and data layers where the AI can actually buy directly from you and it facilitates that process be that with crypto or financial stuff. And their thesis and I thought it was important is right now I think it was as of the last week actually more internet traffic is being caused by bots and AI than real humans. So if anyone's familiar with the dead internet theory, we are now one step closer to that. Um, but uh hopefully uh we'll never realize it fully. Um, I don't think we ever will and what is you know dead on the internet anyway. Um, but it's it's this interesting concept of if you have a service that's sold and it's blocked by payment and there's information and value behind it. Someone else's AI might want to pay to get that information. Case in point, imagine I could let an AI sign up for this course to be in these calls to get these transcripts. If someone thought there would be value in in their AI agent going to these calls and paying for it, then they might approve that because that data has created enough influence and value much like how Krill said, right? Krill's mentioning this. He's being the agent in this case is he's the one deciding where the value should be. I'm going to pull from these courses these processes. Then why wouldn't an AI maybe want to sit in on the call and kind of pay for it, right? If you can kind of build those layers in.

Um, so it's become an interesting area. I think there's certain areas where that will work. I think there's a lot where it won't work. Um, but I did see that there. The one thing I saw and I just I this is opinion. You can disagree with me. I just think so many people are overbuilding huge like I there was six booths and they were spending so much money on huge booths on oh we're the agentic builders of the future. I must have seen that at like seven different companies. Like don't get me wrong, if you're like niching down and like you're a consultancy, you can make a lot of money in that right now and probably for the next couple years you will. But if you're at the top level and you're trying to innovate into the next stage, just overbuilding these crazy custom solutions when you could just, like I said, make a folder and hire two people to get the same outcome. It's it's wild to me. And I I felt a lot of companies and startups were trying to just build these hugely overengineered things when you might not even need a software in that situation. You could just have a structured system, have the AI do something and you would get the outcome of what that software was anyway, right? Like why would I want to build a software to do something when I can build a system that gets that outcome and I can skip most of the software BS anyway? um minus like UIs UIs and and front end are I think we're going to see a shift over the next decade where the backend is even farther away from the front end and there's kind of like most people who are building backend only build back end they don't even touch frontend stuff and everyone else is kind of just building their own front end and connecting to it and you all have your own like kind of layer uh at least that's what I think that's why my I don't know if you ever noticed my company's tagline um is called the faces of interface um and it's specific speifically around that concept. I think people are going to just make their own interface. Every human is going to have their own fingerprint on it. But uh just personal opinions there, you know.

Um, let's see. Uh, oh yeah, and then um they think the opposite side is that they create platforms that like or systems or fe that are just going to be a feature in the next kind of like update. Not because they're not productioning on their their opinion, but because they're trying to solve for like an integration problem like ah, you know, none of the AI integrate with these three tools and we made it so much easier to integrate with them. Well, okay, that could easily be a feature in the next update. Now, if it's the way in which you process data is something you're building, that's fine. again the opinionated stuff but I think solving the problems of what the big models can't do now in terms of like integration and like very structured data stuff I again it's okay if you give me push back here not everyone is is this is true but I think most people are not going to solve it any better than anthropic or Gemini or even some of these open source teams um I did see a couple people like myself building in the talent layer like hey how do we right I think I've heard almost every single person who talked today said, "Hey, I want to hire someone or I need someone to help me with this right this process." Um, obviously if there is a need and you are all business owners and you're saying, "Hey, I need more talent that can do this stuff that means there's a market and I think there's a huge market there." So, I do believe all right and I I urge you if you all want to compete with me like I I am making a kind of talent layer process thing um please build right that's what we're we're going to figure out. I I don't think because someone is making a version of your idea as a startup, you shouldn't make it, right? There's Lyft, there's Uber, there's a hundred different ride share platforms, they're all making millions and billions of dollars, right? Like just because someone else has the idea, you the thing that makes it valuable is your opinion on that idea. Like Lyft has certain opinions that are different than Uber, that is why they think they should be successful. And so they compete. And so I think that we're going to see over the next five years a lot of really big talent layer like software as a service almost but not quite um talent uh things. I think Handshake is one of the ones that is pushing already to dive into it. I think they're doing it the wrong way. Um but they used to just be like a hiring um kind of platform. Um I don't want to sign up. I just want to look at your front page. Um and but now they're like almost Fine. All right. Now they're almost entirely Oh yeah, you get to look at my 27 emails. Um I I think they're kind of diving heavy into that AI kind of layer space. Oh my gosh. Of course this is this is what I mean. Just tell me what you do as a company, dude.

Um, let's see. Here we go. Create the Oh Jesus. Of course. All right. Funnels. Funnels. I'm not talking about Handshake then. That was going to be a good plug for them, but now it's not. Um, but and that's my point, right? Is like if I was Handshake, I would not do that. my my platform, what we're building looks more um it's just very simple and I I'll give a link to this once we're ready to kind of launch it. Um, but the idea is right, let me sign out real quick. Um, is you can come in and you either say I'm hiring or I'm a candidate and you let's say you're a candidate. You come in u you know, we're we're doing it where you have a signin code and whatnot. Let me uh actually that real quick um so that I can show you what this looks like. Um, and basically the kind of idea is if I was going to sit there, I might try to get hired for a certain lead, a certain process. But the difference is everyone inside of this platform is going to be trained on ICM or that method. That's going to be my opinion is that every person who's in here is going to be someone who can actually understand this, actually understands ICM. They're able to upload their workflow so you can look through it. And if anyone knows Portal or has played Portal, um it'd be really cool if we could name a company Aperture. Um but or maybe not. That could be a problem. And the idea is that you can go through and actually like send your intros, push them there, as well as like literally share your work and processes. Um, and so this is just my solution to try to like get people hired who know these problems and processes. Um, and yes, I'm thinking it will be a monthly charge to companies. I don't think I'm going to charge candidates unless they're freelancing. Anyone who's VIP in here is going to have it for free. Um, that's like going to be no matter what. Yeah, don't stress about that. Um, especially if you're all the first and I'll make sure that you all get contracts that if we get bigger, it stays that way. Um, uh if you're in here, gang, I'm I'm not going to charge any of you for access to it. Um, in the future to monetize it, or at least anyone who's not in the community um I think what I really want to do in the really big money maker would be um placement fees. So right now in the recruiting industry if you want to hire someone uh a lot of the times especially at the executive level you'll go to a recruiting firm they'll find you they'll do the her interview process they'll put them in front of you and they'll charge a percentage of that salary that you're hiring them. So if the person's 100K, they'll get 20K for getting them for you and doing the whole process. Um, and so I think uh being able to build a platform that automates the recruiting industry in a certain way, but not in like a annoying AI way, but like just makes it better specifically around the problem of AI talent and ICM talent. It would just be great. And then the other side of it is if that works well, then I'm going to connect it to the other platform, which is the one that allows you to upload your ICMS. And then the freelancers can just immediately license themselves to that company without even working there, right? So the companies can go log in and can be like, "Hey, you have the skills and the opinions I want and you have some workflows. Can you just do this work or can we connect to your ICM?" And then you get like a small extra payment. Um, and I see that being like a really cool industry and I see it solving the college problem because imagine you go through, you get your degree, but instead when you leave, you have a productionized brain that you leave with college or with school that you can then license to companies right out of the gate. Your whole goal of getting a degree is to build a proper workflow process and understanding of your industry and niche, which is what degrees are supposed to be, but most of the schools don't do that. Um, but now there's a software layer. And the idea, my whole [ __ ] excuse my language, my whole thing is basically, hey, what if we were to give IP to the person for that rather than me taking all that data and then training a model. I think there's more value in growth where you have your own models that you're then licensing. That's my kind of niche thesis. People disagree, but whatever. I'll try it and work it out and see what happens.

Um, let's see. I I've been ignoring some of the uh the things here. Uh Ruby, I'm just wondering if I can build a service that is just a chat interface for house cleaners specifically. Connects to do a calendar if they have a job that day. It texts. One thing that I did for my buddy, um this isn't house cleaners. Let me see if I can find it. Uh conbon, where is it? I made a conbon board that connects to his calendar and he can chat with it and it updates it. and he's um he's a construction worker, but he like he runs a bunch of construction jobs. And um let me see if I can find it. And the idea was like the conbon board becomes Oh my gosh. Where is the GitHub repo? I know I have it here somewhere. Hold on. I've got to find this. All right, let's see if we can log in without um breaking everything. Oh my gosh. Of course, I have to uh No one look at this. Hold on. I don't think Oh. Oh, I put the wrong one in. There we go. Um, but the idea was like, hey, you have a conbon board or some sort of way um that my 2,000 repos. Um, there we go. And it's basically like a database that updates um on what he wants and how he does it and it's like his little command center and he can just kind of wander it over. This is his active one, so I'm not going to screw with it right now, but um actually no, this is the fake one, but and he can just say, "Hey, this is what we're doing. Um, this is what we have this week. Here's the backlog. Here's what I can filter it by customers or by like style or what's going on, right? Okay, we have materials that we have to get. And then it's directly linked to his Claude um and his Google calendar uh by proxy. So he just tells Claude, "Hey, update the Combine calendar. Um, I'm doing ABCD." Um, so I think that might be something really cool um that they would like uh in terms of scaling that. So um yeah, I would check that out.

Um, let's see. Uh, I wish I knew enough to freelance. Okay. Uh, start freelancing. You know enough. You're in this community. I promise you there's someone out there who doesn't even know how to prompt an AI who would pay for your time. So, I started freelancing like six years ago, five years ago, uh, in writing and kind of scripting because I just loved writing and talking and speaking. And I didn't really I mean, I was in the Marine Corps for a while. I had a huge technical background and I had been writing myself. And so what I ended up doing is just making a website where I just wrote a whole bunch on it and it's still up. I don't really use it anymore. Um, but I just kept writing and then I would tell people, hey, I'll write an article for you or I'll do something, right? And even if it's like 50 bucks, right? I as long as you can get that first payment, it'll tell you why or why not they won't hire you again, what they want to do. Um, you you always know enough to start freelancing because you know enough to have a job. If you're jobless in here, well then there's a whole other conversation I guess we have to have. But if someone is paying you for something, it means they're getting more value out of you. That's how business works. And if they're not, that's a bad business. But if you are getting paid, you then can freelance 100%. Or start a company. Like I just I have zero doubt in my mind that that's the case.

Um, oh, this was a fun one I wrote back in 2023. Conscious is not binary. Um, so I'll share some of that later for you all. But yeah, just wanted to say that Dawn 100%, especially I've seen your posts, you could totally help companies in freelance um or team Lance. Yeah, work with others.

Um, let's see. What do you think of stays protected, defensible versus ubiquitous? Uh, because of increasing intelligent models. I think once we get to a certain level in every single industry, there is no such thing as best, right? So, what's the best politician? What's the best writer? What's the best artist? Even programmers, we argue about what the best programming language is. Is Rust better? Is Python better? Is C better? Right? And you could build the same exact software in three different languages that gets the same outcome. And the opinion is what ends up being the label. And I think it's the same thing for intelligence. We've been arguing about general intelligence way before robots, right? What IQ tests are built on the idea of uh value G, which is this concept of a general intelligence, but we all know that that's general is so relative, right? So, I think what's going to end up happening is we are going to replace and automate a lot of stuff that we didn't think we're going to. But again, there's so many problems in the world that aren't solved because we have not enough time, not enough work. We can't agree on how it's done. We're just going to do that at a higher scale. So I I I really, I think as long as you're learning, you're breathing, you're creating, I just don't see a replacement for humans because, and this is a weird opinion, it's never enough. Human desire is infinite. It's why the markets exist. I mean, if you go back 200 years, most of the jobs that exist now are unfathomable. And I don't even mean we're going to make new jobs. I just mean like the reason we would even need the job wouldn't even exist in red. So I think there's there's a very I'm a very strong bet on humans, which some people disagree. Obviously I was in the Marine Corps. I saw war. I saw hatred. I saw anger. So there's definitely some bad sides to humans, but I I think there's a small percentage, but it's a net positive over the bad percentage in my opinion.

Um, and if anything, okay, let's say it reaches superhuman intelligence. Okay. Well, then there's just more of us, right? More humans means more work. More intelligent creatures means more work we're going to do anyway. I I think it's it's just going to be at a higher scale. Could it hit a point where problems happen? Absolutely. Um, I mean, humans do that all the time. We're at war constantly. So, I think it's just going to be the same world we've always lived in. Some is going to be amazing, some is going to be disgusting. Uh there's a quote I remember um it's I forget who it's by and this is a beautiful quote and it goes no matter how many bombs we drop no matter how many politicians become corrupt no matter how many people spew hate the trees still grow the birds still chirp and art is still made and yes, you know, there is a lot of negative points to put there but I I really do have faith in in the small percent of net positive and that's why I do what I is there is a lot of bad ways AI is being used. And I but I think if we actively create the good ways, the good things. That is an act of defiance. That is a fight. By creating the good, you negate the bad often. Um, but if you constantly focus on crushing the bad, you often don't create enough good if if that counts. We're getting really philosophical there, so I won't dive too deep. Um, go back to the business stuff, but I hope you all kind of get what that's going on there.

Um, yeah, great, great questions, by the way, everyone. Thank you for all of this.

Um, let's see. Uh, oh yeah, so after London, I flew to Chicago. My flight got delayed four times. I got in at 3:00 a.m. and then I had to give a professional executive workshop to the CEOs, presidents, CTO's, CIOS of a very large data company uh at 7 a.m. Um, so uh to say I was a little tired, it was a little rough, but it was a really cool workshop. We did a lot of work. I had dove into their teams. I talked to every single one of their teams and we brought up like an entire um kind of process of all of their workflows. And this is something that I do with a lot of companies. Um, and so I went through and looked at their product team, their marketing team, um their engineering team, and I asked how each of them and I gave them a workbook and said, "Hey, you know, what task do you do? What tool are you using? How often do you use it? What problems are not working?" And I did it across which ones they think are priorities to get better at, right? All of these things. This is a standard thing I do with every company I work with. Um, and basically we went through and I'll share a version of this template for all of you um, after this call. I just realized this might be useful for all of you to do with yourselves. Um, and uh, but basically I did that for each of their teams and then I kind of created a workshop where I took all of their leadership. So every manager or vice president or whoever is leading each of these teams, we all got into a room and kind of broke down the process. And one thing that I noticed that was consistent not just across this company but a lot of them. So if any of you are running hollow output, right? A lot of people think what the AI is giving them is super solid and polished. Um, but at the end of the day, the steps to create the polished work actually made it almost have zero substance. It sounded really great, but it it just was built on nothing, right? Um, and so I found that being constantly a problem. And that's again that's just because they're not giving it context, right? They're not giving it um rules, processes. More importantly, they're not giving it their opinion. You get substance by giving opinion. Substance comes from something that you can't just read or copy, right? Uh, it's it's that weird kind of fuzzy area.

Um, again, everyone was overbuilding. Oh my gosh, there was people building AI tools that could have been like a Zapier uh solution. Like you could have just done, let's just do a Zap. Again, don't get me wrong, like saving money can be important if you're rebuilding a tool because Zapier is super expensive if you, you know, get a lot of things like like I have Zaps for my school community and it gets pricey very quick, but the amount of time effort to get the same output might not be worth it versus the cash that you can put down. So, it's like, dude, just pay for the tool. Like, don't build monday.com. Just pay for Monday. Like, it's really not that expensive unless you have a huge industry. like if you have a thousand employees then it becomes worth it to build your own because you know the search seats per head but they were just overbuilding which is wild. Um, I'm sure some of you have heard about it but the 603010 rule right my concept that like 90% of your structures your processes should be like just traditional processes code and 10% should be the AI on top of it all which makes it all magic so to speak. Um, a lot of them were struggling with that except for the engineering team. the engineering team really was doing well on that. But that's natural, right? Engineers naturally do that kind of rule process.

Um, also there were so many things they were trying to get an AI to do and I'm like how much, you know, like we calculated how much it would cost an API costs versus having a human for $40,000 a year copy and paste. And um I was like, dude, just hire an intern. Like like just because you can automate it doesn't mean you should. Humans are compute efficient. We don't need a whole bunch of energy and stuff to do some pretty complex tasks. I just need a Red Bull and sandwich most of the time to get most of the work I do. And like that's very that's that needs to be in the calculation. Especially I don't know if there's anyone who's in a big technical role or a data role in the in the call right now. But your efficiency of humans should be in that calculation, right? Like if you can give an AI tool to a person and they can get a lot done that is more efficient and cost-effective than trying to build an automation that does that thing kind of well right um within reason. Again, larger companies, they get this um economies of scale, so it makes more sense to automate more stuff. But it's smaller bespoke teams like AI native in my opinion doesn't mean you don't have any human roles using AI that you have gotten so efficient you don't need to hire certain roles or the roles themselves change what their value is giving.

Um, so yeah, that's kind of a big thing. Red Red Bull and Sour Candy. Oh my gosh, I have a problem with sour Skittles and I keep getting the Sour Boss. Um, boss, what is it? Sour Boss. I forget what it's called. Final Boss. Final Boss Sour. I keep getting ads for them and I really want to buy them. Um, they look so good.

Um, yeah. Meera. Oh, Mera, wait. You're new to this community. I think I me I remember you saying earlier in the chat, you didn't get a chance to introduce yourself. I'm so sorry. Would you like to introduce yourself? Uh, if you can unmute. Yeah, there we go. Uh hopefully it lets you uh maybe possibly if not you uh if it's it becomes a struggle we can but I just I just realized that I recognized I was like wait a second you didn't get to introduce yourself. Oh maybe no still muted. Oh yeah browser permissions it's always fun. Yeah. Darn school and their their movements. I talking with the CEO of school to tell him to he told me to send him a loom video of everything I wanted him to change. Um, so I'm I'm I'm doing that today. like these are all the things that your software should update. Um, if you're able to get it Mera um, just you can go ahead and interrupt me while I'm talking. Um, but if if not, just introduce yourself in the chat, that'd be great.

Um, good night Sandra. Thank you for staying on. Like I said I'm going to be probably another 10 15 minutes or I'll try to close it up. Um, but the recording will be there. Thank you for taking the time to be in here and again make sure to connect in the Discord and and rewatch some of the older um uh recordings if you all have time or just give them to your claude. That's another actually important note if anyone does have to hop off. Um, all of the prior recordings and sessions are in there. Um, and at the end of each one, if you go to the bottom, you you can download a zip file that has um kind of all and I describe what it is. Like I have actual slide deck that I make from all of the transcript here. I have um actual uh kind of like markdown files like skill files that basically talk about what we were doing or how to do it. And I'm going to do the same thing, right? are opinionated packages, not um you know kind of theirs. And it's it allows you to just add that little bit extra to your own um kind of files. It was my way of being like, hey, instead of you having to go filter through all of this, I'll do it for you. Then you add it to your second brains. It's instead of saying, hey, you know, I'm going to put all this behind a gate and then you're going to try to take the transcript and use it AI. I'd rather just give it to you. I know you're going to use AI with it. I'd rather just help you out and make it valuable. Becomes part of the product rather than something I'm trying to hide. But um anyway, yeah, have a good night, Sandra. That'd be great.

Um, also, I was going to spend a lot of time on this um but, uh seeing as how long we were here. Um, but there is a paper that came out called skill opt. Um, and essentially it is it's interesting. Some people are talking about it. I think I saw a couple individuals chat about it. It's from Microsoft. uh it's a lot of their teams and it's this idea for being able to have your skills your markdown files essentially be updated and upgraded to a very specific set based on machine learning. So in the same way we train an LLM, we can train to make your MD files your skills better. And it's a really long paper. They use a lot of really cool stuff and methodologies. They're doing kind of a mixture of neural network and using LLMs as a judge in a kind of validation set. Long story short to kind of get past so you guys all can kind of go into it. The idea is all right actually let me use paint. This will be much easier um to describe here.

Um, and Microsoft said, "Hey, you know what would be really cool? What if you have an MD file and it's got a bunch of text in it? What if we convert all of those words into a vector space?" Right? So, there's a bunch of numbers and that's how we make language models. Now, we just take a word and we assign it a number and we say, "Cool." So, that is what this mo this markdown file is, right? So, like this markdown file. Oops. No, not this one. I'll do this one's a good one.

While you're pausing, I managed to find the browser setting, which was annoying.

Yes.

Um, hi, I'm Mera. Um, I'm in New Zealand, so hello from Sunday morning because I'm usually in the future compared to most people. Um, I uh I'm about 5 months into a new role. Um, FMCG company. We're probably one of the biggest food 100% privately owned food companies in New Zealand. Uh what got me excited about the job is the owner who is not the CEO, but he has a data background and a BA background from back in the day. Um, so he's basically created this role and he's put data at the big table reporting into the CEO. Um, so all data, all tech. um and massive growth uh grown by about six times in the last six years in terms of topline revenue. Um, and now at the scale where we have joint business plans with all of the major supermarket chains in New Zealand. So uh yeah, very very cool. Very exciting time.

Wow. Thank you Mera. That's amazing. I love New Zealand. I've been wanting to to kind of wander out there. Actually almost uh did my masters there instead of Scotland. um uh just because I knew one of the only ways to to spend more time in in New Zealand would probably be through academics for me. Um, but it is that's really interesting and that's a crazy growth process. The food industry as well is is a really hard place to be in right now because you have to deal with compliance, you have to deal with opinion, you have to deal with people, you have to build with logistics, then the logistics are getting upset by politics. Uh and then you have to deal with AI. Is AI the right way to be man? So it's a hard place to be in there. So yeah, thank you Mera. I'm glad to have your expertise here and your opinion.

What's fun is the logistics side. Um, tell you what, what wasn't fun was, you know, literally hundreds of thousands of dollars of FAF per week with um with some of the things happening in the world just like turning up and each week it was like it was like rolling dice. So, what's going to hit our books this week because they were literally adjusting their percentages on a

daily basis. Um, so that was that was interesting. Um, seems to have plateaued at the moment at about double what we had budgeted um based on last year. So that's again interesting place to be. Um but we um we bring or make a lot of Asian food into the country. So what what's done that growth path is more and more of our products are now ranged at supermarket rather than at the Asian supermarkets.

>> Interesting. Ah, I'd love to I we don't have time for it now, but I'd love to look at your data and kind of what you all are looking at because um I think there's a huge market for for Asian foods in in the the South of America or South South not South America, South US um right now because um a lot of veterans are, you know, spent a lot of time in Asia and things like that. we have a kind of huge veteran population paired with kind of like this desire of of Korea and and Japan. And I think the US um could like if if you got a Japanese 7-Eleven in Florida right now, you would make so much money. Um I don't know if anyone's been to Japan, but the 7-Elevens there are top tier, top-notch.

So um we we are about um if the the thing that is nice in these economic times about 50% of the instant noodles in New Zealand we they're our products that are sold. So um when times are tight people go to ramen and instant noodles and that makes us money. So that's quite a nice place to be when things go wrong.

>> That's Wow. That's Yeah. No, that is hard. But wow. Cool. Well, thank you Mera. I'm really excited to have you here and I hope uh hope to see you next week as well at the next one. Maybe you can bring some questions and I apologize that there wasn't a questionnaire for this one um with London Tech Week and everything else. Uh I just did not I knew I wouldn't have time to really sit down with them. I'd rather just do it live in the in the call. But um this coming coming high tea I'll definitely have the questionnaire out.

Um, anyway, so basically they created this process for basically automatically upgrading or testing scale skills, right? And so let's say the goal of a skill is to route the AI somewhere or the goal of a skill is to create a skill. Basically, you can have it go through and have an AI use this skill hundreds of times and every time judge the output, right? Did it do it the right way? Did it create a good skill? What didn't it do? And it does this over and over again. And then will make edits to this your markdown file until you have a good one.

Now there is a version of this that already existed by our lovely man Andrew Kaparthy. He gave this one uh I think about three months ago which is called auto research and it's a much simpler one where basically the AI goes in says hey is this the right skill the right process? No, let's fix it and it keeps doing it and redoing it until finally the agent or the skill is actually really solid.

Um, these people at Microsoft took it to a whole other level and actually brought in machine learning algorithms to keep track of every single token and word and they actually vectorized the markdown as if you would as an AI and did that at huge scale.

Um, I'm telling you all of this because I'm working on creating a open source version that's really easy for everyone to use inside of ICM. So my goal is to create either a version or a hybrid between Kaparthse and this so that you could just throw it at your database or whatever you're doing and say, "Hey, um like case in point, let's like go into uh like you have a brand voice document. Maybe your brand voice needs to be better, right? It actually looks at your chat history and every single time you've said no, you're off. No, you want to do this. It's doing that on auto overnight and then you wake up in the morning and you end up having a condensed skill. And what's cool is they did this already and you can give those skills to any agent and it is increasing them by a disgusting amount in some cases.

So, um there's current processes that already do this, right? Like all of these are processes that you have to do. So like searching um through a spreadsheet or using spreadsheet, there's skills for that. And there's actually um these are all optimization techniques, text optimizations that already exist. Human skill is literally someone going in and re-editing the skill file. But what they found is in a lot of situations, the original baseline will go up by over 30 to 40% by using this system. So like it's using the scale, it tests and like reads through spreadsheets and it's scoring like 40%. you use skill opt on your skill or on your your markdown file your process and it it can get up to 20 30 40% increase in its ability which in the AI market usually requires fine-tuning the entire model like to get these type of numbers um like every single one of these 19% 18% 9% 57% um for the codeex hornet and the claw and that's the other thing on the claude and codeex harnesses it did the to get a jump from 27% capability to 85%. That's like two or three model generations.

Um, but all you're doing is upgrading your skill and context, which I think is just really crazy. Again, the reason I'm sharing this, if you all want to dive into this, let me actually drop this here. Or if you want your AI to dive into it, there's no good YouTube videos on it right now. So, I'm going to make one as well. But I think there's some stuff that they're again overengineering a little bit.

Um, and I think there's a hybrid that could be done. I'm going to try to make something. It'll be open source and I'll drop it for all of you. And the goal is to be able to come in and say, "Okay, let's go ahead and aim it at these couple markdown files or let me aim it at my ICM process for animation." And I'll start small or let me even aim it at my cloud MD. Is my Claude MD routing to the folders as good as it should be? And it basically gets rid of like even individual words that are adding too much noise to the model. and it does it through a series of processes.

Um, and so I think this is super sick paper. Uh, it just came out this May. Um, and very interesting. And so I'll be diving into that. If you all want to dive into it again, by all means. Uh, they also have an open source GitHub for it.

Um, but I'll be I'll I just wanted to let you know I'm doing the work so you don't have to. Um, and I'll I'll put that all out for you uh here shortly. And I do think this is going to be a huge thing or people you're going to see companies and people talking about this soon.

Um, I will say Anthropic already kind of does a version of this. So, if you actually go to where Claude is installed and you go to the um, skill creator, they actually have um, scripts that force it to revalidate the markdown file that's being created. Um, and their skill creator is kind of doing a mini, hey, is this a good skill or is, but it's mostly doing it with um, this, right? So, it's mostly, hey, is the description here good? is what these the description about how a skill should be built.

Um, but it's not doing it to like a high level. And right now a lot of the other automated processes, what ends up happening is after like a million tokens, it starts really having bad context rot. Uh, which is what the paper was trying to solve by using like traditional code, which again just kind of supports my theory. Not saying it, just saying a little bit. They're using traditional code to solve AI problems. So, you know, just putting it out there. It's it's you still need the traditional stuff. Just because AI is doing the coding doesn't mean um the fundamentals go away.

But yeah, I just wanted to share on that. I thought it would be cool. I I I saw I think David uh and Roy or someone someone else posted about it in um in uh the community and I just wanted to chat about it like hey this is what I get out of it. It is pretty interesting.

Um, but uh, long story short, it reads everything you did during a process. It edits your markdown files, makes them shorter, and that was the other cool thing about the paper. Almost all of the markdown files ended up less than 500 to 800 tokens. So, it found that the most efficient markdown files were really small and it was better to break them apart, which all of you know why? Because construction and separating thought is what allows the model to work better. So, now I have mathematical evidence of why my ICM works well.

Um, but, uh, I told you about the deployment layer for the ICM and I'm going to make a video and, um, hopefully get that all to you. We did some questions and show and tell. Um, so that was kind of built in there.

Um, but other than that, I think, let's see, we're coming on an hour and a half here, so we're 30 minutes over our usual hour, but, uh, you know, I always love talking to you all and I could sit for a while.

Um I guess then for the biggest things coming up uh I will try to get all of you access to the kind of employment layer freelance um uh app that we built. Uh and then I will try to get you all access to the ICM this week. Uh that that's my goal is to launch it Wednesdayish hopefully.

Um, right now I've been spending like a disgusting amount of time on security um because that's really all I care about right now. Um and luckily we're using Microsoft Azure as a main deployment layer so um there's there's a lot of good security there just naturally.

Um, and we're trying to create kind of more enterprise solution grade technology but for everyday people as well because the idea is everyday people will be able to be inside of this. We can rely on Microsoft Azure for a lot of compliance and then you would be able to deploy these kind of um folders and that kind of creates the you you as a freelancer or as a small company building these these things. It's really hard to deploy uh at enterprise level but this hopefully helps out a lot.

Um, allegedly that's my goal. Uh, we'll find out with testing and it's probably going to be terrible the first month, so I I'll tell you all that. Uh, but that's how software goes.

Um, so we'll roll with it. Other than that, this has been an amazing day. I hope everyone here got some awesome work out of this. I appreciate everyone sitting for an hour and a half on a Saturday. Uh, I mean, it just shows you're committed and I really appreciate that.

Um, I hope that you all kind of see a better future. You're coming out of this more clear every time we go to one of these. And more importantly, I hope you all find people that you want to work with. Again, my whole goal is to teach you all and and be here and give you my time and just give you updates on all the crazy stuff that I'm seeing. But I also really really really want this to be a space where you're all like, "Cool, I know if I go to talk to Meera or I sit down with Curtis, we don't have to spend an hour making sure we're we're we're caught up to this stuff where I don't have to go through this filter of do you really know what AI is?" No, it's like, okay, they're in this group. We can get right to them. Hey, this is what I'm trying to build. you already are caught up to it and that just it just cuts out so much BS that you have to deal with in the AI world now. So I I hope that's what all you do.

Um, knowing that I am not going to end the call. Um, I am going to stop the recording.