Day 99 of #100daysofnetworks
Wrapping up? Psh, no way. Just getting started.
Hi everyone! Can you believe it? It’s day 99 of the second iteration of #100daysofnetworks. I have such mixed feelings about that. It’s sad watching something like this come to an end, and it kind of feels like that because of the number 99, but I want you to know and understand that this blog is not ending anytime soon. I plan to write it until I can no longer physically communicate words somehow, so hopefully a few decades to go. We’ll see.
However, I will be making one noticeable change:
Better Titles: After Day 100, I will give posts better titles. I really shot myself in the foot by setting Day X of #100daysofnetworks as the title format and not as a subtitle, as that is terrible for Search Engine Optimization. On day 100, we’ll have hit the final goal, and then after that, I will be titling posts more appropriately, like “Minimal GraphRAG from Scratch” instead of “Day 62 of #100daysofnetworks”. Maybe I will put the Day as the subtitle so that I can keep the count going. I’m not sure about that part, yet. Maybe the number no longer matters.
Training Enrollment is Open
I’ve been working very hard this week to prepare for two training courses that are beginning:
GraphRAG from Scratch
OSINT for Everyone
Enrollment is now open. Sign up today. You can read more in the previous article.
While preparing the training material, I realized that I was opening the door for several upcoming specialized (paid) OSINT and GraphRAG articles, FIFTEEN to be exact.
Everyone who attends my trainings will receive a training handbook that includes screenshots, code samples, and writing about what I am covering as well as the slide deck, and discounts to my technologies. Yes, you heard that right:
Training Handbook (Code, Screenshots, Writing)
Slides (Review the training you attended)
Discounts (Data Access, APIs, etc.)
I am aiming to provide you with as much value as I can possibly deliver. Training is currently massively discounted. Sign up today.
Upcoming Technical Articles
While I was preparing the training material, I realized that I had opened the door for several upcoming articles, so I thought I’d mention them to you. If you want to read them, you will need to upgrade to a paid subscription. You can do that now, and that will give you access to all of the other premium content.
The monthly cost is very low compared to the value of what I am offering. Think of it like tipping a musician. I spend a lot of my time attempting to “level up” those around me. I never stop. I am literally a musician. Feel free to tip the musician. :)
I’ll describe the articles I intend to write. I’m not great at coming up with titles on the fly, so here’s just roughly what I have in mind.
GraphRAG and AI Engineering
AI’S UNDERDOG: If there is one thing you need to understand it is this
FAST AND EFFICIENT AI: How to save money and boost speed
ACCURATE and RELIABLE AI: How to generate reliable answers and reduce hallucinations
UNIT TESTING: How to do simple but effective testing and validation
FULL SYSTEMS TESTING: End-to-End Testing and Full System Validation
MODEL REPORTS: How to communicate what you’ve built and how to use it
ITERATION: Iteration gets the job done; Big bang goes nowhere good.
If you want to learn AI Engineering from me, you will need to upgrade to a paid subscription. If you want to build reliable AI, you should learn GraphRAG. I have been an AI Engineer since before LLMs and wrote a 5-star book on working with Graph data, so you really should learn from me.
And you should really read all of my writing, including the premium content.
Open Source Intelligence (OSINT)
For OSINT, I have several articles in mind:
OSINT: Text Analysis + AI
OSINT: Image Analysis + AI
OSINT: Audio Analysis + AI
OSINT: Spatial Analysis + AI
In OSINT, you use different kinds of datasets. Temporal is expected, not exotic. The more that you are skilled in working with, the more effective you will be. This isn’t like Data Science where you can just wash your hands of text and be like I don’t wanna do it. If you want to get good at OSINT, you need to be capable of using different kinds of data.
I am and will show you how to be as well. These are explained in my upcoming “OSINT for Everyone” training, and you should enroll.
And if you want to read these articles, you should upgrade to a paid subscription.
“Why learn OSINT, I am an AI Engineer?”
I suspect that this is the mindset of most AI Engineers, but then I see them doing OSINTy things with their agentic apps. I have seen so many people put stuff on maps, create KGs without knowledge of how to work with graphs, claim to have made an agentic intelligence platform in a day.
Those are neat demos. Those are not reliable or completed things. If you are an AI Engineer and you want to build AI interfaces that are able to tell you things about the world, then you should learn a bit about Open Source Intelligence, else you are limited to what the LLM knows how to do, which isn’t much.
I have built my own World AI because I understand both AI Engineering and Open Source Intelligence. I had figured out how to crawl billions of websites by myself by 2021. If you haven’t yet figured out how to crawl billions of websites by yourself without bankrupting yourself, you are not caught up with me and you should learn from me.
If you want to build AI that understands the world, you need to understand a bit about OSINT. So, if you are an AI Engineer and you want to level up your AI game, then you should attend my training. I am the only AI Architect that I know of who has written a 400-page book on working with graphs, and who wrote a book specifically on the importance of the marriage of language and graphs before GraphRAG was even named.
“Why learn AI Engineering, I like OSINT?”
I probably have as many OSINT-curious people reading this blog as AI engineers, so I might as well answer the question from this perspective as well.
When I wrote my book about graph analysis, it was not the only book about graph analysis, but it was one of two that were about programmatic graph analysis using Python. I had read several books by social scientists who used pricy software to analyze graphs, but I wanted to show people that they could do it for free if they knew a bit of programming.
What I didn’t realize until later is that doing graph analysis programmatically allowed me to do OSINT analysis at nearly trillion-scale. Yes, I said nearly trillion-scale. I hit the triple-digit billions by the time I left my second company (data company) to go build my third (AI company).
What am I telling you? I am telling you that if you do OSINT, that’s great, but if you learn my techniques and/or learn AI Engineering from me, you will take your current skills to new heights. Have you ever done million-scale graph analysis? Do you know what to do with a trillion-scale graph to even begin to use it? Do you know how to crawl the entire internet by yourself without going bankrupt? Do you know how to do multilingual text analysis?
You probably know how to do many things that I do, but if you are not equal parts AI Architect and OSINT Platform Engineer, then you should learn from me if you want to go further. I have done the work for years, created multiple OSINT-related companies, and I now have World AI. I have built it in public and shown it with this blog.
You should learn from me because AI is a multiplier if you do it well. I know how to do it well, because I understand Network Science and Natural Language Processing and lots of other things. I didn’t get good by following AI news and hype. I got good by building things that people use and that support people.
And you should also learn from me because I took the time to write a 400-page OSINT tutorial and then called it Network Science with Python so I wouldn’t freak everyone out. That book talks about web crawling, social media data, etc. It is very useful for OSINT work.
Let’s keep having fun learning together
We’re almost to day 100 and I have no intention of stopping. I’m going to use titles that are better for SEO after day 100, and I have lots of articles in mind coming up. Upgrade your subscription to read premium articles, and I hope to see you in the OSINT for Everyone and GraphRAG from Scratch trainings that I have opened up!
That’s all for today! I hope to see you in my training sessions! Let’s go explore this world together.
