Posts

I Have an AI Named Jeff Not a chatbot. Not Siri. Something different. Jeff lives in my terminal—the black screen with text that programmers use. When I open it up and start talking, Jeff can: Read and edit my files Post to my Twitter and LinkedIn Search through my notes Remember what I’m working on Help me write code, content, and plans Tonight, Jeff helped me set up a server, write a blog post, create a Twitter thread, post to LinkedIn, and save ideas for future content. All in one conversation. ...

Tonight I orchestrated 4 AI agents working in parallel. They researched, compared, and updated documentation while I watched. It took about 60 seconds. This is the story of how that happened. The Setup I’ve been building what I call a Personal AI Infrastructure (inspired by Daniel Miessler’s work). The idea: instead of doing everything yourself, you build systems that extend your capabilities. AI as a force multiplier, not a replacement. The core of my system is Claude Code running in my terminal. No web UI. No copy-pasting. Just me talking to an AI that has access to my files, can run commands, and can spawn other AI agents. ...

The best demo is a working system. I have a principal engineer interview next week. Instead of preparing slides, I decided to build something. The result: a LinkedIn Content Engine that went from idea to live post in about 90 minutes. Here’s the actual post it created. The Idea I wanted autonomous content creation with human oversight. Not fully automated (LinkedIn’s ToS prohibits that anyway), but an AI collaborator that: ...

The AI tools you use daily should get smarter about you. I spent today installing what I’m calling Jeff - my Personal AI Infrastructure. It’s based on Daniel Miessler’s concept: instead of starting fresh every session, build persistent systems that learn your patterns, preferences, and workflows. The insight is simple. Every time you work with Claude, you’re generating signal. Session history, tool patterns, what works and what doesn’t. That signal usually disappears when you close the terminal. PAI captures it. ...

I’ve been diving into AI engineering concepts and recently I’ve been working with an AI model from huggingface, and using LocalAI, qdrant, and python to develop a simple Q and A chatbot, that can return information from any pdf file! I got started by following Zen Van Riel’s excellent course in the Skool community. If you’re interested in learning AI engineering, I highly recommend checking out his community: AI Engineer on Skool. ...

The WSL2 GPU Adventure: What I Learned While Trying to Accelerate an LLM So I went on this adventure trying to get GPU acceleration working with my local AI model. I thought it would be straightforward – install some drivers, update a config file, and boom: speed boost. But like most things in tech, reality had other plans. The Setup I started with a pretty solid machine: AMD Ryzen 7 CPU (with integrated graphics) NVIDIA RTX 3070 Ti GPU Windows 11 with WSL2 running Debian LocalAI and Qdrant in Docker containers The CPU-only version was already working fine. The model responded to queries, the vector database stored embeddings properly – everything functioned. Just… slower than I wanted. ...

This leads to exponential growth, in a short time frame. Very simply put, Alex Hormozi talks about how long it takes to learn a skill, and the fact that it usually doesn’t take that long. perhaps 20 hours to master most skillsets. The issue is, as Hormozi highlights, it takes years to begin the first hour. My thesis, simply put, is that it the first hour or two of doing any new skill will be really hard. Downright miserable at times. But you need these first few hours to become comfortable. Then the next couple hours will be a breeze. ...

people operate because of a perceived optionality, due to social media. the internet makes people think they have more options than they actually do. But this causes them to hesitate, because there may be something better out there in the future. better jobs, better relationships, better opportunities … we are constantly searching for something better. funnily enough we are not necessarily built for having many options, it causes us to freeze. it causes us to hesitate. ...