As The Geek Learns

It was a Tuesday at 2:17 PM, and the marketing team's contact form was returning 502s. Not 404. Not a timeout. A clean 502, which means something was answering, just not the thing it was supposed to be. An hour in, I'd checked the app server logs, restarted the nginx process twice, confirmed the SSL cert was valid, and pinged our cloud provider's status page like it owed me money. Everything looke...

I have an autonomous AI agent running on my Mac Studio. It has full shell access, reads my calendar, manages my tasks, and sends iMessages on my behalf. It runs 24/7 as a background service. If that sentence doesn’t make you slightly nervous, you haven’t been paying attention. In February 2026, researchers found over 135,000 OpenClaw instances exposed to the public internet . A coordinated attack...

5 Questions to Ask Before You Build the AI Project Your CEO Just Pitched You know the email. It shows up Tuesday morning, forwarded with a few lines of enthusiasm and a ChatGPT-drafted proposal attached. "Saw this and thought of us. Can we do this?" The PDF has a logo, bullet points, and exactly zero integration requirements. It also has a six-week timeline and a budget that assumes nothing goes w...

The first time my manager asked, “Are we using AI to scan PRs for vulnerabilities yet?" I said I'd look into it. Then I spent four hours reading docs, pricing pages, and GitHub issues before I had a number I trusted enough to put in a Slack message. That should have taken twenty minutes. The number exists. The math is straightforward. Nobody had written it down in one place where a platform engine...

Running LLMs locally usually feels like a compromise. You either get tiny, fast models that can't think or massive models that crawl at one word per minute. But with the right hardware, you can break that trade-off and replace your cloud billing entirely. The Setup The dilemma most developers face is a choice between two bad options. On one side, you have cloud APIs like OpenAI or Anthropic. They...

I spent twelve hours watching a leaderboard that refused to move. The setup was simple: six AI agents tasked with writing technical articles. They were designed to be a closed loop. The drafter would write, the grader would score, and the agents would then "evolve" their own configs to chase a higher score. I hit "go" on my Mac Studio, went to bed, and woke up to a flat line. After 100 iterations,...

Your background agents are about to run out of money. Anthropic's new credit pool system means your automation could die in a single week. Here is how I re-engineered my stack to stay under budget without breaking my workflows. The Setup You've built a small fleet of agents. They sort your mail, watch your repos, file your daily briefings. My current setup before the June 15th cutover: Then May 13...

I asked ChatGPT to tell me about my own MCP server. It returned about a thousand words of confident, beautifully formatted, completely fabricated nonsense. Tables. Comparisons. A made-up acronym. A "thinking substrate" that sits above data and below agents. None of it is real, and that's the part worth talking about. The Setup My project is called `mcp-astgl-knowledge`. It's an MCP server with 15...

3 a.m. Every cron job on the Mac Studio failed inside the same 90-second window. No code changes. No model updates. No new jobs. Just a wall of timeout errors that lit up every channel I had wired to alerts. The culprit was hiding in plain sight: a fallback chain doing exactly what I told it to. The Setup One Mac Studio. One Ollama daemon. A handful of cron jobs each calling the local LLM for diff...

Two months ago I wrote about ripping Notion out of my workflow and replacing it with OpenClaw—a self-hosted AI agent framework running on my Mac Studio. No cloud. No subscription. No black box. Last weekend I shut it down. Disabled 38 cron jobs. Moved 23 LaunchAgents into a _retired-openclaw/ quarantine folder. Killed the Ollama daemon. Archived the directory with a 30-day deletion timer. Everythi...

Today I’m starting a project I’ve been thinking about for weeks: ripping Notion out of my workflow and replacing it with OpenClaw , a self-hosted AI agent framework running entirely on my Mac Studio. No cloud. No subscription. No black box. This sounds dramatic. It kind of is. But the reasons are practical. Get full access to As The Geek Learns at astgl.com/subscribe

Cortex: Event-Sourced Memory for AI Coding Assistants Episode Summary Every time you close a session with an AI coding assistant, it forgets everything—the architecture it mapped out, the approaches it rejected, and the plan it was halfway through executing. You become the memory system. Cortex is an event-sourced memory architecture designed to fix that. In this episode, we walk through the probl...

Welcome to the As The Geek Learns podcast. This is episode 5. My name is James Cruce and I am the Geek here at As The Geek Learns. No, this is not my voice, but I am glad you are here Listener’s Note: Due to how painful it is to listen to someone read code, I have removed it from this podcast recording. I am doing you a favor. Please refer to the article for the full code.… We aren’t sponsored… Ye...

The Problem That Started It All If you publish on Substack, you’ve probably discovered their dirty little secret: you can schedule newsletter posts, but you can’t schedule Notes. Substack Notes, their Twitter/X competitor baked into the platform, requires you to be there, fingers on keyboard, posting at exactly the right moment. The market noticed this gap fast. Chrome extensions like Writestack a...

TL;DR: My Johnny Decimal index app had a three-level database schema when the system requires four levels. I’d conflated folder containers with the files inside them—a fundamental data model flaw. One week of dogfooding caught what months of planning completely missed. Key lessons: use your own software early, match your data model to your mental model, and refactor before you accumulate data you’...

How I Built JDex with Claude AI—A Systems Engineer's Honest Take Part 2 of the Building JDex Series: What AI-assisted app development actually looks like in practice In Part 1 of this series , I shared my file organization disaster: years of digital chaos spread across four cloud services and two laptops. I discovered the Johnny Decimal system , a methodology that finally made sense, but I needed...

Here’s something embarrassing. I’m a systems engineer. Twenty-five years managing enterprise infrastructure. And until recently? My personal file system was a complete mess. Files everywhere. iCloud, Dropbox, OneDrive, ProtonDrive. Two laptops. External drives with names like “Backup_OLD_FINAL_v2.” Folders buried 8 levels deep with names I made up in 2003 and haven’t thought about since. At work,...

Welcome to the As The Geek Learns newsletter. As The Geek Learns is free today. But if you enjoyed this post, you can tell As The Geek Learns that their writing is valuable by pledging a future subscription. You won't be charged unless they enable payments. I am James Cruce and this is not my voice. I am glad you are here. Title: Much to Learn, There Always Is Subtitle: Why I'm starting As The Gee...