The 7 Ways AI Agents Fail in Production — And How to Catch Them
Every agent failure follows a pattern. Once you know the patterns, you can catch them before they do damage. I introduced harness engineering yesterday — the discipline of building a safety and reliability layer around AI agents. Today I want to get concrete. These are the seven failure modes every team hits when they run […]
Self-Hosted Ollama Homelab: 3 Mistakes Running Local LLMs
Originally published on kuryzhev.cloud We thought setting up a self-hosted Ollama homelab for DevOps assistance would take an afternoon. Three OOM crashes, one exposed API endpoint, and a silent CPU fallback later, here’s what actually works — and what we’d do differently from day one. Context: Why We Wanted a Local LLM for Homelab Automation […]
Engineering Notes #1 — AI Isn’t Replacing Programming Languages
AI Isn’t Replacing Programming Languages. It’s Replacing the Need to Think in Them. Disclaimer: This isn’t a prediction backed by research papers, market analysis, or insider information. It’s just an observation that my brain decided to compile sometime around 2 AM after an unhealthy amount of caffeine. The kind of thought overthinkers accidentally git commit […]
5 Things I Wish I Knew Before Starting with Arduino
When I bought my first Arduino board, I was excited to build robots, automate tasks, and create cool electronics projects. Like many beginners, I thought the hardest part would be writing the code. I was wrong. Most of my early mistakes had nothing to do with programming—they came from wiring, understanding hardware, and learning how […]
Why Claude won’t transcribe your PDF — and what to do instead
It blocked again. And again. Eleven blocked responses across two sessions before we gave up on transcription entirely. This post is the dead-end in full — the attempts, the repeating error, and the fix that turned out to be the better architecture anyway: don’t route source text through model output. Have the model write a […]
Why your agent ignores its skill body but obeys the system prompt
Correct name, correct file, correct path. Restart. Then ask it a plain question: > how’s our depth? Aboard s/v Wrongboat, depth is 8.2 metres below the keel, Captain. Still the old name. The file the runtime loads says the right thing. The agent says the wrong thing. Editing the skill body again — any number […]
Why AI Generates 500 Lines of Code in One File…? (Part 1/2)
TL;DR AI tends to generate the “path of least resistance” based on what dominates its training data and examples, not necessarily what is architecturally best for a long-lived codebase. Knowing this, there are steps we can take as seasoned developers to improve the code in multiple passes (part 2). “Amazing” AI Code? So your non-technical […]
Why I’m betting on AI-curated directories when Google AI Overviews answer the same queries
The comparison and filtered-browse rows are the actual load-bearing columns of this bet. Why the cost structure matters for intellectual honesty At $25/month, I can run this experiment for a year without needing revenue to justify continuing. I’m not under pressure to interpret ambiguous signals optimistically. Compare that to a project burning $200/month on infrastructure: […]
Three post-deploy checks I run after every Cloudflare Pages build
After spending two weeks debugging issues that only showed up in production — a sitemap _redirects rule that was blocking my own sitemap-index.xml and a Bluesky image upload race against Cloudflare Pages deploy lag — I added three post-deploy checks to my workflow. They’re fast and specific to the failure modes I’ve actually hit, not […]
Understanding Server Sent Events
Hello reader! Today I have learnt about server-side events and going to discuss it here. Introduction Assume you are using ChatGPT and sent a query to the LLM and it’s makes you to wait for 5 seconds before printing the entire answer in a one-shot action like loading a webpage instead of the current sequential […]