Honestly, I gotta say, when I first started digging into multimodal AI this year, I was expecting everything to be either crazy expensive or kinda mediocre. You know how it Continue reading How I Tested Every Major Multimodal AI Model in 2026 — And Which One Actually Saved My Wallet
As developers, we’re constantly searching for the right tools to bring our ideas to life efficiently. When I decided to build Netfix, a service marketplace connecting companies with customers, I Continue reading Building a Service Marketplace with Django: Lessons from Netfix
Your MCP server works on your laptop. The tool calls return the right shapes, the client connects cleanly, the session behaves. Then you deploy it and a client reconnects after Continue reading How to test MCP servers in TypeScript before they break in production
I worked with FFmpeg on several large projects, which means I spent more time than is healthy answering “which FFmpeg do I install?” for myself and for other users. Installing Continue reading I built ffmpeg.download because installing FFmpeg shouldn’t take six decisions
How to move from isolated hospital systems to event‑driven, FHIR‑based architectures in a context with poor connectivity and legacy vendors. In many private clinics in Venezuela, “digital transformation” has meant Continue reading Designing Healthcare Interoperability with HL7 FHIR: Lessons from Venezuela
Running AI models locally for code generation used to mean accepting mediocre output. That changed. In 2026, you have real choices — but picking the wrong model for your use Continue reading Mistral Large vs LLaMA 4 vs Phi-4: Best Open-Source LLM for Code Generation in 2026
I Roasted My Friend’s X (Twitter) with This Open-Source Tool and Got Blocked… Recently, that Wordware Twitter personality analysis tool blew up. Everyone was lining up to try it, and Continue reading I Roasted My Friend’s X (Twitter) with This Open-Source Tool and Got Blocked…
This is a submission for the Hermes Agent Challenge. “The harder I committed to surgical precision, the more emotionally resonant the work became. Severity concentrates feeling.” the agent, on the Continue reading The Becoming: I gave an AI a blank sketchbook and it invented its own art style
This is a submission for the Hermes Agent Challenge. (Demo video below.) What I built Fork takes a hard decision and spins up a separate Hermes agent for each option. Continue reading Fork: I made an AI live out both sides of a hard decision, in parallel
Real data from 240 PRs, 72 merges, and 90 rejections — plus the behavioral psychology that explains why some contributions succeed while others die in review purgatory. TL;DR: After submitting Continue reading The Psychology of Open Source: Why Your PR Gets Ignored (And the Science of Getting Merged After 240 Attempts)
When Writing Software, the Typing Was Never the Job. Neither Is the Prompting. With AI coding, the coding steps got easier. The thinking steps got harder. You asked for a Continue reading When Writing Software, the Typing Was Never the Job. Neither Is the Prompting.
I built a custom analytics system into my portfolio backend — a Django REST API that records page visits — and wired the React frontend to call it whenever someone Continue reading Why My Analytics Was Logging Every Page Visit Twice (And How I Fixed It)
When deploying a Flutter web application, you might run into issues, such as the login functionality not working. This can often be perplexing, especially when everything seems to work perfectly Continue reading Why is the Login Failing in My Flutter Web App Release?
Getting Conventional Commits format right from memory is surprisingly annoying. Is it feat or feature? Space after the colon? Breaking change needs ! or a footer? Commitlint solves this but Continue reading I Built a Free Browser Tool to Validate Git Commit Messages — No CLI Required
👋 This is the second chapter of a series where I document what I’m learning about Model Context Protocol Architecture and Tool implementations In Chapter 1, I built a simple Continue reading Building a GitHub Stats MCP Server with Security Metrics
