dev.to
Latest items from this RSS source.
Training a Neural Network in 16-bit Fixed Point on a 1982 BBC Micro
The source code for this post can be found on GitHub. In my previous post on neural networks we went through the basic concepts and simple mathematics involved in training and running a neural network. It's so simple that it gave me an idea: could I run this …
Make your server-rendered website feel like an SPA — with 5KB of JavaScript
Make your server-rendered website feel like an SPA — with 5KB of JavaScript You've built a server-rendered website. PHP, Python, Ruby, Go — doesn't matter. It works. It's fast. It's SEO-friendly. But every link click triggers a full page reload. The browser f…
DumbQuestion.ai - Self-Awareness, Prompt Injection, Search Intent... and darkness
Continued from Part 2 (and Part 1) ... Building DumbQuestion.ai wasn't just about choosing the right LLM and calibrating personas. Once those were working, I hit a series of fun technical problems that reminded me why I actually enjoy software architecture. T…
Gemini 2.5 Flash vs Claude 3.7 Sonnet: 4 Production Constraints That Made the Decision for Me
An evaluation of the Gemini 2.5 flash and Claude 3.7 Sonnet model for an agentic engine. I had a simple rule when choosing an LLM for Ozigi: don't pick based on benchmark leaderboards. After my v2 launch, in recieving feedback, a user suggested I use the Clau…
Building a Rails Engine #9 -- Building the UI with Phlex & Tailwind
Building the UI with Phlex & Tailwind How to build a full component library for a Rails engine using Phlex, scope all CSS with a dp- prefix so styles never leak into the host app, and generate preview tables dynamically from the Target DSL. Context This i…
How I Built a Military-Grade GPS App with React Native — Zero Cloud, Zero Tracking, $3.99
I'm a paratrooper in an Airborne Division. I've used the DAGR and ATAK on many field problems. The military's standard GPS navigator costs $2,500. I rebuilt its core functionality as an open-source phone app. Here's the technical deep dive into MGRS math, the…
I Built a Markdown Linter in Go — Here's How It Stacks Up Against markdownlint and remark-lint
Documentation breaks quietly. Trust erodes loudly. If you've worked on an engineering team with shared documentation, you've probably seen this: An H4 heading appearing directly under an H2 with no H3 in between A [see details](#overview) link silently 404ing…
Building a Production-Ready Agentic AI System with LangGraph and MCP
As AI engineers, we often start by giving a massive LLM (like GPT-4) a giant prompt and a long list of Python functions (tools) it can call. This monolithic approach works for simple scripts, but it quickly becomes expensive, slow, and a security risk when th…
Building Static Social Media Connect Pages & Fixing OOP Errors in My Automation Project
Today was one of those “small work but big progress” days in my Social Media Post Automation System project. Instead of writing more backend logic, I focused on two important things: Creating static HTML pages for social media connections Fixing OOP structure…
FOSDEM 2026
Feedback from FOSDEM in Brussels (Belgium) in 2026: https://fosdem.org/2026/ and https://fosdem.org/2026/about/. Vibe Like last year, I focused more on the social aspect and discussions than trying to cram as many presentations as possible into two days. Ther…
How I Test an AI Support Agent: A Practical Testing Pyramid
A walkthrough of the six testing layers I use to catch regressions, policy drift, hallucinations, and adversarial exploits in a B2B SaaS support agent - with an open-source repo you can fork and try yourself. I built an AI support agent. It looks up invoices,…
Google's A2A Protocol: The HTTP for AI Agents Nobody Asked For, But Everyone Needs
The Fragmentation Problem We have a problem. In 2026, we're drowning in AI agents. Every SaaS product has one. Your CRM has an agent. Your email has an agent. Your calendar, your IDE, your analytics dashboard—all agents, all siloed. They don't talk to each ot…