Apr 12 · 8 min read · I hear this over and over again: "Let's max our use of AI agents." It sounds smart. Agentic coding is getting better every day; every org is feeling pressure to use it more. But optimization is not al
Join discussion
Apr 11 · 9 min read · I Shipped a SaaS MVP in 14 Days Using AI Coding Agents TL;DR: As a solo developer, I built and launched a SaaS MVP in two weeks using AI coding agents (Claude Code, Cursor, and GitHub Copilot). Here's the day-by-day breakdown of what I built, what th...
Join discussion
Apr 10 · 31 min read · TLDR: An AI coding agent is an LLM stapled to a tool registry, wrapped in an orchestration loop that painstakingly rebuilds state on every single API call — because the model itself is completely stateless. Understanding the context window, the ReAct...
Join discussion
Apr 3 · 4 min read · I use multiple Claude Code accounts. One is my office account with the Pro plan. Another is a shared account I use with my colleagues on the Max plan. At first, I assumed this would be simple. Log out
TMarcus commented
Mar 23 · 12 min read · I will be honest with you. For a long time, I wanted nothing to do with AI coding tools. Not because I thought they were useless. I could see other developers using them and getting things done faster
Join discussion
Mar 21 · 5 min read · The Hacker News front page this week turned into a benchmark war. Claude Code uses 1GB of RAM. Codex runs on Rust at 80MB. OpenCode hit 921 points. Developers argued about whether TypeScript is disqualifying for a coding agent, whether Rust is overki...
Join discussionMar 3 · 8 min read · AI CLI Coding Agents Compared: Claude Code, Aider, and Codex CLI IDE-based AI assistants get all the press, but the real power move in AI-assisted development is happening in the terminal. CLI coding agents don't just autocomplete lines -- they read ...
Join discussionFeb 8 · 2 min read · Problema Lo brutal de GPT-5.3 Codex no es que escriba mejor codigo. Es que convierte el ordenador en un entorno de ejecucion para agentes. Cuando un agente puede investigar, usar herramientas y ejecutar tareas largas, el cuello de botella deja de ser...
Join discussion
Oct 16, 2025 · 6 min read · Software development has always been about solving problems faster and more efficiently. In the early days, programmers spent countless hours searching through forums like Stack Overflow, copy-pasting snippets, and manually debugging errors. Then cam...
Join discussion
