Blog
Tech news and programming tutorials.
Codex vs Claude Code: a fair comparison for agentic coding
SWE-bench says they are basically tied. The real differences are cost, the autonomy model, and where each one shines. A field report after using both in production.
Read article →Shipping real software with AI agents: the harness beats the model
After a year of shipping with agents, the lesson is boring and important. The harness around the model, the tools, the context, the verification loop, matters more than which model you picked.
Read article →Open-weight LLMs in 2026: the gap to the frontier is measured in months
Open models had a strong year, and the distance to the closed frontier shrank to a few months, until you look at the hard agentic benchmarks, where it opens back up.
Read article →Next.js 16: caching finally became opt-in
Next.js 16 effectively admitted the App Router caching was a mistake and made it explicit. Here is what actually changed, and why it is the most honest release in a while.
Read article →Flutter in 2026: Impeller everywhere, GenUI, and an honest look at Google
Impeller is now mandatory on Android, Wasm is nearly the default web target, and AI can emit Flutter widgets directly. Also: is Google still committed? An honest read.
Read article →