<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>Vibe-Coding on Scholion</title><link>https://scholion.thluiz.com/tags/vibe-coding/</link><description>Recent content in Vibe-Coding on Scholion</description><generator>Hugo -- gohugo.io</generator><language>pt-BR</language><copyright>© 2026</copyright><lastBuildDate>Wed, 23 Sep 2026 14:37:21 +0100</lastBuildDate><atom:link href="https://scholion.thluiz.com/tags/vibe-coding/index.xml" rel="self" type="application/rss+xml"/><item><title>After two years of vibecoding, I'm back to writing by hand</title><link>https://scholion.thluiz.com/notes/after-two-years-of-vibecoding-back-to-writing-by-hand/</link><pubDate>Wed, 23 Sep 2026 14:35:35 +0100</pubDate><guid>https://scholion.thluiz.com/notes/after-two-years-of-vibecoding-back-to-writing-by-hand/</guid><description>Mo Bitar traces two years of AI coding through excitement, spec docs, and what he calls slop, and explains why he went back to writing most of his code by hand.</description></item><item><title>Code is cheap. Show me the talk.</title><link>https://scholion.thluiz.com/notes/code-is-cheap-show-me-the-talk/</link><pubDate>Wed, 23 Sep 2026 13:52:07 +0100</pubDate><guid>https://scholion.thluiz.com/notes/code-is-cheap-show-me-the-talk/</guid><description>Kailash Nadh argues LLMs made code abundant and cheap, so accountability, provenance, and the ability to think and articulate now matter more than the code itself.</description></item></channel></rss>