For almost two years now, chatting with my AI assistants has become part of my daily routine. It’s a back-and-forth dance: I ask a question, get an answer, refine, dig deeper, redirect, and repeat. They’re always patient and eager to help. Over time, I’ve come to really enjoy this dynamic. It feels like teamwork. Even though I’m technically talking to language models, there’s a sense of collaboration that makes the process surprisingly engaging.
Retrieval-Augmented Generation (RAG) is quickly becoming the go-to technique for making Large Language Models (LLMs) more reliable and less prone to "hallucinations". By integrating a retrieval component that pulls in specific, trusted data, RAG systems can deliver accurate, source-backed answers for everything from customer support to fraud detection.
Yesterday I came along Just in a project and figured out a nice task runner like Makefile. Reading the README I noticed it is written in Rust. That happens all the time for a few months: Rust appears everywhere in my developer eco system. Project manager uv is ultra fast, pydantic v2 core rewritten in rust for performance, my new editor Zed is super sleek and fast, and that is just what I am directly aware of, what about Rust? I need to hello world into it.
You know those website builders made for small business owners? Pick a theme. Drop in blocks. Accordion. Image next to text. Call to action. Maybe a testimonial slider. Everything configurable without touching code. Sounds good in theory.
I've been deep in the world of AI coding assistants lately, exploring what it means to vibe code that is, coding with flow, creativity, and an AI pair at your side. What started out as curiosity became a full-blown journey across tools, editors, and mindsets.