Magnus Hultberg - Updates

I ported my Cloudflare opinionated AI coding template from Claude Code to Mistral Vibe CLI.

Your file system is chaos, and no AI model is going to tidy years of it into a single source of truth.

Product Managers are posting their GitHub commit counts with real pride lately.

I spent a weekend building a thousand-year-old Viking game in the browser, and ended up using a graphics trick from 1993 to make it look good.

Two-thirds of the field notes in my Victorian creature generator started with "Upon".

The first time someone runs Claude Code in a project folder, the AI doesn't ask what they want to build.

🔧 Most of us assemble a stack, get it working, and never question it again.

I built an AI reading triage tool to get on top of my Readwise Reader queue.

🧠 I spent a weekend building a memory system for Claude Code.

There's a maker 🛠️ revolution happening around AI tools that reminds me of the early web.

👍 After a year of AI-assisted building, the interesting question isn't if the model can write the code.

Working with Claude Code doesn't feel like programming.

After more than a year of experimenting with AI assisted coding 💪 the interesting part for me is no longer “can the model do this?”

Seven or eight real apps built with Claude Code, zero “actual” coding from me.

Just grokked: CLAUDE.md files are sent with EVERY request.

What if the best way to get great code from AI is to make it politely argue with itself?

Given the right setup and guardrails coding agents become more and more productive, as shown in a recent article from OpenAI.

China's betting on AI while the West argues culture wars.

The "AI Swiss Army knife" hype isn't empowering young talent.