▶ Videos →

📰 Dev.to · Igor Kramar

3 articles · Updated every 3 hours · View all reads

All Articles 190,145 Blog Posts 171,860 Tech Tutorials 50,959 Research Papers 36,793 News 23,196 ⚡ AI Lessons

I wrapped Claude Code in a zsh function. Here's every decision I almost got wrong.

Dev.to · Igor Kramar 💻 AI-Assisted Coding ⚡ AI Lesson 4mo ago

I wrapped Claude Code in a zsh function. Here's every decision I almost got wrong.

Claude Code's --help lists 50+ flags. After two weeks of using it daily, I built a zsh wrapper called...

Mechanistic Interpretability is a 2026 Breakthrough Technology. Here's What That Means for the "LLMs Are Just Matrix Multiplication" Debate

Dev.to · Igor Kramar 🧠 Large Language Models ⚡ AI Lesson 4mo ago

Mechanistic Interpretability is a 2026 Breakthrough Technology. Here's What That Means for the "LLMs Are Just Matrix Multiplication" Debate

Today a friend of mine — let's leave him nameless — said the line I've been hearing since 2022: "It's...

I built a Claude Code plugin that argues with me about architecture. Then it caught me lying to it.

Dev.to · Igor Kramar 💻 AI-Assisted Coding ⚡ AI Lesson 4mo ago

I built a Claude Code plugin that argues with me about architecture. Then it caught me lying to it.

TL;DR. I built a Claude Code plugin (MIT, github.com/IgorKramar/archforge-marketplace) that turns...