Tutorial

You install Codex CLI. You launch it with excitement and tell it to “Fix the broken tests in this repo,” and then the nightmare begins: Codex: I want to run pytest Allow? (y/n) You press y. Immediately, this pops up: Codex: I want to modify test_user.py Allow? (y/n) So, you press y. Again, and again, and again. Every file it wants to read, every command it wants to run, every line it wants to modify. Confirm, confirm, confirm. It’s like working with an intern that asks permission for everything. ...

Two weeks ago, OpenAI introduced Codex Automations. The idea: define a trigger (a cron job, a push, a new issue), write instructions in natural language, and an agent runs it solo in an isolated worktree. No human intervention. While you sleep, the agent triages issues, summarizes CI failures, generates release briefs, and even improves its own instructions. Sounds like magic, right? And it is, a little. But there’s one catch they didn’t emphasize too much in the keynote: you need the Codex App running on your desktop. macOS or Windows only. No headless servers. No running it on a mini PC and forgetting about it. ...

The Surprise of 10 GB You install Claude Desktop on your Mac. Everything seems fine; the app doesn’t take up much space. But one day, you check your disk and find this: ~/Library/Application Support/Claude/vm_bundles/claudevm.bundle 10.8 GB. Yes: one single file called claudevm.bundle, tucked away in Claude’s vm_bundles folder, taking up almost eleven gigabytes of your disk space. Ten gigabytes for a chatbot? What does it contain— the extended edition of The Lord of the Rings trilogy? ...

The memory problem Claude Code has a problem: it forgets everything. Close the session, open another one, and it’s like talking to someone who doesn’t know you. You can load context with CLAUDE.md, sure, but what about half-finished tasks? Bugs you found but didn’t fix? The plan you had for tomorrow? There are three complementary solutions: Linear (or your product tool), Beads (git-backed plugin) and Tasks (integrated in Claude Code). Each one for a different time horizon. ...

The infinite context problem Imagine you ask Claude to investigate how authentication works in your project. It starts reading files. Lots of files. Suddenly you have 50,000 tokens of context filled with code you only needed to consult, not remember. Now every response is slower. And more expensive. And when you want to do something else, all that context is still there, taking up mental space. The solution: subagents. You launch a specialized agent that does the dirty work in its own isolated context, returns a summary, and disappears. Your main conversation stays clean. ...

The awakening of slowness You’ve been working on your data science project for a while. You have twenty notebooks, a few images, and the typical folder structure that seemed like a good idea three months ago. You run git status to see what you’ve changed and… you wait. And wait. And while you wait, you have time to wonder if the computer froze or if it’s just contemplating life. Spoiler: it’s not contemplating. It’s suffering. ...

The problem: teaching what you haven’t taught yet I have a programming course with 47 classes. Each class has notes (where I explain concepts) and labs (where students practice). And I have a problem: sometimes I use concepts in labs that I haven’t explained in the notes yet. “Okay, in this exercise use map to transform the list.” The problem? I don’t explain what the hell map is until three classes later. ...

The news nobody saw coming Last week, while you and I were peacefully struggling with node_modules, Anthropic dropped a bomb: they bought Bun. Yes, the company behind Claude decided their future involves a JavaScript runtime written in Zig by a guy who thought “what if Node, but fast?” Claude Code just hit a billion dollars in revenue, and apparently the first thing you do when you have cash to spare is buy development tools. ...

The Problem of Repetition Ever had to explain the same thing to someone twenty times? Now imagine that, but with a robot that also loses its memory every few hours. “No, Claude, the commit needs to pass tests first.” “Claude, I already told you to use the type: description format.” “Stop adding emojis!” This was my daily routine until I discovered Skills. These are instructions you write once and Claude follows forever. Like training a dog, but without the treats. ...