A space lobster on your computer Imagine an Austrian developer creates a personal AI assistant, names it after a space lobster, and decides to open-source it. Within 24 hours it has 9,000 GitHub stars. Within 48 hours, 17,000. It also has 300+ open issues, several of them critical security vulnerabilities, and someone has created an unofficial cryptocurrency with its name. Welcome to Clawdbot. What exactly is this? Clawdbot is an open source AI assistant that runs locally on your machine. The difference from other assistants: it doesn’t just answer questions, it does things. ...
10 GB VM for a chatbot: What the hell is Claude doing on your Mac
The 10 GB surprise You install Claude Desktop on your Mac. Everything’s fine, the app is lightweight. But one day you check your disk and discover this: ~/Library/Application Support/Claude/vm_bundles/claudevm.bundle 10.8 GB. Excuse me? Ten gigs for a chatbot? What’s in there, the extended Lord of the Rings trilogy? Nope. It’s Ubuntu. The Claude product trinity Before I explain the what, let me explain the why. Anthropic has three ways to give you access to Claude: ...
Your Terminal is Burning Battery Like It's Mining Bitcoin
The crime scene Zaragoza, Hotel Pilar Plaza café. A café con leche, views of the basilica, and yours truly with a shiny new MacBook Air M3 ready to work a couple hours with Claude Code before a meeting. Two hours later: battery at 15%. Red alert. Panic. But how? I was just in a terminal writing code. No video, no Zoom, nothing that would justify this kind of consumption. I open Activity Monitor, Energy tab, and there’s the culprit: Ghostty, with an accumulated consumption of 3,600 over the last 12 hours. For context, Brave Browser consumed 125. Zoom with video, 99. Claude (desktop app), 46. ...
Linear, Beads, and Tasks: Three Memory Layers for Claude Code
The Memory Problem Claude Code has a problem: it forgets everything. You 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. ...
Subagents in Claude Code: Delegating Without Losing Control
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. ...
Why the hell does git status take so long?
The awakening of slowness You’ve been working on your data science project for a while. You’ve got 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 is just meditating. Spoiler: it’s not meditating. It’s suffering. ...
ChromaDB: How to use a vector database to avoid screwing up while teaching
The problem: teaching what you haven’t taught yet I have a programming course with 47 classes. Each class has notes (where I explain stuff) 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. “Alright, in this exercise use map to transform the list.” The problem? I don’t explain what the hell map is until three classes later. ...
Bun: The Runtime That Wants to Retire Node (and Now Has the Cash to Do It)
The news nobody saw coming Last week, while you and I were peacefully wrestling with node_modules, Anthropic dropped a bomb: they’ve bought Bun. Yes, the company behind Claude has decided that their future depends on a JavaScript runtime written in Zig by a guy who thought “what if Node, but fast?”. Claude Code just hit one billion dollars in revenue, and apparently the first thing you do when you have money to burn is buy development tools. ...
Skills in Claude Code: Teaching Old Dogs New Tricks
The Problem of Repeating Everything Have you 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 has to pass tests first.” “Claude, I already told you to use the type: description format.” “Don’t add emojis, damn it!” This was my daily routine until I discovered Skills. In plain English: they’re instructions you write once and Claude follows forever. Like training a dog, but without the treats. ...
Linear and Beads: How to prevent your AI from getting Alzheimer's
The robot’s amnesia Imagine you hire a brilliant programmer. They solve complex problems, write clean code, understand your architecture. But they have one small flaw: every few hours their memory gets wiped. They start from scratch. They don’t remember what they were doing, what you decided together, or why the code is the way it is. Well, that’s exactly what happens with Claude Code and other AI agents. When the context fills up (and it fills up fast if you’re working on a real project), the system does a “compaction.” In plain English: it summarizes the conversation and throws everything else away. The problem is that summary loses nuances, decisions, and especially the state of ongoing tasks. ...