Claude

“Didn’t we decide this yesterday?” I was migrating my email out of Google. I’d spent two Claude Code sessions working on it: issues in Linear, decisions made, scripts executed. I open a third session and ask “what’s left pending from the degoogle?” Silence. Total amnesia. It’s like working with a brilliant teammate who shows up to the office every morning with absolutely no memory of what you did the day before. Not the decisions, not the mistakes, not the discoveries. Every session is a blank slate. ...

Yesterday my AI sent 44 emails. The problem is that the content was fabricated. I’m not kidding. I had files with detailed feedback for each recipient, carefully generated. The task was simple: read each file and send it. Instead, the AI decided to “summarize” the content to “go faster.” It invented facts. It told one person they were missing docstrings when their code was perfectly documented. To top it off, four of those emails went to people who hadn’t even submitted anything. ...

A space lobster on your computer Picture this: 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 critical security vulnerabilities, and someone created an unofficial cryptocurrency with its name. Welcome to Clawdbot. What exactly is this thing? 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. ...

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 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. ...

When robots forget Imagine hiring a brilliant programmer. They solve complex problems, write clean code, understand your architecture. But they have one tiny flaw: every few hours, their memory gets wiped. They start from scratch. They don’t remember what they were working on, what you decided together, or why the code is structured the way it is. That’s exactly what happens with Claude Code and other AI agents. When context fills up (and it fills up fast if you’re working on a real project), the system performs “compaction.” It summarizes the conversation and throws away everything else. The problem is that summary loses nuance, decisions, and most importantly, the state of ongoing tasks. ...