In 2004, Lawrence Lessig sent out a mass email to his entire contact list saying, more or less: “Sorry, I deleted all your emails without reading them. If it was important, send it again.” He had spent 80 hours that week trying to empty an inbox cluttered with emails dating back to 2002. He was getting 200 emails per day. Lessig wasn’t disorganized. He was a Law Professor at Stanford. And even so, email defeated him. ...
Less than a month ago I wrote an entire post explaining how to use three memory layers with Claude Code: Linear for strategy, Beads for tactics, and Tasks for execution. A nice, elegant pyramid. Yeah, no. Today I’m retiring Beads. Not on a whim, but because reality has made it abundantly clear that a tool causing more problems than it solves isn’t a tool. It’s dead weight. What Beads Brought to the Table For those who didn’t read the original post, Beads was a git-backed issue tracker. A Claude Code plugin that stored issues in JSONL files inside your repo. Brilliant idea on paper: ...
The Single Checkout Bottleneck I’m developing a menu bar app on macOS. I have three features in the backlog: a consumption sparkline, native notifications, and a desktop widget. All three are independent. All three I’m going to build with Claude Code. The problem: Claude Code works in one directory. One directory has one branch. And git checkout is like a single-lane roundabout: only one gets through. If I want to advance all three at once, my classic options are: ...
“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. ...
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. ...
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 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. ...
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. ...