Posts

The failure looked like nothing. No HTTP 500, no timeout exception, no DNS resolution error — just empty content coming back from a feed that had been working fine. Julia Evans’ blog had been a reliable source in LUMIS’s feed pipeline, and then one day it wasn’t, and the logs gave me almost nothing to work with. That’s the thing about Cloudflare blocking your bot: it doesn’t always slam a door in your face. Sometimes it just stops letting anything through and waits to see if you notice. ...

I’ve broken LUMIS’s knowledge base the same way three times now. Each time, the failure looked different on the surface — a session that hit context exhaustion mid-task, a /compact event that truncated the agent’s working memory, a clean session boundary where I just closed the terminal. Underneath, the failure was identical: a research artifact got written, the INDEX didn’t get updated, and the gap was invisible until something downstream tried to find that artifact and couldn’t. ...

Last quarter I watched a Claude Code session spend forty minutes debugging a Python script it had generated itself. The script was supposed to walk a directory tree and emit structured metadata for each file it found. The logic was correct in outline — the right algorithm, reasonable variable names, sensible structure. What it kept getting wrong was subtler: a loop counter that was initialized inside the function body but read outside it after early returns, a zip() that silently truncated when the two lists weren’t the same length, a state dictionary that accumulated across calls because it was defined at module scope. Each bug was individually fixable. Together, they represented something more systematic: the failure modes that appear when you ask an LLM to generate multi-step procedural code in a general-purpose language. ...

When I moved my personal knowledge vault off GitHub, the decision felt almost embarrassingly small — a few configuration changes, a different sync target, maybe an afternoon of work. But the reasoning behind it turned out to be the same reasoning I keep returning to when I look at what the major AI platforms are now calling “memory.” The friction wasn’t technical. It was conceptual. I’d been treating my own thought history like source code: version-controlled, backed up, shareable by default. And that worked fine until I started thinking seriously about what that history actually contains. ...

I noticed the pattern before I decided to fix it: three separate signals in my own vault, all logged on the same day, all hovering in the 7-8 range, all pointing at the same seam in my session lifecycle. That’s usually how these things surface for me — not as a single “aha” but as a cluster of low-grade friction that finally crosses a threshold where it’s cheaper to fix than to keep tolerating. The seam was the gap between creating a git worktree for a new task and the moment the agent actually has enough context to do anything useful in it. ...