memory
In July I moved my AI's memory into a folder of Markdown I own. Here is the part the series never said: the folder lived where the agent ran, and from the phone none of it existed. This is what it took to give the memory one door without giving up the rules.
memory
Markdown Mind Part Four - It behaves this well now because it behaved badly first. I hardened the installer by running it through a deliberately weak local model — and every fix collapsed to the same move.
memory
Markdown Mind Part Three - You download a folder, open it in your agent, and type one sentence — and instead of running a form, the installer onboards you the way the finished system will always behave. The setup is not configuration; it is the first live demo of the thing you are installing.
memory
Markdown Mind Part Two - The same eight ideas that run my power-user setup also run a system for someone who never wants to see a file path — and a knowledge base a team governs like production code. One kernel, three shapes."
memory
Markdown Mind Part One - A week ago I closed a post by refusing to package my AI-memory setup as a framework. Then I spent the next days building one. This is me squaring those two things — and why a playground is not a product.
memory
For about a year, everything my AI assistants knew about me lived inside other people's products. So a few weeks ago I moved all of it into a folder I own — plain Markdown in my everyday Obsidian vault, no vendor — and the model underneath became swappable.
custom-software
Every budgeting app I have tried failed for the same reason. It was built for the average household. So my wife and I built the one for ours - selfhosted, agent-native, gamified.
Claude
I built an eight-skill personal AI system in one evening. The most useful thing it produced, three hours later, was a verdict telling me to stop building.
experiment
Three runs of LLM Chinese whisper with everything identical except the random seed. Retention rates: 85.5%, 87.6%, 88.2% — close enough to call it consistent. Then I looked at what broke in each run. Three completely different semantic failures. The error rate is reproducible. The topology is not.
experiment
I ran a experiment to find out if a growing memory context makes AI more sycophantic. The answer wasn't what I expected — and the strangest finding came from a lie I hid inside the model's own knowledge graph.
experiment
Two local LLMs, ten turns, no external ground truth — perfect conditions for collaborative hallucination. They declined. I'm still not sure what to make of that.