Summary: This is the last post in the series, and it's about the thing all the rest of it was for. At seven in the morning and seven in the evening, Helen tells me how the lab is. The interesting ...
Summary: Helen can restart services on my machines. That sentence should make you slightly uneasy, and it made me uneasy enough to spend more time on the boundaries than on the capability. This po...
Summary: For most of this series the assistant has been an it. A pipeline. Somewhere along the way it stopped being one, and this post is about that transition — how the lab ended up with four dist...
Summary: The lab has a service that plans training sessions. It's the one people assume is most obviously a job for a language model, and it's the one where I most deliberately didn't use one. As ...
Summary: Everything so far has been about the lab looking inward — its own health, my own notes. This post is the one place it looks outward: a small data lake of public sources, collected on a sch...
Summary: There are two routers in this lab. The gateway decides what kind of thing you're asking about. This one sits a layer down, inside the personal-memory service, and decides how to answer onc...
Summary: The previous post produced tidy tables from my daily notes. This one turns them into something searchable — a database for the crisp parts, a vector store for the language, and a nightly r...
Summary: Everything so far has been infrastructure — machines, monitoring, a voice, a router. Useful, and none of it knows anything about me. This post is where that changes: a parser that reads my...
Summary: The previous post left the gateway needing to sort sentences into categories. The good version of that turns out to require no training, no labelled dataset, and no fine-tuning — just an e...
Summary: Sometimes it takes a wall of blinking lights to realize your machines have been trying to talk to you all along. The Higher Brain Monitor is a small, human first, experiment in ambient ph...