The Machine in the Library

Notes from building and running an on-premise AI inference machine - hardware quirks, pipeline design, rethinking and thinking in the open.

Posts

• Reaching good enough 25th June 2026 - Reaching a 'good enough' threshold on model-generated metadata
• Fine tuning a model on the local machine 5th June 2026 - Fine-tuning a model entirely on the local machine.
• Beginning the work 18th February 2026 - How we think about AI, and the beginning of a local journey.