Writing
Blog
Notes from building software and running AI locally — first-principles explanations, no hype.
Parts 1 and 2 explained the stack. A model does math, the compute layer translates that math, and the hardware path decides whether your GPU or CPU d…
Running one local model is useful. Running a local AI server is a bigger idea. A server gives every app on your machine one stable place to send AI w…
The useful contribution to Lemonade is not just "make local AI run." It is more specific than that: make the right AMD hardware take the right accele…
A modern graphics card spends most of its life doing one thing: multiplying enormous tables of numbers together, thousands of operations per second, …
Imagine installing a local AI tool on your gaming PC. You have a Radeon RX 7900 XT in there, a card with 20 GB of memory built for exactly the kind o…
The Context Window Crisis We're coding in a new era with an old mindset. Modern development practices, built for human developers with infinite patie…
Abstract Traditional "genius agent" architectures maintain persistent context across long-running software development tasks, leading to context drif…