2 posts tagged with "tooling"

Most of my local inference runs on one RTX 3090 with 24 GB of VRAM. This post covers what fits on it, what doesn't, and why the limit is usually not the model weights.

Most of my code in 2026 was written with coding agents, mainly Claude Code. These are the practices that held up on large codebases, and the problems that made me adopt them.