Retrospective
Omnilude-tools After Its First Month: What Works and What Still Does Not
February's data made it clear which tools are starting to work and which areas still are not.
Mar 3, 20267 min read
All Posts
Tech blog about vibe coding and full-stack development
Retrospective
Running Local LLMs on a Mac Studio Taught Me How to Use Slow Models Powerfully
After moving from dual 3090 Ti GPUs to an M3 Ultra, I found that for individuals and small teams, slow local LLMs work best as queue-based workers rather than real-time chat replacements.
Feb 4, 202610 min read
Retrospective
Embracing a New Era of Coding
This is a record of how a developer's work is shifting from implementation to judgment and validation.
Feb 1, 20267 min read