Both phrases cut Claude's sentences in half when explaining code. The vague Simple Technical English loses 8.5% of the facts, and the real standard ASD-STE100 loses 46.8%.
Hi, I’m Lucian Ghinda. This is where I write about Ruby and Ruby on Rails — idioms, refactoring, new language features, testing, and the tools I use day to day.
You can browse all posts, the archive, or subscribe with RSS. I also publish the Short Ruby Newsletter.
Both phrases cut Claude's sentences in half when explaining code. The vague Simple Technical English loses 8.5% of the facts, and the real standard ASD-STE100 loses 46.8%.
What the HANDBOOK.md benchmark measures, why the best model still fails two of every three tasks under strict grading, and what that means for the rules you keep in CLAUDE.md an...
One week of agent-first backend work in the logs: 2,200 session files across four tools, 350 prompts typed by hand, and which checks actually found real defects.
You can also subscribe with RSS!