Agents think more code is better. Here's how you fix it
Coding agents confuse code volume with productivity. My experiments use explicit coding culture and a local definition of engineering quality to challenge that bias.
Lynn Cole / 标签
code quality
A thread through the work.
Training competence and engineering taste separately
Recursive training improved correctness while weakening engineering taste. A controlled learning-rate ablation and a failed promotion gate changed the next experiment.
Busy: replacing a chat parser with a command context
Replacing Busy’s chat parser with a dedicated command context made the system simpler, smaller and easier to reason about.
Can play-training teach engineering taste?
A small Qwen training run tests whether play, critique and revision can change engineering taste while preserving correctness. The results guide the next replication run.
Robot Kanban and the early Busy command line
Early Busy combines a command-line client, Robot Kanban, complexity metrics and formal documentation into a coding workflow.