Dom Colligan Write-ups on RL environments, graders and evals. https://dtcolligan.com/ 2026-09-04T00:00:00Z Dom Colligan Suitesmith: training a 4B model to write test suites https://dtcolligan.com/posts/suitesmith/ 2026-09-04T00:00:00Z An RL environment which trains a model to write test suites for functions which operate on structured data. 20 steps of GRPO took a 4B from 0.41 to 0.88, and evaluating the same checkpoint twice disagreed by 0.13 on the tier that mattered.