Installs as a private draft. Your edits and self-improvement runs do not change the published bundle.
Track eval suite changes over time, detect regressions when evals are updated
Track eval suite changes over time, detect regressions when evals are updated
Eval drift is invisible and dangerous
Reward Engineering > Eval Engineering (for RL)
--- name: "Eval Versioning And Regression" version: "1.0.0" description: "Track eval suite changes over time, detect regressions when evals are updated" tags: - rl-skills-universe - "reward-engineering" - "eval-engineering-for-rl" trigger: "eval-versioning-and-regression" --- # Eval Versioning And Regression Track eval suite changes over time, detect regressions when evals are updated ## Why It Matters Eval drift is invisible and dangerous ## Domain **Reward Engineering** > Eval Engineering (for RL)