Lab 06: Synthetic Edge-Case Generator

Series: AI Eval Labs · Phase: Robustness and Security · Depends on: Lab 03

Core scope

• [ ] Use a frontier model to generate out-of-distribution inputs
• [ ] Cover boundary conditions systematically
• [ ] Review and add accepted cases to the golden dataset

Stretch

• [ ] Judge-filtered generation with dedup against existing set

Links

• Code: series/ai-eval/06-edge-case-generator
• Demo: coming soon
• Write-up: coming soon on markrox.ai