#Evaluation Design

Paper Review — Latest Trends in the “Harden­ing” and “Evaluation” of Generative AI

A cross-review of four recently released papers. Organized around robust evaluation design, training that accounts for adversarial conditions and uncertainty, agent safety verification, and model i...

Paper Review — AI Safety and Attack Robustness in the Age of Agents

As of 2026-04-15, we carefully selected three of the most recent related papers (agent attacks, positioning, and evaluation frameworks). Focused on threat models and experimental design for defense...