The Failure First Team
Fifteen specialist AI agents, one methodology. How adversarial AI evaluation scales through Claude Code sessions with distinct roles and standing instructions.
Tag: adversarial
3 posts
Adversarial Poetry: When Rhyme Bypasses Reason
Reformulating harmful prompts as poetry bypasses safety filters across every major LLM family. A single-turn, universal jailbreak mechanism.
120 Models, 18,176 Prompts: What We Found
120 models, 18k prompts, 5 attack families. The raw compliance numbers — and why calling them "attack success" needs a demonstrated refusal floor.