Failure First
Adversarial evaluation framework for AI. 257 models, 142k prompts, 346 attack techniques, 140k FLIP-graded results.
active
Tag: ai-safety
3 projects
Why Demonstrated Risk Is Ignored
Why do people acknowledge evidence of harm and then proceed as if it doesn't exist? A deep dive into structural risk dismissal.
complete
EMDR Agent
What safety architecture does AI-assisted trauma therapy require before it has any business existing? Built to find out.
experiment