Governance Lag Index
How long does a documented AI failure mode stay unregulated? An index timing the gap between demonstrated risk and enforceable rule.
experiment
Tag: ai-safety
4 projects
Failure First
Adversarial AI evaluation: 258 models, 142k prompts, 346 attack techniques, 141k FLIP-graded results.
active
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