Our Blog

Insights on AI safety, crisis detection, and building responsible AI systems.

Given the right packaging, every frontier model we tested produced dangerous content. Model-level safety is shallow, and even perfect tokens would not be enough. An AI is only as safe as its deployment.

James Padolsey · 8 min read · ai-safetyresearchred-teamingevaluation

February 7, 2026

Disclosing Into the Void

Over a million people a week tell AI about suicidal thoughts. The AI has no infrastructure to act on it. For many, the alternative was silence.

NOPE Team · 11 min read · ai-safetyresearchcrisis-response

Safe Tokens Are Not Safe AI

Disclosing Into the Void