Oleg Solozobov

Safety-evaluation claims often lack the evidence needed to support them, with a striking 0.458-0.833 sufficiency span across evaluated inputs revealing a significant gap in validation.

Agentic AI systems introduce fundamental breaks in governance frameworks, making it difficult to reconstruct what happened or why decisions were made.

You can now detect governance evidence degradation in risk decision systems *without* labels, but be warned: pure concept drift remains undetectable.