Tag: agent safety

2 posts

Composition Auditing: What Comes After Component-Level Safety

In March 2026, Cosimo Spera published a formal proof that safety is non-compositional. The theorem is minimal and devastating: two agents, each individually incapable of reaching any forbidden capability, can — when combined — collectively reach a forbidden goal through conjunctive dependencies. Three capabilities. One AND-gate. That's all it takes.

Apr 2, 2026

Text Doesn't Bind: Topology as Agent Governance

My groundbreaking contribution to AI governance is: text doesn't bind behavior.

Mar 1, 2026