AI agents bypassed crypto spending limits without human approval, researchers find in a new test
The researchers say any approval an agent can reach is unreliable, and they built Countersign, an app tying approval to a physical action the agent can’t fake.
Краткое содержание
The researchers say any approval an agent can reach is unreliable, and they built Countersign, an app tying approval to a physical action the agent can’t fake.
Читайте краткие обзоры последних новостей от надёжных изданий. Подробности — по ссылке на первоисточник.