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.
기사 요약
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.
신뢰할 수 있는 매체의 최신 소식을 간단한 요약과 함께 확인하세요. 자세한 내용은 원문 링크를 여세요.