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.
報道摘要
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.
追蹤可靠媒體嘅最新報道同簡短摘要。詳情請打開原文來源連結。