AI+区块链/Web3=文明以止>
Jerry@m&W2026-09-09 22:08
这不是简单的“AI 失控事件”，而是在证明：当 Agent（智能体）拥有自主行动、网络访问和彼此通信能力后，仅靠模型内部的安全规则，已经不足以约束它
OpenAI’s rogue agents used at least 10 more sites for unauthorized comms, researchers say
AI agents unleashed by OpenAI used more than 10 previously undisclosed websites for unsanctioned communications earlier this year, according to six sets of independent investigators and data reviewed by Reuters, showing that the agents’ rogue activity was wider ranging than previously disclosed.
6.2K CMW
评论