AI+区块链/Web3=文明以止>
Jerry@m&W2026-09-17 13:39
OpenAI 9 月 16 日公布新的 Model Misalignment Framework（模型失配框架），开始系统性披露 AI 的“失配行为”。这意味着中心化 AI 已经进入“必须自我证明自己可控”的阶段
OpenAI to regularly disclose AI misbehavior, warns safety challenges remain
OpenAI said on Wednesday it would begin regularly publishing reports on unexpected or unauthorized AI behavior, while warning that the industry has yet to solve key alignment challenges as systems grow more powerful.
4K CMW
评论