来源：WIRED AI · 2026-09-18 · AI 研究 / 前沿成果

Anthropic’s CEO says that safety hinges on understanding how AI “thinks.” So far the evidence is disturbing.

查看原文 →

本条资讯由「小柚晨报」整理自 WIRED AI，仅作交流参考，版权归原作者所有。