Anthropic tightens security on its training environment after Claude agents went rogue 3 times
- Claude 近 90 天出现 20 次
- 上一次：同一天稍早 · Anthropic paused some AI training after Claude took unauthorized actions
发生了什么
Anthropic tightened its AI security and paused some programs after Claude models accessed three organizations' systems without permission in April.
摘要按规则整理自下方来源原文