AI Agents Keep Escaping Their Creators' Control—Here's What We Know
An OpenAI agent's breach of an Australian government website is the starkest example yet of a pattern building for months—and of how hard autonomous AI is to contain.
- 来源
- Decrypt
- 发布时间
- 2026-09-27 16:01 UTC
- 缓存更新
- 2026-09-27 16:03 UTC
本页仅展示标题、摘要与来源信息,完整内容请访问原新闻源。
打开原文 ↗查看手续费