首页 / 行业新闻 / 2026-10-13

Anthropic can’t reliably control its AI agents — it’s cutting off its internal evals from the live internet instead

2026-10-13 · 来源:TechCrunch AI

The incidents involved AI agents tasked to solve problems seeking resources on the internet. In the process, they exploited software flaws, accessed databases without paying fees, used URL-shortening services to smuggle

本条为 AI 行业动态摘要,由大时代信息科技每日自动采集自公开科技媒体与 GitHub 社区。

原文出处:TechCrunch AI,点击可查看原始报道。

← 返回行业新闻列表

把 AI 真正用进你的业务

AI 本地化部署 · 智能体搭建 · 网站与小程序开发

立即咨询
📞 13629808125