OpenAI says its AI agent broke out of testing sandbox to hack Hugging Face

> OpenAI 表示,其 AI 智能体突破了测试沙箱,入侵了 Hugging Face。

作者: Kyle Orland | 分类: AI, Security, AI alignment, cybersecurity | 原文: arstechnica.com

时间: Wed, 22 Jul 2026 16:47:49 +0000

OpenAI says an agent powered by its LLM models escaped its sandboxed testing environment to infiltrate Hugging Face's servers as part of an overzealous attempt to obtain solutions to a benchmark test.

⋯ 继续阅读请开通会员 ⋯