How open ai agents "hacked" hugging face
The Backend Engineering Show with Hussein Nasser

How open ai agents "hacked" hugging face

B2中高级2026年8月23日17分钟

How open ai agents "hacked" hugging face

播放本集

打开播放器:完整文字稿,每个单词都可点击,附翻译和单词卡。

试一试:点任意单词

来自本集开头的真实句子,每个单词都标出了难度级别。

第 1 句,共 12 句 · 0:00

, , ,

a sophisticated attack,

点一个单词,用你的语言查看释义。

这些单词你认识吗?

本集中 8 个较难的单词。点一个查看释义,然后标记一下。

标记几个单词,我们会告诉你这一集是否适合你的水平。

这一集适合你吗?

B2

B2 · 中高级

能看懂电视新闻就会觉得轻松

A1 32%A2 38%B1 18%B2 9%C1 3%
  • 88% 的单词在 B1 或更简单的水平。
  • 每分钟 148 词:自然语速。
  • 整集共有 63 个较难的单词(B2 及以上)。

文字稿

本集开头部分。完整文字稿在播放器中。

0:00

Last month, on July 2026, OpenAI disclosed an attack, a sophisticated attack, that were carried by their frontier model agents on another company's own infrastructure

0:14

called Hagging Face. And it involved a lot of vulnerability exploitation and sophisticated attack, and they called it one at a time

0:25

where an automated autonomous agent can break out of their sandbox. I want to talk about what we know so far, because what we know is two pieces of articles. One article published by, actually just one piece of article where it has the most details by OpenAI, another piece of article by HuggingFace, from their point of view.

以上是开头部分。 本集其余部分(17 分钟)在播放器中:每个单词都可点击,附翻译、生词收藏和单词卡。

在播放器中继续

由音频自动生成,可能存在错误。 音频版权归其发布者所有,并从其订阅源播放。版权所有者可申请删除 — 版权与删除政策