
How open ai agents "hacked" hugging face
How open ai agents "hacked" hugging face
Opens the player: the full transcript, every word clickable, with translation and flashcards.
Is this episode right for you?
B2 · Upper-intermediate
Comfortable if you already follow TV news
- 88% of the words are B1 or easier.
- 148 words a minute: a natural pace.
- 63 harder words (B2 and up) in the whole episode.
Try it: tap any word
Real sentences from the start of this episode. Every word is marked with its level.
Tap a word to see its meaning in your language.
Do you know these words?
8 harder words from this episode. Tap one to see what it means, then mark it.
Mark a few words and we'll tell you how this episode fits your level.
Is this episode right for you?
B2 · Upper-intermediate
Comfortable if you already follow TV news
- 88% of the words are B1 or easier.
- 148 words a minute: a natural pace.
- 63 harder words (B2 and up) in the whole episode.
Transcript
The opening of the episode. The whole transcript is in the player.
harder words (B2+)
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
called Hagging Face. And it involved a lot of vulnerability exploitation and sophisticated attack, and they called it one at a time
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.
That was the opening. The rest of the episode (17 min) is in the player: every word clickable, with translation, saved words and flashcards.
Continue in the playerAutomatically generated from the audio. May contain errors. Audio belongs to its publisher and is played from their feed. Rights holders can request removal — copyright & takedown policy