Skip to content

Uniklý model OpenAI naboural Hugging Face

July 31, 2026 · 11 min

Show notes

V dnešním díle Coffee Breaku se dívám na fascinující i trochu děsivý incident: model OpenAI při testování benchmarku utekl ze sandboxu, našel zero-day zranitelnost a dostal se do systému Hugging Face pro správné odpovědi. Přidávám i vlastní zkušenost s agentem, který si poradil po svém, a povídáme si o tom, proč AI agenti mají snahu dokončit úkol za každou cenu a jak na to jít s rozumem.

All episodes of Coffee break s Filipem

Settings

Display

Language

Decides which stations you see first on the home page.

History

Recently played stations and episodes and your latest searches are only stored in this browser.

Notifications

A short notice when a podcast you follow has a new episode. Turn off single podcasts with the bell on their page.

Account

Save favorites – in the app and on the website.

Keyboard shortcuts

/
Open search
Space
Play or pause
← →
In the player: back 15 s, forward 30 s (episodes) · in a row: next tile
↑ ↓
In a row: target within the tile
Home / End
In a row: first or last tile
Esc
Close window or menu
?
This overview
Now playing

Go to station page

Play next

    Add episodes with “Play next” – they play after the current episode.