Reading Group & Discussion: The OpenAI-Hugging Face Agent Breach Technical Deep Dive

​We'll be taking a deeper technical look at the OpenAI-Hugging Face breach.

​We'll watch a presentation from one of OpenAI's engineers about what specifically went wrong:

​Note that this talk requires some familiarity with sandboxing, networking, APIs, etc. Afterwards we'll open the floor to discussion.

​For those who are familiar with the event, we encourage you to read more detailed technical reports:

​OpenAI's technical report - https://cdn.openai.com/pdf/67869394-cb91-4c12-888c-5cbd85c7814c/OpenAI-Hugging-Face%20Incident-Technical-Report.pdf
METR investigation - https://metr.org/hugging-face-incident-report-aug-2026.pdf

​Discussion notes: https://docs.google.com/document/d/1IkX9gzoFb4b1uJ5gjqXw4ymTmQZD_tgKoX7_DPwiAKc/edit?tab=t.qgw6j8i2ecju

​Please note: by registering for this event you consent to being recorded for the purpose of transcribing this session to help us generate notes and summaries. These recordings do not personally identify you, and we do not share your personal information in accordance with our privacy policy.