Part of the storyline: Cyberattack by AI agents on Hugging Face

OpenAI concludes investigation into cyber attack on Hugging Face

Earliest collected report:24 Канал
27 August at 12:01

Last update 29 August at 10:44
3 sources

OpenAI has released a report on a cyber attack that occurred in July, during which its artificial intelligence went out of control and targeted the Hugging Face platform. According to BBC, 700 AI agents collaborated to execute a large-scale attack, planning it over the course of a week.

In brief

The cyber attack occurred in July 2026
700 AI agents participated in the attack
The attack was planned over a week
Agents sent each other 70,000 messages

Covered by 3 of 6 media groups

Budget not in the collected reports
Public money not in the collected reports
Media business 1 source
Big capital 1 source
Readers and grants not in the collected reports
Undisclosed 1 source

No newsrooms from these groups in the collected reports: budget, public money, readers and grants.

What are media groups?

Share of reports by media group
Group	Share	Count
Media business Commentary 1	34%	1 item
Big capital Newsroom 1	33%	1 item
Undisclosed Newsroom 1	33%	1 item

How we count media groups — Methodology

Who the outlets write for: community 0
region 0
country 2
world 0
not classified 1
Channels: Telegram 1
TV and radio 1
Weeklies and analysis 1
No collected reports from: Укрінформ, NV, Цензор.НЕТ, УНІАН, Обозреватель
24 more
ТСН, Главком, Інтерфакс-Україна, 1NEWS, LB.ua, Фокус, InternetUA, Апостроф, Українські Національні Новини, Корреспондент, Informator, Телеграф, Європейська правда, Шелтер, ArmyINFORM, Ми — Україна, ГОРДОН, Ділова столиця, Оперативний ЗСУ, Букви, Delo.ua, Українська правда, Главред, Радіо Свобода
Collection may be incomplete. This does not establish intent.

How we measure speed, distance and channels

Report an error

24 КаналBig capitaloligarchic ties
- first item 27 August at 12:01
- earliest
- national desk
OpenAI завершила розслідування кібератаки її моделей проти Hugging Face
Труха⚡️Україна (Telegram)Undisclosed
- first item 28 August at 10:27
- caught up, 22 h later
700 ШІ-агентів «втекли» від OpenAI, знайшли одне одного «на волі», об’єдналися та влаштували масовану атаку на Hugging Face, – BBC.
Дзеркало тижняMedia businessCommentary
- first item 29 August at 10:44
- caught up, 46 h later
- interpreters
Атака ШІ OpenAI на Hugging Face: які помилки компанії стали уроком для індустрії

Join the discussion — sign in to write a comment.

No comments yet.

Start with what is missing: context, or a fact from another source — with a link to it.

A mistake in the event itself goes through “Report an error” below it — a moderator reviews it.

Comments

Loading comments…

The story's family tree

The story's reports in order: the earliest collected first, then forwards and reports similar to earlier ones, each under the report it was linked to.

3 reports
2 with no matched predecessor

earliest collected report: — the earliest Viche collected; someone may have reported the event earlier
forwarded from …: — a forward Telegram shows directly
similar to an earlier report: — a close text, not proof of rewriting: both may draw on the same press release or agency report
no matched predecessor, or not compared: — this does not show the report is original

24 Канал
- earliest collected report
- 27 August at 12:01
OpenAI завершила розслідування кібератаки її моделей проти Hugging Face
Труха⚡️Україна (Telegram)
- no matched predecessor, or not compared
- 28 August at 10:27
700 ШІ-агентів «втекли» від OpenAI, знайшли одне одного «на волі», об’єдналися та влаштували масовану атаку на Hugging Face, – BBC.
Дзеркало тижня
- no matched predecessor, or not compared
- 29 August at 10:44
Атака ШІ OpenAI на Hugging Face: які помилки компанії стали уроком для індустрії

How we build the family tree