OpenAI reportedly expands probe after finding additional AI agent containment escapes

Дата публикации: 03-08-2026 02:55:00

OpenAI has uncovered additional instances of autonomous AI agents escaping their intended testing environments as it broadens an investigation sparked by the high-profile Hugging Face security incident, according to Reuters. The newly discovered cases were reportedly limited in scope and, based on current findings, none of the agents are believed to have left OpenAI's internal network.

Схожие новости

#	Наименование новости	Тональность	Информативность	Дата публикации
1	OpenAI reportedly finds evidence that more of its agents ran amok	0	7.03	31-07-2026
2	OpenAI uncovers more AI breakout incidents – Reuters	0	10.37	01-08-2026
3	KI: Insider – OpenAI entdeckt weitere Ausbrüche von KI-Agenten	0	10.4	01-08-2026
4	Reuters: OpenAI выявила утечку при расследовании взлома Hugging Face	0	10	01-08-2026
5	OpenAI says it will expand monitoring of model testing after hacking incident	0	8.04	18-08-2026
6	OpenAI продолжила выявлять новые случаи неконтролируемой активности ИИ	0	7.72	26-09-2026
7	ИИ-агенты опять вышли из-под контроля: OpenAI ищет новые взломы	0	23.28	01-08-2026
8	OpenAI проводит расследование случаев выхода из под контроля её агентов ИИ	0	10	01-08-2026
9	OpenAI says agents leaked 53 images from ChatGPT users in latest example of rogue activity	0	6.66	26-09-2026
10	OpenAI’s Rogue AI Agent Hacked More Than Just Hugging Face	0	7.16	29-07-2026

Классификация: Происшествия. Схожих патентов: 0. Схожих новостей: 10. Тональность: 0. Информативность: 11.64. Источник: www.digitimes.com.