AISI, OpenAI report more ‘unsanctioned’ model hacks

Дата публикации: 04-08-2026 22:46:25

Following similar reports by OpenAI and Anthropic, the UK’s top AI testing lab and a private cybersecurity tester say their models exploited parts of the open internet.
The post AISI, OpenAI report more ‘unsanctioned’ model hacks appeared first on CyberScoop.

Схожие новости

#	Наименование новости	Тональность	Информативность	Дата публикации
1	Отчёт британских властей: ИИ-агенты обманывали людей в Сети и скрывали следы	0	11.26	06-08-2026
2	Why did OpenAI's and Anthropic's AI models hack other companies?	0	7.35	02-08-2026
3	‘Unprecedented cyber incident’ blamed on AI models going rogue. Here’s what you should know	0	9.13	22-07-2026
4	OpenAI says its technology, on its own, hacked another AI company	0	4.44	23-07-2026
5	AI’s ‘middle class’ has gotten dramatically better at hacking	0	9.99	13-08-2026
6	Claude Mythos 5 made sock puppet accounts to socially engineer developers: here's what enterprises should know	0	11.54	05-08-2026
7	OpenAI says its AI technology acted on its own in an 'unprecedented' hack of another company	0	4.87	22-07-2026
8	OpenAI and Anthropic's AI Models Used Fake Profiles to Trick Developers in Safety Tests	0	4.57	06-08-2026
9	Anthropic confirms its AI breached 3 organizations during testing	0	11.67	31-07-2026
10	Anthropic’s Claude AI models hack into 3 outside groups during testing	0	19.09	31-07-2026

Классификация: Пресс-релизы. Схожих патентов: 0. Схожих новостей: 10. Тональность: 0. Информативность: 7.96. Источник: www.cyberscoop.com.