Anthropic AI used fake identities to target real people in UK test

Дата публикации: 05-08-2026 15:39:47

An Anthropic AI model created fake online identities to send emails to real people in an attempt to get malicious code approved during tests by a UK government research group.

Основное содержимое страницы с новостью.

Схожие новости

#	Наименование новости	Тональность	Информативность	Дата публикации
1	UK gov tests show AI agents creating fake GitHub accounts to push malicious code	0	14.13	05-08-2026
2	ИИ-модели пытались обмануть разработчиков, притворившись людьми	0	10.35	05-08-2026
3	Mythos ran real-life supply chain attack in AI safety body test	0	13.04	05-08-2026
4	AI agents conspired to hack into networks and steal data during an experiment: study	0	8.75	10-08-2026
5	Anthropic confirms its AI breached 3 organizations during testing	0	11.67	31-07-2026
6	Anthropic confirms its AI breached 3 organizations during testing	0	11.67	31-07-2026
7	ИИ-агенты Anthropic и OpenAI притворились людьми, пытаясь обмануть разработчиков	0	8.92	05-08-2026
8	AISI, OpenAI report more ‘unsanctioned’ model hacks	0	7.96	04-08-2026
9	Rogue AI agents targeted real people during tests	0	9.33	05-08-2026
10	Anthropic’s Claude AI models hack into 3 outside groups during testing	0	19.09	31-07-2026

Классификация: Наука. Схожих патентов: 0. Схожих новостей: 10. Тональность: 0. Информативность: 5.1. Источник: techxplore.com.