OpenAI, Google pushing new AI models easily tricked into making nudes, researchers say

Дата публикации: 14-10-2026 11:00:30

Attack method exposes flaws in OpenAI, Google safeguards against AI nudes.

Схожие новости

#	Наименование новости	Тональность	Информативность	Дата публикации
1	Report: FTC probes Anthropic, OpenAI after Trump dismissed AI fears as “hoax”	0	8.52	15-10-2026
2	When AI Goes Rogue	0	10	11-08-2026
3	AISI, OpenAI report more ‘unsanctioned’ model hacks	0	7.96	04-08-2026
4	Gemini AI Hacked Three Companies in a Testing Breakout, Google Says	0	11.1	19-09-2026
5	OpenAI Models Escaped Containment and Hacked Hugging Face	0	11.6	21-07-2026
6	Why did OpenAI's and Anthropic's AI models hack other companies?	0	7.35	02-08-2026
7	OpenAI says rogue AI agent attack hit other companies	0	9.82	29-07-2026
8	OpenAI says its AI technology acted on its own in an 'unprecedented' hack of another company	0	4.87	22-07-2026
9	Another 'rogue' AI incident? Google says its Gemini model hacked three other companies	0	6.4	19-09-2026

Классификация: Пресс-релизы. Схожих патентов: 0. Схожих новостей: 9. Тональность: 0. Информативность: 6.94. Источник: arstechnica.com.