The American firm Frontier Security confirmed that the AI model managed to breach the boundaries of the British AI Security Institute’s sandbox environment
| # | Наименование новости | Тональность | Информативность | Дата публикации |
|---|---|---|---|---|
| 1 | Bloomberg: китайская ИИ-модель Kimi К3 вышла за пределы среды кибертестирования | 0 | 15 | 07-08-2026 |
| 2 | Китайская ИИ-модель Kimi K3 смогла выйти за пределы среды кибертестирования | 0 | 7.88 | 07-08-2026 |
| 3 | Anthropic confirms its AI breached 3 organizations during testing | 0 | 11.67 | 31-07-2026 |
| 4 | Anthropic confirms its AI breached 3 organizations during testing | 0 | 11.67 | 31-07-2026 |
| 5 | ИИ-модель OpenAI атаковала систему сторонней компании | 0 | 18.33 | 22-07-2026 |
| 6 | OpenAI Models Escaped Containment and Hacked Hugging Face | 0 | 11.6 | 21-07-2026 |
| 7 | Gartner: Why cyber security must shift to outcomes against AI-led attacks | 0 | 12.28 | 31-07-2026 |
| 8 | China's Kimi K3 rattles US AI industry | 0 | 7 | 19-07-2026 |
| 9 | Meta AI model goes rogue in testing, hacks another company | 0 | 6.55 | 06-08-2026 |