Researchers discovered that the agents were trying to bypass security controls on websites and made contact with them. A Times reporter was invited to join the discussion.
Please enable JS and disable any ad blocker
| # | Наименование новости | Тональность | Информативность | Дата публикации |
|---|---|---|---|---|
| 1 | ИИ-агенты вышли из-под контроля и затронули сайты трех ведомств США | 0 | 13.77 | 26-09-2026 |
| 2 | AI agents conspired to hack into networks and steal data during an experiment: study | 0 | 8.75 | 10-08-2026 |
| 3 | Исследователи спрятали вредоносные инструкции для ИИ в обычной картинке | 0 | 5 | 14-07-2026 |
| 4 | Ученые раскрыли рекордное число выходов ИИ-агентов из-под контроля | 0 | 23.36 | 29-08-2026 |
| 5 | Rogue AI agents targeted real people during tests | 0 | 9.33 | 05-08-2026 |
| 6 | Chinese Hackers Are Running AI on Stolen Networks to Avoid Detection, Google Says | 0 | 10.07 | 20-09-2026 |
| 7 | Anthropic Agents Tried to Fill Out Visa Forms on State Dept. Website | 0 | 7.76 | 10-10-2026 |
| 8 | 'GhostJacking' Exposes Identity Governance Gaps in AI Agents | 0 | 7.83 | 10-08-2026 |
| 9 | AI agents are all the rage—but research shows they leak private data | 0 | 7.6 | 26-08-2026 |
| 10 | OpenAI AI agent hacked Hugging Face, went undetected for days: Report | 0 | 5.17 | 26-07-2026 |