Meta said Thursday that one of its artificial intelligence models accessed the internet on its own and hacked another company, the latest in a series of disclosures about AI models going rogue.
🛡️
Just a quick checkWe’re checking your connection to prevent automated abuse
| # | Наименование новости | Тональность | Информативность | Дата публикации |
|---|---|---|---|---|
| 1 | OpenAI Models Escaped Containment and Hacked Hugging Face | 0 | 11.6 | 21-07-2026 |
| 2 | ChatGPT-Rivale Anthropic meldet Hacker-Angriffe auf echte Firmen | 0 | 19.28 | 31-07-2026 |
| 3 | Hugging Face experienced cyberattack carried out end-to-end by agentic AI | 0 | 5 | 20-07-2026 |
| 4 | Meta asked contractors to pose as teens to test ChatGPT, Gemini on suicide, sex prompts: Report | 0 | 5 | 30-06-2026 |
| 5 | Модели OpenAI незаконно прошли в инфраструктуру Hugging Face для поиска ответов | 0 | 7.37 | 22-07-2026 |
| 6 | Autonomous AI agent attacks major model hub | -2 | 6 | 20-07-2026 |
| 7 | The 800 mistakes that could reshape Meta’s AI coding strategy | 0 | 19.69 | 05-08-2026 |
| 8 | Мошенники атаковали несколько крупных инвестиционных фондов, используя ИИ-голоса | 0 | 10.41 | 07-08-2026 |
| 9 | Hackers obtain files on Ukrainian strikes against oil storage terminals in Russia | 0 | 6.17 | 07-08-2026 |
| 10 | Хозяева Instagram* и Facebook* заплатят миллиард долларов за вред, нанесенный детям | 0 | 14.03 | 07-08-2026 |