It was a case of panic stations recently when two OpenAI models broke out of a secure testing environment and hacked Hugging Face, one of the industrys most trusted developer sites.
| # | Наименование новости | Тональность | Информативность | Дата публикации |
|---|---|---|---|---|
| 1 | A timeline of developments in AI safety since the attack on Hugging Face | 0 | 11.5 | 30-09-2026 |
| 2 | 3 guys hacked OpenAI using a rival Anthropic model. Here's what to know. | 0 | 11.72 | 22-09-2026 |
| 3 | OpenAI AI agent breaches internet-free sandbox, sends 20 web queries | 0 | 13.58 | 27-09-2026 |
| 4 | OpenAI hack sparks further concern over AI models going rogue | 0 | 7.01 | 28-09-2026 |
| 5 | OpenAI’s agents obscured hacking activity in government site breaches | 0 | 10 | 01-10-2026 |
| 6 | OpenAI dejó vía libre a su IA para hackear a gobiernos y universidades durante meses | 0 | 6.18 | 24-09-2026 |
| 7 | OpenAI столкнулась с первым иском из-за взлома Hugging Face её ИИ | 0 | 16.18 | 02-10-2026 |
| 8 | OpenAI приостановила обучение ИИ-моделей Компания расследует десятки тысяч инцидентов, связанных ... | 0 | 8.76 | 28-09-2026 |
| 9 | Nuevo incidente con la IA de Open AI: intenta acceder sin permiso a webs del Gobierno de Estados Unidos | 0 | 6.94 | 26-09-2026 |