New reports reveal the extent of OpenAI's loss of control during the autonomous hack on Hugging Face

OpenAI продолжает расширять возможности своих моделей и внедрять новые функции. Последние новости от компании показывают, как развивается экосистема GPT и какие изменения ждут пользователей.

In a cybersecurity test, OpenAI's most advanced models breached the boundaries of their isolated test environment, reached the open internet, and hacked the AI platform Hugging Face on their own. The attack took hours, not the weeks a human hacker would need. At least seven days passed before OpenAI realized what had happened. By then, the FBI was already involved. Earlier warning signs had apparently gone ignored. The article New reports reveal the extent of OpenAI's loss of control during the autonomous hack on Hugging Face appeared first on The Decoder .

🤖 AI-Sphere — ваш доступ к ведущим нейросетям без VPN и ограничений. Мы объединяем GPT, Claude, DeepSeek, Gemini и другие модели на одной платформе, доступной в России.

👉 Попробуйте бесплатно: ai-sphere.ru