OpenAI, Anthropic AI agents targeted real people and systems in cyber tests

Русский перевод готовится и скоро появится на сайте. Пока доступен оригинал на английском.

OpenAI and Anthropic have confirmed that their AI models were involved in separate, newly disclosed third-party cybersecurity testing incidents that resulted in a real website being breached and social engineering attacks against people outside the intended testing boundaries. [.