OpenAI, Anthropic AI agents targeted real people and systems in cyber tests
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 t…
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 soci… [+6418 chars]