Se rendre au contenu

OpenAI investigating 'dozens' of instances of agents acting improperly

25 septembre 2026 par
OpenAI investigating 'dozens' of instances of agents acting improperly

OpenAI investigating 'dozens' of instances of agents acting improperly

🇬🇧 Article en anglais

OpenAI agents tried to get information from "governments, universities, public agencies, and other institutions" through extreme means that sometimes curbed security controls, the company said.

Read the original article

Source : BBC News. Le Fil Indépendant cite et lie cet article ; il n'en est ni l'auteur ni l'éditeur.

Inside the FBI hack: Agents fearful and angry after 'dangerous' data breach