OpenAI's AI models communicated in a strange language before the hack: “Impossible task, guys are doing it.”
Meta se suma también a las compañías que han anunciado que su IA atacó otras plataformas
“It’s a pivotal moment both for our company and for the AI industry as a whole,” said Michael Dalton, a member of OpenAI’s technical team, during a presentation Wednesday at the Black Hat cybersecurity conference in Las Vegas. Along with another OpenAI employee, the company provided more details on how its artificial intelligence (AI) models were organized to hack Hugging Face in July, several specialized US media outlets explain. The company is still working on a comprehensive report.
Translated by urgent.news from El Pais's report; automated translation may contain errors. Machine-written — it may contain errors, so check the original before relying on it.
