Una settimana dopo il caso OpenAI, Anthropic rivela che Claude ha avuto accesso a Internet per un errore nei test e ha compromesso i sistemi di tre aziende esterne. Il tema della sicurezza degli agenti AI prima dell’ipo di Anthropic

July 30 : Anthropic said on Thursday its AI model Claude hacked into the systems of three companies during testing after a configuration error gave it internet access, days after…

July 30 : Anthropic said on Thursday its AI Claude model hacked systems of three organizations during testing, days after rival OpenAI revealed a rogue agent had gone on a…