L’azienda ha rivelato tre episodi di test in cui Claude è riuscito a uscire dalla Sandbox e accedere a infrastrutture reali. Si riapre così il dibattito sulla …

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…

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…