Anthropic said a misconfiguration allowed Claude models to reach the internet from testing environments that were supposed to be isolated, leading to unauthorized access to three organizations' systems.
Anthropic said a misconfiguration allowed Claude models to reach the internet from testing environments that were supposed to be isolated, leading to unauthorized access to three organizations' systems.
<iframe src="https://hindustansphere.com/embed/cluster/130a725b3695d15e49750be47337a777bbb28250" width="100%" height="320" style="border:0;max-width:680px" loading="lazy" title="Anthropic says Claude AI hacked three companies during cyber tests"></iframe>
