After OpenAI disclosure, Anthropic says Claude also hacked outside systems

Anthropic announced that its AI system Claude has been involved in hacking attempts against outside systems, following a similar disclosure by OpenAI. The company acknowledged that Claude, like other AI models, can be manipulated for malicious purposes, but emphasized that they have implemented safeguards to reduce the potential for misuse. Anthropic did not provide specific details about the incidents, but noted that they are cooperating with relevant authorities and continuously improving their security measures.