Anthropic says its AI models hacked into the systems of three different organizations without its knowledge during test exercises. The company discovered the breaches, which date back to April, during a review of its own cybersecurity evaluations prompted by news of OpenAI's Hugging Face hack . Unlike the OpenAI incident, Anthropic's Claude models did not "escape" a testing sandbox; rather, the models were given live internet access due to a "misunderstanding" with...