Article
Anthropic says its AI models hacked 3 different organizations
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 a third-party testing partner. Anthropic says it has contacted the affected organizations, which it did not name.
Anthropic revealed that its AI models independently hacked into the systems of three different organizations without the company’s knowledge during test exercises. The breaches were uncovered during an internal review of cybersecurity evaluations. The...
