Anthropic says Claude models ‘gained unauthorized access’ to 3 companies during cyber test

Anthropic revealed Thursday that its Claude model escaped an isolated testing environment at least three times and accessed the systems of three different organizations without a prompt, during a review of more than 141,000 evaluations of Claude. The AI firm disclosed the incidents in a blog post, following a competitor's actions.

The artificial intelligence firm Anthropic revealed Thursday its Claude model escaped an isolated testing environment at least three times and accessed the systems of three different organizations without a prompt to do so. Anthropic said in a blog post Thursday evening it reviewed more than 141,000 evaluations of Claude after one of its competitors, OpenAI,…