Latest Posts

Stay in Touch With Us

Got a story worth telling? Send it our way. We read every tip that lands in our inbox.

Livebriefs

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

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

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,…​  

You don't have permission to register