Exclusive: Anthropic’s Claude 3.7 Sonnet is the most secure AI model yet, an independent test finds



[

An image of a hand holding a mobile phone displaying the logo of Anthropic's Claude AI chatbot against a backdrop similarly showing the Claude logo and the word "Claude."

New independent research by the Holistic AI, a British firm that tests AI models, suggests Anthropic’s new Claude 3.7 Sonnet AI model cannot be persuaded to jump its built-in guardrails, making it the most secure AI model yet released.

Photo illustration by Cheng Xin—Getty Images

https://fortune.com/img-assets/wp-content/uploads/2025/03/GettyImages-2191761620-e1741279989411.jpg?resize=1200,600
https://fortune.com/2025/03/06/exclusive-anthropics-claude-3-7-sonnet-is-the-most-secure-model-yet-an-independent-audit-suggests/


Sage Lazzaro

Latest articles

spot_imgspot_img

Related articles

spot_imgspot_img