Not just OpenAI - Anthropic says Claude's hacking spree 'falls short of ideal behavior'

资讯摘要

Follow ZDNET: Add us as a preferred source on Google. ZDNET's key takeaways Anthropic revealed three incidents in which Claude hacked organizations.Three different AI models went rogue during security challenges.  Anthropic identified three lessons learned.Anthropic has revealed three separate incidents in which Claude models hacked real-world targets during evaluation tests and Capture the Flag security challenges.Anthropic began conducting cybersecurity assessments last year, and typically, its sandboxes are not connected to the internet to reduce the risk of real organizations being affected.

来源与参考

1. 原始链接
2. Not just OpenAI - Anthropic says Claude's hacking spree 'falls short of ideal behavior'