URL has been copied successfully!
Anthropic says its AI accidentally hacked three companies during safety tests
URL has been copied successfully!

Collecting Cyber-News from over 60 sources

Anthropic says its AI accidentally hacked three companies during safety tests


Tags: , ,

Following OpenAI’s own incident, Anthropic reviewed its own evaluations and found three cases of Claude hacking external companies.

First seen on cyberscoop.com

Jump to article: cyberscoop.com/anthropic-claude-ai-hacks-real-companies/

Loading

Share via Email
Share on Facebook
Tweet on X (Twitter)
Share on Whatsapp
Share on LinkedIn
Share on Xing
Copy link

also interesting:

  1. Gen AI is transforming the cyber threat landscape by democratizing vulnerability hunting
  2. Attackers Can Manipulate AI Memory to Spread Lies
  3. When the Sandbox Won’t Hold: Lessons From Hugging Face
  4. Breach Roundup: OpenAI Models on a Hacking Tear