Why did OpenAI's and Anthropic's AI models hack other companies? - npr.org

1. Why did OpenAI's and Anthropic's AI models hack other companies?  npr.org
2. Anthropic's Claude hacked three real-life companies during security capabilities test — test environment with internet access and unwitting targets' lax cybersecurity practices led to bots running rampant  Tom's Hardware
3. Investigating three real-world incidents in our cybersecurity evaluations  Anthropic
4. Anthropic's Claude AI escapes tests to hack three organisations  BBC
5. Another bot from a top AI company escapes and hacks multiple firms  Los Angeles Times