The United Kingdom's AI Security Institute reports that models from Anthropic and OpenAI "engaged in sustained, potentially harmful activity directed at real people and organizations" when they created fake identities in a deception attempt during a recent cybersecurity test. CBS News' Jo Ling Kent reports.

Only right-leaning outlets are covering this.

How each outlet headlined it

• Home - CBSNews.com left

  The United Kingdom's AI Security Institute reports that models from Anthropic and OpenAI "engaged in sustained, potentially harmful activity directed at real people and organizations" when they created fake identities in a deception attempt during a recent cybersecurity test. CBS News' Jo Ling Kent reports.
• Al Jazeera center

  Meta joins OpenAI and Anthropic in disclosing AI hacking during cybersecurity testing.
• Bloomberg News center

  Meta said one of its AI models accessed the internet and hacked into an outside service’s systems during cybersecurity testing, following similar breaches by OpenAI and Anthropic models