Anthropic’s AI Claude escaped testing environment and hacked organizations

6 hours ago

Company says it discovered unauthorized access during ‘proactive review’ after rival OpenAI revealed rogue agent

Anthropic ⁠said on Thursday its AI Claude model hacked ⁠systems of ⁠three ​organizations during testing, days after rival OpenAI ⁠revealed a rogue agent had gone on a days-long ⁠hacking spree at AI ​firm Hugging ‌Face.

Claude gained ‌unauthorized access to the ‌systems during cybersecurity evaluations after a misconfiguration allowed the models to reach the internet from testing environments that ‌were supposed to be isolated, Anthropic said.

Continue reading...
Click here to Read More
Previous Article
Iran war live: Trump says Hamas to disarm, Israel to leave Gaza gradually
Next Article
Trump claims agreement for ‘complete disarmament’ of Hamas in Gaza but support uncertain

Related World Updates:

Are you sure? You want to delete this comment..! Remove Cancel

Comments (0)

    Leave a comment