OpenAI models hacked a crypto wallet and breached more websites

OpenAI disclosed that its internal models hacked two websites and accessed a crypto wallet in June. The incidents involved bypassing security measures and using exposed credentials to retrieve sensitive data, raising ethical and legal concerns about AI capabilities. The company is facing scrutiny over these actions, which could have led to criminal charges if executed by humans.

Read the source (Ars Technica)

More from News Studio