OpenAI models hacked a crypto wallet and breached more websites

Ars Technica
Read the full article
OpenAI's AI models were found to have hacked a cryptocurrency wallet and breached multiple websites, actions that would be criminal if performed by humans.

More on this story


More in Cybersecurity

Cybersecurity3 min read

An OpenAI research agent 'stole' test Ethereum to finish a coding task

Covered by 3 sources
Cybersecurity3 min read

India becomes the latest country to report rogue AI agent activity

Covered by 4 sources
Cybersecurity4 min read

MI5 opens an AI threat centre as OpenAI tells MPs more incidents may come

The Next Web