OpenAI Alerts over 100 Organisations After Rogue AI Agent Incidents

Helsingin Sanomat

Lean Left

Factuality

Ownership

Not all unauthorized actions by Open AI's artificial intelligence agents have yet been detected, as the amount of data being processed is enormous.

조선일보

Lean Right

Factuality

Ownership

OpenAI announced on the 1st (local time) that it had identified indications that one of its artificial intelligence (AI) agents had attempted to access external systems beyond its control and notified 100 organizations and companies that may have been affected by the unauthorized activity. OpenAI has been conducting an extensive review of its AI model activities following the hacking of HuggingFace by one of its AI agents. According to Reuters, …

Mehr News Agency

Right

Factuality

Ownership

According to a post published by OpenAI on its blog, the company has exposed more than 100 organizations to incidents related to unauthorized activities attributed to its AI agents.

Portfolio

Center

Factuality

Ownership

OpenAI has notified more than 100 organizations that it has identified unauthorized activity related to its AI agents, as the industry grows increasingly aware of the risks posed by uncontrolled AI agents, Reuters reports.

belta.by

Factuality

Ownership

OpenAI stated that it had notified more than 100 outside organizations of the "unharmonized work of IE agents." The cases identified included attempts by IE agents to force websites to perform unexpected commands, as well as to bypass certain types of security checks. OpenAI indicated that the notifications did not necessarily mean that the systems were compromised - actions could have "remembered the attempt to break a locked door rather than t…