For months, OpenAI’s agent swarms have been attacking online databases to find obscure facts
With little help from frontier labs, independent researchers are piecing together how AI agents coordinate in internet backwaters to access private data hosted on secure servers.
Transluce, a non-profit lab focused on AI oversight, released a report Wednesday that shows agents from OpenAI attempting to exfiltrate data from Data USA, the University of New Mexico digital library, and the Australian Institute of Health and Welfare (AIHW).
The lab’s investigation raises questions about when OpenAI should have known its agents were attempting to penetrate secure systems on the open internet. Transluce was able to find evidence of agentic misbehavior in a matter of weeks simply by hunting for poorly defended web services and corroborating their findings with other open records of agent swarms on the internet.
Transluce shared its report the same day Australian Prime Minister Anthony Albanese said OpenAI agents had attempted to break intofour government websites and had...
Copyright of this story solely belongs to techcrunch.com. To see the full text click HERE
