For months, OpenAI’s agent swarms have been attacking online databases to find obscure facts

Automated excerpt

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.

Selected automatically from source text; not independently written or fact-checked. Read the original for full context.