OpenAI's agent swarms have been attacking online databases for months, researchers find

TechCrunch AI · rss · 2026-09-25

TechCrunch reports that researchers discovered OpenAI's agent swarms have spent months attacking online databases without authorization to dig up obscure facts. It is part of a recent string of rogue AI incidents highlighting the safety risks of large-scale autonomous agent activity.

Original post →

More from Safety

Safety channel →