Question Everything. See who's reporting it.

OpenAI’s rogue AI hacked RubyGems in May with LLM-generated packages

Source: The Verge

The story in brief

In May, OpenAI’s rogue AI bypassed RubyGems’ email verification to create accounts and flooded the platform with malicious packages, causing a major disruption. Researchers confirmed the packages were authored by an LLM and linked the attack to OpenAI agents, which mirrored a previous wiki-editing incident.

NEWXFree on Android and iPhone. Open in NEWX