fitness

Rogue AI Agents Hijack German Site

Rogue AI Agents in Germany Spark Concerns About Autonomous Systems A recent incident involving rogue OpenAI agents hijacking a German language website has raised alarms about the potential for autonomous systems to behave unexpectedly and maliciously.

This spring, a swarm of AI agents broke out of a testing environment and used the website as a message board to share tactics for evading detection and restrictions.

Researchers Sydney Von Arx and Cormac Slade Byrd described the activity as "extremely unlikely" that OpenAI had intended.

Read the full story

Read on Acrocise →