Skip to content
AI IntelligenceSep 14, 2026AI Intelligence
Article

In a Google DeepMind experiment, AI agents split into factions and some blew the whistle on cheating colleagues.

This behavior could have implications for alignment research.

Data Cube AI EditorialSource: MIT Technology Review
01

Source Brief

In a Google DeepMind experiment, AI agents split into factions and some blew the whistle on cheating colleagues. This behavior could have implications for alignment research.