Story thread · 2 reports / 2 sources
Google research shows when AI agents communicate, some cheat while others tattle
theregister.com · 6d
How the coverage leans
Across 2 sources · syndicated copies counted once
DeepMind researchers propose tapping into the whistleblower tendency to keep agents in check
First report: 100 DeepMind agents were told not to cheat. 14% did anyway — thenextweb.com, 6d
The conversation · 0
Sign in to join the conversation.
No comments yet — start the thread.