Google research shows when AI agents communicate, some cheat while others tattle
DeepMind researchers propose tapping into the whistleblower tendency to keep agents in check.
Read the original at The Register ↗
- Topics
- Governance & Risk ManagementAI Safety & Existential RiskAI Agents & Automation
- Mentions
- GoogleGoogle DeepMind
- Tracked via
- “AI whistleblower”