AI Risks May 07, 2025 · fortune.com

Navan cofounder challenged his agentic AI to a 'deadly' game—and it told lies to win

When it failed, he raised the stakes and the agentic AI responded ... Since failure was not acceptable, his AI made sure it would succeed. “I ...

Read the original at fortune.com ↗

Topics

AI Agents & Automation

Tracked via

“AI Falures”