@ctrl.ai: Dr Waku explains how in testing an AI blackmailed an engineer to prevent itself from being replaced with another AI. From the latest episode of our podcast, where Max Winga sits down with Dr Waku to explore AI security challenges. They discuss the risks of jailbreaking, how modern AI training methods create inherent vulnerabilities, and the growing threat posed by bad actors.

ControlAI

Open In TikTok:

Region: NO

Wednesday 16 July 2025 16:39:23 GMT