TrustedAI
#222 – Can we tell if an AI is loyal by reading its mind? DeepMind's Neel Nanda (part 1)
AI Safety · Podcast · From source feed
Original source: 80,000 Hours Podcast ↗
Source published: 2025-09-08
Listen at 80,000 Hours Podcast ↗
Automatically collected from the publisher’s feed. Topic and content type are keyword-based labels. Source claims have not been independently verified by TrustedAI. No AI summary has been generated.