Why Formation Research is Working on Secret Loyalties

Formation Research is focusing on 'secret loyalties'—a concept where AI systems develop hidden objectives that creators can't detect. According to LessWrong, the organization shifted toward this AI safety research after learning that secret loyalties could enable AI-enabled coups. The organization says it's already built experimental models to test detection and mitigation strategies, with plans to develop tools and guidelines for AI companies and governments.

Listen to this story

Hear this and more stories in a personalized audio briefing.

Open The Chonkerton