Tracking AI existential risk. Source-backed context. Original reporting always linked.
MONITORING CORE AI-RISK FEEDS · UPDATED HOURLY
Research

Thousand-dimensional structure

Zac Boring July 30, 2026 1 min read
Read original source →

Summary: One area we plan to explore at Resolution is personas and character training, operationalized as finding and controlling low-dimensional structure in models that emerges in pretraining and flows through post-training to superintelligence. The hope is to expand and systematize phenomena such as emergent misalignment, subliminal learning, and other empirical persona research, then intervene on this structure without accidentally hiding undesirable behavior elsewhere. If this approach reso

By Geoffrey Irving

Read the full article at Alignment Forum →