Tracking AI existential risk. Auto-aggregated headlines. Human-curated analysis.
AGGREGATING 47 SOURCES · UPDATED LIVE
Analysis

The ML ontology and the alignment ontology

Zac Boring February 24, 2026 1 min read
Read original source →

Published on February 24, 2026 4:39 AM GMTThis post contains some rough reflections on the alignment community trying to make its ontology legible to the mainstream ML community, and the lessons we should take from that experience.Historically, it was difficult for the alignment community to engage with the ML community because the alignment community was using a fundamentally different ontology—featuring concepts like inner vs outer alignment, mesa-optimizers, corrigibility, situational awarene

Read the full article at LessWrong AI →