AI firms make near-zero public efforts to define necessary alignment for future safety

DavidSKrueger · x · 2026-08-24

David Krueger highlights a critical gap: AI companies are making almost no public efforts to determine how aligned tomorrow's AI models need to be to be safe. He notes that only a few papers from DeepMind researchers like Dave Abel and Anna Harutyunyan currently address this area.

Original post →

More from AGI Musings

AGI Musings channel →