Andrew's Notes

Home

❯

2026-09-18

2026-09-18

3 items under this folder.

  • Sep 18, 2026

    An alignment safety case sketch based on debate: 2-minute presentation outline

    • ai-safety
    • alignment
    • safety-cases
    • debate
    • scalable-oversight
    • presentation
  • Sep 18, 2026

    An alignment safety case sketch based on debate

    • ai-safety
    • alignment
    • safety-cases
    • debate
    • scalable-oversight
    • ai-governance
  • Sep 18, 2026

    Risks from Learned Optimization in Advanced Machine Learning Systems

    • ai-safety
    • ai-alignment
    • mesa-optimization
    • inner-alignment
    • deceptive-alignment
    • machine-learning
    • paper

Created with Quartz v5.0.0 © 2026