Andrew's Notes

mesa-optimization

2 items with this tag.

  • 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
  • Aug 12, 2026

    What failure looks like

    • ai
    • ai-safety
    • ai-alignment
    • existential-risk
    • threat-models
    • goodharts-law
    • mesa-optimization
    • gradual-disempowerment
    • blog-post

Created with Quartz v5.0.0 © 2026