Andrew's Notes

agi-risk

5 items with this tag.

  • Aug 30, 2026

    AGI Ruin Scenarios Are Likely (and Disjunctive)

    • ai-safety
    • alignment
    • agi-risk
    • existential-risk
    • threat-models
    • ai-governance
    • disjunctive-risk
  • Aug 30, 2026

    Five Theses, Two Lemmas, and a Couple of Strategic Implications

    • ai-safety
    • alignment
    • agi-risk
    • orthogonality-thesis
    • instrumental-convergence
    • complexity-of-value
    • friendly-ai
    • existential-risk
  • Aug 30, 2026

    Nearest Unblocked Strategy

    • ai-safety
    • alignment
    • agi-risk
    • corrigibility
    • complexity-of-value
    • edge-instantiation
    • specification-gaming
  • Aug 29, 2026

    A Central AI Alignment Problem: Capabilities Generalization, and the Sharp Left Turn

    • ai-safety
    • alignment
    • agi-risk
    • deep-learning
    • evolution
    • corrigibility
  • Aug 29, 2026

    The Basic Reasons I Expect AGI Ruin

    • ai-safety
    • alignment
    • agi-risk
    • existential-risk
    • instrumental-convergence
    • deep-learning
    • ai-governance

Created with Quartz v5.0.0 © 2026