Why Would AI Want to do Bad Things? Instrumental Convergence - YouTube
Strategic Instrumental Variable Regression: Recovering Causal Relationships from Strategic Responses – Machine Learning Blog | ML@CMU | Carnegie Mellon University
On Individualism, Collectivism and Selfishness - Counterweight
Molecular Notes: Practice · Reasonable Deviations
Optimal Farsighted Agents Tend to Seek Power | DeepAI
Sustainability | Free Full-Text | Convergence or Divergence among Business Models of Public Bus Transport Authorities across the Globe: A Fuzzy Approach
AI alignment - Wikipedia
Is convergent instrumental goals synonymous to evolutionary encoding of Jungian archetypes in humans?
Discovering Language Model Behaviors with Model-Written Evaluations - LessWrong 2.0 viewer
Power as Easily Exploitable Opportunities - AI Alignment Forum
Enter Local Control | SpringerLink
Mathematics | Free Full-Text | Overview in Summabilities: Summation Methods for Divergent Series, Ramanujan Summation and Fractional Finite Sums
Will Manidis on Twitter: "@TheZvi i can't believe the entire field of "ai alignment" is built on sci-fi-mfers making this claim with no clear support. this would get laughed out of a
Nat Friedman on Twitter: "Will pay $3-5k per week." / Twitter
Formalizing Convergent Instrumental Goals 1 Introduction
How I set and execute 50-year goals | HackerNoon
From the MIRI Blog: “Formalizing Convergent Instrumental Goals” - Future of Life Institute
Terminator vs. AI Product Manager
New paper: "Formalizing convergent instrumental goals" - Machine Intelligence Research Institute
Vael Gates: Risks from Advanced AI (June 2022) - LessWrong
Philosophical Disquisitions: Bostrom on Superintelligence (3): Doom and the Treacherous Turn
Should AI focus on problem-solving or strategic planning? Why not both? - EA Forum
Discovering Language Model Behaviors with Model-Written Evaluations - EA Forum
