AI ALIGNMENT FORUMTags
AF

Game Theory

•
Applied to Boomerang - protocol to dissolve some commitment races by Filip Sondej 8d ago
•
Applied to Evaluating strategic reasoning in GPT models by Steve Phelps 13d ago
•
Applied to Two ideas for alignment, perpetual mutual distrust and induction by APaleBlueDot 14d ago
•
Applied to Explaining “Hell is Game Theory Folk Theorems” by electroswing 1mo ago
•
Applied to Investigating Emergent Goal-Like Behavior in Large Language Models using Experimental Economics by Steve Phelps 1mo ago
•
Applied to Let's look for coherence theorems by Valdes 1mo ago
•
Applied to Hell is Game Theory Folk Theorems by Tassilo Neubauer 1mo ago
•
Applied to "A Note on the Compatibility of Different Robust Program Equilibria of the Prisoner's Dilemma" by Ruben Bloom 1mo ago
•
Applied to Conversational Cultures: Combat vs Nurture (V2) by Ruben Bloom 1mo ago
•
Applied to A short critique of «Boundaries» Part 2: example 1. Expansive Thinking by Chipmonk 2mo ago
•
Applied to conceptualizing infiltration and exfiltration from the «Boundaries» Sequence by Chipmonk 2mo ago
•
Applied to Double-negation as framing by Stuart Johnson 2mo ago
•
Applied to Alignment - Path to AI as ally, not slave nor foe by ozb 2mo ago