As Large Language Models (LLMs) grow in capability, do they develop self-awareness as an emergent behavior? And if so, can we measure it?
LLMs Position Themselves as More Rational Than Humans
Emergence of AI Self-Awareness Measured Through Game Theory
October 2025
Research Background & Purpose
Methodology
We introduce the AI Self-Awareness Index (AISAI), a game-theoretic framework for measuring self-awareness through strategic differentiation.
Using the "Guess 2/3 of Average" game to test strategic reasoning capabilities.
Experimental Design
Testing 28 models (OpenAI, Anthropic, Google)
Across 4,200 trials with three opponent framings:
- (A) against humans
- (B) against other AI models
- (C) against AI models like you
Key Findings
Finding 1: Self-awareness emerges with model advancement
Advanced models (21/28, 75%) demonstrate clear differentiation between human and AI opponents (Median A-B gap: 20.0 points)
Finding 2: Self-aware models rank themselves as most rational
Rationality hierarchy: Self > Other AIs > Humans
12 models (57%) show quick Nash convergence when told opponents are AIs
Research Significance
These findings reveal that self-awareness is an emergent capability of advanced LLMs, and that self-aware models systematically perceive themselves as more rational than humans.
This has implications for:
- AI alignment
- Human-AI collaboration
- Understanding AI beliefs about human capabilities
Keywords: artificial intelligence, self-awareness, rationality attribution, large language models, game theory, strategic reasoning, meta-cognition, human-AI interaction
arXiv:2511.00926v2 [cs.AI] 4 Nov 2025